Date: 2019-12-25 22:25:21 CET, cola version: 1.3.2
Document is loading...
All available functions which can be applied to this res_list object:
res_list
#> A 'ConsensusPartitionList' object with 24 methods.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows are extracted by 'SD, CV, MAD, ATC' methods.
#> Subgroups are detected by 'hclust, kmeans, skmeans, pam, mclust, NMF' method.
#> Number of partitions are tried for k = 2, 3, 4, 5, 6.
#> Performed in total 30000 partitions by row resampling.
#>
#> Following methods can be applied to this 'ConsensusPartitionList' object:
#> [1] "cola_report" "collect_classes" "collect_plots" "collect_stats"
#> [5] "colnames" "functional_enrichment" "get_anno_col" "get_anno"
#> [9] "get_classes" "get_matrix" "get_membership" "get_stats"
#> [13] "is_best_k" "is_stable_k" "ncol" "nrow"
#> [17] "rownames" "show" "suggest_best_k" "test_to_known_factors"
#> [21] "top_rows_heatmap" "top_rows_overlap"
#>
#> You can get result for a single method by, e.g. object["SD", "hclust"] or object["SD:hclust"]
#> or a subset of methods by object[c("SD", "CV")], c("hclust", "kmeans")]
The call of run_all_consensus_partition_methods() was:
#> run_all_consensus_partition_methods(data = mat, mc.cores = 4)
Dimension of the input matrix:
mat = get_matrix(res_list)
dim(mat)
#> [1] 15144 101
The density distribution for each sample is visualized as in one column in the following heatmap. The clustering is based on the distance which is the Kolmogorov-Smirnov statistic between two distributions.
library(ComplexHeatmap)
densityHeatmap(mat, ylab = "value", cluster_columns = TRUE, show_column_names = FALSE,
mc.cores = 4)
Folowing table shows the best k (number of partitions) for each combination
of top-value methods and partition methods. Clicking on the method name in
the table goes to the section for a single combination of methods.
The cola vignette explains the definition of the metrics used for determining the best number of partitions.
suggest_best_k(res_list)
| The best k | 1-PAC | Mean silhouette | Concordance | Optional k | ||
|---|---|---|---|---|---|---|
| CV:hclust | 4 | 1.000 | 0.978 | 0.979 | ** | 3 |
| MAD:mclust | 2 | 1.000 | 0.988 | 0.990 | ** | |
| ATC:skmeans | 3 | 1.000 | 0.984 | 0.989 | ** | 2 |
| ATC:pam | 2 | 1.000 | 1.000 | 1.000 | ** | |
| ATC:mclust | 6 | 1.000 | 0.999 | 0.999 | ** | |
| ATC:NMF | 3 | 1.000 | 0.998 | 0.997 | ** | 2 |
| SD:pam | 6 | 0.957 | 0.971 | 0.975 | ** | 2,3,5 |
| MAD:pam | 6 | 0.945 | 0.947 | 0.956 | * | 2,4,5 |
| SD:NMF | 3 | 0.944 | 0.970 | 0.982 | * | 2 |
| CV:pam | 5 | 0.929 | 0.967 | 0.977 | * | 2,3,4 |
| SD:hclust | 6 | 0.918 | 0.907 | 0.957 | * | 2,3 |
| CV:NMF | 3 | 0.895 | 0.958 | 0.957 | ||
| CV:mclust | 5 | 0.838 | 0.872 | 0.898 | ||
| SD:skmeans | 2 | 0.836 | 0.962 | 0.981 | ||
| MAD:skmeans | 2 | 0.836 | 0.919 | 0.960 | ||
| MAD:NMF | 2 | 0.772 | 0.945 | 0.972 | ||
| ATC:hclust | 4 | 0.770 | 0.914 | 0.932 | ||
| CV:skmeans | 2 | 0.688 | 0.925 | 0.959 | ||
| SD:mclust | 4 | 0.683 | 0.776 | 0.885 | ||
| MAD:hclust | 2 | 0.674 | 0.929 | 0.956 | ||
| ATC:kmeans | 3 | 0.449 | 0.583 | 0.772 | ||
| SD:kmeans | 5 | 0.432 | 0.558 | 0.650 | ||
| CV:kmeans | 3 | 0.132 | 0.680 | 0.764 | ||
| MAD:kmeans | 2 | 0.116 | 0.664 | 0.795 |
**: 1-PAC > 0.95, *: 1-PAC > 0.9
Cumulative distribution function curves of consensus matrix for all methods.
collect_plots(res_list, fun = plot_ecdf)
Consensus heatmaps for all methods. (What is a consensus heatmap?)
collect_plots(res_list, k = 2, fun = consensus_heatmap, mc.cores = 4)
collect_plots(res_list, k = 3, fun = consensus_heatmap, mc.cores = 4)
collect_plots(res_list, k = 4, fun = consensus_heatmap, mc.cores = 4)
collect_plots(res_list, k = 5, fun = consensus_heatmap, mc.cores = 4)
collect_plots(res_list, k = 6, fun = consensus_heatmap, mc.cores = 4)
Membership heatmaps for all methods. (What is a membership heatmap?)
collect_plots(res_list, k = 2, fun = membership_heatmap, mc.cores = 4)
collect_plots(res_list, k = 3, fun = membership_heatmap, mc.cores = 4)
collect_plots(res_list, k = 4, fun = membership_heatmap, mc.cores = 4)
collect_plots(res_list, k = 5, fun = membership_heatmap, mc.cores = 4)
collect_plots(res_list, k = 6, fun = membership_heatmap, mc.cores = 4)
Signature heatmaps for all methods. (What is a signature heatmap?)
Note in following heatmaps, rows are scaled.
collect_plots(res_list, k = 2, fun = get_signatures, mc.cores = 4)
collect_plots(res_list, k = 3, fun = get_signatures, mc.cores = 4)
collect_plots(res_list, k = 4, fun = get_signatures, mc.cores = 4)
collect_plots(res_list, k = 5, fun = get_signatures, mc.cores = 4)
collect_plots(res_list, k = 6, fun = get_signatures, mc.cores = 4)
The statistics used for measuring the stability of consensus partitioning. (How are they defined?)
get_stats(res_list, k = 2)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 2 0.919 0.932 0.967 0.446 0.531 0.531
#> CV:NMF 2 0.836 0.932 0.970 0.427 0.595 0.595
#> MAD:NMF 2 0.772 0.945 0.972 0.464 0.531 0.531
#> ATC:NMF 2 1.000 1.000 1.000 0.405 0.595 0.595
#> SD:skmeans 2 0.836 0.962 0.981 0.476 0.531 0.531
#> CV:skmeans 2 0.688 0.925 0.959 0.485 0.499 0.499
#> MAD:skmeans 2 0.836 0.919 0.960 0.492 0.499 0.499
#> ATC:skmeans 2 1.000 0.992 0.995 0.408 0.595 0.595
#> SD:mclust 2 0.280 0.373 0.688 0.422 0.497 0.497
#> CV:mclust 2 0.203 0.759 0.817 0.453 0.499 0.499
#> MAD:mclust 2 1.000 0.988 0.990 0.290 0.717 0.717
#> ATC:mclust 2 0.836 0.954 0.966 0.489 0.499 0.499
#> SD:kmeans 2 0.150 0.560 0.763 0.383 0.604 0.604
#> CV:kmeans 2 0.185 0.576 0.731 0.357 0.531 0.531
#> MAD:kmeans 2 0.116 0.664 0.795 0.411 0.604 0.604
#> ATC:kmeans 2 0.722 0.938 0.941 0.380 0.595 0.595
#> SD:pam 2 1.000 1.000 1.000 0.405 0.595 0.595
#> CV:pam 2 1.000 1.000 1.000 0.405 0.595 0.595
#> MAD:pam 2 0.901 0.952 0.975 0.452 0.531 0.531
#> ATC:pam 2 1.000 1.000 1.000 0.405 0.595 0.595
#> SD:hclust 2 1.000 0.990 0.994 0.409 0.595 0.595
#> CV:hclust 2 0.531 0.953 0.918 0.352 0.595 0.595
#> MAD:hclust 2 0.674 0.929 0.956 0.442 0.531 0.531
#> ATC:hclust 2 0.820 0.897 0.958 0.342 0.704 0.704
get_stats(res_list, k = 3)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 3 0.944 0.970 0.982 0.198 0.950 0.906
#> CV:NMF 3 0.895 0.958 0.957 0.432 0.804 0.671
#> MAD:NMF 3 0.643 0.756 0.883 0.387 0.740 0.542
#> ATC:NMF 3 1.000 0.998 0.997 0.605 0.754 0.587
#> SD:skmeans 3 0.772 0.831 0.916 0.391 0.754 0.563
#> CV:skmeans 3 0.706 0.692 0.872 0.357 0.704 0.475
#> MAD:skmeans 3 0.706 0.840 0.909 0.348 0.786 0.597
#> ATC:skmeans 3 1.000 0.984 0.989 0.589 0.754 0.587
#> SD:mclust 3 0.380 0.711 0.777 0.426 0.623 0.407
#> CV:mclust 3 0.554 0.548 0.700 0.391 0.636 0.391
#> MAD:mclust 3 0.405 0.758 0.796 1.077 0.733 0.631
#> ATC:mclust 3 0.587 0.866 0.849 0.288 0.836 0.682
#> SD:kmeans 3 0.216 0.538 0.700 0.463 0.806 0.696
#> CV:kmeans 3 0.132 0.680 0.764 0.488 0.754 0.609
#> MAD:kmeans 3 0.200 0.511 0.611 0.393 0.806 0.696
#> ATC:kmeans 3 0.449 0.583 0.772 0.524 0.804 0.671
#> SD:pam 3 1.000 1.000 1.000 0.281 0.886 0.808
#> CV:pam 3 1.000 1.000 1.000 0.281 0.886 0.808
#> MAD:pam 3 0.742 0.825 0.896 0.285 0.950 0.906
#> ATC:pam 3 0.878 0.847 0.942 0.641 0.745 0.571
#> SD:hclust 3 1.000 0.999 1.000 0.270 0.886 0.808
#> CV:hclust 3 1.000 1.000 1.000 0.477 0.886 0.808
#> MAD:hclust 3 0.642 0.921 0.957 0.194 0.950 0.906
#> ATC:hclust 3 0.718 0.768 0.834 0.611 0.663 0.521
get_stats(res_list, k = 4)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 4 0.742 0.783 0.857 0.3487 0.755 0.501
#> CV:NMF 4 0.841 0.942 0.941 0.2055 0.850 0.625
#> MAD:NMF 4 0.699 0.853 0.879 0.1483 0.748 0.403
#> ATC:NMF 4 0.827 0.926 0.915 0.1438 0.900 0.714
#> SD:skmeans 4 0.706 0.659 0.757 0.1200 0.836 0.587
#> CV:skmeans 4 0.706 0.811 0.873 0.1279 0.854 0.598
#> MAD:skmeans 4 0.690 0.798 0.841 0.1176 0.898 0.709
#> ATC:skmeans 4 0.769 0.777 0.852 0.1221 0.940 0.828
#> SD:mclust 4 0.683 0.776 0.885 0.1434 0.918 0.794
#> CV:mclust 4 0.702 0.769 0.845 0.0926 0.950 0.849
#> MAD:mclust 4 0.595 0.603 0.779 0.2017 0.652 0.343
#> ATC:mclust 4 0.720 0.700 0.769 0.1274 0.852 0.629
#> SD:kmeans 4 0.317 0.485 0.672 0.1756 0.886 0.771
#> CV:kmeans 4 0.373 0.582 0.709 0.1948 1.000 1.000
#> MAD:kmeans 4 0.266 0.552 0.653 0.1870 0.754 0.535
#> ATC:kmeans 4 0.469 0.672 0.732 0.1648 0.804 0.577
#> SD:pam 4 0.797 0.840 0.858 0.2838 0.802 0.589
#> CV:pam 4 1.000 0.987 0.986 0.1886 0.902 0.796
#> MAD:pam 4 0.962 0.913 0.964 0.2100 0.813 0.612
#> ATC:pam 4 0.747 0.745 0.825 0.0647 0.958 0.884
#> SD:hclust 4 0.718 0.867 0.814 0.1866 0.966 0.930
#> CV:hclust 4 1.000 0.978 0.979 0.2030 0.902 0.796
#> MAD:hclust 4 0.561 0.764 0.847 0.2927 0.836 0.659
#> ATC:hclust 4 0.770 0.914 0.932 0.2013 0.947 0.854
get_stats(res_list, k = 5)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 5 0.876 0.950 0.939 0.0777 0.930 0.742
#> CV:NMF 5 0.804 0.822 0.857 0.0583 0.934 0.752
#> MAD:NMF 5 0.892 0.930 0.941 0.0565 0.902 0.652
#> ATC:NMF 5 0.863 0.926 0.929 0.0546 0.902 0.652
#> SD:skmeans 5 0.822 0.805 0.795 0.0576 0.902 0.671
#> CV:skmeans 5 0.806 0.770 0.827 0.0561 0.918 0.691
#> MAD:skmeans 5 0.772 0.861 0.868 0.0615 0.968 0.871
#> ATC:skmeans 5 0.850 0.924 0.854 0.0593 0.923 0.736
#> SD:mclust 5 0.752 0.740 0.841 0.0944 0.900 0.684
#> CV:mclust 5 0.838 0.872 0.898 0.1161 0.952 0.829
#> MAD:mclust 5 0.702 0.842 0.800 0.0521 0.818 0.452
#> ATC:mclust 5 0.866 0.916 0.922 0.0724 0.968 0.887
#> SD:kmeans 5 0.432 0.558 0.650 0.0934 0.757 0.459
#> CV:kmeans 5 0.495 0.471 0.653 0.1034 0.902 0.796
#> MAD:kmeans 5 0.467 0.554 0.612 0.0887 0.886 0.656
#> ATC:kmeans 5 0.569 0.599 0.670 0.1012 0.902 0.704
#> SD:pam 5 0.960 0.961 0.982 0.1455 0.939 0.790
#> CV:pam 5 0.929 0.967 0.977 0.1480 0.918 0.786
#> MAD:pam 5 0.954 0.947 0.974 0.0870 0.912 0.715
#> ATC:pam 5 0.739 0.736 0.810 0.0668 0.862 0.610
#> SD:hclust 5 0.800 0.886 0.866 0.1563 0.802 0.558
#> CV:hclust 5 0.852 0.894 0.946 0.1763 0.868 0.656
#> MAD:hclust 5 0.613 0.672 0.791 0.0640 0.868 0.670
#> ATC:hclust 5 0.800 0.854 0.862 0.1674 0.900 0.682
get_stats(res_list, k = 6)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 6 0.850 0.815 0.805 0.0478 0.966 0.843
#> CV:NMF 6 0.820 0.838 0.801 0.0441 0.984 0.926
#> MAD:NMF 6 0.818 0.798 0.822 0.0426 0.913 0.652
#> ATC:NMF 6 0.887 0.837 0.857 0.0373 1.000 1.000
#> SD:skmeans 6 0.818 0.864 0.871 0.0380 0.968 0.851
#> CV:skmeans 6 0.852 0.846 0.776 0.0369 0.984 0.920
#> MAD:skmeans 6 0.836 0.879 0.864 0.0404 0.968 0.851
#> ATC:skmeans 6 0.852 0.894 0.870 0.0470 0.968 0.851
#> SD:mclust 6 0.854 0.827 0.886 0.0863 0.930 0.702
#> CV:mclust 6 0.786 0.807 0.823 0.0467 0.882 0.582
#> MAD:mclust 6 0.834 0.878 0.927 0.0723 0.950 0.786
#> ATC:mclust 6 1.000 0.999 0.999 0.0731 0.932 0.730
#> SD:kmeans 6 0.601 0.629 0.643 0.0732 0.935 0.752
#> CV:kmeans 6 0.595 0.596 0.601 0.0741 0.786 0.524
#> MAD:kmeans 6 0.645 0.617 0.590 0.0598 0.872 0.510
#> ATC:kmeans 6 0.646 0.576 0.661 0.0576 0.936 0.745
#> SD:pam 6 0.957 0.971 0.975 0.0480 0.964 0.849
#> CV:pam 6 0.884 0.946 0.936 0.0865 0.934 0.781
#> MAD:pam 6 0.945 0.947 0.956 0.0480 0.964 0.849
#> ATC:pam 6 0.834 0.757 0.874 0.0552 0.908 0.652
#> SD:hclust 6 0.918 0.907 0.957 0.1130 0.950 0.800
#> CV:hclust 6 0.868 0.921 0.925 0.0573 0.984 0.936
#> MAD:hclust 6 0.834 0.828 0.917 0.1070 0.868 0.622
#> ATC:hclust 6 0.832 0.522 0.698 0.0379 0.848 0.465
Following heatmap plots the partition for each combination of methods and the lightness correspond to the silhouette scores for samples in each method. On top the consensus subgroup is inferred from all methods by taking the mean silhouette scores as weight.
collect_stats(res_list, k = 2)
collect_stats(res_list, k = 3)
collect_stats(res_list, k = 4)
collect_stats(res_list, k = 5)
collect_stats(res_list, k = 6)
Collect partitions from all methods:
collect_classes(res_list, k = 2)
collect_classes(res_list, k = 3)
collect_classes(res_list, k = 4)
collect_classes(res_list, k = 5)
collect_classes(res_list, k = 6)
Overlap of top rows from different top-row methods:
top_rows_overlap(res_list, top_n = 1000, method = "euler")
top_rows_overlap(res_list, top_n = 2000, method = "euler")
top_rows_overlap(res_list, top_n = 3000, method = "euler")
top_rows_overlap(res_list, top_n = 4000, method = "euler")
top_rows_overlap(res_list, top_n = 5000, method = "euler")
Also visualize the correspondance of rankings between different top-row methods:
top_rows_overlap(res_list, top_n = 1000, method = "correspondance")
top_rows_overlap(res_list, top_n = 2000, method = "correspondance")
top_rows_overlap(res_list, top_n = 3000, method = "correspondance")
top_rows_overlap(res_list, top_n = 4000, method = "correspondance")
top_rows_overlap(res_list, top_n = 5000, method = "correspondance")
Heatmaps of the top rows:
top_rows_heatmap(res_list, top_n = 1000)
top_rows_heatmap(res_list, top_n = 2000)
top_rows_heatmap(res_list, top_n = 3000)
top_rows_heatmap(res_list, top_n = 4000)
top_rows_heatmap(res_list, top_n = 5000)
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "hclust"]
# you can also extract it by
# res = res_list["SD:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 6.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.990 0.994 0.409 0.595 0.595
#> 3 3 1.000 0.999 1.000 0.270 0.886 0.808
#> 4 4 0.718 0.867 0.814 0.187 0.966 0.930
#> 5 5 0.800 0.886 0.866 0.156 0.802 0.558
#> 6 6 0.918 0.907 0.957 0.113 0.950 0.800
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 6
#> attr(,"optional")
#> [1] 2 3
There is also optional best \(k\) = 2 3 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.0000 0.992 1.000 0.000
#> ERR342843 1 0.0000 0.992 1.000 0.000
#> ERR342896 1 0.0000 0.992 1.000 0.000
#> ERR342827 2 0.0000 0.998 0.000 1.000
#> ERR342871 1 0.0000 0.992 1.000 0.000
#> ERR342863 2 0.0000 0.998 0.000 1.000
#> ERR342839 1 0.0000 0.992 1.000 0.000
#> ERR342906 1 0.0000 0.992 1.000 0.000
#> ERR342905 2 0.0376 0.997 0.004 0.996
#> ERR342816 1 0.0000 0.992 1.000 0.000
#> ERR342865 2 0.0000 0.998 0.000 1.000
#> ERR342824 1 0.0000 0.992 1.000 0.000
#> ERR342841 2 0.0000 0.998 0.000 1.000
#> ERR342835 1 0.0000 0.992 1.000 0.000
#> ERR342899 2 0.0376 0.997 0.004 0.996
#> ERR342829 1 0.0000 0.992 1.000 0.000
#> ERR342850 1 0.0000 0.992 1.000 0.000
#> ERR342849 2 0.0376 0.997 0.004 0.996
#> ERR342811 1 0.0000 0.992 1.000 0.000
#> ERR342837 1 0.0000 0.992 1.000 0.000
#> ERR342857 1 0.0000 0.992 1.000 0.000
#> ERR342869 1 0.0000 0.992 1.000 0.000
#> ERR342903 1 0.0000 0.992 1.000 0.000
#> ERR342819 1 0.0000 0.992 1.000 0.000
#> ERR342885 1 0.3274 0.943 0.940 0.060
#> ERR342889 2 0.0000 0.998 0.000 1.000
#> ERR342864 1 0.0000 0.992 1.000 0.000
#> ERR342860 2 0.0376 0.997 0.004 0.996
#> ERR342808 1 0.0000 0.992 1.000 0.000
#> ERR342823 1 0.0000 0.992 1.000 0.000
#> ERR342907 2 0.0000 0.998 0.000 1.000
#> ERR342852 1 0.0000 0.992 1.000 0.000
#> ERR342832 2 0.0000 0.998 0.000 1.000
#> ERR342868 1 0.0000 0.992 1.000 0.000
#> ERR342821 1 0.0000 0.992 1.000 0.000
#> ERR342878 2 0.0000 0.998 0.000 1.000
#> ERR342876 1 0.0000 0.992 1.000 0.000
#> ERR342809 1 0.0000 0.992 1.000 0.000
#> ERR342846 1 0.3274 0.943 0.940 0.060
#> ERR342872 2 0.0000 0.998 0.000 1.000
#> ERR342828 2 0.0000 0.998 0.000 1.000
#> ERR342840 1 0.0000 0.992 1.000 0.000
#> ERR342831 1 0.0000 0.992 1.000 0.000
#> ERR342818 1 0.0000 0.992 1.000 0.000
#> ERR342862 1 0.0000 0.992 1.000 0.000
#> ERR342894 1 0.0000 0.992 1.000 0.000
#> ERR342884 2 0.0000 0.998 0.000 1.000
#> ERR342891 1 0.0000 0.992 1.000 0.000
#> ERR342890 1 0.0000 0.992 1.000 0.000
#> ERR342836 2 0.0000 0.998 0.000 1.000
#> ERR342879 1 0.0000 0.992 1.000 0.000
#> ERR342848 1 0.0000 0.992 1.000 0.000
#> ERR342861 1 0.0000 0.992 1.000 0.000
#> ERR342814 2 0.0376 0.997 0.004 0.996
#> ERR342870 1 0.0000 0.992 1.000 0.000
#> ERR342901 1 0.0000 0.992 1.000 0.000
#> ERR342908 1 0.0000 0.992 1.000 0.000
#> ERR342815 2 0.0000 0.998 0.000 1.000
#> ERR342897 1 0.3274 0.943 0.940 0.060
#> ERR342833 2 0.0000 0.998 0.000 1.000
#> ERR342817 1 0.3274 0.943 0.940 0.060
#> ERR342810 2 0.0376 0.997 0.004 0.996
#> ERR342867 1 0.0000 0.992 1.000 0.000
#> ERR342847 1 0.0000 0.992 1.000 0.000
#> ERR342855 1 0.0000 0.992 1.000 0.000
#> ERR342851 1 0.0000 0.992 1.000 0.000
#> ERR342813 1 0.0000 0.992 1.000 0.000
#> ERR342883 1 0.0000 0.992 1.000 0.000
#> ERR342856 1 0.3274 0.943 0.940 0.060
#> ERR342822 2 0.0000 0.998 0.000 1.000
#> ERR342892 1 0.0000 0.992 1.000 0.000
#> ERR342842 1 0.0000 0.992 1.000 0.000
#> ERR342902 2 0.0000 0.998 0.000 1.000
#> ERR342900 2 0.0376 0.997 0.004 0.996
#> ERR342888 1 0.0000 0.992 1.000 0.000
#> ERR342812 1 0.0000 0.992 1.000 0.000
#> ERR342853 2 0.0376 0.997 0.004 0.996
#> ERR342866 1 0.0000 0.992 1.000 0.000
#> ERR342820 1 0.0000 0.992 1.000 0.000
#> ERR342895 1 0.0000 0.992 1.000 0.000
#> ERR342825 1 0.3274 0.943 0.940 0.060
#> ERR342826 1 0.3274 0.943 0.940 0.060
#> ERR342875 2 0.0000 0.998 0.000 1.000
#> ERR342834 1 0.3274 0.943 0.940 0.060
#> ERR342898 1 0.0000 0.992 1.000 0.000
#> ERR342886 2 0.0376 0.997 0.004 0.996
#> ERR342838 1 0.0000 0.992 1.000 0.000
#> ERR342882 1 0.0000 0.992 1.000 0.000
#> ERR342807 2 0.0000 0.998 0.000 1.000
#> ERR342873 1 0.0000 0.992 1.000 0.000
#> ERR342844 1 0.0000 0.992 1.000 0.000
#> ERR342874 1 0.0000 0.992 1.000 0.000
#> ERR342893 1 0.0000 0.992 1.000 0.000
#> ERR342859 1 0.3274 0.943 0.940 0.060
#> ERR342830 2 0.0376 0.997 0.004 0.996
#> ERR342880 1 0.0000 0.992 1.000 0.000
#> ERR342887 1 0.0000 0.992 1.000 0.000
#> ERR342854 1 0.0000 0.992 1.000 0.000
#> ERR342904 1 0.0000 0.992 1.000 0.000
#> ERR342881 1 0.0000 0.992 1.000 0.000
#> ERR342858 1 0.0000 0.992 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.0000 1.000 1.000 0.000 0
#> ERR342843 1 0.0000 1.000 1.000 0.000 0
#> ERR342896 1 0.0000 1.000 1.000 0.000 0
#> ERR342827 2 0.0000 0.998 0.000 1.000 0
#> ERR342871 1 0.0000 1.000 1.000 0.000 0
#> ERR342863 2 0.0000 0.998 0.000 1.000 0
#> ERR342839 1 0.0000 1.000 1.000 0.000 0
#> ERR342906 1 0.0000 1.000 1.000 0.000 0
#> ERR342905 2 0.0237 0.996 0.004 0.996 0
#> ERR342816 1 0.0000 1.000 1.000 0.000 0
#> ERR342865 2 0.0000 0.998 0.000 1.000 0
#> ERR342824 1 0.0000 1.000 1.000 0.000 0
#> ERR342841 2 0.0000 0.998 0.000 1.000 0
#> ERR342835 1 0.0000 1.000 1.000 0.000 0
#> ERR342899 2 0.0237 0.996 0.004 0.996 0
#> ERR342829 1 0.0000 1.000 1.000 0.000 0
#> ERR342850 1 0.0000 1.000 1.000 0.000 0
#> ERR342849 2 0.0237 0.996 0.004 0.996 0
#> ERR342811 1 0.0000 1.000 1.000 0.000 0
#> ERR342837 1 0.0000 1.000 1.000 0.000 0
#> ERR342857 1 0.0000 1.000 1.000 0.000 0
#> ERR342869 1 0.0000 1.000 1.000 0.000 0
#> ERR342903 1 0.0000 1.000 1.000 0.000 0
#> ERR342819 1 0.0000 1.000 1.000 0.000 0
#> ERR342885 3 0.0000 1.000 0.000 0.000 1
#> ERR342889 2 0.0000 0.998 0.000 1.000 0
#> ERR342864 1 0.0000 1.000 1.000 0.000 0
#> ERR342860 2 0.0237 0.996 0.004 0.996 0
#> ERR342808 1 0.0000 1.000 1.000 0.000 0
#> ERR342823 1 0.0000 1.000 1.000 0.000 0
#> ERR342907 2 0.0000 0.998 0.000 1.000 0
#> ERR342852 1 0.0000 1.000 1.000 0.000 0
#> ERR342832 2 0.0000 0.998 0.000 1.000 0
#> ERR342868 1 0.0000 1.000 1.000 0.000 0
#> ERR342821 1 0.0000 1.000 1.000 0.000 0
#> ERR342878 2 0.0000 0.998 0.000 1.000 0
#> ERR342876 1 0.0000 1.000 1.000 0.000 0
#> ERR342809 1 0.0000 1.000 1.000 0.000 0
#> ERR342846 3 0.0000 1.000 0.000 0.000 1
#> ERR342872 2 0.0000 0.998 0.000 1.000 0
#> ERR342828 2 0.0000 0.998 0.000 1.000 0
#> ERR342840 1 0.0000 1.000 1.000 0.000 0
#> ERR342831 1 0.0000 1.000 1.000 0.000 0
#> ERR342818 1 0.0000 1.000 1.000 0.000 0
#> ERR342862 1 0.0000 1.000 1.000 0.000 0
#> ERR342894 1 0.0000 1.000 1.000 0.000 0
#> ERR342884 2 0.0000 0.998 0.000 1.000 0
#> ERR342891 1 0.0000 1.000 1.000 0.000 0
#> ERR342890 1 0.0000 1.000 1.000 0.000 0
#> ERR342836 2 0.0000 0.998 0.000 1.000 0
#> ERR342879 1 0.0000 1.000 1.000 0.000 0
#> ERR342848 1 0.0000 1.000 1.000 0.000 0
#> ERR342861 1 0.0000 1.000 1.000 0.000 0
#> ERR342814 2 0.0237 0.996 0.004 0.996 0
#> ERR342870 1 0.0000 1.000 1.000 0.000 0
#> ERR342901 1 0.0000 1.000 1.000 0.000 0
#> ERR342908 1 0.0000 1.000 1.000 0.000 0
#> ERR342815 2 0.0000 0.998 0.000 1.000 0
#> ERR342897 3 0.0000 1.000 0.000 0.000 1
#> ERR342833 2 0.0000 0.998 0.000 1.000 0
#> ERR342817 3 0.0000 1.000 0.000 0.000 1
#> ERR342810 2 0.0237 0.996 0.004 0.996 0
#> ERR342867 1 0.0000 1.000 1.000 0.000 0
#> ERR342847 1 0.0000 1.000 1.000 0.000 0
#> ERR342855 1 0.0000 1.000 1.000 0.000 0
#> ERR342851 1 0.0000 1.000 1.000 0.000 0
#> ERR342813 1 0.0000 1.000 1.000 0.000 0
#> ERR342883 1 0.0000 1.000 1.000 0.000 0
#> ERR342856 3 0.0000 1.000 0.000 0.000 1
#> ERR342822 2 0.0000 0.998 0.000 1.000 0
#> ERR342892 1 0.0000 1.000 1.000 0.000 0
#> ERR342842 1 0.0000 1.000 1.000 0.000 0
#> ERR342902 2 0.0000 0.998 0.000 1.000 0
#> ERR342900 2 0.0237 0.996 0.004 0.996 0
#> ERR342888 1 0.0000 1.000 1.000 0.000 0
#> ERR342812 1 0.0000 1.000 1.000 0.000 0
#> ERR342853 2 0.0237 0.996 0.004 0.996 0
#> ERR342866 1 0.0000 1.000 1.000 0.000 0
#> ERR342820 1 0.0000 1.000 1.000 0.000 0
#> ERR342895 1 0.0000 1.000 1.000 0.000 0
#> ERR342825 3 0.0000 1.000 0.000 0.000 1
#> ERR342826 3 0.0000 1.000 0.000 0.000 1
#> ERR342875 2 0.0000 0.998 0.000 1.000 0
#> ERR342834 3 0.0000 1.000 0.000 0.000 1
#> ERR342898 1 0.0000 1.000 1.000 0.000 0
#> ERR342886 2 0.0237 0.996 0.004 0.996 0
#> ERR342838 1 0.0000 1.000 1.000 0.000 0
#> ERR342882 1 0.0000 1.000 1.000 0.000 0
#> ERR342807 2 0.0000 0.998 0.000 1.000 0
#> ERR342873 1 0.0000 1.000 1.000 0.000 0
#> ERR342844 1 0.0000 1.000 1.000 0.000 0
#> ERR342874 1 0.0000 1.000 1.000 0.000 0
#> ERR342893 1 0.0000 1.000 1.000 0.000 0
#> ERR342859 3 0.0000 1.000 0.000 0.000 1
#> ERR342830 2 0.0237 0.996 0.004 0.996 0
#> ERR342880 1 0.0000 1.000 1.000 0.000 0
#> ERR342887 1 0.0000 1.000 1.000 0.000 0
#> ERR342854 1 0.0000 1.000 1.000 0.000 0
#> ERR342904 1 0.0000 1.000 1.000 0.000 0
#> ERR342881 1 0.0000 1.000 1.000 0.000 0
#> ERR342858 1 0.0000 1.000 1.000 0.000 0
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342843 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342896 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342827 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342871 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342863 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342839 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342906 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342905 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342816 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342865 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342824 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342841 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342835 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342899 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342829 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342850 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342849 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342811 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342837 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342857 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342869 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342903 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342819 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342885 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342889 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342864 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342860 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342808 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342823 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342907 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342852 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342832 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342868 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342821 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342878 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342876 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342809 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342846 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342872 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342828 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342840 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342831 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342818 1 0.0000 0.778 1.000 0.000 0 0.000
#> ERR342862 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342894 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342884 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342891 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342890 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342836 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342879 1 0.0000 0.778 1.000 0.000 0 0.000
#> ERR342848 1 0.0000 0.778 1.000 0.000 0 0.000
#> ERR342861 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342814 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342870 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342901 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342908 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342815 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342897 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342833 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342817 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342810 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342867 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342847 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342855 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342851 1 0.0000 0.778 1.000 0.000 0 0.000
#> ERR342813 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342883 1 0.0000 0.778 1.000 0.000 0 0.000
#> ERR342856 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342822 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342892 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342842 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342902 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342900 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342888 1 0.4989 0.736 0.528 0.000 0 0.472
#> ERR342812 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342853 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342866 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342820 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342895 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342825 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342875 2 0.0336 0.986 0.000 0.992 0 0.008
#> ERR342834 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342898 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342886 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342838 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342882 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342807 4 0.4989 1.000 0.000 0.472 0 0.528
#> ERR342873 1 0.0000 0.778 1.000 0.000 0 0.000
#> ERR342844 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342874 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342893 1 0.0000 0.778 1.000 0.000 0 0.000
#> ERR342859 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342830 2 0.0188 0.988 0.004 0.996 0 0.000
#> ERR342880 1 0.0000 0.778 1.000 0.000 0 0.000
#> ERR342887 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342854 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342904 1 0.0188 0.778 0.996 0.000 0 0.004
#> ERR342881 1 0.4543 0.828 0.676 0.000 0 0.324
#> ERR342858 1 0.0000 0.778 1.000 0.000 0 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342843 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342896 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342827 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342871 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342863 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342839 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342906 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342905 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342816 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342865 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342824 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342841 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342835 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342899 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342829 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342850 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342849 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342811 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342837 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342857 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342869 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342903 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342819 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342885 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342889 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342864 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342860 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342808 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342823 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342907 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342852 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342832 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342868 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342821 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342878 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342876 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342809 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342872 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342828 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342840 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342831 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342818 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
#> ERR342862 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342894 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342884 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342891 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342890 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342836 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342879 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
#> ERR342848 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
#> ERR342861 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342814 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342870 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342901 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342908 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342815 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342897 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342833 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342817 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342810 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342867 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342847 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342855 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342851 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
#> ERR342813 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342883 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
#> ERR342856 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342822 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342892 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342842 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342902 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342900 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342888 1 0.1544 0.493 0.932 0.000 0 0.068 0.000
#> ERR342812 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342853 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342866 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342820 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342895 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342875 2 0.0404 0.993 0.000 0.988 0 0.000 0.012
#> ERR342834 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342898 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342886 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342838 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342882 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342807 5 0.0000 1.000 0.000 0.000 0 0.000 1.000
#> ERR342873 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
#> ERR342844 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342874 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342893 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
#> ERR342859 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342830 2 0.0000 0.994 0.000 1.000 0 0.000 0.000
#> ERR342880 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
#> ERR342887 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342854 1 0.4299 0.813 0.608 0.004 0 0.388 0.000
#> ERR342904 4 0.0000 0.959 0.000 0.000 0 1.000 0.000
#> ERR342881 1 0.4288 0.811 0.612 0.004 0 0.384 0.000
#> ERR342858 4 0.1768 0.914 0.072 0.004 0 0.924 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342843 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342896 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342827 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342871 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342863 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342839 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342906 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342905 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342816 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342865 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342824 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342841 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342835 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342899 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342829 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342850 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342849 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342811 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342837 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342857 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342869 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342903 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342819 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342885 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342889 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342864 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342860 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342808 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342823 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342907 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342852 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342832 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342868 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342821 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342878 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342876 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342809 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342846 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342872 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342828 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342840 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342831 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342818 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
#> ERR342862 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342894 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342884 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342891 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342890 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342836 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342879 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
#> ERR342848 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
#> ERR342861 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342814 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342870 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342901 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342908 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342815 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342897 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342833 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342817 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342810 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342867 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342847 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342855 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342851 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
#> ERR342813 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342883 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
#> ERR342856 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342822 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342892 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342842 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342902 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342900 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342888 5 0.000 1.000 0.000 0.000 0 0.000 1.000 0.000
#> ERR342812 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342853 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342866 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342820 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342895 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342825 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342826 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342875 2 0.385 0.993 0.000 0.536 0 0.000 0.000 0.464
#> ERR342834 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342898 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342886 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342838 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342882 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342807 6 0.384 1.000 0.452 0.000 0 0.000 0.000 0.548
#> ERR342873 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
#> ERR342844 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342874 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342893 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
#> ERR342859 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342830 2 0.384 0.994 0.000 0.548 0 0.000 0.000 0.452
#> ERR342880 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
#> ERR342887 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342854 1 0.397 0.998 0.548 0.000 0 0.448 0.004 0.000
#> ERR342904 4 0.384 0.784 0.000 0.452 0 0.548 0.000 0.000
#> ERR342881 1 0.384 0.997 0.548 0.000 0 0.452 0.000 0.000
#> ERR342858 4 0.026 0.413 0.008 0.000 0 0.992 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "kmeans"]
# you can also extract it by
# res = res_list["SD:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 5.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.150 0.560 0.763 0.3830 0.604 0.604
#> 3 3 0.216 0.538 0.700 0.4631 0.806 0.696
#> 4 4 0.317 0.485 0.672 0.1756 0.886 0.771
#> 5 5 0.432 0.558 0.650 0.0934 0.757 0.459
#> 6 6 0.601 0.629 0.643 0.0732 0.935 0.752
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 5
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.745 0.6040 0.788 0.212
#> ERR342843 1 0.745 0.6040 0.788 0.212
#> ERR342896 1 0.118 0.7322 0.984 0.016
#> ERR342827 2 0.788 0.7310 0.236 0.764
#> ERR342871 1 0.730 0.6423 0.796 0.204
#> ERR342863 2 0.788 0.7298 0.236 0.764
#> ERR342839 1 0.745 0.6040 0.788 0.212
#> ERR342906 1 0.839 0.5467 0.732 0.268
#> ERR342905 1 0.990 -0.0194 0.560 0.440
#> ERR342816 1 0.839 0.5467 0.732 0.268
#> ERR342865 2 0.788 0.7298 0.236 0.764
#> ERR342824 1 0.118 0.7322 0.984 0.016
#> ERR342841 2 0.788 0.7310 0.236 0.764
#> ERR342835 1 0.327 0.7172 0.940 0.060
#> ERR342899 1 0.990 -0.0194 0.560 0.440
#> ERR342829 1 0.118 0.7322 0.984 0.016
#> ERR342850 1 0.730 0.6423 0.796 0.204
#> ERR342849 1 0.990 -0.0194 0.560 0.440
#> ERR342811 1 0.730 0.6423 0.796 0.204
#> ERR342837 1 0.327 0.7172 0.940 0.060
#> ERR342857 1 0.839 0.5467 0.732 0.268
#> ERR342869 1 0.730 0.6423 0.796 0.204
#> ERR342903 1 0.118 0.7322 0.984 0.016
#> ERR342819 1 0.327 0.7172 0.940 0.060
#> ERR342885 2 1.000 0.1077 0.488 0.512
#> ERR342889 2 0.788 0.7298 0.236 0.764
#> ERR342864 1 0.839 0.5467 0.732 0.268
#> ERR342860 1 0.990 -0.0194 0.560 0.440
#> ERR342808 1 0.730 0.6423 0.796 0.204
#> ERR342823 1 0.118 0.7322 0.984 0.016
#> ERR342907 2 0.788 0.7310 0.236 0.764
#> ERR342852 1 0.839 0.5467 0.732 0.268
#> ERR342832 2 0.788 0.7298 0.236 0.764
#> ERR342868 1 0.745 0.6040 0.788 0.212
#> ERR342821 1 0.839 0.5467 0.732 0.268
#> ERR342878 2 0.788 0.7310 0.236 0.764
#> ERR342876 1 0.118 0.7322 0.984 0.016
#> ERR342809 1 0.118 0.7322 0.984 0.016
#> ERR342846 2 1.000 0.1077 0.488 0.512
#> ERR342872 2 0.788 0.7310 0.236 0.764
#> ERR342828 2 0.788 0.7298 0.236 0.764
#> ERR342840 1 0.327 0.7172 0.940 0.060
#> ERR342831 1 0.745 0.6040 0.788 0.212
#> ERR342818 1 0.625 0.6829 0.844 0.156
#> ERR342862 1 0.327 0.7172 0.940 0.060
#> ERR342894 1 0.745 0.6040 0.788 0.212
#> ERR342884 2 0.788 0.7310 0.236 0.764
#> ERR342891 1 0.118 0.7322 0.984 0.016
#> ERR342890 1 0.745 0.6040 0.788 0.212
#> ERR342836 2 0.788 0.7298 0.236 0.764
#> ERR342879 1 0.625 0.6829 0.844 0.156
#> ERR342848 1 0.625 0.6829 0.844 0.156
#> ERR342861 1 0.118 0.7322 0.984 0.016
#> ERR342814 1 0.990 -0.0194 0.560 0.440
#> ERR342870 1 0.730 0.6423 0.796 0.204
#> ERR342901 1 0.118 0.7322 0.984 0.016
#> ERR342908 1 0.730 0.6423 0.796 0.204
#> ERR342815 2 0.788 0.7298 0.236 0.764
#> ERR342897 2 1.000 0.1077 0.488 0.512
#> ERR342833 2 0.788 0.7310 0.236 0.764
#> ERR342817 2 1.000 0.1077 0.488 0.512
#> ERR342810 1 0.990 -0.0194 0.560 0.440
#> ERR342867 1 0.839 0.5467 0.732 0.268
#> ERR342847 1 0.327 0.7172 0.940 0.060
#> ERR342855 1 0.118 0.7322 0.984 0.016
#> ERR342851 1 0.625 0.6829 0.844 0.156
#> ERR342813 1 0.745 0.6040 0.788 0.212
#> ERR342883 1 0.625 0.6829 0.844 0.156
#> ERR342856 2 1.000 0.1077 0.488 0.512
#> ERR342822 2 0.788 0.7298 0.236 0.764
#> ERR342892 1 0.118 0.7322 0.984 0.016
#> ERR342842 1 0.118 0.7322 0.984 0.016
#> ERR342902 2 0.788 0.7310 0.236 0.764
#> ERR342900 1 0.990 -0.0194 0.560 0.440
#> ERR342888 1 0.745 0.6040 0.788 0.212
#> ERR342812 1 0.118 0.7322 0.984 0.016
#> ERR342853 1 0.990 -0.0194 0.560 0.440
#> ERR342866 1 0.327 0.7172 0.940 0.060
#> ERR342820 1 0.730 0.6423 0.796 0.204
#> ERR342895 1 0.118 0.7322 0.984 0.016
#> ERR342825 2 1.000 0.1077 0.488 0.512
#> ERR342826 2 1.000 0.1077 0.488 0.512
#> ERR342875 2 0.788 0.7298 0.236 0.764
#> ERR342834 2 1.000 0.1077 0.488 0.512
#> ERR342898 1 0.839 0.5467 0.732 0.268
#> ERR342886 1 0.990 -0.0194 0.560 0.440
#> ERR342838 1 0.118 0.7322 0.984 0.016
#> ERR342882 1 0.118 0.7322 0.984 0.016
#> ERR342807 2 0.788 0.7310 0.236 0.764
#> ERR342873 1 0.625 0.6829 0.844 0.156
#> ERR342844 1 0.839 0.5467 0.732 0.268
#> ERR342874 1 0.327 0.7172 0.940 0.060
#> ERR342893 1 0.625 0.6829 0.844 0.156
#> ERR342859 2 1.000 0.1077 0.488 0.512
#> ERR342830 1 0.990 -0.0194 0.560 0.440
#> ERR342880 1 0.625 0.6829 0.844 0.156
#> ERR342887 1 0.118 0.7322 0.984 0.016
#> ERR342854 1 0.118 0.7322 0.984 0.016
#> ERR342904 1 0.730 0.6423 0.796 0.204
#> ERR342881 1 0.327 0.7172 0.940 0.060
#> ERR342858 1 0.625 0.6829 0.844 0.156
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.7529 0.3562 0.624 0.060 0.316
#> ERR342843 1 0.7529 0.3562 0.624 0.060 0.316
#> ERR342896 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342827 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342871 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342863 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342839 1 0.7588 0.3562 0.624 0.064 0.312
#> ERR342906 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342905 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342816 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342865 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342824 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342841 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342835 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342899 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342829 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342850 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342849 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342811 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342837 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342857 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342869 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342903 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342819 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342885 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342889 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342864 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342860 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342808 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342823 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342907 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342852 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342832 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342868 1 0.7588 0.3562 0.624 0.064 0.312
#> ERR342821 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342878 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342876 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342809 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342846 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342872 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342828 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342840 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342831 1 0.7529 0.3562 0.624 0.060 0.316
#> ERR342818 1 0.8513 0.4338 0.596 0.140 0.264
#> ERR342862 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342894 1 0.7529 0.3562 0.624 0.060 0.316
#> ERR342884 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342891 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342890 1 0.7588 0.3562 0.624 0.064 0.312
#> ERR342836 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342879 1 0.8513 0.4338 0.596 0.140 0.264
#> ERR342848 1 0.8513 0.4338 0.596 0.140 0.264
#> ERR342861 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342814 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342870 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342901 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342908 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342815 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342897 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342833 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342817 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342810 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342867 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342847 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342855 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342851 1 0.8513 0.4338 0.596 0.140 0.264
#> ERR342813 1 0.7529 0.3562 0.624 0.060 0.316
#> ERR342883 1 0.8513 0.4338 0.596 0.140 0.264
#> ERR342856 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342822 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342892 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342842 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342902 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342900 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342888 1 0.7588 0.3562 0.624 0.064 0.312
#> ERR342812 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342853 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342866 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342820 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342895 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342825 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342826 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342875 2 0.2173 0.7756 0.048 0.944 0.008
#> ERR342834 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342898 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342886 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342838 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342882 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342807 2 0.5202 0.7441 0.044 0.820 0.136
#> ERR342873 1 0.8513 0.4338 0.596 0.140 0.264
#> ERR342844 1 0.9730 0.0222 0.428 0.232 0.340
#> ERR342874 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342893 1 0.8513 0.4338 0.596 0.140 0.264
#> ERR342859 3 0.8042 1.0000 0.216 0.136 0.648
#> ERR342830 2 0.8266 0.6157 0.240 0.624 0.136
#> ERR342880 1 0.8513 0.4338 0.596 0.140 0.264
#> ERR342887 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342854 1 0.0424 0.6056 0.992 0.008 0.000
#> ERR342904 1 0.9046 0.1773 0.528 0.160 0.312
#> ERR342881 1 0.5757 0.5673 0.792 0.056 0.152
#> ERR342858 1 0.8513 0.4338 0.596 0.140 0.264
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.7860 0.3578 0.464 0.016 0.168 NA
#> ERR342843 1 0.7881 0.3578 0.464 0.016 0.172 NA
#> ERR342896 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342827 2 0.5501 0.7361 0.012 0.748 0.076 NA
#> ERR342871 1 0.9087 -0.2609 0.388 0.092 0.344 NA
#> ERR342863 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342839 1 0.7909 0.3578 0.460 0.016 0.176 NA
#> ERR342906 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342905 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342816 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342865 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342824 1 0.0779 0.5724 0.980 0.016 0.004 NA
#> ERR342841 2 0.5452 0.7362 0.012 0.748 0.068 NA
#> ERR342835 1 0.6510 0.4988 0.636 0.036 0.044 NA
#> ERR342899 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342829 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342850 1 0.9087 -0.2609 0.388 0.092 0.344 NA
#> ERR342849 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342811 1 0.9067 -0.2607 0.388 0.092 0.348 NA
#> ERR342837 1 0.6510 0.4988 0.636 0.036 0.044 NA
#> ERR342857 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342869 1 0.9087 -0.2609 0.388 0.092 0.344 NA
#> ERR342903 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342819 1 0.6510 0.4988 0.636 0.036 0.044 NA
#> ERR342885 3 0.4362 0.6730 0.096 0.088 0.816 NA
#> ERR342889 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342864 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342860 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342808 1 0.9067 -0.2607 0.388 0.092 0.348 NA
#> ERR342823 1 0.0779 0.5724 0.980 0.016 0.004 NA
#> ERR342907 2 0.5452 0.7362 0.012 0.748 0.068 NA
#> ERR342852 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342832 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342868 1 0.7909 0.3578 0.460 0.016 0.176 NA
#> ERR342821 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342878 2 0.5452 0.7362 0.012 0.748 0.068 NA
#> ERR342876 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342809 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342846 3 0.5040 0.6724 0.096 0.088 0.796 NA
#> ERR342872 2 0.5478 0.7361 0.012 0.748 0.072 NA
#> ERR342828 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342840 1 0.6562 0.4989 0.636 0.036 0.048 NA
#> ERR342831 1 0.7860 0.3578 0.464 0.016 0.168 NA
#> ERR342818 1 0.9468 0.0684 0.380 0.120 0.224 NA
#> ERR342862 1 0.6611 0.4989 0.636 0.036 0.052 NA
#> ERR342894 1 0.7881 0.3578 0.464 0.016 0.172 NA
#> ERR342884 2 0.5452 0.7362 0.012 0.748 0.068 NA
#> ERR342891 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342890 1 0.7909 0.3578 0.460 0.016 0.176 NA
#> ERR342836 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342879 1 0.9468 0.0684 0.380 0.120 0.224 NA
#> ERR342848 1 0.9468 0.0684 0.380 0.120 0.224 NA
#> ERR342861 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342814 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342870 1 0.9067 -0.2607 0.388 0.092 0.348 NA
#> ERR342901 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342908 1 0.9067 -0.2607 0.388 0.092 0.348 NA
#> ERR342815 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342897 3 0.5040 0.6724 0.096 0.088 0.796 NA
#> ERR342833 2 0.5452 0.7362 0.012 0.748 0.068 NA
#> ERR342817 3 0.4362 0.6730 0.096 0.088 0.816 NA
#> ERR342810 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342867 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342847 1 0.6562 0.4989 0.636 0.036 0.048 NA
#> ERR342855 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342851 1 0.9468 0.0684 0.380 0.120 0.224 NA
#> ERR342813 1 0.7881 0.3578 0.464 0.016 0.172 NA
#> ERR342883 1 0.9468 0.0684 0.380 0.120 0.224 NA
#> ERR342856 3 0.5040 0.6724 0.096 0.088 0.796 NA
#> ERR342822 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342892 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342842 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342902 2 0.5452 0.7362 0.012 0.748 0.068 NA
#> ERR342900 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342888 1 0.7909 0.3578 0.460 0.016 0.176 NA
#> ERR342812 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342853 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342866 1 0.6562 0.4989 0.636 0.036 0.048 NA
#> ERR342820 1 0.9087 -0.2609 0.388 0.092 0.344 NA
#> ERR342895 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342825 3 0.4362 0.6730 0.096 0.088 0.816 NA
#> ERR342826 3 0.4362 0.6730 0.096 0.088 0.816 NA
#> ERR342875 2 0.0967 0.7885 0.004 0.976 0.016 NA
#> ERR342834 3 0.4362 0.6730 0.096 0.088 0.816 NA
#> ERR342898 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342886 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342838 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342882 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342807 2 0.5452 0.7362 0.012 0.748 0.068 NA
#> ERR342873 1 0.9468 0.0684 0.380 0.120 0.224 NA
#> ERR342844 3 0.9540 0.5914 0.280 0.180 0.384 NA
#> ERR342874 1 0.6611 0.4989 0.636 0.036 0.052 NA
#> ERR342893 1 0.9468 0.0684 0.380 0.120 0.224 NA
#> ERR342859 3 0.5040 0.6724 0.096 0.088 0.796 NA
#> ERR342830 2 0.6530 0.7001 0.096 0.700 0.044 NA
#> ERR342880 1 0.9468 0.0684 0.380 0.120 0.224 NA
#> ERR342887 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342854 1 0.0592 0.5728 0.984 0.016 0.000 NA
#> ERR342904 1 0.9067 -0.2607 0.388 0.092 0.348 NA
#> ERR342881 1 0.6611 0.4989 0.636 0.036 0.052 NA
#> ERR342858 1 0.9468 0.0684 0.380 0.120 0.224 NA
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.6083 0.985 0.352 0.008 0.004 0.092 0.544
#> ERR342843 5 0.6126 0.985 0.352 0.008 0.004 0.096 0.540
#> ERR342896 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.5309 0.639 0.012 0.656 0.288 0.028 0.016
#> ERR342871 4 0.7220 0.439 0.260 0.064 0.060 0.568 0.048
#> ERR342863 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342839 5 0.6548 0.983 0.352 0.008 0.024 0.092 0.524
#> ERR342906 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342905 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342816 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342865 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342824 1 0.1153 0.733 0.964 0.000 0.024 0.004 0.008
#> ERR342841 2 0.4919 0.640 0.012 0.656 0.304 0.028 0.000
#> ERR342835 1 0.7620 0.372 0.540 0.036 0.108 0.072 0.244
#> ERR342899 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342829 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.7220 0.439 0.260 0.064 0.060 0.568 0.048
#> ERR342849 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342811 4 0.7163 0.440 0.260 0.064 0.056 0.572 0.048
#> ERR342837 1 0.7620 0.372 0.540 0.036 0.108 0.072 0.244
#> ERR342857 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342869 4 0.7220 0.439 0.260 0.064 0.060 0.568 0.048
#> ERR342903 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342819 1 0.7620 0.372 0.540 0.036 0.108 0.072 0.244
#> ERR342885 4 0.8507 -0.921 0.040 0.084 0.308 0.396 0.172
#> ERR342889 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342864 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342860 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342808 4 0.7163 0.440 0.260 0.064 0.056 0.572 0.048
#> ERR342823 1 0.1153 0.733 0.964 0.000 0.024 0.004 0.008
#> ERR342907 2 0.4919 0.640 0.012 0.656 0.304 0.028 0.000
#> ERR342852 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342832 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342868 5 0.6548 0.983 0.352 0.008 0.024 0.092 0.524
#> ERR342821 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342878 2 0.4919 0.640 0.012 0.656 0.304 0.028 0.000
#> ERR342876 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.8324 1.000 0.040 0.084 0.380 0.364 0.132
#> ERR342872 2 0.5309 0.639 0.012 0.656 0.288 0.028 0.016
#> ERR342828 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342840 1 0.7650 0.372 0.540 0.036 0.108 0.076 0.240
#> ERR342831 5 0.6083 0.985 0.352 0.008 0.004 0.092 0.544
#> ERR342818 4 0.8508 0.446 0.268 0.088 0.096 0.456 0.092
#> ERR342862 1 0.7675 0.371 0.540 0.036 0.120 0.072 0.232
#> ERR342894 5 0.6126 0.985 0.352 0.008 0.004 0.096 0.540
#> ERR342884 2 0.4919 0.640 0.012 0.656 0.304 0.028 0.000
#> ERR342891 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.6548 0.983 0.352 0.008 0.024 0.092 0.524
#> ERR342836 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342879 4 0.8508 0.446 0.268 0.088 0.096 0.456 0.092
#> ERR342848 4 0.8508 0.446 0.268 0.088 0.092 0.456 0.096
#> ERR342861 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342870 4 0.7163 0.440 0.260 0.064 0.056 0.572 0.048
#> ERR342901 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.7163 0.440 0.260 0.064 0.056 0.572 0.048
#> ERR342815 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342897 3 0.8324 1.000 0.040 0.084 0.380 0.364 0.132
#> ERR342833 2 0.4919 0.640 0.012 0.656 0.304 0.028 0.000
#> ERR342817 4 0.8507 -0.921 0.040 0.084 0.308 0.396 0.172
#> ERR342810 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342867 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342847 1 0.7650 0.372 0.540 0.036 0.108 0.076 0.240
#> ERR342855 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.8508 0.446 0.268 0.088 0.096 0.456 0.092
#> ERR342813 5 0.6126 0.985 0.352 0.008 0.004 0.096 0.540
#> ERR342883 4 0.8508 0.446 0.268 0.088 0.096 0.456 0.092
#> ERR342856 3 0.8324 1.000 0.040 0.084 0.380 0.364 0.132
#> ERR342822 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342892 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.4919 0.640 0.012 0.656 0.304 0.028 0.000
#> ERR342900 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342888 5 0.6548 0.983 0.352 0.008 0.024 0.092 0.524
#> ERR342812 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342866 1 0.7650 0.372 0.540 0.036 0.108 0.076 0.240
#> ERR342820 4 0.7220 0.439 0.260 0.064 0.060 0.568 0.048
#> ERR342895 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342825 4 0.8507 -0.921 0.040 0.084 0.308 0.396 0.172
#> ERR342826 4 0.8527 -0.922 0.040 0.084 0.308 0.392 0.176
#> ERR342875 2 0.0451 0.702 0.008 0.988 0.000 0.004 0.000
#> ERR342834 4 0.8527 -0.922 0.040 0.084 0.308 0.392 0.176
#> ERR342898 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342886 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342838 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.5052 0.640 0.012 0.656 0.300 0.028 0.004
#> ERR342873 4 0.8508 0.446 0.268 0.088 0.096 0.456 0.092
#> ERR342844 4 0.6044 0.484 0.172 0.152 0.008 0.652 0.016
#> ERR342874 1 0.7675 0.371 0.540 0.036 0.120 0.072 0.232
#> ERR342893 4 0.8508 0.446 0.268 0.088 0.096 0.456 0.092
#> ERR342859 3 0.8324 1.000 0.040 0.084 0.380 0.364 0.132
#> ERR342830 2 0.7993 0.605 0.096 0.552 0.088 0.088 0.176
#> ERR342880 4 0.8508 0.446 0.268 0.088 0.096 0.456 0.092
#> ERR342887 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.757 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.7163 0.440 0.260 0.064 0.056 0.572 0.048
#> ERR342881 1 0.7675 0.371 0.540 0.036 0.120 0.072 0.232
#> ERR342858 4 0.8508 0.446 0.268 0.088 0.096 0.456 0.092
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.582 0.965 0.236 0.036 0.100 0.012 0.616 0.000
#> ERR342843 5 0.582 0.965 0.236 0.036 0.100 0.012 0.616 0.000
#> ERR342896 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 6 0.481 0.979 0.004 0.272 0.012 0.032 0.012 0.668
#> ERR342871 4 0.803 0.480 0.140 0.048 0.280 0.432 0.044 0.056
#> ERR342863 2 0.595 0.138 0.004 0.524 0.008 0.072 0.032 0.360
#> ERR342839 5 0.738 0.956 0.236 0.056 0.104 0.036 0.528 0.040
#> ERR342906 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342905 2 0.285 0.596 0.064 0.880 0.020 0.020 0.016 0.000
#> ERR342816 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342865 2 0.595 0.138 0.004 0.524 0.008 0.072 0.032 0.360
#> ERR342824 1 0.187 0.704 0.932 0.004 0.004 0.016 0.008 0.036
#> ERR342841 6 0.433 0.993 0.004 0.272 0.012 0.024 0.000 0.688
#> ERR342835 1 0.823 0.335 0.428 0.140 0.020 0.100 0.244 0.068
#> ERR342899 2 0.246 0.598 0.064 0.896 0.020 0.016 0.004 0.000
#> ERR342829 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.803 0.480 0.140 0.048 0.280 0.432 0.044 0.056
#> ERR342849 2 0.246 0.598 0.064 0.896 0.020 0.016 0.004 0.000
#> ERR342811 4 0.803 0.480 0.140 0.044 0.280 0.432 0.048 0.056
#> ERR342837 1 0.823 0.335 0.428 0.140 0.020 0.100 0.244 0.068
#> ERR342857 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342869 4 0.803 0.480 0.140 0.048 0.280 0.432 0.044 0.056
#> ERR342903 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342819 1 0.823 0.335 0.428 0.140 0.020 0.100 0.244 0.068
#> ERR342885 3 0.166 0.968 0.008 0.024 0.940 0.000 0.004 0.024
#> ERR342889 2 0.595 0.138 0.004 0.524 0.008 0.072 0.032 0.360
#> ERR342864 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342860 2 0.293 0.595 0.064 0.876 0.028 0.016 0.016 0.000
#> ERR342808 4 0.803 0.480 0.140 0.044 0.280 0.432 0.048 0.056
#> ERR342823 1 0.187 0.704 0.932 0.004 0.004 0.016 0.008 0.036
#> ERR342907 6 0.433 0.993 0.004 0.272 0.012 0.024 0.000 0.688
#> ERR342852 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342832 2 0.595 0.138 0.004 0.524 0.008 0.072 0.032 0.360
#> ERR342868 5 0.738 0.956 0.236 0.056 0.104 0.036 0.528 0.040
#> ERR342821 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342878 6 0.433 0.993 0.004 0.272 0.012 0.024 0.000 0.688
#> ERR342876 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.320 0.961 0.008 0.032 0.868 0.008 0.032 0.052
#> ERR342872 6 0.461 0.987 0.004 0.272 0.012 0.032 0.004 0.676
#> ERR342828 2 0.597 0.136 0.004 0.524 0.008 0.068 0.036 0.360
#> ERR342840 1 0.825 0.334 0.428 0.140 0.024 0.100 0.244 0.064
#> ERR342831 5 0.582 0.965 0.236 0.036 0.100 0.012 0.616 0.000
#> ERR342818 4 0.886 0.487 0.204 0.088 0.112 0.412 0.092 0.092
#> ERR342862 1 0.826 0.333 0.428 0.140 0.020 0.108 0.236 0.068
#> ERR342894 5 0.582 0.965 0.236 0.036 0.100 0.012 0.616 0.000
#> ERR342884 6 0.440 0.991 0.004 0.272 0.012 0.028 0.000 0.684
#> ERR342891 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.738 0.956 0.236 0.056 0.104 0.036 0.528 0.040
#> ERR342836 2 0.595 0.138 0.004 0.524 0.008 0.072 0.032 0.360
#> ERR342879 4 0.886 0.487 0.204 0.088 0.112 0.412 0.092 0.092
#> ERR342848 4 0.893 0.485 0.204 0.088 0.108 0.404 0.100 0.096
#> ERR342861 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.257 0.597 0.064 0.892 0.020 0.016 0.008 0.000
#> ERR342870 4 0.803 0.480 0.140 0.040 0.280 0.432 0.052 0.056
#> ERR342901 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.803 0.480 0.140 0.044 0.280 0.432 0.048 0.056
#> ERR342815 2 0.598 0.134 0.004 0.524 0.008 0.064 0.040 0.360
#> ERR342897 3 0.320 0.961 0.008 0.032 0.868 0.008 0.032 0.052
#> ERR342833 6 0.433 0.993 0.004 0.272 0.012 0.024 0.000 0.688
#> ERR342817 3 0.166 0.968 0.008 0.024 0.940 0.000 0.004 0.024
#> ERR342810 2 0.285 0.596 0.064 0.880 0.020 0.020 0.016 0.000
#> ERR342867 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342847 1 0.825 0.334 0.428 0.140 0.024 0.100 0.244 0.064
#> ERR342855 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.886 0.487 0.204 0.088 0.112 0.412 0.092 0.092
#> ERR342813 5 0.582 0.965 0.236 0.036 0.100 0.012 0.616 0.000
#> ERR342883 4 0.886 0.487 0.204 0.088 0.112 0.412 0.092 0.092
#> ERR342856 3 0.320 0.961 0.008 0.032 0.868 0.008 0.032 0.052
#> ERR342822 2 0.597 0.136 0.004 0.524 0.008 0.068 0.036 0.360
#> ERR342892 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342902 6 0.433 0.993 0.004 0.272 0.012 0.024 0.000 0.688
#> ERR342900 2 0.246 0.598 0.064 0.896 0.020 0.016 0.004 0.000
#> ERR342888 5 0.738 0.956 0.236 0.056 0.104 0.036 0.528 0.040
#> ERR342812 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.285 0.596 0.064 0.880 0.020 0.020 0.016 0.000
#> ERR342866 1 0.825 0.334 0.428 0.140 0.024 0.100 0.244 0.064
#> ERR342820 4 0.803 0.480 0.140 0.048 0.280 0.432 0.044 0.056
#> ERR342895 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.166 0.968 0.008 0.024 0.940 0.000 0.004 0.024
#> ERR342826 3 0.178 0.968 0.008 0.024 0.936 0.000 0.008 0.024
#> ERR342875 2 0.597 0.136 0.004 0.524 0.008 0.068 0.036 0.360
#> ERR342834 3 0.166 0.968 0.008 0.024 0.940 0.000 0.004 0.024
#> ERR342898 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342886 2 0.293 0.595 0.064 0.876 0.028 0.016 0.016 0.000
#> ERR342838 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342807 6 0.468 0.980 0.004 0.272 0.012 0.036 0.004 0.672
#> ERR342873 4 0.886 0.487 0.204 0.088 0.112 0.412 0.092 0.092
#> ERR342844 4 0.683 0.486 0.072 0.048 0.304 0.524 0.020 0.032
#> ERR342874 1 0.826 0.333 0.428 0.140 0.020 0.108 0.236 0.068
#> ERR342893 4 0.886 0.487 0.204 0.088 0.112 0.412 0.092 0.092
#> ERR342859 3 0.320 0.961 0.008 0.032 0.868 0.008 0.032 0.052
#> ERR342830 2 0.293 0.595 0.064 0.876 0.028 0.016 0.016 0.000
#> ERR342880 4 0.886 0.487 0.204 0.088 0.112 0.412 0.092 0.092
#> ERR342887 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.000 0.743 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.803 0.480 0.140 0.040 0.280 0.432 0.052 0.056
#> ERR342881 1 0.826 0.333 0.428 0.140 0.020 0.108 0.236 0.068
#> ERR342858 4 0.886 0.487 0.204 0.088 0.112 0.412 0.092 0.092
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "skmeans"]
# you can also extract it by
# res = res_list["SD:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.836 0.962 0.981 0.4761 0.531 0.531
#> 3 3 0.772 0.831 0.916 0.3914 0.754 0.563
#> 4 4 0.706 0.659 0.757 0.1200 0.836 0.587
#> 5 5 0.822 0.805 0.795 0.0576 0.902 0.671
#> 6 6 0.818 0.864 0.871 0.0380 0.968 0.851
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.0376 0.967 0.996 0.004
#> ERR342843 1 0.0376 0.967 0.996 0.004
#> ERR342896 1 0.0000 0.969 1.000 0.000
#> ERR342827 2 0.0000 0.999 0.000 1.000
#> ERR342871 1 0.0000 0.969 1.000 0.000
#> ERR342863 2 0.0000 0.999 0.000 1.000
#> ERR342839 1 0.0376 0.967 0.996 0.004
#> ERR342906 1 0.7299 0.776 0.796 0.204
#> ERR342905 2 0.0000 0.999 0.000 1.000
#> ERR342816 1 0.7299 0.776 0.796 0.204
#> ERR342865 2 0.0000 0.999 0.000 1.000
#> ERR342824 1 0.0000 0.969 1.000 0.000
#> ERR342841 2 0.0000 0.999 0.000 1.000
#> ERR342835 1 0.0000 0.969 1.000 0.000
#> ERR342899 2 0.0000 0.999 0.000 1.000
#> ERR342829 1 0.0000 0.969 1.000 0.000
#> ERR342850 1 0.0000 0.969 1.000 0.000
#> ERR342849 2 0.0000 0.999 0.000 1.000
#> ERR342811 1 0.0000 0.969 1.000 0.000
#> ERR342837 1 0.0000 0.969 1.000 0.000
#> ERR342857 1 0.7299 0.776 0.796 0.204
#> ERR342869 1 0.0000 0.969 1.000 0.000
#> ERR342903 1 0.0000 0.969 1.000 0.000
#> ERR342819 1 0.0000 0.969 1.000 0.000
#> ERR342885 2 0.0376 0.997 0.004 0.996
#> ERR342889 2 0.0000 0.999 0.000 1.000
#> ERR342864 1 0.7299 0.776 0.796 0.204
#> ERR342860 2 0.0000 0.999 0.000 1.000
#> ERR342808 1 0.0000 0.969 1.000 0.000
#> ERR342823 1 0.0000 0.969 1.000 0.000
#> ERR342907 2 0.0000 0.999 0.000 1.000
#> ERR342852 1 0.7299 0.776 0.796 0.204
#> ERR342832 2 0.0000 0.999 0.000 1.000
#> ERR342868 1 0.0376 0.967 0.996 0.004
#> ERR342821 1 0.7299 0.776 0.796 0.204
#> ERR342878 2 0.0000 0.999 0.000 1.000
#> ERR342876 1 0.0000 0.969 1.000 0.000
#> ERR342809 1 0.0000 0.969 1.000 0.000
#> ERR342846 2 0.0376 0.997 0.004 0.996
#> ERR342872 2 0.0000 0.999 0.000 1.000
#> ERR342828 2 0.0000 0.999 0.000 1.000
#> ERR342840 1 0.0000 0.969 1.000 0.000
#> ERR342831 1 0.0376 0.967 0.996 0.004
#> ERR342818 1 0.0376 0.967 0.996 0.004
#> ERR342862 1 0.0000 0.969 1.000 0.000
#> ERR342894 1 0.0376 0.967 0.996 0.004
#> ERR342884 2 0.0000 0.999 0.000 1.000
#> ERR342891 1 0.0000 0.969 1.000 0.000
#> ERR342890 1 0.0376 0.967 0.996 0.004
#> ERR342836 2 0.0000 0.999 0.000 1.000
#> ERR342879 1 0.0376 0.967 0.996 0.004
#> ERR342848 1 0.0376 0.967 0.996 0.004
#> ERR342861 1 0.0000 0.969 1.000 0.000
#> ERR342814 2 0.0000 0.999 0.000 1.000
#> ERR342870 1 0.0000 0.969 1.000 0.000
#> ERR342901 1 0.0000 0.969 1.000 0.000
#> ERR342908 1 0.0000 0.969 1.000 0.000
#> ERR342815 2 0.0000 0.999 0.000 1.000
#> ERR342897 2 0.0376 0.997 0.004 0.996
#> ERR342833 2 0.0000 0.999 0.000 1.000
#> ERR342817 2 0.0376 0.997 0.004 0.996
#> ERR342810 2 0.0000 0.999 0.000 1.000
#> ERR342867 1 0.7299 0.776 0.796 0.204
#> ERR342847 1 0.0000 0.969 1.000 0.000
#> ERR342855 1 0.0000 0.969 1.000 0.000
#> ERR342851 1 0.0376 0.967 0.996 0.004
#> ERR342813 1 0.0376 0.967 0.996 0.004
#> ERR342883 1 0.0376 0.967 0.996 0.004
#> ERR342856 2 0.0376 0.997 0.004 0.996
#> ERR342822 2 0.0000 0.999 0.000 1.000
#> ERR342892 1 0.0000 0.969 1.000 0.000
#> ERR342842 1 0.0000 0.969 1.000 0.000
#> ERR342902 2 0.0000 0.999 0.000 1.000
#> ERR342900 2 0.0000 0.999 0.000 1.000
#> ERR342888 1 0.0376 0.967 0.996 0.004
#> ERR342812 1 0.0000 0.969 1.000 0.000
#> ERR342853 2 0.0000 0.999 0.000 1.000
#> ERR342866 1 0.0000 0.969 1.000 0.000
#> ERR342820 1 0.0000 0.969 1.000 0.000
#> ERR342895 1 0.0000 0.969 1.000 0.000
#> ERR342825 2 0.0376 0.997 0.004 0.996
#> ERR342826 2 0.0376 0.997 0.004 0.996
#> ERR342875 2 0.0000 0.999 0.000 1.000
#> ERR342834 2 0.0376 0.997 0.004 0.996
#> ERR342898 1 0.7299 0.776 0.796 0.204
#> ERR342886 2 0.0000 0.999 0.000 1.000
#> ERR342838 1 0.0000 0.969 1.000 0.000
#> ERR342882 1 0.0000 0.969 1.000 0.000
#> ERR342807 2 0.0000 0.999 0.000 1.000
#> ERR342873 1 0.0376 0.967 0.996 0.004
#> ERR342844 1 0.7299 0.776 0.796 0.204
#> ERR342874 1 0.0000 0.969 1.000 0.000
#> ERR342893 1 0.0376 0.967 0.996 0.004
#> ERR342859 2 0.0376 0.997 0.004 0.996
#> ERR342830 2 0.0000 0.999 0.000 1.000
#> ERR342880 1 0.0376 0.967 0.996 0.004
#> ERR342887 1 0.0000 0.969 1.000 0.000
#> ERR342854 1 0.0000 0.969 1.000 0.000
#> ERR342904 1 0.0000 0.969 1.000 0.000
#> ERR342881 1 0.0000 0.969 1.000 0.000
#> ERR342858 1 0.0376 0.967 0.996 0.004
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342843 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342896 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342827 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342871 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342863 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342839 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342906 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342905 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342816 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342865 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342824 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342841 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342835 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342899 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342829 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342850 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342849 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342811 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342837 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342857 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342869 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342903 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342819 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342885 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342889 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342864 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342860 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342808 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342823 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342907 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342852 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342832 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342868 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342821 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342878 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342876 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342809 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342846 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342872 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342828 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342840 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342831 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342818 1 0.6291 0.267 0.532 0.000 0.468
#> ERR342862 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342894 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342884 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342891 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342890 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342836 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342879 1 0.6291 0.267 0.532 0.000 0.468
#> ERR342848 1 0.6291 0.267 0.532 0.000 0.468
#> ERR342861 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342814 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342870 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342901 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342908 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342815 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342897 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342833 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342817 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342810 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342867 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342847 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342855 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342851 1 0.6291 0.267 0.532 0.000 0.468
#> ERR342813 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342883 1 0.6291 0.267 0.532 0.000 0.468
#> ERR342856 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342822 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342892 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342842 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342902 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342900 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342888 1 0.5621 0.595 0.692 0.000 0.308
#> ERR342812 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342853 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342866 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342820 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342895 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342825 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342826 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342875 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342834 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342898 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342886 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342838 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342882 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342807 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342873 1 0.6291 0.267 0.532 0.000 0.468
#> ERR342844 3 0.0592 0.945 0.012 0.000 0.988
#> ERR342874 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342893 1 0.6291 0.267 0.532 0.000 0.468
#> ERR342859 3 0.2774 0.920 0.008 0.072 0.920
#> ERR342830 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342880 1 0.6291 0.267 0.532 0.000 0.468
#> ERR342887 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342854 1 0.0000 0.821 1.000 0.000 0.000
#> ERR342904 3 0.1860 0.935 0.052 0.000 0.948
#> ERR342881 1 0.0892 0.819 0.980 0.000 0.020
#> ERR342858 1 0.6291 0.267 0.532 0.000 0.468
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342843 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342896 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342827 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342871 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342863 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342839 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342906 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342905 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342816 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342865 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342824 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342841 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342835 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342899 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342829 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342850 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342849 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342811 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342837 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342857 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342869 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342903 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342819 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342885 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342889 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342864 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342860 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342808 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342823 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342907 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342852 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342832 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342868 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342821 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342878 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342876 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342846 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342872 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342828 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342840 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342831 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342818 4 0.3976 1.0000 0.112 0.004 0.044 0.840
#> ERR342862 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342894 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342884 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342891 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342890 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342836 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342879 4 0.3976 1.0000 0.112 0.004 0.044 0.840
#> ERR342848 4 0.3976 1.0000 0.112 0.004 0.044 0.840
#> ERR342861 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342814 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342870 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342901 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342908 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342815 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342897 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342833 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342817 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342810 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342867 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342847 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342855 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342851 4 0.3976 1.0000 0.112 0.004 0.044 0.840
#> ERR342813 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342883 4 0.3976 1.0000 0.112 0.004 0.044 0.840
#> ERR342856 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342822 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342892 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342902 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342900 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342888 3 0.7706 0.0822 0.224 0.000 0.412 0.364
#> ERR342812 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342853 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342866 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342820 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342895 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342825 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342826 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342875 2 0.0000 0.9935 0.000 1.000 0.000 0.000
#> ERR342834 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342898 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342886 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342838 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342807 2 0.0592 0.9889 0.000 0.984 0.016 0.000
#> ERR342873 4 0.3976 1.0000 0.112 0.004 0.044 0.840
#> ERR342844 3 0.4992 0.3568 0.000 0.000 0.524 0.476
#> ERR342874 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342893 4 0.3976 1.0000 0.112 0.004 0.044 0.840
#> ERR342859 3 0.0188 0.4678 0.000 0.004 0.996 0.000
#> ERR342830 2 0.0188 0.9931 0.000 0.996 0.000 0.004
#> ERR342880 4 0.3976 1.0000 0.112 0.004 0.044 0.840
#> ERR342887 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.7966 1.000 0.000 0.000 0.000
#> ERR342904 3 0.5281 0.3547 0.008 0.000 0.528 0.464
#> ERR342881 1 0.6498 0.3665 0.488 0.000 0.072 0.440
#> ERR342858 4 0.3976 1.0000 0.112 0.004 0.044 0.840
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342843 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342871 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342863 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342839 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342906 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342905 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342816 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342865 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342835 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342899 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342850 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342849 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342811 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342837 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342857 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342869 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342885 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342889 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342864 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342860 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342808 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342852 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342832 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342868 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342821 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342878 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342872 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342828 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342840 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342831 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342818 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
#> ERR342862 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342894 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342884 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342836 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342879 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
#> ERR342848 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342870 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342908 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342815 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342897 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342833 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342817 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342810 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342867 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342847 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
#> ERR342813 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342883 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
#> ERR342856 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342822 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342900 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342888 5 0.3891 0.694 0.060 0.000 0.004 0.128 0.808
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342866 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342820 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342826 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342875 2 0.0000 0.984 0.000 1.000 0.000 0.000 0.000
#> ERR342834 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342898 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342886 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.0727 0.980 0.000 0.980 0.004 0.004 0.012
#> ERR342873 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
#> ERR342844 3 0.4522 0.543 0.000 0.000 0.660 0.316 0.024
#> ERR342874 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342893 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
#> ERR342859 3 0.4920 0.445 0.000 0.012 0.572 0.012 0.404
#> ERR342830 2 0.1095 0.978 0.000 0.968 0.012 0.008 0.012
#> ERR342880 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342904 3 0.5188 0.533 0.008 0.000 0.636 0.308 0.048
#> ERR342881 5 0.7413 0.652 0.244 0.000 0.040 0.284 0.432
#> ERR342858 4 0.1653 1.000 0.024 0.000 0.004 0.944 0.028
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342843 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342871 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342863 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342839 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342906 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342905 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342816 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342865 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342835 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342899 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342849 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342811 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342837 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342857 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342869 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342885 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342889 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342864 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342860 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342808 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342852 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342832 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342868 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342821 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342878 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342872 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342828 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342840 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342831 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342818 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
#> ERR342862 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342894 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342884 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342836 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342879 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
#> ERR342848 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342870 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342815 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342897 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342833 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342817 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342810 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342867 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342847 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
#> ERR342813 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342883 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
#> ERR342856 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342822 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342900 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342888 5 0.0291 0.579 0.004 0.000 0.000 0.004 0.992 0.000
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342866 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342820 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342826 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342875 2 0.0000 0.957 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342834 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342898 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342886 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.0858 0.952 0.000 0.968 0.028 0.004 0.000 0.000
#> ERR342873 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
#> ERR342844 4 0.3499 0.748 0.000 0.000 0.044 0.812 0.012 0.132
#> ERR342874 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342893 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
#> ERR342859 3 0.4031 1.000 0.000 0.000 0.736 0.048 0.212 0.004
#> ERR342830 2 0.2314 0.934 0.000 0.900 0.056 0.008 0.000 0.036
#> ERR342880 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.4059 0.760 0.000 0.000 0.148 0.760 0.004 0.088
#> ERR342881 5 0.7635 0.555 0.140 0.000 0.140 0.024 0.396 0.300
#> ERR342858 6 0.2164 1.000 0.000 0.000 0.000 0.068 0.032 0.900
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "pam"]
# you can also extract it by
# res = res_list["SD:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 6.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 1.000 1.000 0.405 0.595 0.595
#> 3 3 1.000 1.000 1.000 0.281 0.886 0.808
#> 4 4 0.797 0.840 0.858 0.284 0.802 0.589
#> 5 5 0.960 0.961 0.982 0.145 0.939 0.790
#> 6 6 0.957 0.971 0.975 0.048 0.964 0.849
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 6
#> attr(,"optional")
#> [1] 2 3 5
There is also optional best \(k\) = 2 3 5 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0 1 1 0
#> ERR342843 1 0 1 1 0
#> ERR342896 1 0 1 1 0
#> ERR342827 2 0 1 0 1
#> ERR342871 1 0 1 1 0
#> ERR342863 2 0 1 0 1
#> ERR342839 1 0 1 1 0
#> ERR342906 1 0 1 1 0
#> ERR342905 2 0 1 0 1
#> ERR342816 1 0 1 1 0
#> ERR342865 2 0 1 0 1
#> ERR342824 1 0 1 1 0
#> ERR342841 2 0 1 0 1
#> ERR342835 1 0 1 1 0
#> ERR342899 2 0 1 0 1
#> ERR342829 1 0 1 1 0
#> ERR342850 1 0 1 1 0
#> ERR342849 2 0 1 0 1
#> ERR342811 1 0 1 1 0
#> ERR342837 1 0 1 1 0
#> ERR342857 1 0 1 1 0
#> ERR342869 1 0 1 1 0
#> ERR342903 1 0 1 1 0
#> ERR342819 1 0 1 1 0
#> ERR342885 1 0 1 1 0
#> ERR342889 2 0 1 0 1
#> ERR342864 1 0 1 1 0
#> ERR342860 2 0 1 0 1
#> ERR342808 1 0 1 1 0
#> ERR342823 1 0 1 1 0
#> ERR342907 2 0 1 0 1
#> ERR342852 1 0 1 1 0
#> ERR342832 2 0 1 0 1
#> ERR342868 1 0 1 1 0
#> ERR342821 1 0 1 1 0
#> ERR342878 2 0 1 0 1
#> ERR342876 1 0 1 1 0
#> ERR342809 1 0 1 1 0
#> ERR342846 1 0 1 1 0
#> ERR342872 2 0 1 0 1
#> ERR342828 2 0 1 0 1
#> ERR342840 1 0 1 1 0
#> ERR342831 1 0 1 1 0
#> ERR342818 1 0 1 1 0
#> ERR342862 1 0 1 1 0
#> ERR342894 1 0 1 1 0
#> ERR342884 2 0 1 0 1
#> ERR342891 1 0 1 1 0
#> ERR342890 1 0 1 1 0
#> ERR342836 2 0 1 0 1
#> ERR342879 1 0 1 1 0
#> ERR342848 1 0 1 1 0
#> ERR342861 1 0 1 1 0
#> ERR342814 2 0 1 0 1
#> ERR342870 1 0 1 1 0
#> ERR342901 1 0 1 1 0
#> ERR342908 1 0 1 1 0
#> ERR342815 2 0 1 0 1
#> ERR342897 1 0 1 1 0
#> ERR342833 2 0 1 0 1
#> ERR342817 1 0 1 1 0
#> ERR342810 2 0 1 0 1
#> ERR342867 1 0 1 1 0
#> ERR342847 1 0 1 1 0
#> ERR342855 1 0 1 1 0
#> ERR342851 1 0 1 1 0
#> ERR342813 1 0 1 1 0
#> ERR342883 1 0 1 1 0
#> ERR342856 1 0 1 1 0
#> ERR342822 2 0 1 0 1
#> ERR342892 1 0 1 1 0
#> ERR342842 1 0 1 1 0
#> ERR342902 2 0 1 0 1
#> ERR342900 2 0 1 0 1
#> ERR342888 1 0 1 1 0
#> ERR342812 1 0 1 1 0
#> ERR342853 2 0 1 0 1
#> ERR342866 1 0 1 1 0
#> ERR342820 1 0 1 1 0
#> ERR342895 1 0 1 1 0
#> ERR342825 1 0 1 1 0
#> ERR342826 1 0 1 1 0
#> ERR342875 2 0 1 0 1
#> ERR342834 1 0 1 1 0
#> ERR342898 1 0 1 1 0
#> ERR342886 2 0 1 0 1
#> ERR342838 1 0 1 1 0
#> ERR342882 1 0 1 1 0
#> ERR342807 2 0 1 0 1
#> ERR342873 1 0 1 1 0
#> ERR342844 1 0 1 1 0
#> ERR342874 1 0 1 1 0
#> ERR342893 1 0 1 1 0
#> ERR342859 1 0 1 1 0
#> ERR342830 2 0 1 0 1
#> ERR342880 1 0 1 1 0
#> ERR342887 1 0 1 1 0
#> ERR342854 1 0 1 1 0
#> ERR342904 1 0 1 1 0
#> ERR342881 1 0 1 1 0
#> ERR342858 1 0 1 1 0
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0 1 1 0 0
#> ERR342843 1 0 1 1 0 0
#> ERR342896 1 0 1 1 0 0
#> ERR342827 2 0 1 0 1 0
#> ERR342871 1 0 1 1 0 0
#> ERR342863 2 0 1 0 1 0
#> ERR342839 1 0 1 1 0 0
#> ERR342906 1 0 1 1 0 0
#> ERR342905 2 0 1 0 1 0
#> ERR342816 1 0 1 1 0 0
#> ERR342865 2 0 1 0 1 0
#> ERR342824 1 0 1 1 0 0
#> ERR342841 2 0 1 0 1 0
#> ERR342835 1 0 1 1 0 0
#> ERR342899 2 0 1 0 1 0
#> ERR342829 1 0 1 1 0 0
#> ERR342850 1 0 1 1 0 0
#> ERR342849 2 0 1 0 1 0
#> ERR342811 1 0 1 1 0 0
#> ERR342837 1 0 1 1 0 0
#> ERR342857 1 0 1 1 0 0
#> ERR342869 1 0 1 1 0 0
#> ERR342903 1 0 1 1 0 0
#> ERR342819 1 0 1 1 0 0
#> ERR342885 3 0 1 0 0 1
#> ERR342889 2 0 1 0 1 0
#> ERR342864 1 0 1 1 0 0
#> ERR342860 2 0 1 0 1 0
#> ERR342808 1 0 1 1 0 0
#> ERR342823 1 0 1 1 0 0
#> ERR342907 2 0 1 0 1 0
#> ERR342852 1 0 1 1 0 0
#> ERR342832 2 0 1 0 1 0
#> ERR342868 1 0 1 1 0 0
#> ERR342821 1 0 1 1 0 0
#> ERR342878 2 0 1 0 1 0
#> ERR342876 1 0 1 1 0 0
#> ERR342809 1 0 1 1 0 0
#> ERR342846 3 0 1 0 0 1
#> ERR342872 2 0 1 0 1 0
#> ERR342828 2 0 1 0 1 0
#> ERR342840 1 0 1 1 0 0
#> ERR342831 1 0 1 1 0 0
#> ERR342818 1 0 1 1 0 0
#> ERR342862 1 0 1 1 0 0
#> ERR342894 1 0 1 1 0 0
#> ERR342884 2 0 1 0 1 0
#> ERR342891 1 0 1 1 0 0
#> ERR342890 1 0 1 1 0 0
#> ERR342836 2 0 1 0 1 0
#> ERR342879 1 0 1 1 0 0
#> ERR342848 1 0 1 1 0 0
#> ERR342861 1 0 1 1 0 0
#> ERR342814 2 0 1 0 1 0
#> ERR342870 1 0 1 1 0 0
#> ERR342901 1 0 1 1 0 0
#> ERR342908 1 0 1 1 0 0
#> ERR342815 2 0 1 0 1 0
#> ERR342897 3 0 1 0 0 1
#> ERR342833 2 0 1 0 1 0
#> ERR342817 3 0 1 0 0 1
#> ERR342810 2 0 1 0 1 0
#> ERR342867 1 0 1 1 0 0
#> ERR342847 1 0 1 1 0 0
#> ERR342855 1 0 1 1 0 0
#> ERR342851 1 0 1 1 0 0
#> ERR342813 1 0 1 1 0 0
#> ERR342883 1 0 1 1 0 0
#> ERR342856 3 0 1 0 0 1
#> ERR342822 2 0 1 0 1 0
#> ERR342892 1 0 1 1 0 0
#> ERR342842 1 0 1 1 0 0
#> ERR342902 2 0 1 0 1 0
#> ERR342900 2 0 1 0 1 0
#> ERR342888 1 0 1 1 0 0
#> ERR342812 1 0 1 1 0 0
#> ERR342853 2 0 1 0 1 0
#> ERR342866 1 0 1 1 0 0
#> ERR342820 1 0 1 1 0 0
#> ERR342895 1 0 1 1 0 0
#> ERR342825 3 0 1 0 0 1
#> ERR342826 3 0 1 0 0 1
#> ERR342875 2 0 1 0 1 0
#> ERR342834 3 0 1 0 0 1
#> ERR342898 1 0 1 1 0 0
#> ERR342886 2 0 1 0 1 0
#> ERR342838 1 0 1 1 0 0
#> ERR342882 1 0 1 1 0 0
#> ERR342807 2 0 1 0 1 0
#> ERR342873 1 0 1 1 0 0
#> ERR342844 1 0 1 1 0 0
#> ERR342874 1 0 1 1 0 0
#> ERR342893 1 0 1 1 0 0
#> ERR342859 3 0 1 0 0 1
#> ERR342830 2 0 1 0 1 0
#> ERR342880 1 0 1 1 0 0
#> ERR342887 1 0 1 1 0 0
#> ERR342854 1 0 1 1 0 0
#> ERR342904 1 0 1 1 0 0
#> ERR342881 1 0 1 1 0 0
#> ERR342858 1 0 1 1 0 0
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.000 0.427 1.000 0 0 0.000
#> ERR342843 1 0.000 0.427 1.000 0 0 0.000
#> ERR342896 1 0.499 0.746 0.532 0 0 0.468
#> ERR342827 2 0.000 1.000 0.000 1 0 0.000
#> ERR342871 4 0.000 0.927 0.000 0 0 1.000
#> ERR342863 2 0.000 1.000 0.000 1 0 0.000
#> ERR342839 1 0.000 0.427 1.000 0 0 0.000
#> ERR342906 4 0.000 0.927 0.000 0 0 1.000
#> ERR342905 2 0.000 1.000 0.000 1 0 0.000
#> ERR342816 4 0.000 0.927 0.000 0 0 1.000
#> ERR342865 2 0.000 1.000 0.000 1 0 0.000
#> ERR342824 1 0.499 0.746 0.532 0 0 0.468
#> ERR342841 2 0.000 1.000 0.000 1 0 0.000
#> ERR342835 1 0.499 0.731 0.520 0 0 0.480
#> ERR342899 2 0.000 1.000 0.000 1 0 0.000
#> ERR342829 1 0.499 0.746 0.532 0 0 0.468
#> ERR342850 4 0.000 0.927 0.000 0 0 1.000
#> ERR342849 2 0.000 1.000 0.000 1 0 0.000
#> ERR342811 4 0.000 0.927 0.000 0 0 1.000
#> ERR342837 1 0.499 0.731 0.520 0 0 0.480
#> ERR342857 4 0.000 0.927 0.000 0 0 1.000
#> ERR342869 4 0.000 0.927 0.000 0 0 1.000
#> ERR342903 1 0.499 0.746 0.532 0 0 0.468
#> ERR342819 1 0.499 0.731 0.520 0 0 0.480
#> ERR342885 3 0.000 1.000 0.000 0 1 0.000
#> ERR342889 2 0.000 1.000 0.000 1 0 0.000
#> ERR342864 4 0.000 0.927 0.000 0 0 1.000
#> ERR342860 2 0.000 1.000 0.000 1 0 0.000
#> ERR342808 4 0.000 0.927 0.000 0 0 1.000
#> ERR342823 1 0.499 0.746 0.532 0 0 0.468
#> ERR342907 2 0.000 1.000 0.000 1 0 0.000
#> ERR342852 4 0.000 0.927 0.000 0 0 1.000
#> ERR342832 2 0.000 1.000 0.000 1 0 0.000
#> ERR342868 1 0.000 0.427 1.000 0 0 0.000
#> ERR342821 4 0.000 0.927 0.000 0 0 1.000
#> ERR342878 2 0.000 1.000 0.000 1 0 0.000
#> ERR342876 1 0.499 0.746 0.532 0 0 0.468
#> ERR342809 1 0.499 0.746 0.532 0 0 0.468
#> ERR342846 3 0.000 1.000 0.000 0 1 0.000
#> ERR342872 2 0.000 1.000 0.000 1 0 0.000
#> ERR342828 2 0.000 1.000 0.000 1 0 0.000
#> ERR342840 1 0.499 0.731 0.520 0 0 0.480
#> ERR342831 1 0.000 0.427 1.000 0 0 0.000
#> ERR342818 4 0.208 0.856 0.084 0 0 0.916
#> ERR342862 1 0.499 0.731 0.520 0 0 0.480
#> ERR342894 1 0.000 0.427 1.000 0 0 0.000
#> ERR342884 2 0.000 1.000 0.000 1 0 0.000
#> ERR342891 1 0.499 0.746 0.532 0 0 0.468
#> ERR342890 1 0.000 0.427 1.000 0 0 0.000
#> ERR342836 2 0.000 1.000 0.000 1 0 0.000
#> ERR342879 4 0.201 0.861 0.080 0 0 0.920
#> ERR342848 4 0.471 -0.212 0.360 0 0 0.640
#> ERR342861 1 0.499 0.746 0.532 0 0 0.468
#> ERR342814 2 0.000 1.000 0.000 1 0 0.000
#> ERR342870 4 0.000 0.927 0.000 0 0 1.000
#> ERR342901 1 0.499 0.746 0.532 0 0 0.468
#> ERR342908 4 0.000 0.927 0.000 0 0 1.000
#> ERR342815 2 0.000 1.000 0.000 1 0 0.000
#> ERR342897 3 0.000 1.000 0.000 0 1 0.000
#> ERR342833 2 0.000 1.000 0.000 1 0 0.000
#> ERR342817 3 0.000 1.000 0.000 0 1 0.000
#> ERR342810 2 0.000 1.000 0.000 1 0 0.000
#> ERR342867 4 0.000 0.927 0.000 0 0 1.000
#> ERR342847 1 0.499 0.731 0.520 0 0 0.480
#> ERR342855 1 0.499 0.746 0.532 0 0 0.468
#> ERR342851 4 0.208 0.856 0.084 0 0 0.916
#> ERR342813 1 0.000 0.427 1.000 0 0 0.000
#> ERR342883 4 0.201 0.861 0.080 0 0 0.920
#> ERR342856 3 0.000 1.000 0.000 0 1 0.000
#> ERR342822 2 0.000 1.000 0.000 1 0 0.000
#> ERR342892 1 0.499 0.746 0.532 0 0 0.468
#> ERR342842 1 0.499 0.746 0.532 0 0 0.468
#> ERR342902 2 0.000 1.000 0.000 1 0 0.000
#> ERR342900 2 0.000 1.000 0.000 1 0 0.000
#> ERR342888 1 0.000 0.427 1.000 0 0 0.000
#> ERR342812 1 0.499 0.746 0.532 0 0 0.468
#> ERR342853 2 0.000 1.000 0.000 1 0 0.000
#> ERR342866 1 0.499 0.731 0.520 0 0 0.480
#> ERR342820 4 0.000 0.927 0.000 0 0 1.000
#> ERR342895 1 0.499 0.746 0.532 0 0 0.468
#> ERR342825 3 0.000 1.000 0.000 0 1 0.000
#> ERR342826 3 0.000 1.000 0.000 0 1 0.000
#> ERR342875 2 0.000 1.000 0.000 1 0 0.000
#> ERR342834 3 0.000 1.000 0.000 0 1 0.000
#> ERR342898 4 0.000 0.927 0.000 0 0 1.000
#> ERR342886 2 0.000 1.000 0.000 1 0 0.000
#> ERR342838 1 0.499 0.746 0.532 0 0 0.468
#> ERR342882 1 0.499 0.746 0.532 0 0 0.468
#> ERR342807 2 0.000 1.000 0.000 1 0 0.000
#> ERR342873 4 0.297 0.731 0.144 0 0 0.856
#> ERR342844 4 0.000 0.927 0.000 0 0 1.000
#> ERR342874 1 0.499 0.731 0.520 0 0 0.480
#> ERR342893 4 0.215 0.849 0.088 0 0 0.912
#> ERR342859 3 0.000 1.000 0.000 0 1 0.000
#> ERR342830 2 0.000 1.000 0.000 1 0 0.000
#> ERR342880 4 0.201 0.861 0.080 0 0 0.920
#> ERR342887 1 0.499 0.746 0.532 0 0 0.468
#> ERR342854 1 0.499 0.746 0.532 0 0 0.468
#> ERR342904 4 0.000 0.927 0.000 0 0 1.000
#> ERR342881 1 0.499 0.731 0.520 0 0 0.480
#> ERR342858 4 0.201 0.861 0.080 0 0 0.920
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342843 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342896 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342827 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342871 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342863 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342839 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342906 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342905 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342816 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342865 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342824 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342841 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342835 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342899 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342829 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342850 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342849 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342811 4 0.0510 0.925 0.016 0 0 0.984 0
#> ERR342837 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342857 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342869 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342903 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342819 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342885 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342889 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342864 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342860 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342808 4 0.0510 0.925 0.016 0 0 0.984 0
#> ERR342823 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342907 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342852 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342832 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342868 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342821 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342878 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342876 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342809 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342846 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342872 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342828 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342840 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342831 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342818 4 0.3210 0.761 0.212 0 0 0.788 0
#> ERR342862 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342894 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342884 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342891 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342890 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342836 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342879 4 0.2230 0.868 0.116 0 0 0.884 0
#> ERR342848 1 0.3534 0.622 0.744 0 0 0.256 0
#> ERR342861 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342814 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342870 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342901 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342908 4 0.0510 0.925 0.016 0 0 0.984 0
#> ERR342815 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342897 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342833 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342817 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342810 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342867 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342847 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342855 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342851 4 0.2690 0.828 0.156 0 0 0.844 0
#> ERR342813 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342883 4 0.2179 0.870 0.112 0 0 0.888 0
#> ERR342856 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342822 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342892 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342842 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342902 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342900 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342888 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342812 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342853 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342866 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342820 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342895 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342825 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342826 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342875 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342834 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342898 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342886 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342838 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342882 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342807 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342873 4 0.4235 0.345 0.424 0 0 0.576 0
#> ERR342844 4 0.0000 0.928 0.000 0 0 1.000 0
#> ERR342874 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342893 4 0.2377 0.857 0.128 0 0 0.872 0
#> ERR342859 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342830 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342880 4 0.2230 0.868 0.116 0 0 0.884 0
#> ERR342887 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342854 1 0.0000 0.984 1.000 0 0 0.000 0
#> ERR342904 4 0.0404 0.926 0.012 0 0 0.988 0
#> ERR342881 1 0.0404 0.980 0.988 0 0 0.012 0
#> ERR342858 4 0.2230 0.868 0.116 0 0 0.884 0
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342843 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342896 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342827 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342871 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342863 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342839 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342906 4 0.120 0.945 0.000 0 0 0.944 0 0.056
#> ERR342905 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342816 4 0.139 0.942 0.000 0 0 0.932 0 0.068
#> ERR342865 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342824 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342841 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342835 1 0.209 0.906 0.876 0 0 0.000 0 0.124
#> ERR342899 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342829 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342850 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342849 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342811 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342837 1 0.209 0.906 0.876 0 0 0.000 0 0.124
#> ERR342857 4 0.139 0.942 0.000 0 0 0.932 0 0.068
#> ERR342869 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342903 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342819 1 0.214 0.904 0.872 0 0 0.000 0 0.128
#> ERR342885 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342889 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342864 4 0.226 0.889 0.000 0 0 0.860 0 0.140
#> ERR342860 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342808 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342823 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342907 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342852 4 0.181 0.922 0.000 0 0 0.900 0 0.100
#> ERR342832 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342868 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342821 4 0.133 0.943 0.000 0 0 0.936 0 0.064
#> ERR342878 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342876 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342809 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342846 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342872 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342828 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342840 1 0.226 0.895 0.860 0 0 0.000 0 0.140
#> ERR342831 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342818 6 0.122 0.994 0.004 0 0 0.048 0 0.948
#> ERR342862 1 0.234 0.888 0.852 0 0 0.000 0 0.148
#> ERR342894 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342884 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342891 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342890 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342836 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342879 6 0.122 0.994 0.004 0 0 0.048 0 0.948
#> ERR342848 6 0.193 0.949 0.036 0 0 0.048 0 0.916
#> ERR342861 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342814 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342870 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342901 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342908 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342815 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342897 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342833 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342817 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342810 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342867 4 0.120 0.945 0.000 0 0 0.944 0 0.056
#> ERR342847 1 0.209 0.906 0.876 0 0 0.000 0 0.124
#> ERR342855 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342851 6 0.122 0.994 0.004 0 0 0.048 0 0.948
#> ERR342813 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342883 6 0.122 0.994 0.004 0 0 0.048 0 0.948
#> ERR342856 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342822 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342892 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342842 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342902 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342900 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342888 5 0.000 1.000 0.000 0 0 0.000 1 0.000
#> ERR342812 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342853 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342866 1 0.222 0.898 0.864 0 0 0.000 0 0.136
#> ERR342820 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342895 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342825 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342826 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342875 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342834 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342898 4 0.238 0.876 0.000 0 0 0.848 0 0.152
#> ERR342886 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342838 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342882 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342807 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342873 6 0.122 0.994 0.004 0 0 0.048 0 0.948
#> ERR342844 4 0.222 0.893 0.000 0 0 0.864 0 0.136
#> ERR342874 1 0.218 0.901 0.868 0 0 0.000 0 0.132
#> ERR342893 6 0.122 0.994 0.004 0 0 0.048 0 0.948
#> ERR342859 3 0.000 1.000 0.000 0 1 0.000 0 0.000
#> ERR342830 2 0.000 1.000 0.000 1 0 0.000 0 0.000
#> ERR342880 6 0.122 0.994 0.004 0 0 0.048 0 0.948
#> ERR342887 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342854 1 0.000 0.958 1.000 0 0 0.000 0 0.000
#> ERR342904 4 0.000 0.950 0.000 0 0 1.000 0 0.000
#> ERR342881 1 0.218 0.901 0.868 0 0 0.000 0 0.132
#> ERR342858 6 0.122 0.994 0.004 0 0 0.048 0 0.948
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "mclust"]
# you can also extract it by
# res = res_list["SD:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 4.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.280 0.373 0.688 0.4218 0.497 0.497
#> 3 3 0.380 0.711 0.777 0.4257 0.623 0.407
#> 4 4 0.683 0.776 0.885 0.1434 0.918 0.794
#> 5 5 0.752 0.740 0.841 0.0944 0.900 0.684
#> 6 6 0.854 0.827 0.886 0.0863 0.930 0.702
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 4
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.961 0.2898 0.616 0.384
#> ERR342843 1 0.961 0.2898 0.616 0.384
#> ERR342896 2 0.958 0.1938 0.380 0.620
#> ERR342827 2 0.969 0.3797 0.396 0.604
#> ERR342871 1 0.000 0.6511 1.000 0.000
#> ERR342863 2 0.969 0.3797 0.396 0.604
#> ERR342839 1 0.961 0.2898 0.616 0.384
#> ERR342906 1 0.000 0.6511 1.000 0.000
#> ERR342905 2 0.973 0.3697 0.404 0.596
#> ERR342816 1 0.000 0.6511 1.000 0.000
#> ERR342865 2 0.969 0.3797 0.396 0.604
#> ERR342824 1 0.983 -0.0135 0.576 0.424
#> ERR342841 2 0.969 0.3797 0.396 0.604
#> ERR342835 1 0.961 0.2898 0.616 0.384
#> ERR342899 2 0.973 0.3697 0.404 0.596
#> ERR342829 2 0.958 0.1938 0.380 0.620
#> ERR342850 1 0.000 0.6511 1.000 0.000
#> ERR342849 2 0.973 0.3697 0.404 0.596
#> ERR342811 1 0.000 0.6511 1.000 0.000
#> ERR342837 1 0.961 0.2898 0.616 0.384
#> ERR342857 1 0.000 0.6511 1.000 0.000
#> ERR342869 1 0.000 0.6511 1.000 0.000
#> ERR342903 2 0.958 0.1938 0.380 0.620
#> ERR342819 1 0.961 0.2898 0.616 0.384
#> ERR342885 2 1.000 0.1184 0.488 0.512
#> ERR342889 2 0.969 0.3797 0.396 0.604
#> ERR342864 1 0.000 0.6511 1.000 0.000
#> ERR342860 2 0.973 0.3697 0.404 0.596
#> ERR342808 1 0.000 0.6511 1.000 0.000
#> ERR342823 1 0.983 -0.0135 0.576 0.424
#> ERR342907 2 0.969 0.3797 0.396 0.604
#> ERR342852 1 0.000 0.6511 1.000 0.000
#> ERR342832 2 0.969 0.3797 0.396 0.604
#> ERR342868 1 0.961 0.2898 0.616 0.384
#> ERR342821 1 0.000 0.6511 1.000 0.000
#> ERR342878 2 0.969 0.3797 0.396 0.604
#> ERR342876 2 0.958 0.1938 0.380 0.620
#> ERR342809 2 0.958 0.1938 0.380 0.620
#> ERR342846 2 1.000 0.1184 0.488 0.512
#> ERR342872 2 0.969 0.3797 0.396 0.604
#> ERR342828 2 0.969 0.3797 0.396 0.604
#> ERR342840 1 0.961 0.2898 0.616 0.384
#> ERR342831 1 0.961 0.2898 0.616 0.384
#> ERR342818 1 0.000 0.6511 1.000 0.000
#> ERR342862 1 0.961 0.2898 0.616 0.384
#> ERR342894 1 0.961 0.2898 0.616 0.384
#> ERR342884 2 0.969 0.3797 0.396 0.604
#> ERR342891 2 0.958 0.1938 0.380 0.620
#> ERR342890 1 0.961 0.2898 0.616 0.384
#> ERR342836 2 0.969 0.3797 0.396 0.604
#> ERR342879 1 0.000 0.6511 1.000 0.000
#> ERR342848 1 0.000 0.6511 1.000 0.000
#> ERR342861 2 0.958 0.1938 0.380 0.620
#> ERR342814 2 0.973 0.3697 0.404 0.596
#> ERR342870 1 0.000 0.6511 1.000 0.000
#> ERR342901 2 0.958 0.1938 0.380 0.620
#> ERR342908 1 0.000 0.6511 1.000 0.000
#> ERR342815 2 0.969 0.3797 0.396 0.604
#> ERR342897 2 1.000 0.1184 0.488 0.512
#> ERR342833 2 0.969 0.3797 0.396 0.604
#> ERR342817 2 1.000 0.1184 0.488 0.512
#> ERR342810 2 0.973 0.3697 0.404 0.596
#> ERR342867 1 0.000 0.6511 1.000 0.000
#> ERR342847 1 0.961 0.2898 0.616 0.384
#> ERR342855 2 0.958 0.1938 0.380 0.620
#> ERR342851 1 0.000 0.6511 1.000 0.000
#> ERR342813 1 0.961 0.2898 0.616 0.384
#> ERR342883 1 0.000 0.6511 1.000 0.000
#> ERR342856 2 1.000 0.1184 0.488 0.512
#> ERR342822 2 0.969 0.3797 0.396 0.604
#> ERR342892 2 0.958 0.1938 0.380 0.620
#> ERR342842 2 0.958 0.1938 0.380 0.620
#> ERR342902 2 0.969 0.3797 0.396 0.604
#> ERR342900 2 0.973 0.3697 0.404 0.596
#> ERR342888 1 0.961 0.2898 0.616 0.384
#> ERR342812 2 0.958 0.1938 0.380 0.620
#> ERR342853 2 0.973 0.3697 0.404 0.596
#> ERR342866 1 0.961 0.2898 0.616 0.384
#> ERR342820 1 0.000 0.6511 1.000 0.000
#> ERR342895 2 0.958 0.1938 0.380 0.620
#> ERR342825 2 1.000 0.1184 0.488 0.512
#> ERR342826 2 1.000 0.1184 0.488 0.512
#> ERR342875 2 0.969 0.3797 0.396 0.604
#> ERR342834 2 1.000 0.1184 0.488 0.512
#> ERR342898 1 0.000 0.6511 1.000 0.000
#> ERR342886 2 0.973 0.3697 0.404 0.596
#> ERR342838 2 0.958 0.1938 0.380 0.620
#> ERR342882 2 0.958 0.1938 0.380 0.620
#> ERR342807 2 0.969 0.3797 0.396 0.604
#> ERR342873 1 0.000 0.6511 1.000 0.000
#> ERR342844 1 0.000 0.6511 1.000 0.000
#> ERR342874 1 0.961 0.2898 0.616 0.384
#> ERR342893 1 0.000 0.6511 1.000 0.000
#> ERR342859 2 1.000 0.1184 0.488 0.512
#> ERR342830 2 0.973 0.3697 0.404 0.596
#> ERR342880 1 0.000 0.6511 1.000 0.000
#> ERR342887 2 0.958 0.1938 0.380 0.620
#> ERR342854 2 0.958 0.1938 0.380 0.620
#> ERR342904 1 0.000 0.6511 1.000 0.000
#> ERR342881 1 0.961 0.2898 0.616 0.384
#> ERR342858 1 0.000 0.6511 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 2 0.658 0.304 0.420 0.572 0.008
#> ERR342843 2 0.658 0.304 0.420 0.572 0.008
#> ERR342896 3 0.000 0.983 0.000 0.000 1.000
#> ERR342827 2 0.347 0.693 0.056 0.904 0.040
#> ERR342871 1 0.635 0.926 0.768 0.140 0.092
#> ERR342863 2 0.456 0.669 0.112 0.852 0.036
#> ERR342839 2 0.658 0.304 0.420 0.572 0.008
#> ERR342906 1 0.643 0.927 0.764 0.140 0.096
#> ERR342905 2 0.437 0.682 0.096 0.864 0.040
#> ERR342816 1 0.643 0.927 0.764 0.140 0.096
#> ERR342865 2 0.456 0.669 0.112 0.852 0.036
#> ERR342824 3 0.375 0.836 0.020 0.096 0.884
#> ERR342841 2 0.347 0.693 0.056 0.904 0.040
#> ERR342835 2 0.930 0.170 0.376 0.460 0.164
#> ERR342899 2 0.437 0.682 0.096 0.864 0.040
#> ERR342829 3 0.000 0.983 0.000 0.000 1.000
#> ERR342850 1 0.635 0.926 0.768 0.140 0.092
#> ERR342849 2 0.437 0.682 0.096 0.864 0.040
#> ERR342811 1 0.635 0.926 0.768 0.140 0.092
#> ERR342837 2 0.930 0.170 0.376 0.460 0.164
#> ERR342857 1 0.643 0.927 0.764 0.140 0.096
#> ERR342869 1 0.635 0.926 0.768 0.140 0.092
#> ERR342903 3 0.000 0.983 0.000 0.000 1.000
#> ERR342819 2 0.930 0.170 0.376 0.460 0.164
#> ERR342885 2 0.478 0.629 0.200 0.796 0.004
#> ERR342889 2 0.456 0.669 0.112 0.852 0.036
#> ERR342864 1 0.643 0.927 0.764 0.140 0.096
#> ERR342860 2 0.437 0.682 0.096 0.864 0.040
#> ERR342808 1 0.635 0.926 0.768 0.140 0.092
#> ERR342823 3 0.375 0.836 0.020 0.096 0.884
#> ERR342907 2 0.347 0.693 0.056 0.904 0.040
#> ERR342852 1 0.643 0.927 0.764 0.140 0.096
#> ERR342832 2 0.456 0.669 0.112 0.852 0.036
#> ERR342868 2 0.658 0.304 0.420 0.572 0.008
#> ERR342821 1 0.643 0.927 0.764 0.140 0.096
#> ERR342878 2 0.347 0.693 0.056 0.904 0.040
#> ERR342876 3 0.000 0.983 0.000 0.000 1.000
#> ERR342809 3 0.000 0.983 0.000 0.000 1.000
#> ERR342846 2 0.478 0.629 0.200 0.796 0.004
#> ERR342872 2 0.347 0.693 0.056 0.904 0.040
#> ERR342828 2 0.456 0.669 0.112 0.852 0.036
#> ERR342840 2 0.930 0.170 0.376 0.460 0.164
#> ERR342831 2 0.658 0.304 0.420 0.572 0.008
#> ERR342818 1 0.797 0.857 0.656 0.140 0.204
#> ERR342862 2 0.930 0.170 0.376 0.460 0.164
#> ERR342894 2 0.658 0.304 0.420 0.572 0.008
#> ERR342884 2 0.347 0.693 0.056 0.904 0.040
#> ERR342891 3 0.000 0.983 0.000 0.000 1.000
#> ERR342890 2 0.658 0.304 0.420 0.572 0.008
#> ERR342836 2 0.456 0.669 0.112 0.852 0.036
#> ERR342879 1 0.797 0.857 0.656 0.140 0.204
#> ERR342848 1 0.815 0.855 0.640 0.144 0.216
#> ERR342861 3 0.000 0.983 0.000 0.000 1.000
#> ERR342814 2 0.437 0.682 0.096 0.864 0.040
#> ERR342870 1 0.635 0.926 0.768 0.140 0.092
#> ERR342901 3 0.000 0.983 0.000 0.000 1.000
#> ERR342908 1 0.635 0.926 0.768 0.140 0.092
#> ERR342815 2 0.456 0.669 0.112 0.852 0.036
#> ERR342897 2 0.478 0.629 0.200 0.796 0.004
#> ERR342833 2 0.347 0.693 0.056 0.904 0.040
#> ERR342817 2 0.478 0.629 0.200 0.796 0.004
#> ERR342810 2 0.437 0.682 0.096 0.864 0.040
#> ERR342867 1 0.643 0.927 0.764 0.140 0.096
#> ERR342847 2 0.930 0.170 0.376 0.460 0.164
#> ERR342855 3 0.000 0.983 0.000 0.000 1.000
#> ERR342851 1 0.797 0.857 0.656 0.140 0.204
#> ERR342813 2 0.658 0.304 0.420 0.572 0.008
#> ERR342883 1 0.797 0.857 0.656 0.140 0.204
#> ERR342856 2 0.478 0.629 0.200 0.796 0.004
#> ERR342822 2 0.456 0.669 0.112 0.852 0.036
#> ERR342892 3 0.000 0.983 0.000 0.000 1.000
#> ERR342842 3 0.000 0.983 0.000 0.000 1.000
#> ERR342902 2 0.347 0.693 0.056 0.904 0.040
#> ERR342900 2 0.437 0.682 0.096 0.864 0.040
#> ERR342888 2 0.658 0.304 0.420 0.572 0.008
#> ERR342812 3 0.000 0.983 0.000 0.000 1.000
#> ERR342853 2 0.437 0.682 0.096 0.864 0.040
#> ERR342866 2 0.930 0.170 0.376 0.460 0.164
#> ERR342820 1 0.635 0.926 0.768 0.140 0.092
#> ERR342895 3 0.000 0.983 0.000 0.000 1.000
#> ERR342825 2 0.478 0.629 0.200 0.796 0.004
#> ERR342826 2 0.478 0.629 0.200 0.796 0.004
#> ERR342875 2 0.456 0.669 0.112 0.852 0.036
#> ERR342834 2 0.478 0.629 0.200 0.796 0.004
#> ERR342898 1 0.643 0.927 0.764 0.140 0.096
#> ERR342886 2 0.437 0.682 0.096 0.864 0.040
#> ERR342838 3 0.000 0.983 0.000 0.000 1.000
#> ERR342882 3 0.000 0.983 0.000 0.000 1.000
#> ERR342807 2 0.347 0.693 0.056 0.904 0.040
#> ERR342873 1 0.797 0.857 0.656 0.140 0.204
#> ERR342844 1 0.643 0.927 0.764 0.140 0.096
#> ERR342874 2 0.930 0.170 0.376 0.460 0.164
#> ERR342893 1 0.797 0.857 0.656 0.140 0.204
#> ERR342859 2 0.478 0.629 0.200 0.796 0.004
#> ERR342830 2 0.437 0.682 0.096 0.864 0.040
#> ERR342880 1 0.797 0.857 0.656 0.140 0.204
#> ERR342887 3 0.000 0.983 0.000 0.000 1.000
#> ERR342854 3 0.000 0.983 0.000 0.000 1.000
#> ERR342904 1 0.635 0.926 0.768 0.140 0.092
#> ERR342881 2 0.930 0.170 0.376 0.460 0.164
#> ERR342858 1 0.797 0.857 0.656 0.140 0.204
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342843 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342896 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342827 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342871 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342863 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342839 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342906 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342905 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342816 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342865 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342841 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342835 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342899 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342829 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342850 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342849 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342811 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342837 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342857 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342869 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342903 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342819 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342885 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342889 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342864 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342860 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342808 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342823 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342907 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342852 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342832 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342868 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342821 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342878 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342876 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342872 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342828 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342840 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342831 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342818 4 0.4181 0.840 0.128 0.052 0 0.820
#> ERR342862 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342894 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342884 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342891 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342890 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342836 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342879 4 0.4181 0.840 0.128 0.052 0 0.820
#> ERR342848 4 0.5578 0.704 0.128 0.144 0 0.728
#> ERR342861 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342814 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342870 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342901 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342908 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342815 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342897 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342833 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342817 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342810 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342867 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342847 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342855 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342851 4 0.4181 0.840 0.128 0.052 0 0.820
#> ERR342813 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342883 4 0.4181 0.840 0.128 0.052 0 0.820
#> ERR342856 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342822 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342902 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342900 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342888 2 0.5155 0.360 0.004 0.528 0 0.468
#> ERR342812 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342853 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342866 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342820 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342895 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342875 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342834 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342898 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342886 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342838 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342807 2 0.0000 0.730 0.000 1.000 0 0.000
#> ERR342873 4 0.4181 0.840 0.128 0.052 0 0.820
#> ERR342844 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342874 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342893 4 0.4181 0.840 0.128 0.052 0 0.820
#> ERR342859 3 0.0000 1.000 0.000 0.000 1 0.000
#> ERR342830 2 0.1978 0.718 0.004 0.928 0 0.068
#> ERR342880 4 0.4181 0.840 0.128 0.052 0 0.820
#> ERR342887 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0 0.000
#> ERR342904 4 0.0188 0.924 0.000 0.004 0 0.996
#> ERR342881 2 0.7143 0.307 0.132 0.460 0 0.408
#> ERR342858 4 0.4181 0.840 0.128 0.052 0 0.820
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342843 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342896 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342827 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342871 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342863 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342839 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342906 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342905 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342816 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342865 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342824 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342841 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342835 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342899 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342829 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342850 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342849 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342811 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342837 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342857 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342869 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342903 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342819 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342885 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342889 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342864 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342860 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342808 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342823 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342907 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342852 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342832 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342868 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342821 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342878 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342876 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342809 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342846 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342872 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342828 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342840 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342831 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342818 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
#> ERR342862 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342894 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342884 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342891 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342890 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342836 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342879 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
#> ERR342848 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
#> ERR342861 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342814 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342870 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342901 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342908 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342815 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342897 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342833 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342817 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342810 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342867 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342847 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342855 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342851 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
#> ERR342813 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342883 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
#> ERR342856 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342822 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342892 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342842 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342902 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342900 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342888 5 0.0510 0.65691 0.000 0.000 0 0.016 0.984
#> ERR342812 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342853 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342866 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342820 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342895 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342825 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342826 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342875 2 0.4446 0.55229 0.000 0.592 0 0.008 0.400
#> ERR342834 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342898 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342886 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342838 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342882 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342807 2 0.0000 0.69303 0.000 1.000 0 0.000 0.000
#> ERR342873 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
#> ERR342844 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342874 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342893 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
#> ERR342859 3 0.0000 1.00000 0.000 0.000 1 0.000 0.000
#> ERR342830 5 0.6758 -0.00348 0.000 0.300 0 0.296 0.404
#> ERR342880 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
#> ERR342887 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342854 1 0.0000 1.00000 1.000 0.000 0 0.000 0.000
#> ERR342904 4 0.3752 0.91611 0.000 0.000 0 0.708 0.292
#> ERR342881 5 0.0609 0.64961 0.000 0.000 0 0.020 0.980
#> ERR342858 4 0.4655 0.81088 0.012 0.000 0 0.512 0.476
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342843 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342896 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342827 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342871 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342863 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342839 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342906 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342905 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342816 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342865 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342824 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342841 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342835 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342899 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342829 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342850 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342849 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342811 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342837 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342857 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342869 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342903 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342819 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342885 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342889 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342864 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342860 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342808 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342823 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342907 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342852 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342832 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342868 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342821 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342878 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342876 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342809 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342846 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342872 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342828 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342840 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342831 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342818 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
#> ERR342862 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342894 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342884 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342891 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342890 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342836 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342879 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
#> ERR342848 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
#> ERR342861 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342814 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342870 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342901 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342908 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342815 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342897 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342833 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342817 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342810 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342867 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342847 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342855 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342851 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
#> ERR342813 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342883 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
#> ERR342856 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342822 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342892 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342842 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342902 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342900 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342888 5 0.397 0.778 0 0.000 0 0.224 0.728 0.048
#> ERR342812 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342853 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342866 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342820 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342895 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342825 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342826 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342875 2 0.368 0.644 0 0.628 0 0.000 0.000 0.372
#> ERR342834 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342898 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342886 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342838 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342882 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342807 6 0.107 1.000 0 0.048 0 0.000 0.000 0.952
#> ERR342873 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
#> ERR342844 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342874 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342893 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
#> ERR342859 3 0.000 1.000 0 0.000 1 0.000 0.000 0.000
#> ERR342830 2 0.000 0.765 0 1.000 0 0.000 0.000 0.000
#> ERR342880 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
#> ERR342887 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342854 1 0.000 1.000 1 0.000 0 0.000 0.000 0.000
#> ERR342904 4 0.000 0.810 0 0.000 0 1.000 0.000 0.000
#> ERR342881 5 0.107 0.788 0 0.000 0 0.048 0.952 0.000
#> ERR342858 4 0.383 0.489 0 0.000 0 0.556 0.444 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "NMF"]
# you can also extract it by
# res = res_list["SD:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.919 0.932 0.967 0.4464 0.531 0.531
#> 3 3 0.944 0.970 0.982 0.1979 0.950 0.906
#> 4 4 0.742 0.783 0.857 0.3487 0.755 0.501
#> 5 5 0.876 0.950 0.939 0.0777 0.930 0.742
#> 6 6 0.850 0.815 0.805 0.0478 0.966 0.843
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
#> attr(,"optional")
#> [1] 2
There is also optional best \(k\) = 2 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 1.000 1.000 0.000
#> ERR342843 1 0.000 1.000 1.000 0.000
#> ERR342896 1 0.000 1.000 1.000 0.000
#> ERR342827 2 0.000 0.905 0.000 1.000
#> ERR342871 1 0.000 1.000 1.000 0.000
#> ERR342863 2 0.000 0.905 0.000 1.000
#> ERR342839 1 0.000 1.000 1.000 0.000
#> ERR342906 1 0.000 1.000 1.000 0.000
#> ERR342905 2 0.000 0.905 0.000 1.000
#> ERR342816 1 0.000 1.000 1.000 0.000
#> ERR342865 2 0.000 0.905 0.000 1.000
#> ERR342824 1 0.000 1.000 1.000 0.000
#> ERR342841 2 0.000 0.905 0.000 1.000
#> ERR342835 1 0.000 1.000 1.000 0.000
#> ERR342899 2 0.000 0.905 0.000 1.000
#> ERR342829 1 0.000 1.000 1.000 0.000
#> ERR342850 1 0.000 1.000 1.000 0.000
#> ERR342849 2 0.000 0.905 0.000 1.000
#> ERR342811 1 0.000 1.000 1.000 0.000
#> ERR342837 1 0.000 1.000 1.000 0.000
#> ERR342857 1 0.000 1.000 1.000 0.000
#> ERR342869 1 0.000 1.000 1.000 0.000
#> ERR342903 1 0.000 1.000 1.000 0.000
#> ERR342819 1 0.000 1.000 1.000 0.000
#> ERR342885 2 0.971 0.472 0.400 0.600
#> ERR342889 2 0.000 0.905 0.000 1.000
#> ERR342864 1 0.000 1.000 1.000 0.000
#> ERR342860 2 0.000 0.905 0.000 1.000
#> ERR342808 1 0.000 1.000 1.000 0.000
#> ERR342823 1 0.000 1.000 1.000 0.000
#> ERR342907 2 0.000 0.905 0.000 1.000
#> ERR342852 1 0.000 1.000 1.000 0.000
#> ERR342832 2 0.000 0.905 0.000 1.000
#> ERR342868 1 0.000 1.000 1.000 0.000
#> ERR342821 1 0.000 1.000 1.000 0.000
#> ERR342878 2 0.000 0.905 0.000 1.000
#> ERR342876 1 0.000 1.000 1.000 0.000
#> ERR342809 1 0.000 1.000 1.000 0.000
#> ERR342846 2 0.891 0.629 0.308 0.692
#> ERR342872 2 0.000 0.905 0.000 1.000
#> ERR342828 2 0.000 0.905 0.000 1.000
#> ERR342840 1 0.000 1.000 1.000 0.000
#> ERR342831 1 0.000 1.000 1.000 0.000
#> ERR342818 1 0.000 1.000 1.000 0.000
#> ERR342862 1 0.000 1.000 1.000 0.000
#> ERR342894 1 0.000 1.000 1.000 0.000
#> ERR342884 2 0.000 0.905 0.000 1.000
#> ERR342891 1 0.000 1.000 1.000 0.000
#> ERR342890 1 0.000 1.000 1.000 0.000
#> ERR342836 2 0.000 0.905 0.000 1.000
#> ERR342879 1 0.000 1.000 1.000 0.000
#> ERR342848 1 0.000 1.000 1.000 0.000
#> ERR342861 1 0.000 1.000 1.000 0.000
#> ERR342814 2 0.000 0.905 0.000 1.000
#> ERR342870 1 0.000 1.000 1.000 0.000
#> ERR342901 1 0.000 1.000 1.000 0.000
#> ERR342908 1 0.000 1.000 1.000 0.000
#> ERR342815 2 0.000 0.905 0.000 1.000
#> ERR342897 2 0.936 0.564 0.352 0.648
#> ERR342833 2 0.000 0.905 0.000 1.000
#> ERR342817 2 0.966 0.490 0.392 0.608
#> ERR342810 2 0.000 0.905 0.000 1.000
#> ERR342867 1 0.000 1.000 1.000 0.000
#> ERR342847 1 0.000 1.000 1.000 0.000
#> ERR342855 1 0.000 1.000 1.000 0.000
#> ERR342851 1 0.000 1.000 1.000 0.000
#> ERR342813 1 0.000 1.000 1.000 0.000
#> ERR342883 1 0.000 1.000 1.000 0.000
#> ERR342856 2 0.929 0.576 0.344 0.656
#> ERR342822 2 0.000 0.905 0.000 1.000
#> ERR342892 1 0.000 1.000 1.000 0.000
#> ERR342842 1 0.000 1.000 1.000 0.000
#> ERR342902 2 0.000 0.905 0.000 1.000
#> ERR342900 2 0.000 0.905 0.000 1.000
#> ERR342888 1 0.000 1.000 1.000 0.000
#> ERR342812 1 0.000 1.000 1.000 0.000
#> ERR342853 2 0.000 0.905 0.000 1.000
#> ERR342866 1 0.000 1.000 1.000 0.000
#> ERR342820 1 0.000 1.000 1.000 0.000
#> ERR342895 1 0.000 1.000 1.000 0.000
#> ERR342825 2 0.969 0.481 0.396 0.604
#> ERR342826 2 0.952 0.529 0.372 0.628
#> ERR342875 2 0.000 0.905 0.000 1.000
#> ERR342834 2 0.980 0.435 0.416 0.584
#> ERR342898 1 0.000 1.000 1.000 0.000
#> ERR342886 2 0.000 0.905 0.000 1.000
#> ERR342838 1 0.000 1.000 1.000 0.000
#> ERR342882 1 0.000 1.000 1.000 0.000
#> ERR342807 2 0.000 0.905 0.000 1.000
#> ERR342873 1 0.000 1.000 1.000 0.000
#> ERR342844 1 0.000 1.000 1.000 0.000
#> ERR342874 1 0.000 1.000 1.000 0.000
#> ERR342893 1 0.000 1.000 1.000 0.000
#> ERR342859 2 0.891 0.629 0.308 0.692
#> ERR342830 2 0.000 0.905 0.000 1.000
#> ERR342880 1 0.000 1.000 1.000 0.000
#> ERR342887 1 0.000 1.000 1.000 0.000
#> ERR342854 1 0.000 1.000 1.000 0.000
#> ERR342904 1 0.000 1.000 1.000 0.000
#> ERR342881 1 0.000 1.000 1.000 0.000
#> ERR342858 1 0.000 1.000 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.3267 0.883 0.884 0.000 0.116
#> ERR342843 1 0.4931 0.744 0.768 0.000 0.232
#> ERR342896 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342827 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342871 1 0.0237 0.972 0.996 0.000 0.004
#> ERR342863 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342839 1 0.3551 0.868 0.868 0.000 0.132
#> ERR342906 1 0.0592 0.968 0.988 0.000 0.012
#> ERR342905 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342816 1 0.0424 0.971 0.992 0.000 0.008
#> ERR342865 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342824 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342841 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342835 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342899 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342829 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342850 1 0.0237 0.972 0.996 0.000 0.004
#> ERR342849 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342811 1 0.0237 0.972 0.996 0.000 0.004
#> ERR342837 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342857 1 0.1529 0.949 0.960 0.000 0.040
#> ERR342869 1 0.0237 0.972 0.996 0.000 0.004
#> ERR342903 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342819 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342885 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342889 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342864 1 0.0424 0.971 0.992 0.000 0.008
#> ERR342860 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342808 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342823 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342907 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342852 1 0.0747 0.966 0.984 0.000 0.016
#> ERR342832 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342868 1 0.4555 0.789 0.800 0.000 0.200
#> ERR342821 1 0.0237 0.972 0.996 0.000 0.004
#> ERR342878 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342876 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342809 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342846 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342872 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342828 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342840 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342831 1 0.3192 0.887 0.888 0.000 0.112
#> ERR342818 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342862 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342894 1 0.4121 0.829 0.832 0.000 0.168
#> ERR342884 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342891 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342890 1 0.3412 0.876 0.876 0.000 0.124
#> ERR342836 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342879 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342848 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342861 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342814 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342870 1 0.0237 0.972 0.996 0.000 0.004
#> ERR342901 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342908 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342815 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342897 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342833 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342817 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342810 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342867 1 0.0424 0.971 0.992 0.000 0.008
#> ERR342847 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342855 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342851 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342813 1 0.4291 0.815 0.820 0.000 0.180
#> ERR342883 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342856 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342822 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342892 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342842 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342902 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342900 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342888 1 0.4346 0.810 0.816 0.000 0.184
#> ERR342812 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342853 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342866 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342820 1 0.0237 0.972 0.996 0.000 0.004
#> ERR342895 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342825 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342826 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342875 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342834 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342898 1 0.0424 0.971 0.992 0.000 0.008
#> ERR342886 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342838 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342882 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342807 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342873 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342844 1 0.0892 0.964 0.980 0.000 0.020
#> ERR342874 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342893 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342859 3 0.0237 1.000 0.000 0.004 0.996
#> ERR342830 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342880 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342887 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342854 1 0.0424 0.972 0.992 0.000 0.008
#> ERR342904 1 0.0237 0.972 0.996 0.000 0.004
#> ERR342881 1 0.0000 0.973 1.000 0.000 0.000
#> ERR342858 1 0.0000 0.973 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.7830 -0.179 0.404 0.000 0.324 0.272
#> ERR342843 3 0.7806 0.313 0.332 0.000 0.408 0.260
#> ERR342896 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342827 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342871 4 0.1733 0.946 0.028 0.000 0.024 0.948
#> ERR342863 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342839 3 0.7844 0.221 0.368 0.000 0.368 0.264
#> ERR342906 4 0.2376 0.923 0.016 0.000 0.068 0.916
#> ERR342905 2 0.0188 0.991 0.004 0.996 0.000 0.000
#> ERR342816 4 0.2222 0.929 0.016 0.000 0.060 0.924
#> ERR342865 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342824 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342841 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342835 1 0.5573 0.490 0.604 0.000 0.028 0.368
#> ERR342899 2 0.0188 0.991 0.004 0.996 0.000 0.000
#> ERR342829 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342850 4 0.1733 0.946 0.028 0.000 0.024 0.948
#> ERR342849 2 0.0188 0.991 0.004 0.996 0.000 0.000
#> ERR342811 4 0.1677 0.943 0.040 0.000 0.012 0.948
#> ERR342837 1 0.5573 0.490 0.604 0.000 0.028 0.368
#> ERR342857 4 0.2611 0.889 0.008 0.000 0.096 0.896
#> ERR342869 4 0.1936 0.945 0.028 0.000 0.032 0.940
#> ERR342903 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342819 1 0.5573 0.490 0.604 0.000 0.028 0.368
#> ERR342885 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342889 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342864 4 0.1798 0.938 0.016 0.000 0.040 0.944
#> ERR342860 2 0.0469 0.987 0.012 0.988 0.000 0.000
#> ERR342808 4 0.1854 0.939 0.048 0.000 0.012 0.940
#> ERR342823 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342907 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342852 4 0.2255 0.919 0.012 0.000 0.068 0.920
#> ERR342832 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342868 3 0.7818 0.310 0.332 0.000 0.404 0.264
#> ERR342821 4 0.1798 0.941 0.016 0.000 0.040 0.944
#> ERR342878 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342876 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342809 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342846 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342872 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342828 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342840 1 0.5573 0.490 0.604 0.000 0.028 0.368
#> ERR342831 1 0.7811 -0.163 0.412 0.000 0.320 0.268
#> ERR342818 4 0.1118 0.933 0.036 0.000 0.000 0.964
#> ERR342862 1 0.5587 0.485 0.600 0.000 0.028 0.372
#> ERR342894 3 0.7824 0.283 0.348 0.000 0.392 0.260
#> ERR342884 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342891 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342890 1 0.7835 -0.210 0.396 0.000 0.336 0.268
#> ERR342836 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342879 4 0.1211 0.932 0.040 0.000 0.000 0.960
#> ERR342848 4 0.1211 0.933 0.040 0.000 0.000 0.960
#> ERR342861 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342814 2 0.0188 0.991 0.004 0.996 0.000 0.000
#> ERR342870 4 0.1733 0.946 0.028 0.000 0.024 0.948
#> ERR342901 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342908 4 0.1854 0.939 0.048 0.000 0.012 0.940
#> ERR342815 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342897 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342833 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342817 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342810 2 0.0336 0.989 0.008 0.992 0.000 0.000
#> ERR342867 4 0.1938 0.932 0.012 0.000 0.052 0.936
#> ERR342847 1 0.5573 0.490 0.604 0.000 0.028 0.368
#> ERR342855 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342851 4 0.1211 0.932 0.040 0.000 0.000 0.960
#> ERR342813 3 0.7824 0.283 0.348 0.000 0.392 0.260
#> ERR342883 4 0.1118 0.933 0.036 0.000 0.000 0.964
#> ERR342856 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342822 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342892 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342842 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342902 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342900 2 0.0188 0.991 0.004 0.996 0.000 0.000
#> ERR342888 3 0.7818 0.310 0.332 0.000 0.404 0.264
#> ERR342812 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342853 2 0.0188 0.991 0.004 0.996 0.000 0.000
#> ERR342866 1 0.5573 0.490 0.604 0.000 0.028 0.368
#> ERR342820 4 0.1733 0.946 0.028 0.000 0.024 0.948
#> ERR342895 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342825 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342826 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342875 2 0.0000 0.992 0.000 1.000 0.000 0.000
#> ERR342834 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342898 4 0.2179 0.923 0.012 0.000 0.064 0.924
#> ERR342886 2 0.0469 0.987 0.012 0.988 0.000 0.000
#> ERR342838 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342882 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342807 2 0.0804 0.987 0.012 0.980 0.000 0.008
#> ERR342873 4 0.1118 0.933 0.036 0.000 0.000 0.964
#> ERR342844 4 0.2480 0.899 0.008 0.000 0.088 0.904
#> ERR342874 1 0.5573 0.490 0.604 0.000 0.028 0.368
#> ERR342893 4 0.1211 0.932 0.040 0.000 0.000 0.960
#> ERR342859 3 0.0921 0.714 0.000 0.000 0.972 0.028
#> ERR342830 2 0.0469 0.987 0.012 0.988 0.000 0.000
#> ERR342880 4 0.1211 0.932 0.040 0.000 0.000 0.960
#> ERR342887 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342854 1 0.2408 0.746 0.896 0.000 0.000 0.104
#> ERR342904 4 0.1820 0.945 0.036 0.000 0.020 0.944
#> ERR342881 1 0.5573 0.490 0.604 0.000 0.028 0.368
#> ERR342858 4 0.1118 0.933 0.036 0.000 0.000 0.964
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.4774 0.876 0.036 0.000 0.068 0.128 0.768
#> ERR342843 5 0.4789 0.873 0.036 0.000 0.072 0.124 0.768
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342871 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342863 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342839 5 0.4774 0.876 0.036 0.000 0.068 0.128 0.768
#> ERR342906 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342905 2 0.2020 0.903 0.000 0.900 0.000 0.000 0.100
#> ERR342816 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342865 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342835 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342899 2 0.1197 0.932 0.000 0.952 0.000 0.000 0.048
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342849 2 0.1121 0.933 0.000 0.956 0.000 0.000 0.044
#> ERR342811 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342837 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342857 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342869 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342885 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342889 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342864 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342860 2 0.1851 0.909 0.000 0.912 0.000 0.000 0.088
#> ERR342808 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342852 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342832 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342868 5 0.4774 0.876 0.036 0.000 0.068 0.128 0.768
#> ERR342821 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342878 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342872 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342828 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342840 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342831 5 0.4774 0.876 0.036 0.000 0.068 0.128 0.768
#> ERR342818 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
#> ERR342862 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342894 5 0.4789 0.873 0.036 0.000 0.072 0.124 0.768
#> ERR342884 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.4788 0.876 0.040 0.000 0.064 0.128 0.768
#> ERR342836 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342879 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
#> ERR342848 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.1270 0.930 0.000 0.948 0.000 0.000 0.052
#> ERR342870 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342815 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342897 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342833 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342817 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342810 2 0.2074 0.899 0.000 0.896 0.000 0.000 0.104
#> ERR342867 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342847 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
#> ERR342813 5 0.4789 0.873 0.036 0.000 0.072 0.124 0.768
#> ERR342883 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
#> ERR342856 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342822 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342900 2 0.1043 0.934 0.000 0.960 0.000 0.000 0.040
#> ERR342888 5 0.4774 0.876 0.036 0.000 0.068 0.128 0.768
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.1197 0.932 0.000 0.952 0.000 0.000 0.048
#> ERR342866 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342820 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342875 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342834 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342898 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342886 2 0.1908 0.907 0.000 0.908 0.000 0.000 0.092
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.2127 0.916 0.000 0.892 0.000 0.000 0.108
#> ERR342873 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
#> ERR342844 4 0.0290 0.975 0.000 0.000 0.000 0.992 0.008
#> ERR342874 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342893 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
#> ERR342859 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000
#> ERR342830 2 0.1792 0.912 0.000 0.916 0.000 0.000 0.084
#> ERR342880 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.0404 0.975 0.000 0.000 0.000 0.988 0.012
#> ERR342881 5 0.4025 0.882 0.076 0.000 0.000 0.132 0.792
#> ERR342858 4 0.1043 0.961 0.000 0.000 0.000 0.960 0.040
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.0820 0.682 0.000 0.000 0.016 0.012 0.972 0.000
#> ERR342843 5 0.0820 0.682 0.000 0.000 0.016 0.012 0.972 0.000
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342871 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342863 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342839 5 0.0820 0.682 0.000 0.000 0.016 0.012 0.972 0.000
#> ERR342906 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342905 2 0.2058 0.582 0.000 0.908 0.000 0.008 0.012 0.072
#> ERR342816 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342865 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342841 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342835 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342899 2 0.1065 0.637 0.000 0.964 0.000 0.008 0.008 0.020
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342849 2 0.0622 0.634 0.000 0.980 0.000 0.008 0.000 0.012
#> ERR342811 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342837 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342857 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342869 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342885 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342889 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342864 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342860 2 0.0984 0.637 0.000 0.968 0.000 0.008 0.012 0.012
#> ERR342808 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342907 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342852 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342832 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342868 5 0.0964 0.679 0.000 0.000 0.016 0.012 0.968 0.004
#> ERR342821 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342878 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342872 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342828 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342840 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342831 5 0.0820 0.682 0.000 0.000 0.016 0.012 0.972 0.000
#> ERR342818 4 0.2573 0.862 0.000 0.012 0.000 0.872 0.012 0.104
#> ERR342862 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342894 5 0.0820 0.682 0.000 0.000 0.016 0.012 0.972 0.000
#> ERR342884 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.0820 0.682 0.000 0.000 0.016 0.012 0.972 0.000
#> ERR342836 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342879 4 0.2525 0.863 0.000 0.012 0.000 0.876 0.012 0.100
#> ERR342848 4 0.2620 0.859 0.000 0.012 0.000 0.868 0.012 0.108
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.0862 0.639 0.000 0.972 0.000 0.008 0.004 0.016
#> ERR342870 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342815 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342897 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342833 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342817 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342810 2 0.2114 0.577 0.000 0.904 0.000 0.008 0.012 0.076
#> ERR342867 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342847 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.2620 0.859 0.000 0.012 0.000 0.868 0.012 0.108
#> ERR342813 5 0.0820 0.682 0.000 0.000 0.016 0.012 0.972 0.000
#> ERR342883 4 0.2525 0.863 0.000 0.012 0.000 0.876 0.012 0.100
#> ERR342856 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342822 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342902 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342900 2 0.0622 0.634 0.000 0.980 0.000 0.008 0.000 0.012
#> ERR342888 5 0.0820 0.682 0.000 0.000 0.016 0.012 0.972 0.000
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.1268 0.630 0.000 0.952 0.000 0.008 0.004 0.036
#> ERR342866 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342820 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342875 2 0.3076 0.376 0.000 0.760 0.000 0.000 0.000 0.240
#> ERR342834 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342898 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342886 2 0.1577 0.620 0.000 0.940 0.000 0.008 0.016 0.036
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342807 6 0.3866 1.000 0.000 0.484 0.000 0.000 0.000 0.516
#> ERR342873 4 0.2573 0.862 0.000 0.012 0.000 0.872 0.012 0.104
#> ERR342844 4 0.0653 0.890 0.000 0.004 0.000 0.980 0.004 0.012
#> ERR342874 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342893 4 0.2573 0.862 0.000 0.012 0.000 0.872 0.012 0.104
#> ERR342859 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342830 2 0.1251 0.633 0.000 0.956 0.000 0.008 0.012 0.024
#> ERR342880 4 0.2573 0.862 0.000 0.012 0.000 0.872 0.012 0.104
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.3139 0.844 0.000 0.000 0.000 0.816 0.032 0.152
#> ERR342881 5 0.6874 0.692 0.016 0.236 0.000 0.032 0.444 0.272
#> ERR342858 4 0.2525 0.863 0.000 0.012 0.000 0.876 0.012 0.100
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "hclust"]
# you can also extract it by
# res = res_list["CV:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 4.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.531 0.953 0.918 0.3516 0.595 0.595
#> 3 3 1.000 1.000 1.000 0.4770 0.886 0.808
#> 4 4 1.000 0.978 0.979 0.2030 0.902 0.796
#> 5 5 0.852 0.894 0.946 0.1763 0.868 0.656
#> 6 6 0.868 0.921 0.925 0.0573 0.984 0.936
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 4
#> attr(,"optional")
#> [1] 3
There is also optional best \(k\) = 3 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 0.964 1.000 0.000
#> ERR342843 1 0.000 0.964 1.000 0.000
#> ERR342896 1 0.000 0.964 1.000 0.000
#> ERR342827 2 0.767 1.000 0.224 0.776
#> ERR342871 1 0.000 0.964 1.000 0.000
#> ERR342863 2 0.767 1.000 0.224 0.776
#> ERR342839 1 0.000 0.964 1.000 0.000
#> ERR342906 1 0.000 0.964 1.000 0.000
#> ERR342905 2 0.767 1.000 0.224 0.776
#> ERR342816 1 0.000 0.964 1.000 0.000
#> ERR342865 2 0.767 1.000 0.224 0.776
#> ERR342824 1 0.000 0.964 1.000 0.000
#> ERR342841 2 0.767 1.000 0.224 0.776
#> ERR342835 1 0.000 0.964 1.000 0.000
#> ERR342899 2 0.767 1.000 0.224 0.776
#> ERR342829 1 0.000 0.964 1.000 0.000
#> ERR342850 1 0.000 0.964 1.000 0.000
#> ERR342849 2 0.767 1.000 0.224 0.776
#> ERR342811 1 0.000 0.964 1.000 0.000
#> ERR342837 1 0.000 0.964 1.000 0.000
#> ERR342857 1 0.000 0.964 1.000 0.000
#> ERR342869 1 0.000 0.964 1.000 0.000
#> ERR342903 1 0.000 0.964 1.000 0.000
#> ERR342819 1 0.000 0.964 1.000 0.000
#> ERR342885 1 0.767 0.734 0.776 0.224
#> ERR342889 2 0.767 1.000 0.224 0.776
#> ERR342864 1 0.000 0.964 1.000 0.000
#> ERR342860 2 0.767 1.000 0.224 0.776
#> ERR342808 1 0.000 0.964 1.000 0.000
#> ERR342823 1 0.000 0.964 1.000 0.000
#> ERR342907 2 0.767 1.000 0.224 0.776
#> ERR342852 1 0.000 0.964 1.000 0.000
#> ERR342832 2 0.767 1.000 0.224 0.776
#> ERR342868 1 0.000 0.964 1.000 0.000
#> ERR342821 1 0.000 0.964 1.000 0.000
#> ERR342878 2 0.767 1.000 0.224 0.776
#> ERR342876 1 0.000 0.964 1.000 0.000
#> ERR342809 1 0.000 0.964 1.000 0.000
#> ERR342846 1 0.767 0.734 0.776 0.224
#> ERR342872 2 0.767 1.000 0.224 0.776
#> ERR342828 2 0.767 1.000 0.224 0.776
#> ERR342840 1 0.000 0.964 1.000 0.000
#> ERR342831 1 0.000 0.964 1.000 0.000
#> ERR342818 1 0.000 0.964 1.000 0.000
#> ERR342862 1 0.000 0.964 1.000 0.000
#> ERR342894 1 0.000 0.964 1.000 0.000
#> ERR342884 2 0.767 1.000 0.224 0.776
#> ERR342891 1 0.000 0.964 1.000 0.000
#> ERR342890 1 0.000 0.964 1.000 0.000
#> ERR342836 2 0.767 1.000 0.224 0.776
#> ERR342879 1 0.000 0.964 1.000 0.000
#> ERR342848 1 0.000 0.964 1.000 0.000
#> ERR342861 1 0.000 0.964 1.000 0.000
#> ERR342814 2 0.767 1.000 0.224 0.776
#> ERR342870 1 0.000 0.964 1.000 0.000
#> ERR342901 1 0.000 0.964 1.000 0.000
#> ERR342908 1 0.000 0.964 1.000 0.000
#> ERR342815 2 0.767 1.000 0.224 0.776
#> ERR342897 1 0.767 0.734 0.776 0.224
#> ERR342833 2 0.767 1.000 0.224 0.776
#> ERR342817 1 0.767 0.734 0.776 0.224
#> ERR342810 2 0.767 1.000 0.224 0.776
#> ERR342867 1 0.000 0.964 1.000 0.000
#> ERR342847 1 0.000 0.964 1.000 0.000
#> ERR342855 1 0.000 0.964 1.000 0.000
#> ERR342851 1 0.000 0.964 1.000 0.000
#> ERR342813 1 0.000 0.964 1.000 0.000
#> ERR342883 1 0.000 0.964 1.000 0.000
#> ERR342856 1 0.767 0.734 0.776 0.224
#> ERR342822 2 0.767 1.000 0.224 0.776
#> ERR342892 1 0.000 0.964 1.000 0.000
#> ERR342842 1 0.000 0.964 1.000 0.000
#> ERR342902 2 0.767 1.000 0.224 0.776
#> ERR342900 2 0.767 1.000 0.224 0.776
#> ERR342888 1 0.000 0.964 1.000 0.000
#> ERR342812 1 0.000 0.964 1.000 0.000
#> ERR342853 2 0.767 1.000 0.224 0.776
#> ERR342866 1 0.000 0.964 1.000 0.000
#> ERR342820 1 0.000 0.964 1.000 0.000
#> ERR342895 1 0.000 0.964 1.000 0.000
#> ERR342825 1 0.767 0.734 0.776 0.224
#> ERR342826 1 0.767 0.734 0.776 0.224
#> ERR342875 2 0.767 1.000 0.224 0.776
#> ERR342834 1 0.767 0.734 0.776 0.224
#> ERR342898 1 0.000 0.964 1.000 0.000
#> ERR342886 2 0.767 1.000 0.224 0.776
#> ERR342838 1 0.000 0.964 1.000 0.000
#> ERR342882 1 0.000 0.964 1.000 0.000
#> ERR342807 2 0.767 1.000 0.224 0.776
#> ERR342873 1 0.000 0.964 1.000 0.000
#> ERR342844 1 0.000 0.964 1.000 0.000
#> ERR342874 1 0.000 0.964 1.000 0.000
#> ERR342893 1 0.000 0.964 1.000 0.000
#> ERR342859 1 0.767 0.734 0.776 0.224
#> ERR342830 2 0.767 1.000 0.224 0.776
#> ERR342880 1 0.000 0.964 1.000 0.000
#> ERR342887 1 0.000 0.964 1.000 0.000
#> ERR342854 1 0.000 0.964 1.000 0.000
#> ERR342904 1 0.000 0.964 1.000 0.000
#> ERR342881 1 0.000 0.964 1.000 0.000
#> ERR342858 1 0.000 0.964 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0 1 1 0 0
#> ERR342843 1 0 1 1 0 0
#> ERR342896 1 0 1 1 0 0
#> ERR342827 2 0 1 0 1 0
#> ERR342871 1 0 1 1 0 0
#> ERR342863 2 0 1 0 1 0
#> ERR342839 1 0 1 1 0 0
#> ERR342906 1 0 1 1 0 0
#> ERR342905 2 0 1 0 1 0
#> ERR342816 1 0 1 1 0 0
#> ERR342865 2 0 1 0 1 0
#> ERR342824 1 0 1 1 0 0
#> ERR342841 2 0 1 0 1 0
#> ERR342835 1 0 1 1 0 0
#> ERR342899 2 0 1 0 1 0
#> ERR342829 1 0 1 1 0 0
#> ERR342850 1 0 1 1 0 0
#> ERR342849 2 0 1 0 1 0
#> ERR342811 1 0 1 1 0 0
#> ERR342837 1 0 1 1 0 0
#> ERR342857 1 0 1 1 0 0
#> ERR342869 1 0 1 1 0 0
#> ERR342903 1 0 1 1 0 0
#> ERR342819 1 0 1 1 0 0
#> ERR342885 3 0 1 0 0 1
#> ERR342889 2 0 1 0 1 0
#> ERR342864 1 0 1 1 0 0
#> ERR342860 2 0 1 0 1 0
#> ERR342808 1 0 1 1 0 0
#> ERR342823 1 0 1 1 0 0
#> ERR342907 2 0 1 0 1 0
#> ERR342852 1 0 1 1 0 0
#> ERR342832 2 0 1 0 1 0
#> ERR342868 1 0 1 1 0 0
#> ERR342821 1 0 1 1 0 0
#> ERR342878 2 0 1 0 1 0
#> ERR342876 1 0 1 1 0 0
#> ERR342809 1 0 1 1 0 0
#> ERR342846 3 0 1 0 0 1
#> ERR342872 2 0 1 0 1 0
#> ERR342828 2 0 1 0 1 0
#> ERR342840 1 0 1 1 0 0
#> ERR342831 1 0 1 1 0 0
#> ERR342818 1 0 1 1 0 0
#> ERR342862 1 0 1 1 0 0
#> ERR342894 1 0 1 1 0 0
#> ERR342884 2 0 1 0 1 0
#> ERR342891 1 0 1 1 0 0
#> ERR342890 1 0 1 1 0 0
#> ERR342836 2 0 1 0 1 0
#> ERR342879 1 0 1 1 0 0
#> ERR342848 1 0 1 1 0 0
#> ERR342861 1 0 1 1 0 0
#> ERR342814 2 0 1 0 1 0
#> ERR342870 1 0 1 1 0 0
#> ERR342901 1 0 1 1 0 0
#> ERR342908 1 0 1 1 0 0
#> ERR342815 2 0 1 0 1 0
#> ERR342897 3 0 1 0 0 1
#> ERR342833 2 0 1 0 1 0
#> ERR342817 3 0 1 0 0 1
#> ERR342810 2 0 1 0 1 0
#> ERR342867 1 0 1 1 0 0
#> ERR342847 1 0 1 1 0 0
#> ERR342855 1 0 1 1 0 0
#> ERR342851 1 0 1 1 0 0
#> ERR342813 1 0 1 1 0 0
#> ERR342883 1 0 1 1 0 0
#> ERR342856 3 0 1 0 0 1
#> ERR342822 2 0 1 0 1 0
#> ERR342892 1 0 1 1 0 0
#> ERR342842 1 0 1 1 0 0
#> ERR342902 2 0 1 0 1 0
#> ERR342900 2 0 1 0 1 0
#> ERR342888 1 0 1 1 0 0
#> ERR342812 1 0 1 1 0 0
#> ERR342853 2 0 1 0 1 0
#> ERR342866 1 0 1 1 0 0
#> ERR342820 1 0 1 1 0 0
#> ERR342895 1 0 1 1 0 0
#> ERR342825 3 0 1 0 0 1
#> ERR342826 3 0 1 0 0 1
#> ERR342875 2 0 1 0 1 0
#> ERR342834 3 0 1 0 0 1
#> ERR342898 1 0 1 1 0 0
#> ERR342886 2 0 1 0 1 0
#> ERR342838 1 0 1 1 0 0
#> ERR342882 1 0 1 1 0 0
#> ERR342807 2 0 1 0 1 0
#> ERR342873 1 0 1 1 0 0
#> ERR342844 1 0 1 1 0 0
#> ERR342874 1 0 1 1 0 0
#> ERR342893 1 0 1 1 0 0
#> ERR342859 3 0 1 0 0 1
#> ERR342830 2 0 1 0 1 0
#> ERR342880 1 0 1 1 0 0
#> ERR342887 1 0 1 1 0 0
#> ERR342854 1 0 1 1 0 0
#> ERR342904 1 0 1 1 0 0
#> ERR342881 1 0 1 1 0 0
#> ERR342858 1 0 1 1 0 0
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342843 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342896 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342827 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342871 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342863 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342839 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342906 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342905 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342816 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342865 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342824 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342841 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342835 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342899 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342829 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342850 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342849 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342811 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342837 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342857 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342869 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342903 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342819 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342885 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342889 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342864 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342860 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342808 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342823 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342907 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342852 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342832 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342868 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342821 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342878 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342876 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342809 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342846 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342872 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342828 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342840 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342831 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342818 4 0.0000 0.959 0.000 0 0 1.000
#> ERR342862 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342894 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342884 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342891 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342890 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342836 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342879 4 0.0000 0.959 0.000 0 0 1.000
#> ERR342848 4 0.0000 0.959 0.000 0 0 1.000
#> ERR342861 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342814 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342870 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342901 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342908 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342815 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342897 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342833 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342817 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342810 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342867 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342847 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342855 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342851 4 0.0000 0.959 0.000 0 0 1.000
#> ERR342813 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342883 4 0.0000 0.959 0.000 0 0 1.000
#> ERR342856 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342822 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342892 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342842 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342902 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342900 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342888 1 0.0000 1.000 1.000 0 0 0.000
#> ERR342812 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342853 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342866 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342820 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342895 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342825 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342826 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342875 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342834 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342898 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342886 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342838 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342882 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342807 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342873 4 0.0000 0.959 0.000 0 0 1.000
#> ERR342844 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342874 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342893 4 0.0000 0.959 0.000 0 0 1.000
#> ERR342859 3 0.0000 1.000 0.000 0 1 0.000
#> ERR342830 2 0.0000 1.000 0.000 1 0 0.000
#> ERR342880 4 0.0000 0.959 0.000 0 0 1.000
#> ERR342887 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342854 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342904 4 0.0188 0.958 0.004 0 0 0.996
#> ERR342881 4 0.1867 0.960 0.072 0 0 0.928
#> ERR342858 4 0.0000 0.959 0.000 0 0 1.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342843 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342896 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342827 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342871 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342863 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342839 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342906 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342905 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342816 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342865 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342824 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342841 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342835 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342899 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342829 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342850 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342849 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342811 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342837 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342857 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342869 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342903 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342819 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342885 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342889 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342864 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342860 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342808 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342823 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342907 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342852 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342832 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342868 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342821 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342878 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342876 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342809 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342846 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342872 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342828 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342840 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342831 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342818 1 0.324 0.723 0.784 0 0 0.216 0
#> ERR342862 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342894 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342884 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342891 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342890 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342836 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342879 1 0.324 0.723 0.784 0 0 0.216 0
#> ERR342848 1 0.324 0.723 0.784 0 0 0.216 0
#> ERR342861 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342814 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342870 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342901 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342908 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342815 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342897 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342833 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342817 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342810 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342867 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342847 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342855 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342851 1 0.324 0.723 0.784 0 0 0.216 0
#> ERR342813 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342883 1 0.324 0.723 0.784 0 0 0.216 0
#> ERR342856 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342822 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342892 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342842 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342902 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342900 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342888 5 0.000 1.000 0.000 0 0 0.000 1
#> ERR342812 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342853 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342866 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342820 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342895 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342825 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342826 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342875 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342834 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342898 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342886 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342838 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342882 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342807 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342873 1 0.324 0.723 0.784 0 0 0.216 0
#> ERR342844 4 0.000 0.685 0.000 0 0 1.000 0
#> ERR342874 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342893 1 0.324 0.723 0.784 0 0 0.216 0
#> ERR342859 3 0.000 1.000 0.000 0 1 0.000 0
#> ERR342830 2 0.000 1.000 0.000 1 0 0.000 0
#> ERR342880 1 0.324 0.723 0.784 0 0 0.216 0
#> ERR342887 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342854 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342904 4 0.415 0.629 0.388 0 0 0.612 0
#> ERR342881 1 0.000 0.928 1.000 0 0 0.000 0
#> ERR342858 1 0.324 0.723 0.784 0 0 0.216 0
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342843 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342896 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342827 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342871 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342863 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342839 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342906 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342905 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342816 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342865 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342824 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342841 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342835 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342899 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342829 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342850 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342849 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342811 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342837 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342857 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342869 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342903 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342819 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342885 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342889 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342864 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342860 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342808 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342823 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342907 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342852 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342832 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342868 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342821 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342878 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342876 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342809 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342872 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342828 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342840 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342831 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342818 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
#> ERR342862 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342894 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342884 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342891 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342890 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342836 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342879 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
#> ERR342848 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
#> ERR342861 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342814 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342870 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342901 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342908 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342815 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342897 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342833 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342817 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342810 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342867 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342847 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342855 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342851 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
#> ERR342813 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342883 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
#> ERR342856 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342822 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342892 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342842 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342902 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342900 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342888 5 0.0000 1.000 0.000 0.000 0 0.000 1 0.000
#> ERR342812 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342853 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342866 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342820 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342895 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342875 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342834 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342898 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342886 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342838 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342882 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342807 2 0.3618 0.840 0.000 0.768 0 0.040 0 0.192
#> ERR342873 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
#> ERR342844 6 0.2996 1.000 0.000 0.000 0 0.228 0 0.772
#> ERR342874 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342893 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
#> ERR342859 3 0.0000 1.000 0.000 0.000 1 0.000 0 0.000
#> ERR342830 2 0.0000 0.929 0.000 1.000 0 0.000 0 0.000
#> ERR342880 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
#> ERR342887 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342854 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342904 4 0.0937 1.000 0.040 0.000 0 0.960 0 0.000
#> ERR342881 1 0.0000 0.917 1.000 0.000 0 0.000 0 0.000
#> ERR342858 1 0.4671 0.678 0.688 0.000 0 0.152 0 0.160
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "kmeans"]
# you can also extract it by
# res = res_list["CV:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.185 0.576 0.731 0.3574 0.531 0.531
#> 3 3 0.132 0.680 0.764 0.4878 0.754 0.609
#> 4 4 0.373 0.582 0.709 0.1948 1.000 1.000
#> 5 5 0.495 0.471 0.653 0.1034 0.902 0.796
#> 6 6 0.595 0.596 0.601 0.0741 0.786 0.524
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.808 0.617 0.752 0.248
#> ERR342843 1 0.808 0.617 0.752 0.248
#> ERR342896 1 0.975 0.740 0.592 0.408
#> ERR342827 2 0.141 0.752 0.020 0.980
#> ERR342871 1 0.955 0.703 0.624 0.376
#> ERR342863 2 0.000 0.757 0.000 1.000
#> ERR342839 1 0.808 0.617 0.752 0.248
#> ERR342906 2 0.998 -0.464 0.472 0.528
#> ERR342905 2 0.278 0.740 0.048 0.952
#> ERR342816 2 0.998 -0.464 0.472 0.528
#> ERR342865 2 0.000 0.757 0.000 1.000
#> ERR342824 1 0.975 0.740 0.592 0.408
#> ERR342841 2 0.141 0.752 0.020 0.980
#> ERR342835 1 0.973 0.728 0.596 0.404
#> ERR342899 2 0.278 0.740 0.048 0.952
#> ERR342829 1 0.975 0.740 0.592 0.408
#> ERR342850 1 0.955 0.703 0.624 0.376
#> ERR342849 2 0.278 0.740 0.048 0.952
#> ERR342811 1 0.955 0.703 0.624 0.376
#> ERR342837 1 0.973 0.728 0.596 0.404
#> ERR342857 2 0.998 -0.464 0.472 0.528
#> ERR342869 1 0.955 0.703 0.624 0.376
#> ERR342903 1 0.975 0.740 0.592 0.408
#> ERR342819 1 0.973 0.728 0.596 0.404
#> ERR342885 1 0.814 0.381 0.748 0.252
#> ERR342889 2 0.000 0.757 0.000 1.000
#> ERR342864 2 0.998 -0.464 0.472 0.528
#> ERR342860 2 0.278 0.740 0.048 0.952
#> ERR342808 1 0.955 0.703 0.624 0.376
#> ERR342823 1 0.975 0.740 0.592 0.408
#> ERR342907 2 0.141 0.752 0.020 0.980
#> ERR342852 2 0.998 -0.464 0.472 0.528
#> ERR342832 2 0.000 0.757 0.000 1.000
#> ERR342868 1 0.808 0.617 0.752 0.248
#> ERR342821 2 0.998 -0.464 0.472 0.528
#> ERR342878 2 0.141 0.752 0.020 0.980
#> ERR342876 1 0.975 0.740 0.592 0.408
#> ERR342809 1 0.975 0.740 0.592 0.408
#> ERR342846 1 0.814 0.381 0.748 0.252
#> ERR342872 2 0.141 0.752 0.020 0.980
#> ERR342828 2 0.000 0.757 0.000 1.000
#> ERR342840 1 0.973 0.728 0.596 0.404
#> ERR342831 1 0.808 0.617 0.752 0.248
#> ERR342818 1 1.000 0.605 0.508 0.492
#> ERR342862 1 0.973 0.728 0.596 0.404
#> ERR342894 1 0.808 0.617 0.752 0.248
#> ERR342884 2 0.141 0.752 0.020 0.980
#> ERR342891 1 0.975 0.740 0.592 0.408
#> ERR342890 1 0.808 0.617 0.752 0.248
#> ERR342836 2 0.000 0.757 0.000 1.000
#> ERR342879 1 1.000 0.605 0.508 0.492
#> ERR342848 1 1.000 0.605 0.508 0.492
#> ERR342861 1 0.975 0.740 0.592 0.408
#> ERR342814 2 0.278 0.740 0.048 0.952
#> ERR342870 1 0.955 0.703 0.624 0.376
#> ERR342901 1 0.975 0.740 0.592 0.408
#> ERR342908 1 0.955 0.703 0.624 0.376
#> ERR342815 2 0.000 0.757 0.000 1.000
#> ERR342897 1 0.814 0.381 0.748 0.252
#> ERR342833 2 0.141 0.752 0.020 0.980
#> ERR342817 1 0.814 0.381 0.748 0.252
#> ERR342810 2 0.278 0.740 0.048 0.952
#> ERR342867 2 0.998 -0.464 0.472 0.528
#> ERR342847 1 0.973 0.728 0.596 0.404
#> ERR342855 1 0.975 0.740 0.592 0.408
#> ERR342851 1 1.000 0.605 0.508 0.492
#> ERR342813 1 0.808 0.617 0.752 0.248
#> ERR342883 1 1.000 0.605 0.508 0.492
#> ERR342856 1 0.814 0.381 0.748 0.252
#> ERR342822 2 0.000 0.757 0.000 1.000
#> ERR342892 1 0.975 0.740 0.592 0.408
#> ERR342842 1 0.975 0.740 0.592 0.408
#> ERR342902 2 0.141 0.752 0.020 0.980
#> ERR342900 2 0.278 0.740 0.048 0.952
#> ERR342888 1 0.808 0.617 0.752 0.248
#> ERR342812 1 0.975 0.740 0.592 0.408
#> ERR342853 2 0.278 0.740 0.048 0.952
#> ERR342866 1 0.973 0.728 0.596 0.404
#> ERR342820 1 0.955 0.703 0.624 0.376
#> ERR342895 1 0.975 0.740 0.592 0.408
#> ERR342825 1 0.814 0.381 0.748 0.252
#> ERR342826 1 0.814 0.381 0.748 0.252
#> ERR342875 2 0.000 0.757 0.000 1.000
#> ERR342834 1 0.814 0.381 0.748 0.252
#> ERR342898 2 0.998 -0.464 0.472 0.528
#> ERR342886 2 0.278 0.740 0.048 0.952
#> ERR342838 1 0.975 0.740 0.592 0.408
#> ERR342882 1 0.975 0.740 0.592 0.408
#> ERR342807 2 0.141 0.752 0.020 0.980
#> ERR342873 1 1.000 0.605 0.508 0.492
#> ERR342844 2 0.998 -0.464 0.472 0.528
#> ERR342874 1 0.973 0.728 0.596 0.404
#> ERR342893 1 1.000 0.605 0.508 0.492
#> ERR342859 1 0.814 0.381 0.748 0.252
#> ERR342830 2 0.278 0.740 0.048 0.952
#> ERR342880 1 1.000 0.605 0.508 0.492
#> ERR342887 1 0.975 0.740 0.592 0.408
#> ERR342854 1 0.975 0.740 0.592 0.408
#> ERR342904 1 0.955 0.703 0.624 0.376
#> ERR342881 1 0.973 0.728 0.596 0.404
#> ERR342858 1 1.000 0.605 0.508 0.492
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.792 0.325 0.644 0.108 0.248
#> ERR342843 1 0.792 0.325 0.644 0.108 0.248
#> ERR342896 1 0.232 0.669 0.944 0.028 0.028
#> ERR342827 2 0.579 0.891 0.116 0.800 0.084
#> ERR342871 1 0.651 0.539 0.756 0.088 0.156
#> ERR342863 2 0.392 0.909 0.120 0.868 0.012
#> ERR342839 1 0.792 0.325 0.644 0.108 0.248
#> ERR342906 1 0.856 0.387 0.604 0.232 0.164
#> ERR342905 2 0.639 0.874 0.184 0.752 0.064
#> ERR342816 1 0.856 0.387 0.604 0.232 0.164
#> ERR342865 2 0.392 0.909 0.120 0.868 0.012
#> ERR342824 1 0.232 0.669 0.944 0.028 0.028
#> ERR342841 2 0.579 0.891 0.116 0.800 0.084
#> ERR342835 1 0.602 0.626 0.788 0.092 0.120
#> ERR342899 2 0.639 0.874 0.184 0.752 0.064
#> ERR342829 1 0.232 0.669 0.944 0.028 0.028
#> ERR342850 1 0.651 0.539 0.756 0.088 0.156
#> ERR342849 2 0.639 0.874 0.184 0.752 0.064
#> ERR342811 1 0.651 0.539 0.756 0.088 0.156
#> ERR342837 1 0.602 0.626 0.788 0.092 0.120
#> ERR342857 1 0.856 0.387 0.604 0.232 0.164
#> ERR342869 1 0.651 0.539 0.756 0.088 0.156
#> ERR342903 1 0.232 0.669 0.944 0.028 0.028
#> ERR342819 1 0.602 0.626 0.788 0.092 0.120
#> ERR342885 3 0.829 0.994 0.308 0.104 0.588
#> ERR342889 2 0.392 0.909 0.120 0.868 0.012
#> ERR342864 1 0.856 0.387 0.604 0.232 0.164
#> ERR342860 2 0.639 0.874 0.184 0.752 0.064
#> ERR342808 1 0.651 0.539 0.756 0.088 0.156
#> ERR342823 1 0.232 0.669 0.944 0.028 0.028
#> ERR342907 2 0.579 0.891 0.116 0.800 0.084
#> ERR342852 1 0.856 0.387 0.604 0.232 0.164
#> ERR342832 2 0.392 0.909 0.120 0.868 0.012
#> ERR342868 1 0.792 0.325 0.644 0.108 0.248
#> ERR342821 1 0.856 0.387 0.604 0.232 0.164
#> ERR342878 2 0.579 0.891 0.116 0.800 0.084
#> ERR342876 1 0.232 0.669 0.944 0.028 0.028
#> ERR342809 1 0.232 0.669 0.944 0.028 0.028
#> ERR342846 3 0.853 0.992 0.308 0.120 0.572
#> ERR342872 2 0.579 0.891 0.116 0.800 0.084
#> ERR342828 2 0.392 0.909 0.120 0.868 0.012
#> ERR342840 1 0.601 0.626 0.788 0.088 0.124
#> ERR342831 1 0.792 0.325 0.644 0.108 0.248
#> ERR342818 1 0.744 0.577 0.700 0.136 0.164
#> ERR342862 1 0.601 0.626 0.788 0.088 0.124
#> ERR342894 1 0.792 0.325 0.644 0.108 0.248
#> ERR342884 2 0.579 0.891 0.116 0.800 0.084
#> ERR342891 1 0.232 0.669 0.944 0.028 0.028
#> ERR342890 1 0.792 0.325 0.644 0.108 0.248
#> ERR342836 2 0.392 0.909 0.120 0.868 0.012
#> ERR342879 1 0.744 0.577 0.700 0.136 0.164
#> ERR342848 1 0.744 0.577 0.700 0.136 0.164
#> ERR342861 1 0.232 0.669 0.944 0.028 0.028
#> ERR342814 2 0.639 0.874 0.184 0.752 0.064
#> ERR342870 1 0.651 0.539 0.756 0.088 0.156
#> ERR342901 1 0.232 0.669 0.944 0.028 0.028
#> ERR342908 1 0.651 0.539 0.756 0.088 0.156
#> ERR342815 2 0.392 0.909 0.120 0.868 0.012
#> ERR342897 3 0.853 0.992 0.308 0.120 0.572
#> ERR342833 2 0.579 0.891 0.116 0.800 0.084
#> ERR342817 3 0.829 0.994 0.308 0.104 0.588
#> ERR342810 2 0.639 0.874 0.184 0.752 0.064
#> ERR342867 1 0.856 0.387 0.604 0.232 0.164
#> ERR342847 1 0.602 0.626 0.788 0.092 0.120
#> ERR342855 1 0.232 0.669 0.944 0.028 0.028
#> ERR342851 1 0.744 0.577 0.700 0.136 0.164
#> ERR342813 1 0.792 0.325 0.644 0.108 0.248
#> ERR342883 1 0.744 0.577 0.700 0.136 0.164
#> ERR342856 3 0.853 0.992 0.308 0.120 0.572
#> ERR342822 2 0.392 0.909 0.120 0.868 0.012
#> ERR342892 1 0.232 0.669 0.944 0.028 0.028
#> ERR342842 1 0.232 0.669 0.944 0.028 0.028
#> ERR342902 2 0.579 0.891 0.116 0.800 0.084
#> ERR342900 2 0.639 0.874 0.184 0.752 0.064
#> ERR342888 1 0.792 0.325 0.644 0.108 0.248
#> ERR342812 1 0.232 0.669 0.944 0.028 0.028
#> ERR342853 2 0.639 0.874 0.184 0.752 0.064
#> ERR342866 1 0.601 0.626 0.788 0.088 0.124
#> ERR342820 1 0.651 0.539 0.756 0.088 0.156
#> ERR342895 1 0.232 0.669 0.944 0.028 0.028
#> ERR342825 3 0.829 0.994 0.308 0.104 0.588
#> ERR342826 3 0.829 0.994 0.308 0.104 0.588
#> ERR342875 2 0.392 0.909 0.120 0.868 0.012
#> ERR342834 3 0.829 0.994 0.308 0.104 0.588
#> ERR342898 1 0.856 0.387 0.604 0.232 0.164
#> ERR342886 2 0.639 0.874 0.184 0.752 0.064
#> ERR342838 1 0.232 0.669 0.944 0.028 0.028
#> ERR342882 1 0.232 0.669 0.944 0.028 0.028
#> ERR342807 2 0.579 0.891 0.116 0.800 0.084
#> ERR342873 1 0.744 0.577 0.700 0.136 0.164
#> ERR342844 1 0.856 0.387 0.604 0.232 0.164
#> ERR342874 1 0.601 0.626 0.788 0.088 0.124
#> ERR342893 1 0.744 0.577 0.700 0.136 0.164
#> ERR342859 3 0.853 0.992 0.308 0.120 0.572
#> ERR342830 2 0.639 0.874 0.184 0.752 0.064
#> ERR342880 1 0.744 0.577 0.700 0.136 0.164
#> ERR342887 1 0.232 0.669 0.944 0.028 0.028
#> ERR342854 1 0.232 0.669 0.944 0.028 0.028
#> ERR342904 1 0.651 0.539 0.756 0.088 0.156
#> ERR342881 1 0.601 0.626 0.788 0.088 0.124
#> ERR342858 1 0.744 0.577 0.700 0.136 0.164
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.7845 0.192 0.476 0.008 0.288 NA
#> ERR342843 1 0.7845 0.192 0.476 0.008 0.288 NA
#> ERR342896 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342827 2 0.5108 0.819 0.032 0.768 0.024 NA
#> ERR342871 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342863 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342839 1 0.8058 0.192 0.476 0.020 0.300 NA
#> ERR342906 1 0.9685 0.165 0.384 0.208 0.200 NA
#> ERR342905 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342816 1 0.9685 0.165 0.384 0.208 0.200 NA
#> ERR342865 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342824 1 0.0524 0.585 0.988 0.008 0.000 NA
#> ERR342841 2 0.5048 0.819 0.032 0.768 0.020 NA
#> ERR342835 1 0.7051 0.501 0.620 0.040 0.080 NA
#> ERR342899 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342829 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342850 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342849 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342811 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342837 1 0.7051 0.501 0.620 0.040 0.080 NA
#> ERR342857 1 0.9686 0.165 0.384 0.208 0.204 NA
#> ERR342869 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342903 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342819 1 0.7051 0.501 0.620 0.040 0.080 NA
#> ERR342885 3 0.5109 0.990 0.196 0.060 0.744 NA
#> ERR342889 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342864 1 0.9686 0.165 0.384 0.208 0.204 NA
#> ERR342860 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342808 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342823 1 0.0524 0.585 0.988 0.008 0.000 NA
#> ERR342907 2 0.5048 0.819 0.032 0.768 0.020 NA
#> ERR342852 1 0.9686 0.165 0.384 0.208 0.204 NA
#> ERR342832 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342868 1 0.8058 0.192 0.476 0.020 0.300 NA
#> ERR342821 1 0.9685 0.165 0.384 0.208 0.200 NA
#> ERR342878 2 0.5048 0.819 0.032 0.768 0.020 NA
#> ERR342876 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342809 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342846 3 0.5969 0.986 0.196 0.060 0.716 NA
#> ERR342872 2 0.5048 0.819 0.032 0.768 0.020 NA
#> ERR342828 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342840 1 0.6979 0.501 0.620 0.040 0.072 NA
#> ERR342831 1 0.7845 0.192 0.476 0.008 0.288 NA
#> ERR342818 1 0.8165 0.478 0.560 0.120 0.088 NA
#> ERR342862 1 0.6979 0.501 0.620 0.040 0.072 NA
#> ERR342894 1 0.7845 0.192 0.476 0.008 0.288 NA
#> ERR342884 2 0.5048 0.819 0.032 0.768 0.020 NA
#> ERR342891 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342890 1 0.8058 0.192 0.476 0.020 0.300 NA
#> ERR342836 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342879 1 0.8165 0.478 0.560 0.120 0.088 NA
#> ERR342848 1 0.8165 0.478 0.560 0.120 0.088 NA
#> ERR342861 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342814 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342870 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342901 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342908 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342815 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342897 3 0.5913 0.986 0.196 0.068 0.716 NA
#> ERR342833 2 0.5048 0.819 0.032 0.768 0.020 NA
#> ERR342817 3 0.5109 0.990 0.196 0.060 0.744 NA
#> ERR342810 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342867 1 0.9685 0.165 0.384 0.208 0.200 NA
#> ERR342847 1 0.7051 0.501 0.620 0.040 0.080 NA
#> ERR342855 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342851 1 0.8165 0.478 0.560 0.120 0.088 NA
#> ERR342813 1 0.7845 0.192 0.476 0.008 0.288 NA
#> ERR342883 1 0.8165 0.478 0.560 0.120 0.088 NA
#> ERR342856 3 0.5913 0.986 0.196 0.068 0.716 NA
#> ERR342822 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342892 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342842 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342902 2 0.5048 0.819 0.032 0.768 0.020 NA
#> ERR342900 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342888 1 0.8058 0.192 0.476 0.020 0.300 NA
#> ERR342812 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342853 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342866 1 0.6979 0.501 0.620 0.040 0.072 NA
#> ERR342820 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342895 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342825 3 0.5109 0.990 0.196 0.060 0.744 NA
#> ERR342826 3 0.5109 0.990 0.196 0.060 0.744 NA
#> ERR342875 2 0.1833 0.862 0.032 0.944 0.000 NA
#> ERR342834 3 0.5109 0.990 0.196 0.060 0.744 NA
#> ERR342898 1 0.9686 0.165 0.384 0.208 0.204 NA
#> ERR342886 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342838 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342882 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342807 2 0.5048 0.819 0.032 0.768 0.020 NA
#> ERR342873 1 0.8165 0.478 0.560 0.120 0.088 NA
#> ERR342844 1 0.9686 0.165 0.384 0.208 0.204 NA
#> ERR342874 1 0.6979 0.501 0.620 0.040 0.072 NA
#> ERR342893 1 0.8165 0.478 0.560 0.120 0.088 NA
#> ERR342859 3 0.5969 0.986 0.196 0.060 0.716 NA
#> ERR342830 2 0.5164 0.831 0.104 0.796 0.044 NA
#> ERR342880 1 0.8165 0.478 0.560 0.120 0.088 NA
#> ERR342887 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342854 1 0.0336 0.585 0.992 0.008 0.000 NA
#> ERR342904 1 0.7467 0.375 0.576 0.024 0.256 NA
#> ERR342881 1 0.6979 0.501 0.620 0.040 0.072 NA
#> ERR342858 1 0.8165 0.478 0.560 0.120 0.088 NA
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 1 0.8070 0.1661 0.444 0.004 0.156 0.144 NA
#> ERR342843 1 0.8070 0.1661 0.444 0.004 0.156 0.144 NA
#> ERR342896 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342827 2 0.1095 0.7116 0.012 0.968 0.008 0.012 NA
#> ERR342871 1 0.8095 0.1186 0.484 0.020 0.228 0.152 NA
#> ERR342863 2 0.5615 0.7880 0.016 0.660 0.012 0.056 NA
#> ERR342839 1 0.7831 0.1649 0.444 0.004 0.152 0.100 NA
#> ERR342906 1 0.9596 -0.0925 0.308 0.100 0.204 0.236 NA
#> ERR342905 2 0.6621 0.7387 0.072 0.468 0.020 0.020 NA
#> ERR342816 1 0.9596 -0.0925 0.308 0.100 0.204 0.236 NA
#> ERR342865 2 0.5615 0.7880 0.016 0.660 0.012 0.056 NA
#> ERR342824 1 0.0162 0.3684 0.996 0.000 0.000 0.000 NA
#> ERR342841 2 0.0566 0.7115 0.012 0.984 0.004 0.000 NA
#> ERR342835 1 0.7090 0.0271 0.528 0.008 0.072 0.304 NA
#> ERR342899 2 0.6621 0.7387 0.072 0.468 0.020 0.020 NA
#> ERR342829 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342850 1 0.8087 0.1188 0.484 0.020 0.228 0.156 NA
#> ERR342849 2 0.6621 0.7387 0.072 0.468 0.020 0.020 NA
#> ERR342811 1 0.8095 0.1189 0.484 0.020 0.228 0.152 NA
#> ERR342837 1 0.7090 0.0271 0.528 0.008 0.072 0.304 NA
#> ERR342857 1 0.9584 -0.0924 0.308 0.100 0.204 0.240 NA
#> ERR342869 1 0.8087 0.1188 0.484 0.020 0.228 0.156 NA
#> ERR342903 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342819 1 0.7090 0.0271 0.528 0.008 0.072 0.304 NA
#> ERR342885 3 0.2351 0.9692 0.088 0.016 0.896 0.000 NA
#> ERR342889 2 0.5615 0.7880 0.016 0.660 0.012 0.056 NA
#> ERR342864 1 0.9584 -0.0924 0.308 0.100 0.204 0.240 NA
#> ERR342860 2 0.6694 0.7386 0.072 0.468 0.024 0.020 NA
#> ERR342808 1 0.8101 0.1186 0.484 0.020 0.228 0.148 NA
#> ERR342823 1 0.0162 0.3684 0.996 0.000 0.000 0.000 NA
#> ERR342907 2 0.0693 0.7115 0.012 0.980 0.008 0.000 NA
#> ERR342852 1 0.9584 -0.0924 0.308 0.100 0.204 0.240 NA
#> ERR342832 2 0.5615 0.7880 0.016 0.660 0.012 0.056 NA
#> ERR342868 1 0.7831 0.1649 0.444 0.004 0.152 0.100 NA
#> ERR342821 1 0.9596 -0.0925 0.308 0.100 0.204 0.236 NA
#> ERR342878 2 0.0566 0.7115 0.012 0.984 0.004 0.000 NA
#> ERR342876 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342809 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342846 3 0.4514 0.9601 0.088 0.024 0.808 0.056 NA
#> ERR342872 2 0.0727 0.7115 0.012 0.980 0.004 0.004 NA
#> ERR342828 2 0.5652 0.7880 0.016 0.660 0.012 0.060 NA
#> ERR342840 1 0.6963 0.0268 0.528 0.004 0.076 0.312 NA
#> ERR342831 1 0.8070 0.1661 0.444 0.004 0.156 0.144 NA
#> ERR342818 4 0.6966 0.9990 0.404 0.064 0.060 0.460 NA
#> ERR342862 1 0.7057 0.0261 0.528 0.004 0.076 0.300 NA
#> ERR342894 1 0.8070 0.1661 0.444 0.004 0.156 0.144 NA
#> ERR342884 2 0.0566 0.7115 0.012 0.984 0.004 0.000 NA
#> ERR342891 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342890 1 0.7831 0.1649 0.444 0.004 0.152 0.100 NA
#> ERR342836 2 0.5615 0.7880 0.016 0.660 0.012 0.056 NA
#> ERR342879 4 0.6966 0.9990 0.404 0.064 0.060 0.460 NA
#> ERR342848 4 0.7133 0.9916 0.404 0.064 0.060 0.452 NA
#> ERR342861 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342814 2 0.6621 0.7387 0.072 0.468 0.020 0.020 NA
#> ERR342870 1 0.8095 0.1189 0.484 0.020 0.228 0.152 NA
#> ERR342901 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342908 1 0.8101 0.1186 0.484 0.020 0.228 0.148 NA
#> ERR342815 2 0.5652 0.7880 0.016 0.660 0.012 0.060 NA
#> ERR342897 3 0.4447 0.9612 0.088 0.024 0.812 0.052 NA
#> ERR342833 2 0.0566 0.7115 0.012 0.984 0.004 0.000 NA
#> ERR342817 3 0.2351 0.9692 0.088 0.016 0.896 0.000 NA
#> ERR342810 2 0.6621 0.7387 0.072 0.468 0.020 0.020 NA
#> ERR342867 1 0.9596 -0.0925 0.308 0.100 0.204 0.236 NA
#> ERR342847 1 0.7090 0.0271 0.528 0.008 0.072 0.304 NA
#> ERR342855 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342851 4 0.6966 0.9990 0.404 0.064 0.060 0.460 NA
#> ERR342813 1 0.8070 0.1661 0.444 0.004 0.156 0.144 NA
#> ERR342883 4 0.6966 0.9990 0.404 0.064 0.060 0.460 NA
#> ERR342856 3 0.4447 0.9612 0.088 0.024 0.812 0.052 NA
#> ERR342822 2 0.5652 0.7880 0.016 0.660 0.012 0.060 NA
#> ERR342892 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342842 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342902 2 0.0566 0.7115 0.012 0.984 0.004 0.000 NA
#> ERR342900 2 0.6621 0.7387 0.072 0.468 0.020 0.020 NA
#> ERR342888 1 0.7831 0.1649 0.444 0.004 0.152 0.100 NA
#> ERR342812 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342853 2 0.6621 0.7387 0.072 0.468 0.020 0.020 NA
#> ERR342866 1 0.6963 0.0268 0.528 0.004 0.076 0.312 NA
#> ERR342820 1 0.8087 0.1188 0.484 0.020 0.228 0.156 NA
#> ERR342895 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342825 3 0.2351 0.9692 0.088 0.016 0.896 0.000 NA
#> ERR342826 3 0.2351 0.9692 0.088 0.016 0.896 0.000 NA
#> ERR342875 2 0.5652 0.7880 0.016 0.660 0.012 0.060 NA
#> ERR342834 3 0.2351 0.9692 0.088 0.016 0.896 0.000 NA
#> ERR342898 1 0.9584 -0.0924 0.308 0.100 0.204 0.240 NA
#> ERR342886 2 0.6694 0.7386 0.072 0.468 0.024 0.020 NA
#> ERR342838 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342882 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342807 2 0.0968 0.7116 0.012 0.972 0.012 0.004 NA
#> ERR342873 4 0.6966 0.9990 0.404 0.064 0.060 0.460 NA
#> ERR342844 1 0.9584 -0.0924 0.308 0.100 0.204 0.240 NA
#> ERR342874 1 0.7057 0.0261 0.528 0.004 0.076 0.300 NA
#> ERR342893 4 0.6966 0.9990 0.404 0.064 0.060 0.460 NA
#> ERR342859 3 0.4514 0.9601 0.088 0.024 0.808 0.056 NA
#> ERR342830 2 0.6694 0.7386 0.072 0.468 0.024 0.020 NA
#> ERR342880 4 0.6966 0.9990 0.404 0.064 0.060 0.460 NA
#> ERR342887 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342854 1 0.0000 0.3698 1.000 0.000 0.000 0.000 NA
#> ERR342904 1 0.8095 0.1189 0.484 0.020 0.228 0.152 NA
#> ERR342881 1 0.7057 0.0261 0.528 0.004 0.076 0.300 NA
#> ERR342858 4 0.6966 0.9990 0.404 0.064 0.060 0.460 NA
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.7232 0.969 0.272 0.004 0.136 0.152 0.436 NA
#> ERR342843 5 0.7232 0.969 0.272 0.004 0.136 0.152 0.436 NA
#> ERR342896 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342827 2 0.4991 0.656 0.004 0.580 0.000 0.020 0.032 NA
#> ERR342871 1 0.8496 0.178 0.300 0.004 0.160 0.228 0.056 NA
#> ERR342863 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.004 NA
#> ERR342839 5 0.8095 0.960 0.272 0.004 0.140 0.184 0.364 NA
#> ERR342906 4 0.8931 0.991 0.176 0.048 0.224 0.360 0.076 NA
#> ERR342905 2 0.7132 0.658 0.076 0.572 0.012 0.056 0.172 NA
#> ERR342816 4 0.8931 0.991 0.176 0.048 0.224 0.360 0.076 NA
#> ERR342865 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.004 NA
#> ERR342824 1 0.4323 0.467 0.508 0.000 0.000 0.476 0.008 NA
#> ERR342841 2 0.3923 0.657 0.004 0.580 0.000 0.000 0.000 NA
#> ERR342835 1 0.0696 0.298 0.980 0.004 0.008 0.000 0.004 NA
#> ERR342899 2 0.6891 0.658 0.076 0.572 0.004 0.044 0.196 NA
#> ERR342829 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342850 1 0.8494 0.178 0.300 0.004 0.160 0.224 0.056 NA
#> ERR342849 2 0.6856 0.658 0.076 0.572 0.004 0.040 0.200 NA
#> ERR342811 1 0.8494 0.178 0.300 0.004 0.160 0.224 0.056 NA
#> ERR342837 1 0.0696 0.298 0.980 0.004 0.008 0.000 0.004 NA
#> ERR342857 4 0.8814 0.993 0.176 0.048 0.224 0.376 0.072 NA
#> ERR342869 1 0.8494 0.178 0.300 0.004 0.160 0.224 0.056 NA
#> ERR342903 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342819 1 0.0551 0.298 0.984 0.004 0.008 0.000 0.004 NA
#> ERR342885 3 0.1341 0.966 0.028 0.000 0.948 0.024 0.000 NA
#> ERR342889 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.004 NA
#> ERR342864 4 0.8814 0.993 0.176 0.048 0.224 0.376 0.072 NA
#> ERR342860 2 0.6934 0.658 0.076 0.572 0.004 0.044 0.180 NA
#> ERR342808 1 0.8496 0.178 0.300 0.004 0.160 0.228 0.056 NA
#> ERR342823 1 0.4323 0.467 0.508 0.000 0.000 0.476 0.008 NA
#> ERR342907 2 0.4049 0.657 0.004 0.580 0.000 0.000 0.004 NA
#> ERR342852 4 0.8814 0.993 0.176 0.048 0.224 0.376 0.072 NA
#> ERR342832 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.004 NA
#> ERR342868 5 0.8057 0.960 0.272 0.004 0.140 0.188 0.364 NA
#> ERR342821 4 0.8931 0.991 0.176 0.048 0.224 0.360 0.076 NA
#> ERR342878 2 0.4049 0.657 0.004 0.580 0.004 0.000 0.000 NA
#> ERR342876 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342809 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342846 3 0.3090 0.958 0.028 0.000 0.872 0.048 0.020 NA
#> ERR342872 2 0.4352 0.657 0.004 0.580 0.000 0.004 0.012 NA
#> ERR342828 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.000 NA
#> ERR342840 1 0.0551 0.298 0.984 0.004 0.008 0.000 0.000 NA
#> ERR342831 5 0.7232 0.969 0.272 0.004 0.136 0.152 0.436 NA
#> ERR342818 1 0.7669 0.190 0.420 0.016 0.012 0.196 0.264 NA
#> ERR342862 1 0.0810 0.298 0.976 0.004 0.008 0.000 0.008 NA
#> ERR342894 5 0.7232 0.969 0.272 0.004 0.136 0.152 0.436 NA
#> ERR342884 2 0.4049 0.657 0.004 0.580 0.000 0.000 0.004 NA
#> ERR342891 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342890 5 0.8057 0.960 0.272 0.004 0.140 0.188 0.364 NA
#> ERR342836 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.004 NA
#> ERR342879 1 0.7669 0.190 0.420 0.016 0.012 0.196 0.264 NA
#> ERR342848 1 0.7747 0.187 0.420 0.016 0.012 0.192 0.252 NA
#> ERR342861 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342814 2 0.6856 0.658 0.076 0.572 0.004 0.040 0.200 NA
#> ERR342870 1 0.8496 0.177 0.300 0.004 0.160 0.228 0.056 NA
#> ERR342901 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342908 1 0.8496 0.178 0.300 0.004 0.160 0.228 0.056 NA
#> ERR342815 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.000 NA
#> ERR342897 3 0.3090 0.958 0.028 0.000 0.872 0.048 0.020 NA
#> ERR342833 2 0.4049 0.657 0.004 0.580 0.004 0.000 0.000 NA
#> ERR342817 3 0.1341 0.966 0.028 0.000 0.948 0.024 0.000 NA
#> ERR342810 2 0.7132 0.658 0.076 0.572 0.012 0.056 0.172 NA
#> ERR342867 4 0.8931 0.991 0.176 0.048 0.224 0.360 0.076 NA
#> ERR342847 1 0.0551 0.298 0.984 0.004 0.008 0.000 0.004 NA
#> ERR342855 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342851 1 0.7669 0.190 0.420 0.016 0.012 0.196 0.264 NA
#> ERR342813 5 0.7232 0.969 0.272 0.004 0.136 0.152 0.436 NA
#> ERR342883 1 0.7669 0.190 0.420 0.016 0.012 0.196 0.264 NA
#> ERR342856 3 0.3090 0.958 0.028 0.000 0.872 0.048 0.020 NA
#> ERR342822 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.000 NA
#> ERR342892 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342842 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342902 2 0.4049 0.657 0.004 0.580 0.004 0.000 0.000 NA
#> ERR342900 2 0.6856 0.658 0.076 0.572 0.004 0.040 0.200 NA
#> ERR342888 5 0.8057 0.960 0.272 0.004 0.140 0.188 0.364 NA
#> ERR342812 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342853 2 0.6915 0.658 0.076 0.572 0.004 0.044 0.188 NA
#> ERR342866 1 0.0810 0.298 0.976 0.004 0.008 0.000 0.004 NA
#> ERR342820 1 0.8494 0.178 0.300 0.004 0.160 0.224 0.056 NA
#> ERR342895 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342825 3 0.1341 0.966 0.028 0.000 0.948 0.024 0.000 NA
#> ERR342826 3 0.1485 0.966 0.028 0.000 0.944 0.024 0.004 NA
#> ERR342875 2 0.0146 0.725 0.000 0.996 0.000 0.000 0.000 NA
#> ERR342834 3 0.1341 0.966 0.028 0.000 0.948 0.024 0.000 NA
#> ERR342898 4 0.8814 0.993 0.176 0.048 0.224 0.376 0.072 NA
#> ERR342886 2 0.6934 0.658 0.076 0.572 0.004 0.044 0.180 NA
#> ERR342838 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342882 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342807 2 0.4664 0.657 0.004 0.580 0.012 0.008 0.008 NA
#> ERR342873 1 0.7669 0.190 0.420 0.016 0.012 0.196 0.264 NA
#> ERR342844 4 0.8814 0.993 0.176 0.048 0.224 0.376 0.072 NA
#> ERR342874 1 0.0810 0.298 0.976 0.004 0.008 0.000 0.008 NA
#> ERR342893 1 0.7669 0.190 0.420 0.016 0.012 0.196 0.264 NA
#> ERR342859 3 0.3090 0.958 0.028 0.000 0.872 0.048 0.020 NA
#> ERR342830 2 0.6934 0.658 0.076 0.572 0.004 0.044 0.180 NA
#> ERR342880 1 0.7669 0.190 0.420 0.016 0.012 0.196 0.264 NA
#> ERR342887 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342854 1 0.3868 0.472 0.508 0.000 0.000 0.492 0.000 NA
#> ERR342904 1 0.8496 0.177 0.300 0.004 0.160 0.228 0.056 NA
#> ERR342881 1 0.0810 0.298 0.976 0.004 0.008 0.000 0.008 NA
#> ERR342858 1 0.7669 0.190 0.420 0.016 0.012 0.196 0.264 NA
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "skmeans"]
# you can also extract it by
# res = res_list["CV:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.688 0.925 0.959 0.4853 0.499 0.499
#> 3 3 0.706 0.692 0.872 0.3569 0.704 0.475
#> 4 4 0.706 0.811 0.873 0.1279 0.854 0.598
#> 5 5 0.806 0.770 0.827 0.0561 0.918 0.691
#> 6 6 0.852 0.846 0.776 0.0369 0.984 0.920
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 1.000 1.000 0.000
#> ERR342843 1 0.000 1.000 1.000 0.000
#> ERR342896 1 0.000 1.000 1.000 0.000
#> ERR342827 2 0.000 0.906 0.000 1.000
#> ERR342871 1 0.000 1.000 1.000 0.000
#> ERR342863 2 0.000 0.906 0.000 1.000
#> ERR342839 1 0.000 1.000 1.000 0.000
#> ERR342906 2 0.936 0.581 0.352 0.648
#> ERR342905 2 0.000 0.906 0.000 1.000
#> ERR342816 2 0.936 0.581 0.352 0.648
#> ERR342865 2 0.000 0.906 0.000 1.000
#> ERR342824 1 0.000 1.000 1.000 0.000
#> ERR342841 2 0.000 0.906 0.000 1.000
#> ERR342835 1 0.000 1.000 1.000 0.000
#> ERR342899 2 0.000 0.906 0.000 1.000
#> ERR342829 1 0.000 1.000 1.000 0.000
#> ERR342850 1 0.000 1.000 1.000 0.000
#> ERR342849 2 0.000 0.906 0.000 1.000
#> ERR342811 1 0.000 1.000 1.000 0.000
#> ERR342837 1 0.000 1.000 1.000 0.000
#> ERR342857 2 0.936 0.581 0.352 0.648
#> ERR342869 1 0.000 1.000 1.000 0.000
#> ERR342903 1 0.000 1.000 1.000 0.000
#> ERR342819 1 0.000 1.000 1.000 0.000
#> ERR342885 2 0.482 0.865 0.104 0.896
#> ERR342889 2 0.000 0.906 0.000 1.000
#> ERR342864 2 0.936 0.581 0.352 0.648
#> ERR342860 2 0.000 0.906 0.000 1.000
#> ERR342808 1 0.000 1.000 1.000 0.000
#> ERR342823 1 0.000 1.000 1.000 0.000
#> ERR342907 2 0.000 0.906 0.000 1.000
#> ERR342852 2 0.936 0.581 0.352 0.648
#> ERR342832 2 0.000 0.906 0.000 1.000
#> ERR342868 1 0.000 1.000 1.000 0.000
#> ERR342821 2 0.936 0.581 0.352 0.648
#> ERR342878 2 0.000 0.906 0.000 1.000
#> ERR342876 1 0.000 1.000 1.000 0.000
#> ERR342809 1 0.000 1.000 1.000 0.000
#> ERR342846 2 0.482 0.865 0.104 0.896
#> ERR342872 2 0.000 0.906 0.000 1.000
#> ERR342828 2 0.000 0.906 0.000 1.000
#> ERR342840 1 0.000 1.000 1.000 0.000
#> ERR342831 1 0.000 1.000 1.000 0.000
#> ERR342818 1 0.000 1.000 1.000 0.000
#> ERR342862 1 0.000 1.000 1.000 0.000
#> ERR342894 1 0.000 1.000 1.000 0.000
#> ERR342884 2 0.000 0.906 0.000 1.000
#> ERR342891 1 0.000 1.000 1.000 0.000
#> ERR342890 1 0.000 1.000 1.000 0.000
#> ERR342836 2 0.000 0.906 0.000 1.000
#> ERR342879 1 0.000 1.000 1.000 0.000
#> ERR342848 1 0.000 1.000 1.000 0.000
#> ERR342861 1 0.000 1.000 1.000 0.000
#> ERR342814 2 0.000 0.906 0.000 1.000
#> ERR342870 1 0.000 1.000 1.000 0.000
#> ERR342901 1 0.000 1.000 1.000 0.000
#> ERR342908 1 0.000 1.000 1.000 0.000
#> ERR342815 2 0.000 0.906 0.000 1.000
#> ERR342897 2 0.482 0.865 0.104 0.896
#> ERR342833 2 0.000 0.906 0.000 1.000
#> ERR342817 2 0.482 0.865 0.104 0.896
#> ERR342810 2 0.000 0.906 0.000 1.000
#> ERR342867 2 0.936 0.581 0.352 0.648
#> ERR342847 1 0.000 1.000 1.000 0.000
#> ERR342855 1 0.000 1.000 1.000 0.000
#> ERR342851 1 0.000 1.000 1.000 0.000
#> ERR342813 1 0.000 1.000 1.000 0.000
#> ERR342883 1 0.000 1.000 1.000 0.000
#> ERR342856 2 0.482 0.865 0.104 0.896
#> ERR342822 2 0.000 0.906 0.000 1.000
#> ERR342892 1 0.000 1.000 1.000 0.000
#> ERR342842 1 0.000 1.000 1.000 0.000
#> ERR342902 2 0.000 0.906 0.000 1.000
#> ERR342900 2 0.000 0.906 0.000 1.000
#> ERR342888 1 0.000 1.000 1.000 0.000
#> ERR342812 1 0.000 1.000 1.000 0.000
#> ERR342853 2 0.000 0.906 0.000 1.000
#> ERR342866 1 0.000 1.000 1.000 0.000
#> ERR342820 1 0.000 1.000 1.000 0.000
#> ERR342895 1 0.000 1.000 1.000 0.000
#> ERR342825 2 0.482 0.865 0.104 0.896
#> ERR342826 2 0.482 0.865 0.104 0.896
#> ERR342875 2 0.000 0.906 0.000 1.000
#> ERR342834 2 0.482 0.865 0.104 0.896
#> ERR342898 2 0.936 0.581 0.352 0.648
#> ERR342886 2 0.000 0.906 0.000 1.000
#> ERR342838 1 0.000 1.000 1.000 0.000
#> ERR342882 1 0.000 1.000 1.000 0.000
#> ERR342807 2 0.000 0.906 0.000 1.000
#> ERR342873 1 0.000 1.000 1.000 0.000
#> ERR342844 2 0.936 0.581 0.352 0.648
#> ERR342874 1 0.000 1.000 1.000 0.000
#> ERR342893 1 0.000 1.000 1.000 0.000
#> ERR342859 2 0.482 0.865 0.104 0.896
#> ERR342830 2 0.000 0.906 0.000 1.000
#> ERR342880 1 0.000 1.000 1.000 0.000
#> ERR342887 1 0.000 1.000 1.000 0.000
#> ERR342854 1 0.000 1.000 1.000 0.000
#> ERR342904 1 0.000 1.000 1.000 0.000
#> ERR342881 1 0.000 1.000 1.000 0.000
#> ERR342858 1 0.000 1.000 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342843 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342896 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342827 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342871 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342863 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342839 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342906 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342905 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342816 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342865 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342824 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342841 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342835 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342899 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342829 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342850 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342849 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342811 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342837 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342857 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342869 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342903 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342819 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342885 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342889 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342864 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342860 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342808 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342823 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342907 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342852 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342832 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342868 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342821 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342878 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342876 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342809 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342846 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342872 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342828 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342840 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342831 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342818 1 0.6823 0.094 0.504 0.012 0.484
#> ERR342862 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342894 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342884 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342891 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342890 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342836 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342879 1 0.6823 0.094 0.504 0.012 0.484
#> ERR342848 1 0.6823 0.094 0.504 0.012 0.484
#> ERR342861 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342814 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342870 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342901 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342908 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342815 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342897 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342833 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342817 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342810 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342867 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342847 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342855 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342851 1 0.6823 0.094 0.504 0.012 0.484
#> ERR342813 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342883 1 0.6823 0.094 0.504 0.012 0.484
#> ERR342856 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342822 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342892 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342842 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342902 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342900 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342888 3 0.6267 0.313 0.452 0.000 0.548
#> ERR342812 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342853 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342866 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342820 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342895 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342825 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342826 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342875 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342834 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342898 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342886 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342838 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342882 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342807 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342873 1 0.6823 0.094 0.504 0.012 0.484
#> ERR342844 3 0.1491 0.693 0.016 0.016 0.968
#> ERR342874 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342893 1 0.6823 0.094 0.504 0.012 0.484
#> ERR342859 3 0.2313 0.693 0.024 0.032 0.944
#> ERR342830 2 0.0000 1.000 0.000 1.000 0.000
#> ERR342880 1 0.6823 0.094 0.504 0.012 0.484
#> ERR342887 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342854 1 0.0237 0.819 0.996 0.000 0.004
#> ERR342904 3 0.6026 0.319 0.376 0.000 0.624
#> ERR342881 1 0.0892 0.813 0.980 0.000 0.020
#> ERR342858 1 0.6823 0.094 0.504 0.012 0.484
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342843 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342896 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342827 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342871 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342863 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342839 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342906 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342905 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342816 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342865 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342824 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342841 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342835 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342899 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342829 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342850 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342849 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342811 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342837 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342857 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342869 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342903 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342819 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342885 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342889 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342864 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342860 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342808 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342823 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342907 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342852 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342832 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342868 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342821 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342878 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342876 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342846 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342872 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342828 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342840 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342831 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342818 4 0.2450 0.700 0.072 0.000 0.016 0.912
#> ERR342862 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342894 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342884 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342891 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342890 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342836 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342879 4 0.2450 0.700 0.072 0.000 0.016 0.912
#> ERR342848 4 0.2450 0.700 0.072 0.000 0.016 0.912
#> ERR342861 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342814 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342870 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342901 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342908 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342815 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342897 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342833 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342817 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342810 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342867 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342847 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342855 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342851 4 0.2450 0.700 0.072 0.000 0.016 0.912
#> ERR342813 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342883 4 0.2450 0.700 0.072 0.000 0.016 0.912
#> ERR342856 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342822 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342892 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342902 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342900 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342888 3 0.5722 0.775 0.148 0.000 0.716 0.136
#> ERR342812 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342853 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342866 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342820 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342895 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342825 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342826 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342875 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342834 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342898 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342886 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342838 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342807 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342873 4 0.2450 0.700 0.072 0.000 0.016 0.912
#> ERR342844 4 0.5376 0.553 0.000 0.016 0.396 0.588
#> ERR342874 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342893 4 0.2450 0.700 0.072 0.000 0.016 0.912
#> ERR342859 3 0.1545 0.769 0.000 0.008 0.952 0.040
#> ERR342830 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342880 4 0.2450 0.700 0.072 0.000 0.016 0.912
#> ERR342887 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.868 1.000 0.000 0.000 0.000
#> ERR342904 4 0.5578 0.701 0.128 0.000 0.144 0.728
#> ERR342881 1 0.5639 0.661 0.636 0.000 0.040 0.324
#> ERR342858 4 0.2450 0.700 0.072 0.000 0.016 0.912
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342843 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342871 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342863 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342839 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342906 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342905 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342816 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342865 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342835 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342899 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342849 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342811 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342837 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342857 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342869 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342885 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342889 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342864 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342860 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342808 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342852 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342832 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342868 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342821 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342878 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342872 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342828 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342840 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342831 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342818 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
#> ERR342862 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342894 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342884 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342890 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342836 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342879 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
#> ERR342848 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342870 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342815 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342897 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342833 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342817 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342810 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342867 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342847 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342851 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
#> ERR342813 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342883 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
#> ERR342856 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342822 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342900 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342888 3 0.5479 0.793 0.036 0.000 0.688 0.064 0.212
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342866 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342820 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342826 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342875 2 0.0000 0.993 0.000 1.000 0.000 0.000 0.000
#> ERR342834 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342898 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342886 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.0613 0.989 0.000 0.984 0.008 0.004 0.004
#> ERR342873 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
#> ERR342844 4 0.1544 0.663 0.000 0.000 0.068 0.932 0.000
#> ERR342874 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342893 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
#> ERR342859 3 0.1608 0.790 0.000 0.000 0.928 0.072 0.000
#> ERR342830 2 0.0290 0.992 0.000 0.992 0.000 0.000 0.008
#> ERR342880 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.6273 0.615 0.032 0.000 0.076 0.532 0.360
#> ERR342881 5 0.5093 0.448 0.340 0.000 0.020 0.020 0.620
#> ERR342858 5 0.5256 0.133 0.024 0.000 0.012 0.472 0.492
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342843 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342896 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342871 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342863 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342839 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342906 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342905 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342816 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342865 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342824 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342835 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342899 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342829 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342849 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342811 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342837 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342857 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342869 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342903 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342885 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342889 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342864 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342860 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342808 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342823 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342852 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342832 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342868 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342821 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342878 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342876 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342872 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342828 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342840 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342831 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342818 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
#> ERR342862 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342894 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342884 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342891 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342890 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342836 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342879 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
#> ERR342848 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
#> ERR342861 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342870 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342901 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342815 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342897 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342833 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342817 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342810 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342867 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342847 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342855 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
#> ERR342813 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342883 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
#> ERR342856 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342822 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342892 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342900 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342888 3 0.630 0.716 0.012 0.000 0.520 0.152 0.292 0.024
#> ERR342812 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342866 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342820 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342895 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342826 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342875 2 0.000 0.967 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342834 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342898 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342886 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342838 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.164 0.951 0.000 0.936 0.004 0.024 0.036 0.000
#> ERR342873 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
#> ERR342844 4 0.345 0.500 0.000 0.000 0.012 0.744 0.000 0.244
#> ERR342874 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342893 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
#> ERR342859 3 0.101 0.729 0.000 0.000 0.960 0.036 0.000 0.004
#> ERR342830 2 0.115 0.961 0.000 0.956 0.000 0.012 0.032 0.000
#> ERR342880 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
#> ERR342887 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.745 0.448 0.016 0.000 0.068 0.320 0.288 0.308
#> ERR342881 5 0.571 1.000 0.184 0.000 0.004 0.000 0.536 0.276
#> ERR342858 6 0.000 1.000 0.000 0.000 0.000 0.000 0.000 1.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "pam"]
# you can also extract it by
# res = res_list["CV:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 5.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 1.000 1.000 0.4053 0.595 0.595
#> 3 3 1.000 1.000 1.000 0.2811 0.886 0.808
#> 4 4 1.000 0.987 0.986 0.1886 0.902 0.796
#> 5 5 0.929 0.967 0.977 0.1480 0.918 0.786
#> 6 6 0.884 0.946 0.936 0.0865 0.934 0.781
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 5
#> attr(,"optional")
#> [1] 2 3 4
There is also optional best \(k\) = 2 3 4 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0 1 1 0
#> ERR342843 1 0 1 1 0
#> ERR342896 1 0 1 1 0
#> ERR342827 2 0 1 0 1
#> ERR342871 1 0 1 1 0
#> ERR342863 2 0 1 0 1
#> ERR342839 1 0 1 1 0
#> ERR342906 1 0 1 1 0
#> ERR342905 2 0 1 0 1
#> ERR342816 1 0 1 1 0
#> ERR342865 2 0 1 0 1
#> ERR342824 1 0 1 1 0
#> ERR342841 2 0 1 0 1
#> ERR342835 1 0 1 1 0
#> ERR342899 2 0 1 0 1
#> ERR342829 1 0 1 1 0
#> ERR342850 1 0 1 1 0
#> ERR342849 2 0 1 0 1
#> ERR342811 1 0 1 1 0
#> ERR342837 1 0 1 1 0
#> ERR342857 1 0 1 1 0
#> ERR342869 1 0 1 1 0
#> ERR342903 1 0 1 1 0
#> ERR342819 1 0 1 1 0
#> ERR342885 1 0 1 1 0
#> ERR342889 2 0 1 0 1
#> ERR342864 1 0 1 1 0
#> ERR342860 2 0 1 0 1
#> ERR342808 1 0 1 1 0
#> ERR342823 1 0 1 1 0
#> ERR342907 2 0 1 0 1
#> ERR342852 1 0 1 1 0
#> ERR342832 2 0 1 0 1
#> ERR342868 1 0 1 1 0
#> ERR342821 1 0 1 1 0
#> ERR342878 2 0 1 0 1
#> ERR342876 1 0 1 1 0
#> ERR342809 1 0 1 1 0
#> ERR342846 1 0 1 1 0
#> ERR342872 2 0 1 0 1
#> ERR342828 2 0 1 0 1
#> ERR342840 1 0 1 1 0
#> ERR342831 1 0 1 1 0
#> ERR342818 1 0 1 1 0
#> ERR342862 1 0 1 1 0
#> ERR342894 1 0 1 1 0
#> ERR342884 2 0 1 0 1
#> ERR342891 1 0 1 1 0
#> ERR342890 1 0 1 1 0
#> ERR342836 2 0 1 0 1
#> ERR342879 1 0 1 1 0
#> ERR342848 1 0 1 1 0
#> ERR342861 1 0 1 1 0
#> ERR342814 2 0 1 0 1
#> ERR342870 1 0 1 1 0
#> ERR342901 1 0 1 1 0
#> ERR342908 1 0 1 1 0
#> ERR342815 2 0 1 0 1
#> ERR342897 1 0 1 1 0
#> ERR342833 2 0 1 0 1
#> ERR342817 1 0 1 1 0
#> ERR342810 2 0 1 0 1
#> ERR342867 1 0 1 1 0
#> ERR342847 1 0 1 1 0
#> ERR342855 1 0 1 1 0
#> ERR342851 1 0 1 1 0
#> ERR342813 1 0 1 1 0
#> ERR342883 1 0 1 1 0
#> ERR342856 1 0 1 1 0
#> ERR342822 2 0 1 0 1
#> ERR342892 1 0 1 1 0
#> ERR342842 1 0 1 1 0
#> ERR342902 2 0 1 0 1
#> ERR342900 2 0 1 0 1
#> ERR342888 1 0 1 1 0
#> ERR342812 1 0 1 1 0
#> ERR342853 2 0 1 0 1
#> ERR342866 1 0 1 1 0
#> ERR342820 1 0 1 1 0
#> ERR342895 1 0 1 1 0
#> ERR342825 1 0 1 1 0
#> ERR342826 1 0 1 1 0
#> ERR342875 2 0 1 0 1
#> ERR342834 1 0 1 1 0
#> ERR342898 1 0 1 1 0
#> ERR342886 2 0 1 0 1
#> ERR342838 1 0 1 1 0
#> ERR342882 1 0 1 1 0
#> ERR342807 2 0 1 0 1
#> ERR342873 1 0 1 1 0
#> ERR342844 1 0 1 1 0
#> ERR342874 1 0 1 1 0
#> ERR342893 1 0 1 1 0
#> ERR342859 1 0 1 1 0
#> ERR342830 2 0 1 0 1
#> ERR342880 1 0 1 1 0
#> ERR342887 1 0 1 1 0
#> ERR342854 1 0 1 1 0
#> ERR342904 1 0 1 1 0
#> ERR342881 1 0 1 1 0
#> ERR342858 1 0 1 1 0
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0 1 1 0 0
#> ERR342843 1 0 1 1 0 0
#> ERR342896 1 0 1 1 0 0
#> ERR342827 2 0 1 0 1 0
#> ERR342871 1 0 1 1 0 0
#> ERR342863 2 0 1 0 1 0
#> ERR342839 1 0 1 1 0 0
#> ERR342906 1 0 1 1 0 0
#> ERR342905 2 0 1 0 1 0
#> ERR342816 1 0 1 1 0 0
#> ERR342865 2 0 1 0 1 0
#> ERR342824 1 0 1 1 0 0
#> ERR342841 2 0 1 0 1 0
#> ERR342835 1 0 1 1 0 0
#> ERR342899 2 0 1 0 1 0
#> ERR342829 1 0 1 1 0 0
#> ERR342850 1 0 1 1 0 0
#> ERR342849 2 0 1 0 1 0
#> ERR342811 1 0 1 1 0 0
#> ERR342837 1 0 1 1 0 0
#> ERR342857 1 0 1 1 0 0
#> ERR342869 1 0 1 1 0 0
#> ERR342903 1 0 1 1 0 0
#> ERR342819 1 0 1 1 0 0
#> ERR342885 3 0 1 0 0 1
#> ERR342889 2 0 1 0 1 0
#> ERR342864 1 0 1 1 0 0
#> ERR342860 2 0 1 0 1 0
#> ERR342808 1 0 1 1 0 0
#> ERR342823 1 0 1 1 0 0
#> ERR342907 2 0 1 0 1 0
#> ERR342852 1 0 1 1 0 0
#> ERR342832 2 0 1 0 1 0
#> ERR342868 1 0 1 1 0 0
#> ERR342821 1 0 1 1 0 0
#> ERR342878 2 0 1 0 1 0
#> ERR342876 1 0 1 1 0 0
#> ERR342809 1 0 1 1 0 0
#> ERR342846 3 0 1 0 0 1
#> ERR342872 2 0 1 0 1 0
#> ERR342828 2 0 1 0 1 0
#> ERR342840 1 0 1 1 0 0
#> ERR342831 1 0 1 1 0 0
#> ERR342818 1 0 1 1 0 0
#> ERR342862 1 0 1 1 0 0
#> ERR342894 1 0 1 1 0 0
#> ERR342884 2 0 1 0 1 0
#> ERR342891 1 0 1 1 0 0
#> ERR342890 1 0 1 1 0 0
#> ERR342836 2 0 1 0 1 0
#> ERR342879 1 0 1 1 0 0
#> ERR342848 1 0 1 1 0 0
#> ERR342861 1 0 1 1 0 0
#> ERR342814 2 0 1 0 1 0
#> ERR342870 1 0 1 1 0 0
#> ERR342901 1 0 1 1 0 0
#> ERR342908 1 0 1 1 0 0
#> ERR342815 2 0 1 0 1 0
#> ERR342897 3 0 1 0 0 1
#> ERR342833 2 0 1 0 1 0
#> ERR342817 3 0 1 0 0 1
#> ERR342810 2 0 1 0 1 0
#> ERR342867 1 0 1 1 0 0
#> ERR342847 1 0 1 1 0 0
#> ERR342855 1 0 1 1 0 0
#> ERR342851 1 0 1 1 0 0
#> ERR342813 1 0 1 1 0 0
#> ERR342883 1 0 1 1 0 0
#> ERR342856 3 0 1 0 0 1
#> ERR342822 2 0 1 0 1 0
#> ERR342892 1 0 1 1 0 0
#> ERR342842 1 0 1 1 0 0
#> ERR342902 2 0 1 0 1 0
#> ERR342900 2 0 1 0 1 0
#> ERR342888 1 0 1 1 0 0
#> ERR342812 1 0 1 1 0 0
#> ERR342853 2 0 1 0 1 0
#> ERR342866 1 0 1 1 0 0
#> ERR342820 1 0 1 1 0 0
#> ERR342895 1 0 1 1 0 0
#> ERR342825 3 0 1 0 0 1
#> ERR342826 3 0 1 0 0 1
#> ERR342875 2 0 1 0 1 0
#> ERR342834 3 0 1 0 0 1
#> ERR342898 1 0 1 1 0 0
#> ERR342886 2 0 1 0 1 0
#> ERR342838 1 0 1 1 0 0
#> ERR342882 1 0 1 1 0 0
#> ERR342807 2 0 1 0 1 0
#> ERR342873 1 0 1 1 0 0
#> ERR342844 1 0 1 1 0 0
#> ERR342874 1 0 1 1 0 0
#> ERR342893 1 0 1 1 0 0
#> ERR342859 3 0 1 0 0 1
#> ERR342830 2 0 1 0 1 0
#> ERR342880 1 0 1 1 0 0
#> ERR342887 1 0 1 1 0 0
#> ERR342854 1 0 1 1 0 0
#> ERR342904 1 0 1 1 0 0
#> ERR342881 1 0 1 1 0 0
#> ERR342858 1 0 1 1 0 0
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.201 1.000 0.92 0 0 0.08
#> ERR342843 1 0.201 1.000 0.92 0 0 0.08
#> ERR342896 4 0.000 0.986 0.00 0 0 1.00
#> ERR342827 2 0.000 1.000 0.00 1 0 0.00
#> ERR342871 4 0.000 0.986 0.00 0 0 1.00
#> ERR342863 2 0.000 1.000 0.00 1 0 0.00
#> ERR342839 1 0.201 1.000 0.92 0 0 0.08
#> ERR342906 4 0.201 0.923 0.08 0 0 0.92
#> ERR342905 2 0.000 1.000 0.00 1 0 0.00
#> ERR342816 4 0.201 0.923 0.08 0 0 0.92
#> ERR342865 2 0.000 1.000 0.00 1 0 0.00
#> ERR342824 4 0.000 0.986 0.00 0 0 1.00
#> ERR342841 2 0.000 1.000 0.00 1 0 0.00
#> ERR342835 4 0.000 0.986 0.00 0 0 1.00
#> ERR342899 2 0.000 1.000 0.00 1 0 0.00
#> ERR342829 4 0.000 0.986 0.00 0 0 1.00
#> ERR342850 4 0.000 0.986 0.00 0 0 1.00
#> ERR342849 2 0.000 1.000 0.00 1 0 0.00
#> ERR342811 4 0.000 0.986 0.00 0 0 1.00
#> ERR342837 4 0.000 0.986 0.00 0 0 1.00
#> ERR342857 4 0.201 0.923 0.08 0 0 0.92
#> ERR342869 4 0.000 0.986 0.00 0 0 1.00
#> ERR342903 4 0.000 0.986 0.00 0 0 1.00
#> ERR342819 4 0.000 0.986 0.00 0 0 1.00
#> ERR342885 3 0.000 1.000 0.00 0 1 0.00
#> ERR342889 2 0.000 1.000 0.00 1 0 0.00
#> ERR342864 4 0.201 0.923 0.08 0 0 0.92
#> ERR342860 2 0.000 1.000 0.00 1 0 0.00
#> ERR342808 4 0.000 0.986 0.00 0 0 1.00
#> ERR342823 4 0.000 0.986 0.00 0 0 1.00
#> ERR342907 2 0.000 1.000 0.00 1 0 0.00
#> ERR342852 4 0.201 0.923 0.08 0 0 0.92
#> ERR342832 2 0.000 1.000 0.00 1 0 0.00
#> ERR342868 1 0.201 1.000 0.92 0 0 0.08
#> ERR342821 4 0.201 0.923 0.08 0 0 0.92
#> ERR342878 2 0.000 1.000 0.00 1 0 0.00
#> ERR342876 4 0.000 0.986 0.00 0 0 1.00
#> ERR342809 4 0.000 0.986 0.00 0 0 1.00
#> ERR342846 3 0.000 1.000 0.00 0 1 0.00
#> ERR342872 2 0.000 1.000 0.00 1 0 0.00
#> ERR342828 2 0.000 1.000 0.00 1 0 0.00
#> ERR342840 4 0.000 0.986 0.00 0 0 1.00
#> ERR342831 1 0.201 1.000 0.92 0 0 0.08
#> ERR342818 4 0.000 0.986 0.00 0 0 1.00
#> ERR342862 4 0.000 0.986 0.00 0 0 1.00
#> ERR342894 1 0.201 1.000 0.92 0 0 0.08
#> ERR342884 2 0.000 1.000 0.00 1 0 0.00
#> ERR342891 4 0.000 0.986 0.00 0 0 1.00
#> ERR342890 1 0.201 1.000 0.92 0 0 0.08
#> ERR342836 2 0.000 1.000 0.00 1 0 0.00
#> ERR342879 4 0.000 0.986 0.00 0 0 1.00
#> ERR342848 4 0.000 0.986 0.00 0 0 1.00
#> ERR342861 4 0.000 0.986 0.00 0 0 1.00
#> ERR342814 2 0.000 1.000 0.00 1 0 0.00
#> ERR342870 4 0.000 0.986 0.00 0 0 1.00
#> ERR342901 4 0.000 0.986 0.00 0 0 1.00
#> ERR342908 4 0.000 0.986 0.00 0 0 1.00
#> ERR342815 2 0.000 1.000 0.00 1 0 0.00
#> ERR342897 3 0.000 1.000 0.00 0 1 0.00
#> ERR342833 2 0.000 1.000 0.00 1 0 0.00
#> ERR342817 3 0.000 1.000 0.00 0 1 0.00
#> ERR342810 2 0.000 1.000 0.00 1 0 0.00
#> ERR342867 4 0.201 0.923 0.08 0 0 0.92
#> ERR342847 4 0.000 0.986 0.00 0 0 1.00
#> ERR342855 4 0.000 0.986 0.00 0 0 1.00
#> ERR342851 4 0.000 0.986 0.00 0 0 1.00
#> ERR342813 1 0.201 1.000 0.92 0 0 0.08
#> ERR342883 4 0.000 0.986 0.00 0 0 1.00
#> ERR342856 3 0.000 1.000 0.00 0 1 0.00
#> ERR342822 2 0.000 1.000 0.00 1 0 0.00
#> ERR342892 4 0.000 0.986 0.00 0 0 1.00
#> ERR342842 4 0.000 0.986 0.00 0 0 1.00
#> ERR342902 2 0.000 1.000 0.00 1 0 0.00
#> ERR342900 2 0.000 1.000 0.00 1 0 0.00
#> ERR342888 1 0.201 1.000 0.92 0 0 0.08
#> ERR342812 4 0.000 0.986 0.00 0 0 1.00
#> ERR342853 2 0.000 1.000 0.00 1 0 0.00
#> ERR342866 4 0.000 0.986 0.00 0 0 1.00
#> ERR342820 4 0.000 0.986 0.00 0 0 1.00
#> ERR342895 4 0.000 0.986 0.00 0 0 1.00
#> ERR342825 3 0.000 1.000 0.00 0 1 0.00
#> ERR342826 3 0.000 1.000 0.00 0 1 0.00
#> ERR342875 2 0.000 1.000 0.00 1 0 0.00
#> ERR342834 3 0.000 1.000 0.00 0 1 0.00
#> ERR342898 4 0.201 0.923 0.08 0 0 0.92
#> ERR342886 2 0.000 1.000 0.00 1 0 0.00
#> ERR342838 4 0.000 0.986 0.00 0 0 1.00
#> ERR342882 4 0.000 0.986 0.00 0 0 1.00
#> ERR342807 2 0.000 1.000 0.00 1 0 0.00
#> ERR342873 4 0.000 0.986 0.00 0 0 1.00
#> ERR342844 4 0.201 0.923 0.08 0 0 0.92
#> ERR342874 4 0.000 0.986 0.00 0 0 1.00
#> ERR342893 4 0.000 0.986 0.00 0 0 1.00
#> ERR342859 3 0.000 1.000 0.00 0 1 0.00
#> ERR342830 2 0.000 1.000 0.00 1 0 0.00
#> ERR342880 4 0.000 0.986 0.00 0 0 1.00
#> ERR342887 4 0.000 0.986 0.00 0 0 1.00
#> ERR342854 4 0.000 0.986 0.00 0 0 1.00
#> ERR342904 4 0.000 0.986 0.00 0 0 1.00
#> ERR342881 4 0.000 0.986 0.00 0 0 1.00
#> ERR342858 4 0.000 0.986 0.00 0 0 1.00
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342843 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342896 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342827 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342871 1 0.1732 0.925 0.920 0 0 0.080 0
#> ERR342863 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342839 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342906 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342905 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342816 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342865 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342824 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342841 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342835 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342899 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342829 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342850 1 0.1671 0.927 0.924 0 0 0.076 0
#> ERR342849 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342811 1 0.1544 0.930 0.932 0 0 0.068 0
#> ERR342837 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342857 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342869 1 0.1792 0.923 0.916 0 0 0.084 0
#> ERR342903 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342819 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342885 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342889 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342864 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342860 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342808 1 0.1608 0.929 0.928 0 0 0.072 0
#> ERR342823 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342907 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342852 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342832 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342868 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342821 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342878 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342876 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342809 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342846 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342872 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342828 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342840 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342831 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342818 1 0.2852 0.862 0.828 0 0 0.172 0
#> ERR342862 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342894 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342884 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342891 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342890 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342836 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342879 1 0.2852 0.862 0.828 0 0 0.172 0
#> ERR342848 1 0.2852 0.862 0.828 0 0 0.172 0
#> ERR342861 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342814 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342870 1 0.1671 0.927 0.924 0 0 0.076 0
#> ERR342901 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342908 1 0.1544 0.930 0.932 0 0 0.068 0
#> ERR342815 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342897 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342833 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342817 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342810 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342867 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342847 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342855 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342851 1 0.2852 0.862 0.828 0 0 0.172 0
#> ERR342813 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342883 1 0.2852 0.862 0.828 0 0 0.172 0
#> ERR342856 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342822 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342892 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342842 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342902 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342900 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342888 5 0.0000 1.000 0.000 0 0 0.000 1
#> ERR342812 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342853 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342866 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342820 1 0.1671 0.927 0.924 0 0 0.076 0
#> ERR342895 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342825 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342826 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342875 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342834 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342898 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342886 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342838 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342882 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342807 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342873 1 0.2852 0.862 0.828 0 0 0.172 0
#> ERR342844 4 0.0290 1.000 0.008 0 0 0.992 0
#> ERR342874 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342893 1 0.2852 0.862 0.828 0 0 0.172 0
#> ERR342859 3 0.0000 1.000 0.000 0 1 0.000 0
#> ERR342830 2 0.0000 1.000 0.000 1 0 0.000 0
#> ERR342880 1 0.2852 0.862 0.828 0 0 0.172 0
#> ERR342887 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342854 1 0.0000 0.950 1.000 0 0 0.000 0
#> ERR342904 1 0.1732 0.925 0.920 0 0 0.080 0
#> ERR342881 1 0.0162 0.950 0.996 0 0 0.004 0
#> ERR342858 1 0.2852 0.862 0.828 0 0 0.172 0
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342843 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342896 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342827 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342871 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342863 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342839 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342906 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342905 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342816 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342865 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342824 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342841 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342835 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342899 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342829 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342850 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342849 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342811 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342837 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342857 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342869 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342903 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342819 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342885 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342889 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342864 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342860 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342808 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342823 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342907 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342852 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342832 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342868 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342821 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342878 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342876 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342809 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342846 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342872 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342828 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342840 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342831 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342818 6 0.469 0.999 0.176 0 0 0.14 0 0.684
#> ERR342862 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342894 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342884 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342891 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342890 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342836 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342879 6 0.469 0.999 0.176 0 0 0.14 0 0.684
#> ERR342848 6 0.472 0.993 0.180 0 0 0.14 0 0.680
#> ERR342861 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342814 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342870 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342901 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342908 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342815 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342897 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342833 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342817 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342810 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342867 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342847 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342855 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342851 6 0.469 0.999 0.176 0 0 0.14 0 0.684
#> ERR342813 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342883 6 0.469 0.999 0.176 0 0 0.14 0 0.684
#> ERR342856 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342822 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342892 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342842 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342902 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342900 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342888 5 0.000 1.000 0.000 0 0 0.00 1 0.000
#> ERR342812 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342853 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342866 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342820 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342895 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342825 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342826 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342875 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342834 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342898 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342886 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342838 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342882 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342807 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342873 6 0.469 0.999 0.176 0 0 0.14 0 0.684
#> ERR342844 4 0.000 1.000 0.000 0 0 1.00 0 0.000
#> ERR342874 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342893 6 0.469 0.999 0.176 0 0 0.14 0 0.684
#> ERR342859 3 0.000 1.000 0.000 0 1 0.00 0 0.000
#> ERR342830 2 0.000 1.000 0.000 1 0 0.00 0 0.000
#> ERR342880 6 0.469 0.999 0.176 0 0 0.14 0 0.684
#> ERR342887 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342854 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342904 1 0.350 0.687 0.680 0 0 0.00 0 0.320
#> ERR342881 1 0.000 0.907 1.000 0 0 0.00 0 0.000
#> ERR342858 6 0.469 0.999 0.176 0 0 0.14 0 0.684
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "mclust"]
# you can also extract it by
# res = res_list["CV:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 5.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.203 0.759 0.817 0.4527 0.499 0.499
#> 3 3 0.554 0.548 0.700 0.3909 0.636 0.391
#> 4 4 0.702 0.769 0.845 0.0926 0.950 0.849
#> 5 5 0.838 0.872 0.898 0.1161 0.952 0.829
#> 6 6 0.786 0.807 0.823 0.0467 0.882 0.582
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 5
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 2 0.9710 0.281 0.400 0.600
#> ERR342843 2 0.9710 0.281 0.400 0.600
#> ERR342896 1 0.5737 0.778 0.864 0.136
#> ERR342827 2 0.0672 0.865 0.008 0.992
#> ERR342871 1 0.7883 0.759 0.764 0.236
#> ERR342863 2 0.0376 0.865 0.004 0.996
#> ERR342839 2 0.9710 0.281 0.400 0.600
#> ERR342906 1 0.8443 0.774 0.728 0.272
#> ERR342905 2 0.0672 0.865 0.008 0.992
#> ERR342816 1 0.8443 0.774 0.728 0.272
#> ERR342865 2 0.0376 0.865 0.004 0.996
#> ERR342824 1 0.7453 0.794 0.788 0.212
#> ERR342841 2 0.0672 0.865 0.008 0.992
#> ERR342835 1 0.7883 0.790 0.764 0.236
#> ERR342899 2 0.0672 0.865 0.008 0.992
#> ERR342829 1 0.5737 0.778 0.864 0.136
#> ERR342850 1 0.7883 0.759 0.764 0.236
#> ERR342849 2 0.0672 0.865 0.008 0.992
#> ERR342811 1 0.7883 0.759 0.764 0.236
#> ERR342837 1 0.7883 0.790 0.764 0.236
#> ERR342857 1 0.8443 0.774 0.728 0.272
#> ERR342869 1 0.7883 0.759 0.764 0.236
#> ERR342903 1 0.5737 0.778 0.864 0.136
#> ERR342819 1 0.7883 0.790 0.764 0.236
#> ERR342885 2 0.5408 0.811 0.124 0.876
#> ERR342889 2 0.0376 0.865 0.004 0.996
#> ERR342864 1 0.8443 0.774 0.728 0.272
#> ERR342860 2 0.0672 0.865 0.008 0.992
#> ERR342808 1 0.7883 0.759 0.764 0.236
#> ERR342823 1 0.7453 0.794 0.788 0.212
#> ERR342907 2 0.0672 0.865 0.008 0.992
#> ERR342852 1 0.8443 0.774 0.728 0.272
#> ERR342832 2 0.0376 0.865 0.004 0.996
#> ERR342868 2 0.9710 0.281 0.400 0.600
#> ERR342821 1 0.8443 0.774 0.728 0.272
#> ERR342878 2 0.0672 0.865 0.008 0.992
#> ERR342876 1 0.5737 0.778 0.864 0.136
#> ERR342809 1 0.5737 0.778 0.864 0.136
#> ERR342846 2 0.5408 0.811 0.124 0.876
#> ERR342872 2 0.0672 0.865 0.008 0.992
#> ERR342828 2 0.0376 0.865 0.004 0.996
#> ERR342840 1 0.7883 0.790 0.764 0.236
#> ERR342831 2 0.9710 0.281 0.400 0.600
#> ERR342818 1 0.7528 0.770 0.784 0.216
#> ERR342862 1 0.7883 0.790 0.764 0.236
#> ERR342894 2 0.9710 0.281 0.400 0.600
#> ERR342884 2 0.0672 0.865 0.008 0.992
#> ERR342891 1 0.5737 0.778 0.864 0.136
#> ERR342890 2 0.9710 0.281 0.400 0.600
#> ERR342836 2 0.0376 0.865 0.004 0.996
#> ERR342879 1 0.7528 0.770 0.784 0.216
#> ERR342848 1 0.7528 0.770 0.784 0.216
#> ERR342861 1 0.5737 0.778 0.864 0.136
#> ERR342814 2 0.0672 0.865 0.008 0.992
#> ERR342870 1 0.7883 0.759 0.764 0.236
#> ERR342901 1 0.5737 0.778 0.864 0.136
#> ERR342908 1 0.7883 0.759 0.764 0.236
#> ERR342815 2 0.0376 0.865 0.004 0.996
#> ERR342897 2 0.5408 0.811 0.124 0.876
#> ERR342833 2 0.0672 0.865 0.008 0.992
#> ERR342817 2 0.5408 0.811 0.124 0.876
#> ERR342810 2 0.0672 0.865 0.008 0.992
#> ERR342867 1 0.8443 0.774 0.728 0.272
#> ERR342847 1 0.7883 0.790 0.764 0.236
#> ERR342855 1 0.5737 0.778 0.864 0.136
#> ERR342851 1 0.7528 0.770 0.784 0.216
#> ERR342813 2 0.9710 0.281 0.400 0.600
#> ERR342883 1 0.7528 0.770 0.784 0.216
#> ERR342856 2 0.5408 0.811 0.124 0.876
#> ERR342822 2 0.0376 0.865 0.004 0.996
#> ERR342892 1 0.5737 0.778 0.864 0.136
#> ERR342842 1 0.5737 0.778 0.864 0.136
#> ERR342902 2 0.0672 0.865 0.008 0.992
#> ERR342900 2 0.0672 0.865 0.008 0.992
#> ERR342888 2 0.9710 0.281 0.400 0.600
#> ERR342812 1 0.5737 0.778 0.864 0.136
#> ERR342853 2 0.0672 0.865 0.008 0.992
#> ERR342866 1 0.7883 0.790 0.764 0.236
#> ERR342820 1 0.7883 0.759 0.764 0.236
#> ERR342895 1 0.5737 0.778 0.864 0.136
#> ERR342825 2 0.5408 0.811 0.124 0.876
#> ERR342826 2 0.5408 0.811 0.124 0.876
#> ERR342875 2 0.0376 0.865 0.004 0.996
#> ERR342834 2 0.5408 0.811 0.124 0.876
#> ERR342898 1 0.8443 0.774 0.728 0.272
#> ERR342886 2 0.0672 0.865 0.008 0.992
#> ERR342838 1 0.5737 0.778 0.864 0.136
#> ERR342882 1 0.5737 0.778 0.864 0.136
#> ERR342807 2 0.0672 0.865 0.008 0.992
#> ERR342873 1 0.7528 0.770 0.784 0.216
#> ERR342844 1 0.8443 0.774 0.728 0.272
#> ERR342874 1 0.7883 0.790 0.764 0.236
#> ERR342893 1 0.7528 0.770 0.784 0.216
#> ERR342859 2 0.5408 0.811 0.124 0.876
#> ERR342830 2 0.0672 0.865 0.008 0.992
#> ERR342880 1 0.7528 0.770 0.784 0.216
#> ERR342887 1 0.5737 0.778 0.864 0.136
#> ERR342854 1 0.5737 0.778 0.864 0.136
#> ERR342904 1 0.7950 0.755 0.760 0.240
#> ERR342881 1 0.7883 0.790 0.764 0.236
#> ERR342858 1 0.7528 0.770 0.784 0.216
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342843 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342896 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342827 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342871 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342863 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342839 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342906 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342905 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342816 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342865 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342824 3 0.6396 0.507 0.320 0.016 0.664
#> ERR342841 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342835 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342899 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342829 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342850 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342849 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342811 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342837 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342857 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342869 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342903 3 0.6897 0.542 0.292 0.040 0.668
#> ERR342819 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342885 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342889 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342864 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342860 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342808 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342823 3 0.6396 0.507 0.320 0.016 0.664
#> ERR342907 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342852 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342832 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342868 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342821 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342878 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342876 3 0.6897 0.542 0.292 0.040 0.668
#> ERR342809 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342846 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342872 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342828 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342840 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342831 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342818 1 0.6026 0.485 0.732 0.024 0.244
#> ERR342862 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342894 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342884 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342891 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342890 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342836 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342879 1 0.6026 0.485 0.732 0.024 0.244
#> ERR342848 1 0.6026 0.474 0.732 0.024 0.244
#> ERR342861 3 0.6897 0.542 0.292 0.040 0.668
#> ERR342814 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342870 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342901 3 0.6897 0.542 0.292 0.040 0.668
#> ERR342908 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342815 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342897 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342833 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342817 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342810 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342867 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342847 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342855 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342851 1 0.6026 0.485 0.732 0.024 0.244
#> ERR342813 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342883 1 0.6026 0.485 0.732 0.024 0.244
#> ERR342856 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342822 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342892 3 0.6897 0.542 0.292 0.040 0.668
#> ERR342842 3 0.6897 0.542 0.292 0.040 0.668
#> ERR342902 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342900 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342888 1 0.9964 0.148 0.372 0.328 0.300
#> ERR342812 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342853 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342866 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342820 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342895 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342825 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342826 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342875 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342834 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342898 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342886 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342838 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342882 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342807 2 0.0747 0.982 0.016 0.984 0.000
#> ERR342873 1 0.6026 0.485 0.732 0.024 0.244
#> ERR342844 1 0.5874 0.507 0.760 0.032 0.208
#> ERR342874 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342893 1 0.6026 0.485 0.732 0.024 0.244
#> ERR342859 3 0.9975 -0.108 0.312 0.320 0.368
#> ERR342830 2 0.0424 0.992 0.000 0.992 0.008
#> ERR342880 1 0.6026 0.485 0.732 0.024 0.244
#> ERR342887 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342854 3 0.6967 0.543 0.288 0.044 0.668
#> ERR342904 1 0.1399 0.526 0.968 0.028 0.004
#> ERR342881 3 0.7389 0.384 0.408 0.036 0.556
#> ERR342858 1 0.6026 0.485 0.732 0.024 0.244
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342843 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342896 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342827 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342871 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342863 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342839 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342906 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342905 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342816 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342865 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342824 1 0.0817 0.772 0.976 0.000 0.000 0.024
#> ERR342841 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342835 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342899 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342829 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342850 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342849 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342811 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342837 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342857 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342869 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342903 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342819 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342885 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342889 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342864 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342860 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342808 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342823 1 0.0817 0.772 0.976 0.000 0.000 0.024
#> ERR342907 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342852 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342832 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342868 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342821 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342878 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342876 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342872 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342828 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342840 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342831 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342818 4 0.4382 0.722 0.296 0.000 0.000 0.704
#> ERR342862 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342894 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342884 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342891 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342890 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342836 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342879 4 0.4382 0.722 0.296 0.000 0.000 0.704
#> ERR342848 4 0.4382 0.722 0.296 0.000 0.000 0.704
#> ERR342861 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342814 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342870 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342901 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342908 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342815 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342897 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342833 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342817 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342810 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342867 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342847 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342855 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342851 4 0.4382 0.722 0.296 0.000 0.000 0.704
#> ERR342813 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342883 4 0.4382 0.722 0.296 0.000 0.000 0.704
#> ERR342856 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342822 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342892 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342902 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342900 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342888 4 0.6696 0.404 0.104 0.064 0.132 0.700
#> ERR342812 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342853 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342866 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342820 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342895 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342875 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342834 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342898 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342886 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342838 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342807 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342873 4 0.4382 0.722 0.296 0.000 0.000 0.704
#> ERR342844 4 0.4072 0.761 0.252 0.000 0.000 0.748
#> ERR342874 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342893 4 0.4382 0.722 0.296 0.000 0.000 0.704
#> ERR342859 3 0.0000 1.000 0.000 0.000 1.000 0.000
#> ERR342830 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342880 4 0.4382 0.722 0.296 0.000 0.000 0.704
#> ERR342887 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.788 1.000 0.000 0.000 0.000
#> ERR342904 4 0.3942 0.765 0.236 0.000 0.000 0.764
#> ERR342881 1 0.5548 0.207 0.588 0.024 0.000 0.388
#> ERR342858 4 0.4382 0.722 0.296 0.000 0.000 0.704
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342843 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342896 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342827 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342871 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342863 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342839 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342906 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342905 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342816 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342865 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342824 1 0.0703 0.776 0.976 0.000 0 0.024 0.000
#> ERR342841 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342835 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342899 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342829 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342850 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342849 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342811 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342837 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342857 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342869 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342903 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342819 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342885 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342889 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342864 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342860 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342808 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342823 1 0.0703 0.776 0.976 0.000 0 0.024 0.000
#> ERR342907 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342852 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342832 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342868 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342821 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342878 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342876 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342809 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342872 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342828 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342840 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342831 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342818 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
#> ERR342862 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342894 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342884 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342891 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342890 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342836 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342879 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
#> ERR342848 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
#> ERR342861 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342814 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342870 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342901 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342908 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342815 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342897 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342833 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342817 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342810 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342867 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342847 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342855 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342851 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
#> ERR342813 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342883 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
#> ERR342856 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342822 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342892 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342842 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342902 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342900 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342888 5 0.3143 1.000 0.000 0.000 0 0.204 0.796
#> ERR342812 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342853 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342866 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342820 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342895 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342875 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342834 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342898 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342886 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342838 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342882 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342807 2 0.0000 0.991 0.000 1.000 0 0.000 0.000
#> ERR342873 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
#> ERR342844 4 0.2329 0.854 0.000 0.000 0 0.876 0.124
#> ERR342874 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342893 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
#> ERR342859 3 0.0000 1.000 0.000 0.000 1 0.000 0.000
#> ERR342830 2 0.0794 0.983 0.000 0.972 0 0.000 0.028
#> ERR342880 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
#> ERR342887 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342854 1 0.0290 0.784 0.992 0.000 0 0.008 0.000
#> ERR342904 4 0.0404 0.925 0.000 0.000 0 0.988 0.012
#> ERR342881 1 0.6952 0.349 0.388 0.012 0 0.216 0.384
#> ERR342858 4 0.0000 0.929 0.000 0.000 0 1.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342843 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342896 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342827 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342871 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342863 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342839 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342906 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342905 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342816 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342865 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342824 1 0.3508 0.993 0.704 0.000 0 0.004 0.292 0.000
#> ERR342841 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342835 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342899 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342829 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342850 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342849 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342811 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342837 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342857 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342869 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342903 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342819 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342885 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342889 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342864 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342860 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342808 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342823 1 0.3508 0.993 0.704 0.000 0 0.004 0.292 0.000
#> ERR342907 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342852 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342832 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342868 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342821 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342878 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342876 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342809 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342872 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342828 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342840 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342831 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342818 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
#> ERR342862 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342894 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342884 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342891 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342890 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342836 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342879 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
#> ERR342848 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
#> ERR342861 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342814 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342870 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342901 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342908 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342815 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342897 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342833 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342817 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342810 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342867 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342847 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342855 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342851 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
#> ERR342813 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342883 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
#> ERR342856 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342822 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342892 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342842 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342902 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342900 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342888 4 0.7650 0.124 0.292 0.000 0 0.296 0.204 0.208
#> ERR342812 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342853 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342866 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342820 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342895 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342875 2 0.3175 0.747 0.000 0.744 0 0.000 0.000 0.256
#> ERR342834 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342898 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342886 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342838 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342882 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342807 2 0.0000 0.798 0.000 1.000 0 0.000 0.000 0.000
#> ERR342873 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
#> ERR342844 4 0.0458 0.715 0.000 0.000 0 0.984 0.000 0.016
#> ERR342874 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342893 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
#> ERR342859 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342830 6 0.2854 1.000 0.000 0.208 0 0.000 0.000 0.792
#> ERR342880 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
#> ERR342887 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342854 1 0.3371 0.999 0.708 0.000 0 0.000 0.292 0.000
#> ERR342904 4 0.2092 0.727 0.000 0.000 0 0.876 0.124 0.000
#> ERR342881 5 0.0937 1.000 0.000 0.000 0 0.040 0.960 0.000
#> ERR342858 4 0.1957 0.731 0.000 0.000 0 0.888 0.112 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "NMF"]
# you can also extract it by
# res = res_list["CV:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.836 0.932 0.970 0.4269 0.595 0.595
#> 3 3 0.895 0.958 0.957 0.4321 0.804 0.671
#> 4 4 0.841 0.942 0.941 0.2055 0.850 0.625
#> 5 5 0.804 0.822 0.857 0.0583 0.934 0.752
#> 6 6 0.820 0.838 0.801 0.0441 0.984 0.926
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 0.956 1.000 0.000
#> ERR342843 1 0.000 0.956 1.000 0.000
#> ERR342896 1 0.000 0.956 1.000 0.000
#> ERR342827 2 0.000 1.000 0.000 1.000
#> ERR342871 1 0.000 0.956 1.000 0.000
#> ERR342863 2 0.000 1.000 0.000 1.000
#> ERR342839 1 0.000 0.956 1.000 0.000
#> ERR342906 1 0.000 0.956 1.000 0.000
#> ERR342905 2 0.000 1.000 0.000 1.000
#> ERR342816 1 0.000 0.956 1.000 0.000
#> ERR342865 2 0.000 1.000 0.000 1.000
#> ERR342824 1 0.000 0.956 1.000 0.000
#> ERR342841 2 0.000 1.000 0.000 1.000
#> ERR342835 1 0.000 0.956 1.000 0.000
#> ERR342899 2 0.000 1.000 0.000 1.000
#> ERR342829 1 0.000 0.956 1.000 0.000
#> ERR342850 1 0.000 0.956 1.000 0.000
#> ERR342849 2 0.000 1.000 0.000 1.000
#> ERR342811 1 0.000 0.956 1.000 0.000
#> ERR342837 1 0.000 0.956 1.000 0.000
#> ERR342857 1 0.000 0.956 1.000 0.000
#> ERR342869 1 0.000 0.956 1.000 0.000
#> ERR342903 1 0.000 0.956 1.000 0.000
#> ERR342819 1 0.000 0.956 1.000 0.000
#> ERR342885 1 0.921 0.550 0.664 0.336
#> ERR342889 2 0.000 1.000 0.000 1.000
#> ERR342864 1 0.000 0.956 1.000 0.000
#> ERR342860 2 0.000 1.000 0.000 1.000
#> ERR342808 1 0.000 0.956 1.000 0.000
#> ERR342823 1 0.000 0.956 1.000 0.000
#> ERR342907 2 0.000 1.000 0.000 1.000
#> ERR342852 1 0.000 0.956 1.000 0.000
#> ERR342832 2 0.000 1.000 0.000 1.000
#> ERR342868 1 0.000 0.956 1.000 0.000
#> ERR342821 1 0.000 0.956 1.000 0.000
#> ERR342878 2 0.000 1.000 0.000 1.000
#> ERR342876 1 0.000 0.956 1.000 0.000
#> ERR342809 1 0.000 0.956 1.000 0.000
#> ERR342846 1 0.921 0.550 0.664 0.336
#> ERR342872 2 0.000 1.000 0.000 1.000
#> ERR342828 2 0.000 1.000 0.000 1.000
#> ERR342840 1 0.000 0.956 1.000 0.000
#> ERR342831 1 0.000 0.956 1.000 0.000
#> ERR342818 1 0.000 0.956 1.000 0.000
#> ERR342862 1 0.000 0.956 1.000 0.000
#> ERR342894 1 0.000 0.956 1.000 0.000
#> ERR342884 2 0.000 1.000 0.000 1.000
#> ERR342891 1 0.000 0.956 1.000 0.000
#> ERR342890 1 0.000 0.956 1.000 0.000
#> ERR342836 2 0.000 1.000 0.000 1.000
#> ERR342879 1 0.000 0.956 1.000 0.000
#> ERR342848 1 0.000 0.956 1.000 0.000
#> ERR342861 1 0.000 0.956 1.000 0.000
#> ERR342814 2 0.000 1.000 0.000 1.000
#> ERR342870 1 0.000 0.956 1.000 0.000
#> ERR342901 1 0.000 0.956 1.000 0.000
#> ERR342908 1 0.000 0.956 1.000 0.000
#> ERR342815 2 0.000 1.000 0.000 1.000
#> ERR342897 1 0.921 0.550 0.664 0.336
#> ERR342833 2 0.000 1.000 0.000 1.000
#> ERR342817 1 0.921 0.550 0.664 0.336
#> ERR342810 2 0.000 1.000 0.000 1.000
#> ERR342867 1 0.000 0.956 1.000 0.000
#> ERR342847 1 0.000 0.956 1.000 0.000
#> ERR342855 1 0.000 0.956 1.000 0.000
#> ERR342851 1 0.000 0.956 1.000 0.000
#> ERR342813 1 0.000 0.956 1.000 0.000
#> ERR342883 1 0.000 0.956 1.000 0.000
#> ERR342856 1 0.921 0.550 0.664 0.336
#> ERR342822 2 0.000 1.000 0.000 1.000
#> ERR342892 1 0.000 0.956 1.000 0.000
#> ERR342842 1 0.000 0.956 1.000 0.000
#> ERR342902 2 0.000 1.000 0.000 1.000
#> ERR342900 2 0.000 1.000 0.000 1.000
#> ERR342888 1 0.000 0.956 1.000 0.000
#> ERR342812 1 0.000 0.956 1.000 0.000
#> ERR342853 2 0.000 1.000 0.000 1.000
#> ERR342866 1 0.000 0.956 1.000 0.000
#> ERR342820 1 0.000 0.956 1.000 0.000
#> ERR342895 1 0.000 0.956 1.000 0.000
#> ERR342825 1 0.921 0.550 0.664 0.336
#> ERR342826 1 0.921 0.550 0.664 0.336
#> ERR342875 2 0.000 1.000 0.000 1.000
#> ERR342834 1 0.921 0.550 0.664 0.336
#> ERR342898 1 0.000 0.956 1.000 0.000
#> ERR342886 2 0.000 1.000 0.000 1.000
#> ERR342838 1 0.000 0.956 1.000 0.000
#> ERR342882 1 0.000 0.956 1.000 0.000
#> ERR342807 2 0.000 1.000 0.000 1.000
#> ERR342873 1 0.000 0.956 1.000 0.000
#> ERR342844 1 0.000 0.956 1.000 0.000
#> ERR342874 1 0.000 0.956 1.000 0.000
#> ERR342893 1 0.000 0.956 1.000 0.000
#> ERR342859 1 0.921 0.550 0.664 0.336
#> ERR342830 2 0.000 1.000 0.000 1.000
#> ERR342880 1 0.000 0.956 1.000 0.000
#> ERR342887 1 0.000 0.956 1.000 0.000
#> ERR342854 1 0.000 0.956 1.000 0.000
#> ERR342904 1 0.000 0.956 1.000 0.000
#> ERR342881 1 0.000 0.956 1.000 0.000
#> ERR342858 1 0.000 0.956 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 3 0.1163 0.975 0.028 0 0.972
#> ERR342843 3 0.1031 0.975 0.024 0 0.976
#> ERR342896 1 0.1643 0.943 0.956 0 0.044
#> ERR342827 2 0.0000 1.000 0.000 1 0.000
#> ERR342871 1 0.1964 0.937 0.944 0 0.056
#> ERR342863 2 0.0000 1.000 0.000 1 0.000
#> ERR342839 3 0.1163 0.975 0.028 0 0.972
#> ERR342906 1 0.3752 0.874 0.856 0 0.144
#> ERR342905 2 0.0000 1.000 0.000 1 0.000
#> ERR342816 1 0.3686 0.877 0.860 0 0.140
#> ERR342865 2 0.0000 1.000 0.000 1 0.000
#> ERR342824 1 0.1643 0.943 0.956 0 0.044
#> ERR342841 2 0.0000 1.000 0.000 1 0.000
#> ERR342835 1 0.0237 0.948 0.996 0 0.004
#> ERR342899 2 0.0000 1.000 0.000 1 0.000
#> ERR342829 1 0.1643 0.943 0.956 0 0.044
#> ERR342850 1 0.1964 0.937 0.944 0 0.056
#> ERR342849 2 0.0000 1.000 0.000 1 0.000
#> ERR342811 1 0.1964 0.937 0.944 0 0.056
#> ERR342837 1 0.0237 0.948 0.996 0 0.004
#> ERR342857 1 0.4121 0.848 0.832 0 0.168
#> ERR342869 1 0.1964 0.937 0.944 0 0.056
#> ERR342903 1 0.1643 0.943 0.956 0 0.044
#> ERR342819 1 0.0237 0.948 0.996 0 0.004
#> ERR342885 3 0.0747 0.976 0.016 0 0.984
#> ERR342889 2 0.0000 1.000 0.000 1 0.000
#> ERR342864 1 0.3752 0.874 0.856 0 0.144
#> ERR342860 2 0.0000 1.000 0.000 1 0.000
#> ERR342808 1 0.1964 0.937 0.944 0 0.056
#> ERR342823 1 0.1643 0.943 0.956 0 0.044
#> ERR342907 2 0.0000 1.000 0.000 1 0.000
#> ERR342852 1 0.3816 0.870 0.852 0 0.148
#> ERR342832 2 0.0000 1.000 0.000 1 0.000
#> ERR342868 3 0.1163 0.975 0.028 0 0.972
#> ERR342821 1 0.3686 0.877 0.860 0 0.140
#> ERR342878 2 0.0000 1.000 0.000 1 0.000
#> ERR342876 1 0.1643 0.943 0.956 0 0.044
#> ERR342809 1 0.1643 0.943 0.956 0 0.044
#> ERR342846 3 0.0747 0.976 0.016 0 0.984
#> ERR342872 2 0.0000 1.000 0.000 1 0.000
#> ERR342828 2 0.0000 1.000 0.000 1 0.000
#> ERR342840 1 0.0237 0.948 0.996 0 0.004
#> ERR342831 3 0.1163 0.975 0.028 0 0.972
#> ERR342818 1 0.0892 0.946 0.980 0 0.020
#> ERR342862 1 0.0237 0.948 0.996 0 0.004
#> ERR342894 3 0.1163 0.975 0.028 0 0.972
#> ERR342884 2 0.0000 1.000 0.000 1 0.000
#> ERR342891 1 0.1643 0.943 0.956 0 0.044
#> ERR342890 3 0.1163 0.975 0.028 0 0.972
#> ERR342836 2 0.0000 1.000 0.000 1 0.000
#> ERR342879 1 0.0892 0.946 0.980 0 0.020
#> ERR342848 1 0.0892 0.946 0.980 0 0.020
#> ERR342861 1 0.1643 0.943 0.956 0 0.044
#> ERR342814 2 0.0000 1.000 0.000 1 0.000
#> ERR342870 1 0.1964 0.937 0.944 0 0.056
#> ERR342901 1 0.1643 0.943 0.956 0 0.044
#> ERR342908 1 0.1964 0.937 0.944 0 0.056
#> ERR342815 2 0.0000 1.000 0.000 1 0.000
#> ERR342897 3 0.0747 0.976 0.016 0 0.984
#> ERR342833 2 0.0000 1.000 0.000 1 0.000
#> ERR342817 3 0.0747 0.976 0.016 0 0.984
#> ERR342810 2 0.0000 1.000 0.000 1 0.000
#> ERR342867 1 0.3752 0.874 0.856 0 0.144
#> ERR342847 1 0.0237 0.948 0.996 0 0.004
#> ERR342855 1 0.1643 0.943 0.956 0 0.044
#> ERR342851 1 0.0892 0.946 0.980 0 0.020
#> ERR342813 3 0.0892 0.974 0.020 0 0.980
#> ERR342883 1 0.0892 0.946 0.980 0 0.020
#> ERR342856 3 0.0747 0.976 0.016 0 0.984
#> ERR342822 2 0.0000 1.000 0.000 1 0.000
#> ERR342892 1 0.1643 0.943 0.956 0 0.044
#> ERR342842 1 0.1643 0.943 0.956 0 0.044
#> ERR342902 2 0.0000 1.000 0.000 1 0.000
#> ERR342900 2 0.0000 1.000 0.000 1 0.000
#> ERR342888 3 0.1163 0.975 0.028 0 0.972
#> ERR342812 1 0.1643 0.943 0.956 0 0.044
#> ERR342853 2 0.0000 1.000 0.000 1 0.000
#> ERR342866 1 0.0237 0.948 0.996 0 0.004
#> ERR342820 1 0.1964 0.937 0.944 0 0.056
#> ERR342895 1 0.1643 0.943 0.956 0 0.044
#> ERR342825 3 0.0747 0.976 0.016 0 0.984
#> ERR342826 3 0.0747 0.976 0.016 0 0.984
#> ERR342875 2 0.0000 1.000 0.000 1 0.000
#> ERR342834 3 0.0747 0.976 0.016 0 0.984
#> ERR342898 1 0.3752 0.874 0.856 0 0.144
#> ERR342886 2 0.0000 1.000 0.000 1 0.000
#> ERR342838 1 0.1643 0.943 0.956 0 0.044
#> ERR342882 1 0.1643 0.943 0.956 0 0.044
#> ERR342807 2 0.0000 1.000 0.000 1 0.000
#> ERR342873 1 0.0892 0.946 0.980 0 0.020
#> ERR342844 1 0.3879 0.866 0.848 0 0.152
#> ERR342874 1 0.0237 0.948 0.996 0 0.004
#> ERR342893 1 0.0892 0.946 0.980 0 0.020
#> ERR342859 3 0.0747 0.976 0.016 0 0.984
#> ERR342830 2 0.0000 1.000 0.000 1 0.000
#> ERR342880 1 0.0892 0.946 0.980 0 0.020
#> ERR342887 1 0.1643 0.943 0.956 0 0.044
#> ERR342854 1 0.1643 0.943 0.956 0 0.044
#> ERR342904 1 0.1964 0.937 0.944 0 0.056
#> ERR342881 1 0.0237 0.948 0.996 0 0.004
#> ERR342858 1 0.0892 0.946 0.980 0 0.020
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 3 0.5464 0.832 0.072 0.000 0.716 0.212
#> ERR342843 3 0.5397 0.833 0.068 0.000 0.720 0.212
#> ERR342896 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342827 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342871 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342863 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342839 3 0.5464 0.832 0.072 0.000 0.716 0.212
#> ERR342906 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342905 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342816 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342865 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342824 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342841 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342835 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342899 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342829 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342850 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342849 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342811 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342837 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342857 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342869 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342903 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342819 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342885 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342889 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342864 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342860 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342808 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342823 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342907 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342852 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342832 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342868 3 0.5397 0.833 0.068 0.000 0.720 0.212
#> ERR342821 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342878 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342876 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342809 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342846 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342872 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342828 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342840 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342831 3 0.5464 0.832 0.072 0.000 0.716 0.212
#> ERR342818 4 0.1637 0.964 0.060 0.000 0.000 0.940
#> ERR342862 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342894 3 0.5397 0.833 0.068 0.000 0.720 0.212
#> ERR342884 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342891 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342890 3 0.5464 0.832 0.072 0.000 0.716 0.212
#> ERR342836 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342879 4 0.1637 0.964 0.060 0.000 0.000 0.940
#> ERR342848 4 0.1637 0.964 0.060 0.000 0.000 0.940
#> ERR342861 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342814 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342870 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342901 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342908 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342815 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342897 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342833 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342817 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342810 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342867 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342847 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342855 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342851 4 0.1637 0.964 0.060 0.000 0.000 0.940
#> ERR342813 3 0.5397 0.833 0.068 0.000 0.720 0.212
#> ERR342883 4 0.1637 0.964 0.060 0.000 0.000 0.940
#> ERR342856 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342822 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342892 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342842 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342902 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342900 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342888 3 0.5397 0.833 0.068 0.000 0.720 0.212
#> ERR342812 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342853 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342866 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342820 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342895 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342825 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342826 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342875 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342834 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342898 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342886 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342838 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342882 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342807 2 0.1398 0.974 0.000 0.956 0.004 0.040
#> ERR342873 4 0.1637 0.964 0.060 0.000 0.000 0.940
#> ERR342844 4 0.0657 0.942 0.000 0.012 0.004 0.984
#> ERR342874 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342893 4 0.1637 0.964 0.060 0.000 0.000 0.940
#> ERR342859 3 0.0524 0.859 0.008 0.000 0.988 0.004
#> ERR342830 2 0.0000 0.988 0.000 1.000 0.000 0.000
#> ERR342880 4 0.1637 0.964 0.060 0.000 0.000 0.940
#> ERR342887 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342854 1 0.1637 0.963 0.940 0.000 0.000 0.060
#> ERR342904 4 0.1978 0.962 0.068 0.000 0.004 0.928
#> ERR342881 1 0.1576 0.919 0.948 0.000 0.004 0.048
#> ERR342858 4 0.1637 0.964 0.060 0.000 0.000 0.940
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342843 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342871 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342863 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342839 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342906 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342905 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342816 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342865 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342835 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342899 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342849 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342811 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342837 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342857 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342869 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342885 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342889 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342864 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342860 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342808 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342852 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342832 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342868 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342821 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342878 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342872 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342828 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342840 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342831 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342818 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
#> ERR342862 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342894 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342884 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342836 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342879 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
#> ERR342848 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342870 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342815 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342897 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342833 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342817 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342810 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342867 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342847 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
#> ERR342813 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342883 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
#> ERR342856 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342822 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342900 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342888 5 0.6495 0.501 0.036 0.000 0.196 0.168 0.600
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342866 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342820 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342826 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342875 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342834 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342898 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342886 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.3475 0.868 0.000 0.804 0.004 0.012 0.180
#> ERR342873 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
#> ERR342844 4 0.2280 0.797 0.000 0.000 0.000 0.880 0.120
#> ERR342874 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342893 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
#> ERR342859 3 0.0162 1.000 0.004 0.000 0.996 0.000 0.000
#> ERR342830 2 0.0000 0.941 0.000 1.000 0.000 0.000 0.000
#> ERR342880 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.3278 0.781 0.020 0.000 0.000 0.824 0.156
#> ERR342881 5 0.5601 0.406 0.448 0.000 0.000 0.072 0.480
#> ERR342858 4 0.2930 0.775 0.004 0.000 0.000 0.832 0.164
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.2415 0.995 0.024 0.000 0.036 0.040 0.900 0.000
#> ERR342843 5 0.2403 0.996 0.020 0.000 0.040 0.040 0.900 0.000
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342871 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342863 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342839 5 0.2415 0.995 0.024 0.000 0.036 0.040 0.900 0.000
#> ERR342906 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342905 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342816 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342865 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342835 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342899 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342849 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342811 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342837 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342857 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342869 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342819 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342885 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342889 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342864 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342860 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342808 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342852 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342832 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342868 5 0.2403 0.996 0.020 0.000 0.040 0.040 0.900 0.000
#> ERR342821 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342878 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342872 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342828 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342840 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342831 5 0.2415 0.995 0.024 0.000 0.036 0.040 0.900 0.000
#> ERR342818 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
#> ERR342862 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342894 5 0.2403 0.996 0.020 0.000 0.040 0.040 0.900 0.000
#> ERR342884 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.2415 0.995 0.024 0.000 0.036 0.040 0.900 0.000
#> ERR342836 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342879 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
#> ERR342848 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342870 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342815 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342897 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342833 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342817 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342810 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342867 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342847 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
#> ERR342813 5 0.2403 0.996 0.020 0.000 0.040 0.040 0.900 0.000
#> ERR342883 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
#> ERR342856 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342822 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342900 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342888 5 0.2403 0.996 0.020 0.000 0.040 0.040 0.900 0.000
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342866 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342820 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342826 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342875 2 0.0146 0.890 0.000 0.996 0.000 0.000 0.004 0.000
#> ERR342834 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342898 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342886 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.4617 0.747 0.000 0.652 0.000 0.004 0.060 0.284
#> ERR342873 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
#> ERR342844 4 0.5029 0.588 0.000 0.000 0.004 0.656 0.172 0.168
#> ERR342874 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342893 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
#> ERR342859 3 0.0146 1.000 0.004 0.000 0.996 0.000 0.000 0.000
#> ERR342830 2 0.0000 0.890 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342880 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.2926 0.586 0.004 0.000 0.000 0.844 0.124 0.028
#> ERR342881 6 0.6239 1.000 0.152 0.000 0.000 0.036 0.316 0.496
#> ERR342858 4 0.4509 0.493 0.000 0.000 0.000 0.532 0.032 0.436
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "hclust"]
# you can also extract it by
# res = res_list["MAD:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.674 0.929 0.956 0.442 0.531 0.531
#> 3 3 0.642 0.921 0.957 0.194 0.950 0.906
#> 4 4 0.561 0.764 0.847 0.293 0.836 0.659
#> 5 5 0.613 0.672 0.791 0.064 0.868 0.670
#> 6 6 0.834 0.828 0.917 0.107 0.868 0.622
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 0.991 1.000 0.000
#> ERR342843 1 0.000 0.991 1.000 0.000
#> ERR342896 1 0.000 0.991 1.000 0.000
#> ERR342827 2 0.000 0.882 0.000 1.000
#> ERR342871 1 0.184 0.976 0.972 0.028
#> ERR342863 2 0.000 0.882 0.000 1.000
#> ERR342839 1 0.000 0.991 1.000 0.000
#> ERR342906 1 0.184 0.976 0.972 0.028
#> ERR342905 2 0.584 0.846 0.140 0.860
#> ERR342816 1 0.184 0.976 0.972 0.028
#> ERR342865 2 0.000 0.882 0.000 1.000
#> ERR342824 1 0.000 0.991 1.000 0.000
#> ERR342841 2 0.000 0.882 0.000 1.000
#> ERR342835 1 0.000 0.991 1.000 0.000
#> ERR342899 2 0.584 0.846 0.140 0.860
#> ERR342829 1 0.000 0.991 1.000 0.000
#> ERR342850 1 0.184 0.976 0.972 0.028
#> ERR342849 2 0.584 0.846 0.140 0.860
#> ERR342811 1 0.184 0.976 0.972 0.028
#> ERR342837 1 0.000 0.991 1.000 0.000
#> ERR342857 1 0.184 0.976 0.972 0.028
#> ERR342869 1 0.184 0.976 0.972 0.028
#> ERR342903 1 0.000 0.991 1.000 0.000
#> ERR342819 1 0.000 0.991 1.000 0.000
#> ERR342885 2 0.855 0.704 0.280 0.720
#> ERR342889 2 0.000 0.882 0.000 1.000
#> ERR342864 1 0.184 0.976 0.972 0.028
#> ERR342860 2 0.584 0.846 0.140 0.860
#> ERR342808 1 0.184 0.976 0.972 0.028
#> ERR342823 1 0.000 0.991 1.000 0.000
#> ERR342907 2 0.000 0.882 0.000 1.000
#> ERR342852 1 0.184 0.976 0.972 0.028
#> ERR342832 2 0.000 0.882 0.000 1.000
#> ERR342868 1 0.000 0.991 1.000 0.000
#> ERR342821 1 0.184 0.976 0.972 0.028
#> ERR342878 2 0.000 0.882 0.000 1.000
#> ERR342876 1 0.000 0.991 1.000 0.000
#> ERR342809 1 0.000 0.991 1.000 0.000
#> ERR342846 2 0.855 0.704 0.280 0.720
#> ERR342872 2 0.000 0.882 0.000 1.000
#> ERR342828 2 0.000 0.882 0.000 1.000
#> ERR342840 1 0.000 0.991 1.000 0.000
#> ERR342831 1 0.000 0.991 1.000 0.000
#> ERR342818 1 0.000 0.991 1.000 0.000
#> ERR342862 1 0.000 0.991 1.000 0.000
#> ERR342894 1 0.000 0.991 1.000 0.000
#> ERR342884 2 0.000 0.882 0.000 1.000
#> ERR342891 1 0.000 0.991 1.000 0.000
#> ERR342890 1 0.000 0.991 1.000 0.000
#> ERR342836 2 0.000 0.882 0.000 1.000
#> ERR342879 1 0.000 0.991 1.000 0.000
#> ERR342848 1 0.000 0.991 1.000 0.000
#> ERR342861 1 0.000 0.991 1.000 0.000
#> ERR342814 2 0.584 0.846 0.140 0.860
#> ERR342870 1 0.184 0.976 0.972 0.028
#> ERR342901 1 0.000 0.991 1.000 0.000
#> ERR342908 1 0.184 0.976 0.972 0.028
#> ERR342815 2 0.000 0.882 0.000 1.000
#> ERR342897 2 0.855 0.704 0.280 0.720
#> ERR342833 2 0.000 0.882 0.000 1.000
#> ERR342817 2 0.855 0.704 0.280 0.720
#> ERR342810 2 0.584 0.846 0.140 0.860
#> ERR342867 1 0.184 0.976 0.972 0.028
#> ERR342847 1 0.000 0.991 1.000 0.000
#> ERR342855 1 0.000 0.991 1.000 0.000
#> ERR342851 1 0.000 0.991 1.000 0.000
#> ERR342813 1 0.000 0.991 1.000 0.000
#> ERR342883 1 0.000 0.991 1.000 0.000
#> ERR342856 2 0.855 0.704 0.280 0.720
#> ERR342822 2 0.000 0.882 0.000 1.000
#> ERR342892 1 0.000 0.991 1.000 0.000
#> ERR342842 1 0.000 0.991 1.000 0.000
#> ERR342902 2 0.000 0.882 0.000 1.000
#> ERR342900 2 0.584 0.846 0.140 0.860
#> ERR342888 1 0.000 0.991 1.000 0.000
#> ERR342812 1 0.000 0.991 1.000 0.000
#> ERR342853 2 0.584 0.846 0.140 0.860
#> ERR342866 1 0.000 0.991 1.000 0.000
#> ERR342820 1 0.184 0.976 0.972 0.028
#> ERR342895 1 0.000 0.991 1.000 0.000
#> ERR342825 2 0.855 0.704 0.280 0.720
#> ERR342826 2 0.855 0.704 0.280 0.720
#> ERR342875 2 0.000 0.882 0.000 1.000
#> ERR342834 2 0.855 0.704 0.280 0.720
#> ERR342898 1 0.184 0.976 0.972 0.028
#> ERR342886 2 0.584 0.846 0.140 0.860
#> ERR342838 1 0.000 0.991 1.000 0.000
#> ERR342882 1 0.000 0.991 1.000 0.000
#> ERR342807 2 0.000 0.882 0.000 1.000
#> ERR342873 1 0.000 0.991 1.000 0.000
#> ERR342844 1 0.184 0.976 0.972 0.028
#> ERR342874 1 0.000 0.991 1.000 0.000
#> ERR342893 1 0.000 0.991 1.000 0.000
#> ERR342859 2 0.855 0.704 0.280 0.720
#> ERR342830 2 0.584 0.846 0.140 0.860
#> ERR342880 1 0.000 0.991 1.000 0.000
#> ERR342887 1 0.000 0.991 1.000 0.000
#> ERR342854 1 0.000 0.991 1.000 0.000
#> ERR342904 1 0.184 0.976 0.972 0.028
#> ERR342881 1 0.000 0.991 1.000 0.000
#> ERR342858 1 0.000 0.991 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.000 0.950 1.000 0.00 0.000
#> ERR342843 1 0.000 0.950 1.000 0.00 0.000
#> ERR342896 1 0.000 0.950 1.000 0.00 0.000
#> ERR342827 2 0.000 0.916 0.000 1.00 0.000
#> ERR342871 1 0.406 0.857 0.836 0.00 0.164
#> ERR342863 2 0.000 0.916 0.000 1.00 0.000
#> ERR342839 1 0.000 0.950 1.000 0.00 0.000
#> ERR342906 1 0.406 0.857 0.836 0.00 0.164
#> ERR342905 2 0.369 0.846 0.140 0.86 0.000
#> ERR342816 1 0.406 0.857 0.836 0.00 0.164
#> ERR342865 2 0.000 0.916 0.000 1.00 0.000
#> ERR342824 1 0.000 0.950 1.000 0.00 0.000
#> ERR342841 2 0.000 0.916 0.000 1.00 0.000
#> ERR342835 1 0.000 0.950 1.000 0.00 0.000
#> ERR342899 2 0.369 0.846 0.140 0.86 0.000
#> ERR342829 1 0.000 0.950 1.000 0.00 0.000
#> ERR342850 1 0.406 0.857 0.836 0.00 0.164
#> ERR342849 2 0.369 0.846 0.140 0.86 0.000
#> ERR342811 1 0.406 0.857 0.836 0.00 0.164
#> ERR342837 1 0.000 0.950 1.000 0.00 0.000
#> ERR342857 1 0.406 0.857 0.836 0.00 0.164
#> ERR342869 1 0.406 0.857 0.836 0.00 0.164
#> ERR342903 1 0.000 0.950 1.000 0.00 0.000
#> ERR342819 1 0.000 0.950 1.000 0.00 0.000
#> ERR342885 3 0.000 1.000 0.000 0.00 1.000
#> ERR342889 2 0.000 0.916 0.000 1.00 0.000
#> ERR342864 1 0.406 0.857 0.836 0.00 0.164
#> ERR342860 2 0.369 0.846 0.140 0.86 0.000
#> ERR342808 1 0.406 0.857 0.836 0.00 0.164
#> ERR342823 1 0.000 0.950 1.000 0.00 0.000
#> ERR342907 2 0.000 0.916 0.000 1.00 0.000
#> ERR342852 1 0.406 0.857 0.836 0.00 0.164
#> ERR342832 2 0.000 0.916 0.000 1.00 0.000
#> ERR342868 1 0.000 0.950 1.000 0.00 0.000
#> ERR342821 1 0.406 0.857 0.836 0.00 0.164
#> ERR342878 2 0.000 0.916 0.000 1.00 0.000
#> ERR342876 1 0.000 0.950 1.000 0.00 0.000
#> ERR342809 1 0.000 0.950 1.000 0.00 0.000
#> ERR342846 3 0.000 1.000 0.000 0.00 1.000
#> ERR342872 2 0.000 0.916 0.000 1.00 0.000
#> ERR342828 2 0.000 0.916 0.000 1.00 0.000
#> ERR342840 1 0.000 0.950 1.000 0.00 0.000
#> ERR342831 1 0.000 0.950 1.000 0.00 0.000
#> ERR342818 1 0.000 0.950 1.000 0.00 0.000
#> ERR342862 1 0.000 0.950 1.000 0.00 0.000
#> ERR342894 1 0.000 0.950 1.000 0.00 0.000
#> ERR342884 2 0.000 0.916 0.000 1.00 0.000
#> ERR342891 1 0.000 0.950 1.000 0.00 0.000
#> ERR342890 1 0.000 0.950 1.000 0.00 0.000
#> ERR342836 2 0.000 0.916 0.000 1.00 0.000
#> ERR342879 1 0.000 0.950 1.000 0.00 0.000
#> ERR342848 1 0.000 0.950 1.000 0.00 0.000
#> ERR342861 1 0.000 0.950 1.000 0.00 0.000
#> ERR342814 2 0.369 0.846 0.140 0.86 0.000
#> ERR342870 1 0.406 0.857 0.836 0.00 0.164
#> ERR342901 1 0.000 0.950 1.000 0.00 0.000
#> ERR342908 1 0.406 0.857 0.836 0.00 0.164
#> ERR342815 2 0.000 0.916 0.000 1.00 0.000
#> ERR342897 3 0.000 1.000 0.000 0.00 1.000
#> ERR342833 2 0.000 0.916 0.000 1.00 0.000
#> ERR342817 3 0.000 1.000 0.000 0.00 1.000
#> ERR342810 2 0.369 0.846 0.140 0.86 0.000
#> ERR342867 1 0.406 0.857 0.836 0.00 0.164
#> ERR342847 1 0.000 0.950 1.000 0.00 0.000
#> ERR342855 1 0.000 0.950 1.000 0.00 0.000
#> ERR342851 1 0.000 0.950 1.000 0.00 0.000
#> ERR342813 1 0.000 0.950 1.000 0.00 0.000
#> ERR342883 1 0.000 0.950 1.000 0.00 0.000
#> ERR342856 3 0.000 1.000 0.000 0.00 1.000
#> ERR342822 2 0.000 0.916 0.000 1.00 0.000
#> ERR342892 1 0.000 0.950 1.000 0.00 0.000
#> ERR342842 1 0.000 0.950 1.000 0.00 0.000
#> ERR342902 2 0.000 0.916 0.000 1.00 0.000
#> ERR342900 2 0.369 0.846 0.140 0.86 0.000
#> ERR342888 1 0.000 0.950 1.000 0.00 0.000
#> ERR342812 1 0.000 0.950 1.000 0.00 0.000
#> ERR342853 2 0.369 0.846 0.140 0.86 0.000
#> ERR342866 1 0.000 0.950 1.000 0.00 0.000
#> ERR342820 1 0.406 0.857 0.836 0.00 0.164
#> ERR342895 1 0.000 0.950 1.000 0.00 0.000
#> ERR342825 3 0.000 1.000 0.000 0.00 1.000
#> ERR342826 3 0.000 1.000 0.000 0.00 1.000
#> ERR342875 2 0.000 0.916 0.000 1.00 0.000
#> ERR342834 3 0.000 1.000 0.000 0.00 1.000
#> ERR342898 1 0.406 0.857 0.836 0.00 0.164
#> ERR342886 2 0.369 0.846 0.140 0.86 0.000
#> ERR342838 1 0.000 0.950 1.000 0.00 0.000
#> ERR342882 1 0.000 0.950 1.000 0.00 0.000
#> ERR342807 2 0.000 0.916 0.000 1.00 0.000
#> ERR342873 1 0.000 0.950 1.000 0.00 0.000
#> ERR342844 1 0.406 0.857 0.836 0.00 0.164
#> ERR342874 1 0.000 0.950 1.000 0.00 0.000
#> ERR342893 1 0.000 0.950 1.000 0.00 0.000
#> ERR342859 3 0.000 1.000 0.000 0.00 1.000
#> ERR342830 2 0.369 0.846 0.140 0.86 0.000
#> ERR342880 1 0.000 0.950 1.000 0.00 0.000
#> ERR342887 1 0.000 0.950 1.000 0.00 0.000
#> ERR342854 1 0.000 0.950 1.000 0.00 0.000
#> ERR342904 1 0.406 0.857 0.836 0.00 0.164
#> ERR342881 1 0.000 0.950 1.000 0.00 0.000
#> ERR342858 1 0.000 0.950 1.000 0.00 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342843 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342896 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342827 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342871 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342863 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342839 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342906 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342905 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342816 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342865 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342824 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342841 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342835 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342899 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342829 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342850 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342849 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342811 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342837 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342857 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342869 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342903 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342819 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342885 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342889 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342864 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342860 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342808 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342823 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342907 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342852 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342832 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342868 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342821 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342878 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342876 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342809 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342846 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342872 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342828 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342840 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342831 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342818 4 0.000 0.685 0.000 0.000 0.000 1.000
#> ERR342862 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342894 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342884 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342891 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342890 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342836 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342879 4 0.000 0.685 0.000 0.000 0.000 1.000
#> ERR342848 4 0.000 0.685 0.000 0.000 0.000 1.000
#> ERR342861 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342814 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342870 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342901 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342908 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342815 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342897 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342833 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342817 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342810 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342867 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342847 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342855 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342851 4 0.000 0.685 0.000 0.000 0.000 1.000
#> ERR342813 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342883 4 0.000 0.685 0.000 0.000 0.000 1.000
#> ERR342856 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342822 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342892 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342842 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342902 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342900 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342888 1 0.147 0.823 0.948 0.000 0.000 0.052
#> ERR342812 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342853 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342866 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342820 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342895 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342825 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342826 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342875 2 0.000 0.918 0.000 1.000 0.000 0.000
#> ERR342834 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342898 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342886 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342838 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342882 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342807 2 0.130 0.912 0.044 0.956 0.000 0.000
#> ERR342873 4 0.000 0.685 0.000 0.000 0.000 1.000
#> ERR342844 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342874 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342893 4 0.000 0.685 0.000 0.000 0.000 1.000
#> ERR342859 3 0.000 1.000 0.000 0.000 1.000 0.000
#> ERR342830 2 0.343 0.869 0.112 0.860 0.000 0.028
#> ERR342880 4 0.000 0.685 0.000 0.000 0.000 1.000
#> ERR342887 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342854 4 0.430 0.541 0.284 0.000 0.000 0.716
#> ERR342904 4 0.454 0.671 0.048 0.000 0.164 0.788
#> ERR342881 1 0.425 0.783 0.724 0.000 0.000 0.276
#> ERR342858 4 0.000 0.685 0.000 0.000 0.000 1.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342843 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342896 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342827 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342871 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342863 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342839 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342906 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342905 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342816 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342865 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342824 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342841 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342835 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342899 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342829 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342850 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342849 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342811 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342837 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342857 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342869 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342903 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342819 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342885 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342889 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342864 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342860 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342808 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342823 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342907 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342852 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342832 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342868 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342821 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342878 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342876 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342809 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342846 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342872 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342828 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342840 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342831 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342818 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
#> ERR342862 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342894 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342884 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342891 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342890 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342836 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342879 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
#> ERR342848 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
#> ERR342861 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342814 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342870 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342901 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342908 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342815 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342897 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342833 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342817 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342810 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342867 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342847 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342855 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342851 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
#> ERR342813 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342883 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
#> ERR342856 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342822 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342892 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342842 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342902 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342900 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342888 5 0.530 1.000 0.000 0.120 0.00 0.212 0.668
#> ERR342812 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342853 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342866 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342820 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342895 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342825 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342826 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342875 2 0.260 0.875 0.148 0.852 0.00 0.000 0.000
#> ERR342834 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342898 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342886 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342838 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342882 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342807 1 0.000 1.000 1.000 0.000 0.00 0.000 0.000
#> ERR342873 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
#> ERR342844 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342874 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342893 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
#> ERR342859 3 0.000 1.000 0.000 0.000 1.00 0.000 0.000
#> ERR342830 2 0.228 0.896 0.000 0.880 0.00 0.120 0.000
#> ERR342880 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
#> ERR342887 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342854 4 0.000 0.585 0.000 0.000 0.00 1.000 0.000
#> ERR342904 4 0.630 0.573 0.000 0.000 0.16 0.480 0.360
#> ERR342881 4 0.427 -0.354 0.000 0.000 0.00 0.552 0.448
#> ERR342858 4 0.397 0.637 0.000 0.004 0.00 0.692 0.304
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342843 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342896 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342827 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342871 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342863 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342839 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342906 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342905 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342816 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342865 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342824 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342841 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342835 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342899 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342829 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342850 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342849 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342811 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342837 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342857 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342869 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342903 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342819 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342885 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342889 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342864 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342860 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342808 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342823 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342907 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342852 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342832 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342868 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342821 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342878 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342876 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342809 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342846 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342872 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342828 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342840 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342831 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342818 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
#> ERR342862 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342894 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342884 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342891 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342890 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342836 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342879 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
#> ERR342848 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
#> ERR342861 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342814 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342870 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342901 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342908 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342815 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342897 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342833 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342817 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342810 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342867 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342847 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342855 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342851 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
#> ERR342813 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342883 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
#> ERR342856 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342822 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342892 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342842 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342902 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342900 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342888 5 0.000 1.000 0.000 0.000 0 0.00 1.000 0.000
#> ERR342812 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342853 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342866 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342820 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342895 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342825 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342826 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342875 2 0.234 0.903 0.000 0.852 0 0.00 0.000 0.148
#> ERR342834 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342898 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342886 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342838 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342882 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342807 6 0.000 1.000 0.000 0.000 0 0.00 0.000 1.000
#> ERR342873 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
#> ERR342844 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342874 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342893 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
#> ERR342859 3 0.000 1.000 0.000 0.000 1 0.00 0.000 0.000
#> ERR342830 2 0.000 0.919 0.000 1.000 0 0.00 0.000 0.000
#> ERR342880 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
#> ERR342887 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342854 1 0.000 0.758 1.000 0.000 0 0.00 0.000 0.000
#> ERR342904 4 0.000 1.000 0.000 0.000 0 1.00 0.000 0.000
#> ERR342881 1 0.384 0.253 0.552 0.000 0 0.00 0.448 0.000
#> ERR342858 1 0.392 0.513 0.664 0.016 0 0.32 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "kmeans"]
# you can also extract it by
# res = res_list["MAD:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.116 0.664 0.795 0.4105 0.604 0.604
#> 3 3 0.200 0.511 0.611 0.3929 0.806 0.696
#> 4 4 0.266 0.552 0.653 0.1870 0.754 0.535
#> 5 5 0.467 0.554 0.612 0.0887 0.886 0.656
#> 6 6 0.645 0.617 0.590 0.0598 0.872 0.510
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.795 0.681 0.760 0.240
#> ERR342843 1 0.795 0.681 0.760 0.240
#> ERR342896 1 0.163 0.747 0.976 0.024
#> ERR342827 2 0.714 0.803 0.196 0.804
#> ERR342871 1 0.722 0.673 0.800 0.200
#> ERR342863 2 0.662 0.800 0.172 0.828
#> ERR342839 1 0.795 0.681 0.760 0.240
#> ERR342906 1 0.881 0.563 0.700 0.300
#> ERR342905 1 0.993 0.288 0.548 0.452
#> ERR342816 1 0.881 0.563 0.700 0.300
#> ERR342865 2 0.662 0.800 0.172 0.828
#> ERR342824 1 0.163 0.747 0.976 0.024
#> ERR342841 2 0.714 0.803 0.196 0.804
#> ERR342835 1 0.529 0.739 0.880 0.120
#> ERR342899 1 0.993 0.288 0.548 0.452
#> ERR342829 1 0.163 0.747 0.976 0.024
#> ERR342850 1 0.722 0.673 0.800 0.200
#> ERR342849 1 0.993 0.288 0.548 0.452
#> ERR342811 1 0.722 0.673 0.800 0.200
#> ERR342837 1 0.529 0.739 0.880 0.120
#> ERR342857 1 0.881 0.563 0.700 0.300
#> ERR342869 1 0.722 0.673 0.800 0.200
#> ERR342903 1 0.163 0.747 0.976 0.024
#> ERR342819 1 0.529 0.739 0.880 0.120
#> ERR342885 2 0.917 0.585 0.332 0.668
#> ERR342889 2 0.662 0.800 0.172 0.828
#> ERR342864 1 0.881 0.563 0.700 0.300
#> ERR342860 1 0.993 0.288 0.548 0.452
#> ERR342808 1 0.722 0.673 0.800 0.200
#> ERR342823 1 0.163 0.747 0.976 0.024
#> ERR342907 2 0.714 0.803 0.196 0.804
#> ERR342852 1 0.881 0.563 0.700 0.300
#> ERR342832 2 0.662 0.800 0.172 0.828
#> ERR342868 1 0.795 0.681 0.760 0.240
#> ERR342821 1 0.881 0.563 0.700 0.300
#> ERR342878 2 0.714 0.803 0.196 0.804
#> ERR342876 1 0.163 0.747 0.976 0.024
#> ERR342809 1 0.163 0.747 0.976 0.024
#> ERR342846 2 0.917 0.585 0.332 0.668
#> ERR342872 2 0.714 0.803 0.196 0.804
#> ERR342828 2 0.662 0.800 0.172 0.828
#> ERR342840 1 0.529 0.739 0.880 0.120
#> ERR342831 1 0.795 0.681 0.760 0.240
#> ERR342818 1 0.697 0.714 0.812 0.188
#> ERR342862 1 0.529 0.739 0.880 0.120
#> ERR342894 1 0.795 0.681 0.760 0.240
#> ERR342884 2 0.714 0.803 0.196 0.804
#> ERR342891 1 0.163 0.747 0.976 0.024
#> ERR342890 1 0.795 0.681 0.760 0.240
#> ERR342836 2 0.662 0.800 0.172 0.828
#> ERR342879 1 0.697 0.714 0.812 0.188
#> ERR342848 1 0.697 0.714 0.812 0.188
#> ERR342861 1 0.163 0.747 0.976 0.024
#> ERR342814 1 0.993 0.288 0.548 0.452
#> ERR342870 1 0.722 0.673 0.800 0.200
#> ERR342901 1 0.163 0.747 0.976 0.024
#> ERR342908 1 0.722 0.673 0.800 0.200
#> ERR342815 2 0.662 0.800 0.172 0.828
#> ERR342897 2 0.917 0.585 0.332 0.668
#> ERR342833 2 0.714 0.803 0.196 0.804
#> ERR342817 2 0.917 0.585 0.332 0.668
#> ERR342810 1 0.993 0.288 0.548 0.452
#> ERR342867 1 0.881 0.563 0.700 0.300
#> ERR342847 1 0.529 0.739 0.880 0.120
#> ERR342855 1 0.163 0.747 0.976 0.024
#> ERR342851 1 0.697 0.714 0.812 0.188
#> ERR342813 1 0.795 0.681 0.760 0.240
#> ERR342883 1 0.697 0.714 0.812 0.188
#> ERR342856 2 0.917 0.585 0.332 0.668
#> ERR342822 2 0.662 0.800 0.172 0.828
#> ERR342892 1 0.163 0.747 0.976 0.024
#> ERR342842 1 0.163 0.747 0.976 0.024
#> ERR342902 2 0.714 0.803 0.196 0.804
#> ERR342900 1 0.993 0.288 0.548 0.452
#> ERR342888 1 0.795 0.681 0.760 0.240
#> ERR342812 1 0.163 0.747 0.976 0.024
#> ERR342853 1 0.993 0.288 0.548 0.452
#> ERR342866 1 0.529 0.739 0.880 0.120
#> ERR342820 1 0.722 0.673 0.800 0.200
#> ERR342895 1 0.163 0.747 0.976 0.024
#> ERR342825 2 0.917 0.585 0.332 0.668
#> ERR342826 2 0.917 0.585 0.332 0.668
#> ERR342875 2 0.662 0.800 0.172 0.828
#> ERR342834 2 0.917 0.585 0.332 0.668
#> ERR342898 1 0.881 0.563 0.700 0.300
#> ERR342886 1 0.993 0.288 0.548 0.452
#> ERR342838 1 0.163 0.747 0.976 0.024
#> ERR342882 1 0.163 0.747 0.976 0.024
#> ERR342807 2 0.714 0.803 0.196 0.804
#> ERR342873 1 0.697 0.714 0.812 0.188
#> ERR342844 1 0.881 0.563 0.700 0.300
#> ERR342874 1 0.529 0.739 0.880 0.120
#> ERR342893 1 0.697 0.714 0.812 0.188
#> ERR342859 2 0.917 0.585 0.332 0.668
#> ERR342830 1 0.993 0.288 0.548 0.452
#> ERR342880 1 0.697 0.714 0.812 0.188
#> ERR342887 1 0.163 0.747 0.976 0.024
#> ERR342854 1 0.163 0.747 0.976 0.024
#> ERR342904 1 0.722 0.673 0.800 0.200
#> ERR342881 1 0.529 0.739 0.880 0.120
#> ERR342858 1 0.697 0.714 0.812 0.188
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342843 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342896 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342827 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342871 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342863 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342839 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342906 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342905 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342816 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342865 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342824 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342841 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342835 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342899 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342829 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342850 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342849 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342811 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342837 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342857 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342869 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342903 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342819 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342885 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342889 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342864 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342860 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342808 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342823 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342907 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342852 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342832 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342868 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342821 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342878 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342876 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342809 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342846 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342872 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342828 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342840 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342831 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342818 1 0.8647 0.475 0.600 0.192 0.208
#> ERR342862 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342894 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342884 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342891 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342890 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342836 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342879 1 0.8647 0.475 0.600 0.192 0.208
#> ERR342848 1 0.8647 0.475 0.600 0.192 0.208
#> ERR342861 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342814 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342870 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342901 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342908 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342815 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342897 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342833 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342817 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342810 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342867 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342847 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342855 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342851 1 0.8647 0.475 0.600 0.192 0.208
#> ERR342813 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342883 1 0.8647 0.475 0.600 0.192 0.208
#> ERR342856 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342822 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342892 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342842 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342902 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342900 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342888 1 0.8701 0.352 0.492 0.108 0.400
#> ERR342812 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342853 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342866 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342820 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342895 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342825 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342826 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342875 2 0.1878 0.583 0.044 0.952 0.004
#> ERR342834 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342898 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342886 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342838 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342882 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342807 2 0.6059 0.504 0.048 0.764 0.188
#> ERR342873 1 0.8647 0.475 0.600 0.192 0.208
#> ERR342844 1 0.9725 0.111 0.452 0.272 0.276
#> ERR342874 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342893 1 0.8647 0.475 0.600 0.192 0.208
#> ERR342859 3 0.9273 1.000 0.164 0.364 0.472
#> ERR342830 2 0.8863 0.435 0.312 0.544 0.144
#> ERR342880 1 0.8647 0.475 0.600 0.192 0.208
#> ERR342887 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342854 1 0.0424 0.622 0.992 0.008 0.000
#> ERR342904 1 0.8670 0.356 0.592 0.168 0.240
#> ERR342881 1 0.7276 0.562 0.704 0.104 0.192
#> ERR342858 1 0.8647 0.475 0.600 0.192 0.208
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342843 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342896 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342827 2 0.629 0.666 0.004 0.672 NA 0.128
#> ERR342871 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342863 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342839 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342906 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342905 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342816 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342865 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342824 1 0.825 0.610 0.412 0.016 NA 0.256
#> ERR342841 2 0.615 0.667 0.000 0.672 NA 0.128
#> ERR342835 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342899 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342829 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342850 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342849 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342811 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342837 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342857 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342869 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342903 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342819 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342885 4 0.821 0.442 0.068 0.124 NA 0.524
#> ERR342889 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342864 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342860 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342808 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342823 1 0.825 0.610 0.412 0.016 NA 0.256
#> ERR342907 2 0.615 0.667 0.000 0.672 NA 0.128
#> ERR342852 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342832 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342868 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342821 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342878 2 0.615 0.667 0.000 0.672 NA 0.128
#> ERR342876 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342809 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342846 4 0.836 0.442 0.080 0.124 NA 0.516
#> ERR342872 2 0.629 0.666 0.004 0.672 NA 0.128
#> ERR342828 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342840 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342831 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342818 4 0.944 0.324 0.172 0.184 NA 0.428
#> ERR342862 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342894 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342884 2 0.615 0.667 0.000 0.672 NA 0.128
#> ERR342891 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342890 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342836 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342879 4 0.944 0.324 0.172 0.184 NA 0.428
#> ERR342848 4 0.944 0.324 0.172 0.184 NA 0.428
#> ERR342861 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342814 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342870 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342901 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342908 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342815 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342897 4 0.836 0.442 0.080 0.124 NA 0.516
#> ERR342833 2 0.615 0.667 0.000 0.672 NA 0.128
#> ERR342817 4 0.821 0.442 0.068 0.124 NA 0.524
#> ERR342810 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342867 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342847 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342855 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342851 4 0.944 0.324 0.172 0.184 NA 0.428
#> ERR342813 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342883 4 0.944 0.324 0.172 0.184 NA 0.428
#> ERR342856 4 0.836 0.442 0.080 0.124 NA 0.516
#> ERR342822 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342892 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342842 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342902 2 0.615 0.667 0.000 0.672 NA 0.128
#> ERR342900 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342888 1 0.443 0.421 0.824 0.088 NA 0.080
#> ERR342812 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342853 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342866 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342820 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342895 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342825 4 0.821 0.442 0.068 0.124 NA 0.524
#> ERR342826 4 0.821 0.442 0.068 0.124 NA 0.524
#> ERR342875 2 0.246 0.737 0.008 0.912 NA 0.076
#> ERR342834 4 0.821 0.442 0.068 0.124 NA 0.524
#> ERR342898 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342886 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342838 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342882 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342807 2 0.615 0.667 0.000 0.672 NA 0.128
#> ERR342873 4 0.944 0.324 0.172 0.184 NA 0.428
#> ERR342844 4 0.466 0.610 0.056 0.116 NA 0.812
#> ERR342874 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342893 4 0.944 0.324 0.172 0.184 NA 0.428
#> ERR342859 4 0.836 0.442 0.080 0.124 NA 0.516
#> ERR342830 2 0.686 0.634 0.168 0.676 NA 0.048
#> ERR342880 4 0.944 0.324 0.172 0.184 NA 0.428
#> ERR342887 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342854 1 0.825 0.611 0.412 0.016 NA 0.252
#> ERR342904 4 0.473 0.554 0.128 0.036 NA 0.808
#> ERR342881 1 0.830 0.448 0.564 0.112 NA 0.196
#> ERR342858 4 0.944 0.324 0.172 0.184 NA 0.428
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.6121 0.986 0.196 0.072 0.052 0.012 0.668
#> ERR342843 5 0.5961 0.986 0.196 0.072 0.056 0.004 0.672
#> ERR342896 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342827 2 0.6146 0.624 0.000 0.668 0.072 0.136 0.124
#> ERR342871 3 0.8747 0.290 0.264 0.044 0.336 0.280 0.076
#> ERR342863 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342839 5 0.6572 0.984 0.196 0.072 0.064 0.024 0.644
#> ERR342906 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342905 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342816 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342865 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342824 1 0.1467 0.708 0.956 0.004 0.016 0.016 0.008
#> ERR342841 2 0.6129 0.625 0.000 0.668 0.068 0.140 0.124
#> ERR342835 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342899 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342829 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342850 3 0.8747 0.290 0.264 0.044 0.336 0.280 0.076
#> ERR342849 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342811 3 0.8741 0.290 0.260 0.044 0.340 0.280 0.076
#> ERR342837 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342857 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342869 3 0.8747 0.290 0.264 0.044 0.336 0.280 0.076
#> ERR342903 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342819 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342885 3 0.3126 0.502 0.028 0.088 0.868 0.000 0.016
#> ERR342889 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342864 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342860 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342808 3 0.8741 0.290 0.260 0.044 0.340 0.280 0.076
#> ERR342823 1 0.1467 0.708 0.956 0.004 0.016 0.016 0.008
#> ERR342907 2 0.6129 0.625 0.000 0.668 0.068 0.140 0.124
#> ERR342852 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342832 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342868 5 0.6488 0.984 0.196 0.072 0.064 0.020 0.648
#> ERR342821 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342878 2 0.6129 0.625 0.000 0.668 0.068 0.140 0.124
#> ERR342876 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342809 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342846 3 0.4152 0.500 0.028 0.088 0.828 0.020 0.036
#> ERR342872 2 0.6146 0.624 0.000 0.668 0.072 0.136 0.124
#> ERR342828 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342840 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342831 5 0.6121 0.986 0.196 0.072 0.052 0.012 0.668
#> ERR342818 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
#> ERR342862 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342894 5 0.5961 0.986 0.196 0.072 0.056 0.004 0.672
#> ERR342884 2 0.6129 0.625 0.000 0.668 0.068 0.140 0.124
#> ERR342891 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342890 5 0.6572 0.984 0.196 0.072 0.064 0.024 0.644
#> ERR342836 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342879 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
#> ERR342848 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
#> ERR342861 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342814 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342870 3 0.8741 0.290 0.260 0.044 0.340 0.280 0.076
#> ERR342901 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342908 3 0.8741 0.290 0.260 0.044 0.340 0.280 0.076
#> ERR342815 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342897 3 0.4152 0.500 0.028 0.088 0.828 0.020 0.036
#> ERR342833 2 0.6129 0.625 0.000 0.668 0.068 0.140 0.124
#> ERR342817 3 0.3126 0.502 0.028 0.088 0.868 0.000 0.016
#> ERR342810 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342867 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342847 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342855 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342851 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
#> ERR342813 5 0.5961 0.986 0.196 0.072 0.056 0.004 0.672
#> ERR342883 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
#> ERR342856 3 0.4152 0.500 0.028 0.088 0.828 0.020 0.036
#> ERR342822 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342892 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342842 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342902 2 0.6129 0.625 0.000 0.668 0.068 0.140 0.124
#> ERR342900 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342888 5 0.6488 0.984 0.196 0.072 0.064 0.020 0.648
#> ERR342812 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342853 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342866 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342820 3 0.8747 0.290 0.264 0.044 0.336 0.280 0.076
#> ERR342895 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342825 3 0.3126 0.502 0.028 0.088 0.868 0.000 0.016
#> ERR342826 3 0.3126 0.502 0.028 0.088 0.868 0.000 0.016
#> ERR342875 2 0.0671 0.693 0.000 0.980 0.016 0.004 0.000
#> ERR342834 3 0.3126 0.502 0.028 0.088 0.868 0.000 0.016
#> ERR342898 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342886 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342838 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342882 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342807 2 0.6129 0.625 0.000 0.668 0.068 0.140 0.124
#> ERR342873 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
#> ERR342844 4 0.8519 0.323 0.136 0.104 0.356 0.364 0.040
#> ERR342874 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342893 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
#> ERR342859 3 0.4152 0.500 0.028 0.088 0.828 0.020 0.036
#> ERR342830 2 0.7493 0.520 0.052 0.568 0.040 0.164 0.176
#> ERR342880 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
#> ERR342887 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342854 1 0.0162 0.730 0.996 0.004 0.000 0.000 0.000
#> ERR342904 3 0.8741 0.290 0.260 0.044 0.340 0.280 0.076
#> ERR342881 1 0.8831 0.128 0.384 0.092 0.052 0.220 0.252
#> ERR342858 4 0.7940 0.564 0.260 0.064 0.072 0.512 0.092
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.6956 0.980 0.148 0.008 0.052 0.020 0.512 0.260
#> ERR342843 5 0.6919 0.980 0.148 0.008 0.048 0.020 0.512 0.264
#> ERR342896 1 0.0146 0.990 0.996 0.000 0.000 0.004 0.000 0.000
#> ERR342827 2 0.1434 0.760 0.000 0.948 0.028 0.012 0.012 0.000
#> ERR342871 3 0.8924 -0.331 0.168 0.016 0.280 0.276 0.164 0.096
#> ERR342863 2 0.5743 0.732 0.000 0.640 0.004 0.048 0.144 0.164
#> ERR342839 5 0.7281 0.976 0.148 0.008 0.052 0.036 0.476 0.280
#> ERR342906 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342905 6 0.8030 0.365 0.036 0.268 0.028 0.108 0.128 0.432
#> ERR342816 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342865 2 0.5743 0.732 0.000 0.640 0.004 0.048 0.144 0.164
#> ERR342824 1 0.1511 0.944 0.940 0.000 0.004 0.012 0.044 0.000
#> ERR342841 2 0.1074 0.762 0.000 0.960 0.028 0.012 0.000 0.000
#> ERR342835 6 0.5473 0.225 0.284 0.016 0.008 0.088 0.000 0.604
#> ERR342899 6 0.8030 0.365 0.036 0.268 0.028 0.108 0.128 0.432
#> ERR342829 1 0.0291 0.990 0.992 0.000 0.000 0.004 0.004 0.000
#> ERR342850 4 0.8900 0.235 0.168 0.016 0.280 0.280 0.164 0.092
#> ERR342849 6 0.8030 0.365 0.036 0.268 0.028 0.108 0.128 0.432
#> ERR342811 4 0.8888 0.235 0.168 0.016 0.280 0.284 0.160 0.092
#> ERR342837 6 0.5473 0.225 0.284 0.016 0.008 0.088 0.000 0.604
#> ERR342857 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342869 4 0.8900 0.235 0.168 0.016 0.280 0.280 0.164 0.092
#> ERR342903 1 0.0291 0.990 0.992 0.000 0.000 0.004 0.004 0.000
#> ERR342819 6 0.5473 0.225 0.284 0.016 0.008 0.088 0.000 0.604
#> ERR342885 3 0.1737 0.778 0.020 0.040 0.932 0.000 0.000 0.008
#> ERR342889 2 0.5743 0.732 0.000 0.640 0.004 0.048 0.144 0.164
#> ERR342864 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342860 6 0.8060 0.363 0.036 0.268 0.028 0.112 0.128 0.428
#> ERR342808 4 0.8912 0.234 0.168 0.016 0.280 0.280 0.160 0.096
#> ERR342823 1 0.1511 0.944 0.940 0.000 0.004 0.012 0.044 0.000
#> ERR342907 2 0.0972 0.762 0.000 0.964 0.028 0.008 0.000 0.000
#> ERR342852 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342832 2 0.5743 0.732 0.000 0.640 0.004 0.048 0.144 0.164
#> ERR342868 5 0.7281 0.976 0.148 0.008 0.052 0.036 0.476 0.280
#> ERR342821 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342878 2 0.0972 0.762 0.000 0.964 0.028 0.008 0.000 0.000
#> ERR342876 1 0.0000 0.991 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0291 0.990 0.992 0.000 0.000 0.004 0.004 0.000
#> ERR342846 3 0.3931 0.768 0.020 0.040 0.832 0.012 0.044 0.052
#> ERR342872 2 0.1313 0.761 0.000 0.952 0.028 0.016 0.004 0.000
#> ERR342828 2 0.5791 0.732 0.000 0.640 0.004 0.056 0.140 0.160
#> ERR342840 6 0.5516 0.224 0.284 0.016 0.008 0.092 0.000 0.600
#> ERR342831 5 0.6956 0.980 0.148 0.008 0.052 0.020 0.512 0.260
#> ERR342818 4 0.5477 0.463 0.160 0.012 0.056 0.684 0.000 0.088
#> ERR342862 6 0.5608 0.225 0.284 0.016 0.008 0.088 0.004 0.600
#> ERR342894 5 0.6919 0.980 0.148 0.008 0.048 0.020 0.512 0.264
#> ERR342884 2 0.1074 0.762 0.000 0.960 0.028 0.012 0.000 0.000
#> ERR342891 1 0.0291 0.990 0.992 0.000 0.000 0.004 0.004 0.000
#> ERR342890 5 0.7281 0.976 0.148 0.008 0.052 0.036 0.476 0.280
#> ERR342836 2 0.5743 0.732 0.000 0.640 0.004 0.048 0.144 0.164
#> ERR342879 4 0.5477 0.463 0.160 0.012 0.056 0.684 0.000 0.088
#> ERR342848 4 0.5703 0.460 0.160 0.012 0.056 0.672 0.004 0.096
#> ERR342861 1 0.0291 0.990 0.992 0.000 0.000 0.004 0.004 0.000
#> ERR342814 6 0.8030 0.365 0.036 0.268 0.028 0.108 0.128 0.432
#> ERR342870 4 0.8888 0.235 0.168 0.016 0.280 0.284 0.160 0.092
#> ERR342901 1 0.0000 0.991 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 3 0.8912 -0.331 0.168 0.016 0.280 0.280 0.160 0.096
#> ERR342815 2 0.5791 0.732 0.000 0.640 0.004 0.056 0.140 0.160
#> ERR342897 3 0.3892 0.769 0.020 0.040 0.836 0.016 0.040 0.048
#> ERR342833 2 0.0972 0.762 0.000 0.964 0.028 0.008 0.000 0.000
#> ERR342817 3 0.1737 0.778 0.020 0.040 0.932 0.000 0.000 0.008
#> ERR342810 6 0.8030 0.365 0.036 0.268 0.028 0.108 0.128 0.432
#> ERR342867 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342847 6 0.5473 0.225 0.284 0.016 0.008 0.088 0.000 0.604
#> ERR342855 1 0.0000 0.991 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.5477 0.463 0.160 0.012 0.056 0.684 0.000 0.088
#> ERR342813 5 0.6919 0.980 0.148 0.008 0.048 0.020 0.512 0.264
#> ERR342883 4 0.5477 0.463 0.160 0.012 0.056 0.684 0.000 0.088
#> ERR342856 3 0.3892 0.769 0.020 0.040 0.836 0.016 0.040 0.048
#> ERR342822 2 0.5791 0.732 0.000 0.640 0.004 0.056 0.140 0.160
#> ERR342892 1 0.0000 0.991 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0146 0.990 0.996 0.000 0.000 0.000 0.004 0.000
#> ERR342902 2 0.0972 0.762 0.000 0.964 0.028 0.008 0.000 0.000
#> ERR342900 6 0.8030 0.365 0.036 0.268 0.028 0.108 0.128 0.432
#> ERR342888 5 0.7281 0.976 0.148 0.008 0.052 0.036 0.476 0.280
#> ERR342812 1 0.0000 0.991 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 6 0.8030 0.365 0.036 0.268 0.028 0.108 0.128 0.432
#> ERR342866 6 0.5516 0.224 0.284 0.016 0.008 0.092 0.000 0.600
#> ERR342820 4 0.8900 0.235 0.168 0.016 0.280 0.280 0.164 0.092
#> ERR342895 1 0.0291 0.990 0.992 0.000 0.000 0.004 0.004 0.000
#> ERR342825 3 0.1737 0.778 0.020 0.040 0.932 0.000 0.000 0.008
#> ERR342826 3 0.1881 0.778 0.020 0.040 0.928 0.004 0.000 0.008
#> ERR342875 2 0.5791 0.732 0.000 0.640 0.004 0.056 0.140 0.160
#> ERR342834 3 0.1737 0.778 0.020 0.040 0.932 0.000 0.000 0.008
#> ERR342898 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342886 6 0.8060 0.363 0.036 0.268 0.028 0.112 0.128 0.428
#> ERR342838 1 0.0000 0.991 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0291 0.990 0.992 0.000 0.000 0.004 0.004 0.000
#> ERR342807 2 0.1151 0.761 0.000 0.956 0.032 0.012 0.000 0.000
#> ERR342873 4 0.5477 0.463 0.160 0.012 0.056 0.684 0.000 0.088
#> ERR342844 4 0.8085 0.396 0.076 0.064 0.328 0.388 0.120 0.024
#> ERR342874 6 0.5608 0.225 0.284 0.016 0.008 0.088 0.004 0.600
#> ERR342893 4 0.5477 0.463 0.160 0.012 0.056 0.684 0.000 0.088
#> ERR342859 3 0.3931 0.768 0.020 0.040 0.832 0.012 0.044 0.052
#> ERR342830 6 0.8060 0.363 0.036 0.268 0.028 0.112 0.128 0.428
#> ERR342880 4 0.5477 0.463 0.160 0.012 0.056 0.684 0.000 0.088
#> ERR342887 1 0.0000 0.991 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.991 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.8888 0.235 0.168 0.016 0.280 0.284 0.160 0.092
#> ERR342881 6 0.5608 0.225 0.284 0.016 0.008 0.088 0.004 0.600
#> ERR342858 4 0.5477 0.463 0.160 0.012 0.056 0.684 0.000 0.088
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "skmeans"]
# you can also extract it by
# res = res_list["MAD:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.836 0.919 0.960 0.4919 0.499 0.499
#> 3 3 0.706 0.840 0.909 0.3483 0.786 0.597
#> 4 4 0.690 0.798 0.841 0.1176 0.898 0.709
#> 5 5 0.772 0.861 0.868 0.0615 0.968 0.871
#> 6 6 0.836 0.879 0.864 0.0404 0.968 0.851
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.3114 0.946 0.944 0.056
#> ERR342843 1 0.3114 0.946 0.944 0.056
#> ERR342896 1 0.0000 0.983 1.000 0.000
#> ERR342827 2 0.0000 0.925 0.000 1.000
#> ERR342871 1 0.1633 0.972 0.976 0.024
#> ERR342863 2 0.0000 0.925 0.000 1.000
#> ERR342839 1 0.3114 0.946 0.944 0.056
#> ERR342906 2 0.9358 0.555 0.352 0.648
#> ERR342905 2 0.0000 0.925 0.000 1.000
#> ERR342816 2 0.9358 0.555 0.352 0.648
#> ERR342865 2 0.0000 0.925 0.000 1.000
#> ERR342824 1 0.0000 0.983 1.000 0.000
#> ERR342841 2 0.0000 0.925 0.000 1.000
#> ERR342835 1 0.0000 0.983 1.000 0.000
#> ERR342899 2 0.0000 0.925 0.000 1.000
#> ERR342829 1 0.0000 0.983 1.000 0.000
#> ERR342850 1 0.1633 0.972 0.976 0.024
#> ERR342849 2 0.0000 0.925 0.000 1.000
#> ERR342811 1 0.1633 0.972 0.976 0.024
#> ERR342837 1 0.0000 0.983 1.000 0.000
#> ERR342857 2 0.9358 0.555 0.352 0.648
#> ERR342869 1 0.1633 0.972 0.976 0.024
#> ERR342903 1 0.0000 0.983 1.000 0.000
#> ERR342819 1 0.0000 0.983 1.000 0.000
#> ERR342885 2 0.0672 0.922 0.008 0.992
#> ERR342889 2 0.0000 0.925 0.000 1.000
#> ERR342864 2 0.9358 0.555 0.352 0.648
#> ERR342860 2 0.0000 0.925 0.000 1.000
#> ERR342808 1 0.1633 0.972 0.976 0.024
#> ERR342823 1 0.0000 0.983 1.000 0.000
#> ERR342907 2 0.0000 0.925 0.000 1.000
#> ERR342852 2 0.9358 0.555 0.352 0.648
#> ERR342832 2 0.0000 0.925 0.000 1.000
#> ERR342868 1 0.3114 0.946 0.944 0.056
#> ERR342821 2 0.9358 0.555 0.352 0.648
#> ERR342878 2 0.0000 0.925 0.000 1.000
#> ERR342876 1 0.0000 0.983 1.000 0.000
#> ERR342809 1 0.0000 0.983 1.000 0.000
#> ERR342846 2 0.0672 0.922 0.008 0.992
#> ERR342872 2 0.0000 0.925 0.000 1.000
#> ERR342828 2 0.0000 0.925 0.000 1.000
#> ERR342840 1 0.0000 0.983 1.000 0.000
#> ERR342831 1 0.3114 0.946 0.944 0.056
#> ERR342818 1 0.0938 0.980 0.988 0.012
#> ERR342862 1 0.0000 0.983 1.000 0.000
#> ERR342894 1 0.3114 0.946 0.944 0.056
#> ERR342884 2 0.0000 0.925 0.000 1.000
#> ERR342891 1 0.0000 0.983 1.000 0.000
#> ERR342890 1 0.3114 0.946 0.944 0.056
#> ERR342836 2 0.0000 0.925 0.000 1.000
#> ERR342879 1 0.0938 0.980 0.988 0.012
#> ERR342848 1 0.0938 0.980 0.988 0.012
#> ERR342861 1 0.0000 0.983 1.000 0.000
#> ERR342814 2 0.0000 0.925 0.000 1.000
#> ERR342870 1 0.1633 0.972 0.976 0.024
#> ERR342901 1 0.0000 0.983 1.000 0.000
#> ERR342908 1 0.1633 0.972 0.976 0.024
#> ERR342815 2 0.0000 0.925 0.000 1.000
#> ERR342897 2 0.0672 0.922 0.008 0.992
#> ERR342833 2 0.0000 0.925 0.000 1.000
#> ERR342817 2 0.0672 0.922 0.008 0.992
#> ERR342810 2 0.0000 0.925 0.000 1.000
#> ERR342867 2 0.9358 0.555 0.352 0.648
#> ERR342847 1 0.0000 0.983 1.000 0.000
#> ERR342855 1 0.0000 0.983 1.000 0.000
#> ERR342851 1 0.0938 0.980 0.988 0.012
#> ERR342813 1 0.3114 0.946 0.944 0.056
#> ERR342883 1 0.0938 0.980 0.988 0.012
#> ERR342856 2 0.0672 0.922 0.008 0.992
#> ERR342822 2 0.0000 0.925 0.000 1.000
#> ERR342892 1 0.0000 0.983 1.000 0.000
#> ERR342842 1 0.0000 0.983 1.000 0.000
#> ERR342902 2 0.0000 0.925 0.000 1.000
#> ERR342900 2 0.0000 0.925 0.000 1.000
#> ERR342888 1 0.3114 0.946 0.944 0.056
#> ERR342812 1 0.0000 0.983 1.000 0.000
#> ERR342853 2 0.0000 0.925 0.000 1.000
#> ERR342866 1 0.0000 0.983 1.000 0.000
#> ERR342820 1 0.1633 0.972 0.976 0.024
#> ERR342895 1 0.0000 0.983 1.000 0.000
#> ERR342825 2 0.0672 0.922 0.008 0.992
#> ERR342826 2 0.0672 0.922 0.008 0.992
#> ERR342875 2 0.0000 0.925 0.000 1.000
#> ERR342834 2 0.0672 0.922 0.008 0.992
#> ERR342898 2 0.9358 0.555 0.352 0.648
#> ERR342886 2 0.0000 0.925 0.000 1.000
#> ERR342838 1 0.0000 0.983 1.000 0.000
#> ERR342882 1 0.0000 0.983 1.000 0.000
#> ERR342807 2 0.0000 0.925 0.000 1.000
#> ERR342873 1 0.0938 0.980 0.988 0.012
#> ERR342844 2 0.9358 0.555 0.352 0.648
#> ERR342874 1 0.0000 0.983 1.000 0.000
#> ERR342893 1 0.0938 0.980 0.988 0.012
#> ERR342859 2 0.0672 0.922 0.008 0.992
#> ERR342830 2 0.0000 0.925 0.000 1.000
#> ERR342880 1 0.0938 0.980 0.988 0.012
#> ERR342887 1 0.0000 0.983 1.000 0.000
#> ERR342854 1 0.0000 0.983 1.000 0.000
#> ERR342904 1 0.1633 0.972 0.976 0.024
#> ERR342881 1 0.0000 0.983 1.000 0.000
#> ERR342858 1 0.0938 0.980 0.988 0.012
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342843 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342896 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342827 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342871 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342863 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342839 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342906 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342905 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342816 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342865 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342824 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342841 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342835 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342899 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342829 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342850 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342849 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342811 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342837 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342857 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342869 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342903 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342819 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342885 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342889 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342864 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342860 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342808 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342823 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342907 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342852 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342832 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342868 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342821 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342878 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342876 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342809 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342846 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342872 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342828 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342840 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342831 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342818 1 0.6917 0.476 0.608 0.024 0.368
#> ERR342862 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342894 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342884 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342891 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342890 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342836 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342879 1 0.6917 0.476 0.608 0.024 0.368
#> ERR342848 1 0.6917 0.476 0.608 0.024 0.368
#> ERR342861 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342814 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342870 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342901 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342908 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342815 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342897 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342833 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342817 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342810 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342867 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342847 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342855 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342851 1 0.6917 0.476 0.608 0.024 0.368
#> ERR342813 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342883 1 0.6917 0.476 0.608 0.024 0.368
#> ERR342856 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342822 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342892 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342842 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342902 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342900 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342888 1 0.6448 0.569 0.656 0.016 0.328
#> ERR342812 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342853 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342866 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342820 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342895 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342825 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342826 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342875 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342834 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342898 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342886 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342838 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342882 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342807 2 0.0592 0.990 0.000 0.988 0.012
#> ERR342873 1 0.6917 0.476 0.608 0.024 0.368
#> ERR342844 3 0.1129 0.932 0.020 0.004 0.976
#> ERR342874 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342893 1 0.6917 0.476 0.608 0.024 0.368
#> ERR342859 3 0.3340 0.886 0.000 0.120 0.880
#> ERR342830 2 0.0000 0.995 0.000 1.000 0.000
#> ERR342880 1 0.6917 0.476 0.608 0.024 0.368
#> ERR342887 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342854 1 0.0237 0.823 0.996 0.000 0.004
#> ERR342904 3 0.1411 0.926 0.036 0.000 0.964
#> ERR342881 1 0.2448 0.814 0.924 0.000 0.076
#> ERR342858 1 0.6917 0.476 0.608 0.024 0.368
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342843 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342896 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342827 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342871 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342863 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342839 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342906 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342905 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342816 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342865 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342824 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342841 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342835 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342899 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342829 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342850 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342849 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342811 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342837 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342857 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342869 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342903 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342819 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342885 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342889 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342864 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342860 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342808 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342823 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342907 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342852 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342832 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342868 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342821 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342878 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342876 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342809 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342846 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342872 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342828 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342840 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342831 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342818 3 0.830 0.407 0.232 0.020 0.404 0.344
#> ERR342862 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342894 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342884 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342891 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342890 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342836 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342879 3 0.830 0.407 0.232 0.020 0.404 0.344
#> ERR342848 3 0.830 0.407 0.232 0.020 0.404 0.344
#> ERR342861 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342814 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342870 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342901 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342908 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342815 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342897 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342833 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342817 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342810 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342867 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342847 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342855 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342851 3 0.830 0.407 0.232 0.020 0.404 0.344
#> ERR342813 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342883 3 0.830 0.407 0.232 0.020 0.404 0.344
#> ERR342856 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342822 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342892 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342842 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342902 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342900 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342888 3 0.559 0.580 0.180 0.000 0.720 0.100
#> ERR342812 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342853 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342866 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342820 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342895 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342825 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342826 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342875 2 0.000 0.968 0.000 1.000 0.000 0.000
#> ERR342834 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342898 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342886 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342838 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342882 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342807 2 0.183 0.952 0.000 0.944 0.024 0.032
#> ERR342873 3 0.830 0.407 0.232 0.020 0.404 0.344
#> ERR342844 4 0.164 0.801 0.008 0.000 0.044 0.948
#> ERR342874 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342893 3 0.830 0.407 0.232 0.020 0.404 0.344
#> ERR342859 4 0.576 0.709 0.000 0.076 0.240 0.684
#> ERR342830 2 0.112 0.962 0.000 0.964 0.036 0.000
#> ERR342880 3 0.830 0.407 0.232 0.020 0.404 0.344
#> ERR342887 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342854 1 0.000 1.000 1.000 0.000 0.000 0.000
#> ERR342904 4 0.291 0.796 0.020 0.000 0.092 0.888
#> ERR342881 3 0.556 0.567 0.308 0.000 0.652 0.040
#> ERR342858 3 0.830 0.407 0.232 0.020 0.404 0.344
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342843 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342896 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342871 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342863 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342839 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342906 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342905 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342816 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342865 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342824 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342835 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342899 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342829 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342849 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342811 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342837 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342857 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342869 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342903 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342885 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342889 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342864 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342860 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342808 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342823 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342852 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342832 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342868 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342821 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342878 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342876 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342846 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342872 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342828 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342840 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342831 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342818 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
#> ERR342862 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342894 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342884 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342891 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342836 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342879 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
#> ERR342848 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
#> ERR342861 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342870 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342901 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342815 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342897 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342833 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342817 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342810 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342867 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342847 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342855 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342851 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
#> ERR342813 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342883 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
#> ERR342856 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342822 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342892 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342900 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342888 5 0.112 0.774 0.020 0.000 0.000 0.016 0.964
#> ERR342812 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342866 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342820 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342895 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342825 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342826 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342875 2 0.000 0.935 0.000 1.000 0.000 0.000 0.000
#> ERR342834 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342898 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342886 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342838 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.280 0.901 0.000 0.884 0.044 0.068 0.004
#> ERR342873 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
#> ERR342844 4 0.394 0.742 0.000 0.004 0.224 0.756 0.016
#> ERR342874 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342893 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
#> ERR342859 4 0.479 0.681 0.000 0.028 0.068 0.760 0.144
#> ERR342830 2 0.199 0.922 0.000 0.924 0.032 0.000 0.044
#> ERR342880 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
#> ERR342887 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.392 0.756 0.012 0.000 0.164 0.796 0.028
#> ERR342881 5 0.574 0.740 0.120 0.000 0.196 0.020 0.664
#> ERR342858 3 0.366 1.000 0.044 0.000 0.832 0.012 0.112
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342843 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342871 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342863 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342839 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342906 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342905 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342816 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342865 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342835 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342899 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342849 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342811 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342837 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342857 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342869 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342885 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342889 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342864 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342860 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342808 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342852 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342832 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342868 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342821 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342878 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342872 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342828 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342840 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342831 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342818 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
#> ERR342862 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342894 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342884 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342836 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342879 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
#> ERR342848 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342870 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342815 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342897 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342833 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342817 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342810 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342867 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342847 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
#> ERR342813 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342883 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
#> ERR342856 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342822 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342900 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342888 5 0.1787 0.782 0.004 0.000 0.068 0.000 0.920 0.008
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342866 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342820 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342826 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342875 2 0.0458 0.877 0.000 0.984 0.016 0.000 0.000 0.000
#> ERR342834 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342898 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342886 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.3959 0.770 0.000 0.724 0.244 0.012 0.000 0.020
#> ERR342873 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
#> ERR342844 4 0.2994 0.808 0.000 0.000 0.064 0.852 0.004 0.080
#> ERR342874 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342893 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
#> ERR342859 3 0.3789 1.000 0.000 0.000 0.760 0.196 0.040 0.004
#> ERR342830 2 0.1942 0.863 0.000 0.916 0.064 0.000 0.012 0.008
#> ERR342880 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.2933 0.804 0.000 0.000 0.108 0.852 0.008 0.032
#> ERR342881 5 0.5302 0.750 0.040 0.000 0.056 0.020 0.684 0.200
#> ERR342858 6 0.1065 1.000 0.008 0.000 0.000 0.020 0.008 0.964
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "pam"]
# you can also extract it by
# res = res_list["MAD:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 6.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.901 0.952 0.975 0.452 0.531 0.531
#> 3 3 0.742 0.825 0.896 0.285 0.950 0.906
#> 4 4 0.962 0.913 0.964 0.210 0.813 0.612
#> 5 5 0.954 0.947 0.974 0.087 0.912 0.715
#> 6 6 0.945 0.947 0.956 0.048 0.964 0.849
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 6
#> attr(,"optional")
#> [1] 2 4 5
There is also optional best \(k\) = 2 4 5 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 1.000 1.000 0.000
#> ERR342843 1 0.000 1.000 1.000 0.000
#> ERR342896 1 0.000 1.000 1.000 0.000
#> ERR342827 2 0.000 0.929 0.000 1.000
#> ERR342871 1 0.000 1.000 1.000 0.000
#> ERR342863 2 0.000 0.929 0.000 1.000
#> ERR342839 1 0.000 1.000 1.000 0.000
#> ERR342906 1 0.000 1.000 1.000 0.000
#> ERR342905 2 0.000 0.929 0.000 1.000
#> ERR342816 1 0.000 1.000 1.000 0.000
#> ERR342865 2 0.000 0.929 0.000 1.000
#> ERR342824 1 0.000 1.000 1.000 0.000
#> ERR342841 2 0.000 0.929 0.000 1.000
#> ERR342835 1 0.000 1.000 1.000 0.000
#> ERR342899 2 0.000 0.929 0.000 1.000
#> ERR342829 1 0.000 1.000 1.000 0.000
#> ERR342850 1 0.000 1.000 1.000 0.000
#> ERR342849 2 0.000 0.929 0.000 1.000
#> ERR342811 1 0.000 1.000 1.000 0.000
#> ERR342837 1 0.000 1.000 1.000 0.000
#> ERR342857 1 0.000 1.000 1.000 0.000
#> ERR342869 1 0.000 1.000 1.000 0.000
#> ERR342903 1 0.000 1.000 1.000 0.000
#> ERR342819 1 0.000 1.000 1.000 0.000
#> ERR342885 2 0.839 0.704 0.268 0.732
#> ERR342889 2 0.000 0.929 0.000 1.000
#> ERR342864 1 0.000 1.000 1.000 0.000
#> ERR342860 2 0.000 0.929 0.000 1.000
#> ERR342808 1 0.000 1.000 1.000 0.000
#> ERR342823 1 0.000 1.000 1.000 0.000
#> ERR342907 2 0.000 0.929 0.000 1.000
#> ERR342852 1 0.000 1.000 1.000 0.000
#> ERR342832 2 0.000 0.929 0.000 1.000
#> ERR342868 1 0.000 1.000 1.000 0.000
#> ERR342821 1 0.000 1.000 1.000 0.000
#> ERR342878 2 0.000 0.929 0.000 1.000
#> ERR342876 1 0.000 1.000 1.000 0.000
#> ERR342809 1 0.000 1.000 1.000 0.000
#> ERR342846 2 0.891 0.644 0.308 0.692
#> ERR342872 2 0.000 0.929 0.000 1.000
#> ERR342828 2 0.000 0.929 0.000 1.000
#> ERR342840 1 0.000 1.000 1.000 0.000
#> ERR342831 1 0.000 1.000 1.000 0.000
#> ERR342818 1 0.000 1.000 1.000 0.000
#> ERR342862 1 0.000 1.000 1.000 0.000
#> ERR342894 1 0.000 1.000 1.000 0.000
#> ERR342884 2 0.000 0.929 0.000 1.000
#> ERR342891 1 0.000 1.000 1.000 0.000
#> ERR342890 1 0.000 1.000 1.000 0.000
#> ERR342836 2 0.000 0.929 0.000 1.000
#> ERR342879 1 0.000 1.000 1.000 0.000
#> ERR342848 1 0.000 1.000 1.000 0.000
#> ERR342861 1 0.000 1.000 1.000 0.000
#> ERR342814 2 0.000 0.929 0.000 1.000
#> ERR342870 1 0.000 1.000 1.000 0.000
#> ERR342901 1 0.000 1.000 1.000 0.000
#> ERR342908 1 0.000 1.000 1.000 0.000
#> ERR342815 2 0.000 0.929 0.000 1.000
#> ERR342897 2 0.850 0.694 0.276 0.724
#> ERR342833 2 0.000 0.929 0.000 1.000
#> ERR342817 2 0.850 0.694 0.276 0.724
#> ERR342810 2 0.000 0.929 0.000 1.000
#> ERR342867 1 0.000 1.000 1.000 0.000
#> ERR342847 1 0.000 1.000 1.000 0.000
#> ERR342855 1 0.000 1.000 1.000 0.000
#> ERR342851 1 0.000 1.000 1.000 0.000
#> ERR342813 1 0.000 1.000 1.000 0.000
#> ERR342883 1 0.000 1.000 1.000 0.000
#> ERR342856 2 0.738 0.771 0.208 0.792
#> ERR342822 2 0.000 0.929 0.000 1.000
#> ERR342892 1 0.000 1.000 1.000 0.000
#> ERR342842 1 0.000 1.000 1.000 0.000
#> ERR342902 2 0.000 0.929 0.000 1.000
#> ERR342900 2 0.000 0.929 0.000 1.000
#> ERR342888 1 0.000 1.000 1.000 0.000
#> ERR342812 1 0.000 1.000 1.000 0.000
#> ERR342853 2 0.000 0.929 0.000 1.000
#> ERR342866 1 0.000 1.000 1.000 0.000
#> ERR342820 1 0.000 1.000 1.000 0.000
#> ERR342895 1 0.000 1.000 1.000 0.000
#> ERR342825 2 0.855 0.689 0.280 0.720
#> ERR342826 2 0.753 0.763 0.216 0.784
#> ERR342875 2 0.000 0.929 0.000 1.000
#> ERR342834 2 0.886 0.651 0.304 0.696
#> ERR342898 1 0.000 1.000 1.000 0.000
#> ERR342886 2 0.000 0.929 0.000 1.000
#> ERR342838 1 0.000 1.000 1.000 0.000
#> ERR342882 1 0.000 1.000 1.000 0.000
#> ERR342807 2 0.000 0.929 0.000 1.000
#> ERR342873 1 0.000 1.000 1.000 0.000
#> ERR342844 1 0.000 1.000 1.000 0.000
#> ERR342874 1 0.000 1.000 1.000 0.000
#> ERR342893 1 0.000 1.000 1.000 0.000
#> ERR342859 2 0.936 0.561 0.352 0.648
#> ERR342830 2 0.000 0.929 0.000 1.000
#> ERR342880 1 0.000 1.000 1.000 0.000
#> ERR342887 1 0.000 1.000 1.000 0.000
#> ERR342854 1 0.000 1.000 1.000 0.000
#> ERR342904 1 0.000 1.000 1.000 0.000
#> ERR342881 1 0.000 1.000 1.000 0.000
#> ERR342858 1 0.000 1.000 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.1163 0.805 0.972 0 0.028
#> ERR342843 1 0.1964 0.800 0.944 0 0.056
#> ERR342896 1 0.0000 0.806 1.000 0 0.000
#> ERR342827 2 0.0000 1.000 0.000 1 0.000
#> ERR342871 1 0.6204 0.572 0.576 0 0.424
#> ERR342863 2 0.0000 1.000 0.000 1 0.000
#> ERR342839 1 0.1289 0.805 0.968 0 0.032
#> ERR342906 1 0.6204 0.572 0.576 0 0.424
#> ERR342905 2 0.0000 1.000 0.000 1 0.000
#> ERR342816 1 0.6204 0.572 0.576 0 0.424
#> ERR342865 2 0.0000 1.000 0.000 1 0.000
#> ERR342824 1 0.0000 0.806 1.000 0 0.000
#> ERR342841 2 0.0000 1.000 0.000 1 0.000
#> ERR342835 1 0.0000 0.806 1.000 0 0.000
#> ERR342899 2 0.0000 1.000 0.000 1 0.000
#> ERR342829 1 0.0000 0.806 1.000 0 0.000
#> ERR342850 1 0.6204 0.572 0.576 0 0.424
#> ERR342849 2 0.0000 1.000 0.000 1 0.000
#> ERR342811 1 0.6204 0.572 0.576 0 0.424
#> ERR342837 1 0.0000 0.806 1.000 0 0.000
#> ERR342857 1 0.6204 0.572 0.576 0 0.424
#> ERR342869 1 0.6204 0.572 0.576 0 0.424
#> ERR342903 1 0.0000 0.806 1.000 0 0.000
#> ERR342819 1 0.0000 0.806 1.000 0 0.000
#> ERR342885 3 0.0000 1.000 0.000 0 1.000
#> ERR342889 2 0.0000 1.000 0.000 1 0.000
#> ERR342864 1 0.6204 0.572 0.576 0 0.424
#> ERR342860 2 0.0000 1.000 0.000 1 0.000
#> ERR342808 1 0.6204 0.572 0.576 0 0.424
#> ERR342823 1 0.0000 0.806 1.000 0 0.000
#> ERR342907 2 0.0000 1.000 0.000 1 0.000
#> ERR342852 1 0.6204 0.572 0.576 0 0.424
#> ERR342832 2 0.0000 1.000 0.000 1 0.000
#> ERR342868 1 0.2356 0.795 0.928 0 0.072
#> ERR342821 1 0.6204 0.572 0.576 0 0.424
#> ERR342878 2 0.0000 1.000 0.000 1 0.000
#> ERR342876 1 0.0000 0.806 1.000 0 0.000
#> ERR342809 1 0.0000 0.806 1.000 0 0.000
#> ERR342846 3 0.0000 1.000 0.000 0 1.000
#> ERR342872 2 0.0000 1.000 0.000 1 0.000
#> ERR342828 2 0.0000 1.000 0.000 1 0.000
#> ERR342840 1 0.0592 0.805 0.988 0 0.012
#> ERR342831 1 0.0237 0.806 0.996 0 0.004
#> ERR342818 1 0.5216 0.703 0.740 0 0.260
#> ERR342862 1 0.1163 0.802 0.972 0 0.028
#> ERR342894 1 0.1411 0.804 0.964 0 0.036
#> ERR342884 2 0.0000 1.000 0.000 1 0.000
#> ERR342891 1 0.0000 0.806 1.000 0 0.000
#> ERR342890 1 0.1529 0.803 0.960 0 0.040
#> ERR342836 2 0.0000 1.000 0.000 1 0.000
#> ERR342879 1 0.5835 0.647 0.660 0 0.340
#> ERR342848 1 0.1031 0.806 0.976 0 0.024
#> ERR342861 1 0.0000 0.806 1.000 0 0.000
#> ERR342814 2 0.0000 1.000 0.000 1 0.000
#> ERR342870 1 0.6204 0.572 0.576 0 0.424
#> ERR342901 1 0.0000 0.806 1.000 0 0.000
#> ERR342908 1 0.6204 0.572 0.576 0 0.424
#> ERR342815 2 0.0000 1.000 0.000 1 0.000
#> ERR342897 3 0.0000 1.000 0.000 0 1.000
#> ERR342833 2 0.0000 1.000 0.000 1 0.000
#> ERR342817 3 0.0000 1.000 0.000 0 1.000
#> ERR342810 2 0.0000 1.000 0.000 1 0.000
#> ERR342867 1 0.6204 0.572 0.576 0 0.424
#> ERR342847 1 0.0237 0.806 0.996 0 0.004
#> ERR342855 1 0.0000 0.806 1.000 0 0.000
#> ERR342851 1 0.5327 0.696 0.728 0 0.272
#> ERR342813 1 0.1411 0.804 0.964 0 0.036
#> ERR342883 1 0.5948 0.629 0.640 0 0.360
#> ERR342856 3 0.0000 1.000 0.000 0 1.000
#> ERR342822 2 0.0000 1.000 0.000 1 0.000
#> ERR342892 1 0.0000 0.806 1.000 0 0.000
#> ERR342842 1 0.0000 0.806 1.000 0 0.000
#> ERR342902 2 0.0000 1.000 0.000 1 0.000
#> ERR342900 2 0.0000 1.000 0.000 1 0.000
#> ERR342888 1 0.2261 0.796 0.932 0 0.068
#> ERR342812 1 0.0000 0.806 1.000 0 0.000
#> ERR342853 2 0.0000 1.000 0.000 1 0.000
#> ERR342866 1 0.1031 0.803 0.976 0 0.024
#> ERR342820 1 0.6204 0.572 0.576 0 0.424
#> ERR342895 1 0.0000 0.806 1.000 0 0.000
#> ERR342825 3 0.0000 1.000 0.000 0 1.000
#> ERR342826 3 0.0000 1.000 0.000 0 1.000
#> ERR342875 2 0.0000 1.000 0.000 1 0.000
#> ERR342834 3 0.0000 1.000 0.000 0 1.000
#> ERR342898 1 0.6204 0.572 0.576 0 0.424
#> ERR342886 2 0.0000 1.000 0.000 1 0.000
#> ERR342838 1 0.0000 0.806 1.000 0 0.000
#> ERR342882 1 0.0000 0.806 1.000 0 0.000
#> ERR342807 2 0.0000 1.000 0.000 1 0.000
#> ERR342873 1 0.4002 0.756 0.840 0 0.160
#> ERR342844 1 0.6204 0.572 0.576 0 0.424
#> ERR342874 1 0.0892 0.804 0.980 0 0.020
#> ERR342893 1 0.5431 0.687 0.716 0 0.284
#> ERR342859 3 0.0000 1.000 0.000 0 1.000
#> ERR342830 2 0.0000 1.000 0.000 1 0.000
#> ERR342880 1 0.5835 0.647 0.660 0 0.340
#> ERR342887 1 0.0000 0.806 1.000 0 0.000
#> ERR342854 1 0.0000 0.806 1.000 0 0.000
#> ERR342904 1 0.6204 0.572 0.576 0 0.424
#> ERR342881 1 0.0592 0.805 0.988 0 0.012
#> ERR342858 1 0.5835 0.647 0.660 0 0.340
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.1109 0.9398 0.968 0 0.004 0.028
#> ERR342843 1 0.1489 0.9303 0.952 0 0.004 0.044
#> ERR342896 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342827 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342871 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342863 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342839 1 0.1305 0.9355 0.960 0 0.004 0.036
#> ERR342906 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342905 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342816 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342865 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342824 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342841 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342835 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342899 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342829 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342850 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342849 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342811 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342837 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342857 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342869 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342903 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342819 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342885 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342889 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342864 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342860 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342808 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342823 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342907 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342852 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342832 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342868 1 0.1978 0.9101 0.928 0 0.004 0.068
#> ERR342821 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342878 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342876 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342809 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342846 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342872 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342828 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342840 1 0.0707 0.9416 0.980 0 0.000 0.020
#> ERR342831 1 0.0657 0.9452 0.984 0 0.004 0.012
#> ERR342818 1 0.4977 0.0460 0.540 0 0.000 0.460
#> ERR342862 1 0.0921 0.9361 0.972 0 0.000 0.028
#> ERR342894 1 0.1398 0.9331 0.956 0 0.004 0.040
#> ERR342884 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342891 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342890 1 0.1398 0.9331 0.956 0 0.004 0.040
#> ERR342836 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342879 4 0.4585 0.5527 0.332 0 0.000 0.668
#> ERR342848 1 0.1211 0.9256 0.960 0 0.000 0.040
#> ERR342861 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342814 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342870 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342901 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342908 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342815 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342897 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342833 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342817 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342810 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342867 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342847 1 0.0188 0.9499 0.996 0 0.000 0.004
#> ERR342855 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342851 1 0.4994 -0.0395 0.520 0 0.000 0.480
#> ERR342813 1 0.1398 0.9331 0.956 0 0.004 0.040
#> ERR342883 4 0.4250 0.6483 0.276 0 0.000 0.724
#> ERR342856 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342822 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342892 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342842 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342902 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342900 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342888 1 0.1902 0.9139 0.932 0 0.004 0.064
#> ERR342812 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342853 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342866 1 0.1022 0.9330 0.968 0 0.000 0.032
#> ERR342820 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342895 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342825 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342826 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342875 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342834 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342898 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342886 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342838 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342882 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342807 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342873 1 0.4164 0.6038 0.736 0 0.000 0.264
#> ERR342844 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342874 1 0.0817 0.9390 0.976 0 0.000 0.024
#> ERR342893 4 0.4967 0.2437 0.452 0 0.000 0.548
#> ERR342859 3 0.0188 1.0000 0.000 0 0.996 0.004
#> ERR342830 2 0.0000 1.0000 0.000 1 0.000 0.000
#> ERR342880 4 0.4304 0.6365 0.284 0 0.000 0.716
#> ERR342887 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342854 1 0.0000 0.9514 1.000 0 0.000 0.000
#> ERR342904 4 0.0336 0.8931 0.008 0 0.000 0.992
#> ERR342881 1 0.0707 0.9416 0.980 0 0.000 0.020
#> ERR342858 4 0.4605 0.5446 0.336 0 0.000 0.664
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342843 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342896 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342827 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342871 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342863 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342839 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342906 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342905 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342816 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342865 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342824 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342841 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342835 1 0.0404 0.969 0.988 0 0 0.012 0.000
#> ERR342899 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342829 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342850 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342849 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342811 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342837 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342857 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342869 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342903 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342819 1 0.0404 0.969 0.988 0 0 0.012 0.000
#> ERR342885 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342889 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342864 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342860 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342808 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342823 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342907 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342852 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342832 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342868 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342821 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342878 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342876 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342809 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342846 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342872 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342828 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342840 1 0.2390 0.901 0.896 0 0 0.084 0.020
#> ERR342831 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342818 4 0.3730 0.693 0.288 0 0 0.712 0.000
#> ERR342862 1 0.1851 0.909 0.912 0 0 0.088 0.000
#> ERR342894 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342884 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342891 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342890 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342836 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342879 4 0.3210 0.780 0.212 0 0 0.788 0.000
#> ERR342848 1 0.1341 0.925 0.944 0 0 0.056 0.000
#> ERR342861 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342814 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342870 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342901 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342908 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342815 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342897 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342833 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342817 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342810 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342867 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342847 1 0.1992 0.929 0.924 0 0 0.044 0.032
#> ERR342855 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342851 4 0.3424 0.753 0.240 0 0 0.760 0.000
#> ERR342813 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342883 4 0.3210 0.780 0.212 0 0 0.788 0.000
#> ERR342856 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342822 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342892 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342842 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342902 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342900 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342888 5 0.0000 1.000 0.000 0 0 0.000 1.000
#> ERR342812 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342853 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342866 1 0.2068 0.902 0.904 0 0 0.092 0.004
#> ERR342820 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342895 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342825 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342875 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342834 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342898 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342886 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342838 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342882 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342807 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342873 4 0.4294 0.288 0.468 0 0 0.532 0.000
#> ERR342844 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342874 1 0.1851 0.909 0.912 0 0 0.088 0.000
#> ERR342893 4 0.3242 0.777 0.216 0 0 0.784 0.000
#> ERR342859 3 0.0000 1.000 0.000 0 1 0.000 0.000
#> ERR342830 2 0.0000 1.000 0.000 1 0 0.000 0.000
#> ERR342880 4 0.3210 0.780 0.212 0 0 0.788 0.000
#> ERR342887 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342854 1 0.0000 0.975 1.000 0 0 0.000 0.000
#> ERR342904 4 0.0000 0.899 0.000 0 0 1.000 0.000
#> ERR342881 1 0.1732 0.916 0.920 0 0 0.080 0.000
#> ERR342858 4 0.3210 0.780 0.212 0 0 0.788 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342843 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342896 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342827 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342871 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342863 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342839 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342906 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342905 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342816 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342865 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342824 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342841 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342835 1 0.293 0.806 0.796 0 0 0.004 0.000 0.200
#> ERR342899 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342829 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342850 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342849 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342811 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342837 1 0.279 0.807 0.800 0 0 0.000 0.000 0.200
#> ERR342857 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342869 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342903 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342819 1 0.293 0.806 0.796 0 0 0.004 0.000 0.200
#> ERR342885 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342889 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342864 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342860 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342808 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342823 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342907 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342852 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342832 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342868 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342821 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342878 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342876 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342809 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342846 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342872 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342828 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342840 1 0.529 0.670 0.628 0 0 0.160 0.008 0.204
#> ERR342831 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342818 6 0.352 0.899 0.072 0 0 0.128 0.000 0.800
#> ERR342862 1 0.517 0.658 0.620 0 0 0.176 0.000 0.204
#> ERR342894 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342884 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342891 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342890 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342836 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342879 6 0.310 0.914 0.016 0 0 0.184 0.000 0.800
#> ERR342848 6 0.279 0.747 0.200 0 0 0.000 0.000 0.800
#> ERR342861 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342814 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342870 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342901 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342908 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342815 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342897 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342833 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342817 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342810 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342867 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342847 1 0.396 0.778 0.748 0 0 0.040 0.008 0.204
#> ERR342855 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342851 6 0.338 0.917 0.044 0 0 0.156 0.000 0.800
#> ERR342813 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342883 6 0.298 0.905 0.008 0 0 0.192 0.000 0.800
#> ERR342856 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342822 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342892 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342842 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342902 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342900 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342888 5 0.000 1.000 0.000 0 0 0.000 1.000 0.000
#> ERR342812 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342853 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342866 1 0.525 0.664 0.624 0 0 0.168 0.004 0.204
#> ERR342820 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342895 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342825 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342826 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342875 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342834 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342898 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342886 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342838 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342882 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342807 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342873 6 0.341 0.816 0.152 0 0 0.048 0.000 0.800
#> ERR342844 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342874 1 0.506 0.676 0.636 0 0 0.164 0.000 0.200
#> ERR342893 6 0.324 0.920 0.028 0 0 0.172 0.000 0.800
#> ERR342859 3 0.000 1.000 0.000 0 1 0.000 0.000 0.000
#> ERR342830 2 0.000 1.000 0.000 1 0 0.000 0.000 0.000
#> ERR342880 6 0.305 0.910 0.012 0 0 0.188 0.000 0.800
#> ERR342887 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342854 1 0.000 0.901 1.000 0 0 0.000 0.000 0.000
#> ERR342904 4 0.000 1.000 0.000 0 0 1.000 0.000 0.000
#> ERR342881 1 0.483 0.705 0.664 0 0 0.136 0.000 0.200
#> ERR342858 6 0.324 0.920 0.028 0 0 0.172 0.000 0.800
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "mclust"]
# you can also extract it by
# res = res_list["MAD:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.988 0.990 0.2898 0.717 0.717
#> 3 3 0.405 0.758 0.796 1.0765 0.733 0.631
#> 4 4 0.595 0.603 0.779 0.2017 0.652 0.343
#> 5 5 0.702 0.842 0.800 0.0521 0.818 0.452
#> 6 6 0.834 0.878 0.927 0.0723 0.950 0.786
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 0.988 1.000 0.000
#> ERR342843 1 0.000 0.988 1.000 0.000
#> ERR342896 2 0.000 1.000 0.000 1.000
#> ERR342827 1 0.000 0.988 1.000 0.000
#> ERR342871 1 0.163 0.985 0.976 0.024
#> ERR342863 1 0.000 0.988 1.000 0.000
#> ERR342839 1 0.000 0.988 1.000 0.000
#> ERR342906 1 0.163 0.985 0.976 0.024
#> ERR342905 1 0.000 0.988 1.000 0.000
#> ERR342816 1 0.163 0.985 0.976 0.024
#> ERR342865 1 0.000 0.988 1.000 0.000
#> ERR342824 1 0.388 0.938 0.924 0.076
#> ERR342841 1 0.000 0.988 1.000 0.000
#> ERR342835 1 0.000 0.988 1.000 0.000
#> ERR342899 1 0.000 0.988 1.000 0.000
#> ERR342829 2 0.000 1.000 0.000 1.000
#> ERR342850 1 0.163 0.985 0.976 0.024
#> ERR342849 1 0.000 0.988 1.000 0.000
#> ERR342811 1 0.163 0.985 0.976 0.024
#> ERR342837 1 0.000 0.988 1.000 0.000
#> ERR342857 1 0.163 0.985 0.976 0.024
#> ERR342869 1 0.163 0.985 0.976 0.024
#> ERR342903 2 0.000 1.000 0.000 1.000
#> ERR342819 1 0.000 0.988 1.000 0.000
#> ERR342885 1 0.163 0.985 0.976 0.024
#> ERR342889 1 0.000 0.988 1.000 0.000
#> ERR342864 1 0.163 0.985 0.976 0.024
#> ERR342860 1 0.000 0.988 1.000 0.000
#> ERR342808 1 0.163 0.985 0.976 0.024
#> ERR342823 1 0.388 0.938 0.924 0.076
#> ERR342907 1 0.000 0.988 1.000 0.000
#> ERR342852 1 0.163 0.985 0.976 0.024
#> ERR342832 1 0.000 0.988 1.000 0.000
#> ERR342868 1 0.000 0.988 1.000 0.000
#> ERR342821 1 0.163 0.985 0.976 0.024
#> ERR342878 1 0.000 0.988 1.000 0.000
#> ERR342876 2 0.000 1.000 0.000 1.000
#> ERR342809 2 0.000 1.000 0.000 1.000
#> ERR342846 1 0.163 0.985 0.976 0.024
#> ERR342872 1 0.000 0.988 1.000 0.000
#> ERR342828 1 0.000 0.988 1.000 0.000
#> ERR342840 1 0.000 0.988 1.000 0.000
#> ERR342831 1 0.000 0.988 1.000 0.000
#> ERR342818 1 0.163 0.985 0.976 0.024
#> ERR342862 1 0.000 0.988 1.000 0.000
#> ERR342894 1 0.000 0.988 1.000 0.000
#> ERR342884 1 0.000 0.988 1.000 0.000
#> ERR342891 2 0.000 1.000 0.000 1.000
#> ERR342890 1 0.000 0.988 1.000 0.000
#> ERR342836 1 0.000 0.988 1.000 0.000
#> ERR342879 1 0.163 0.985 0.976 0.024
#> ERR342848 1 0.163 0.985 0.976 0.024
#> ERR342861 2 0.000 1.000 0.000 1.000
#> ERR342814 1 0.000 0.988 1.000 0.000
#> ERR342870 1 0.163 0.985 0.976 0.024
#> ERR342901 2 0.000 1.000 0.000 1.000
#> ERR342908 1 0.163 0.985 0.976 0.024
#> ERR342815 1 0.000 0.988 1.000 0.000
#> ERR342897 1 0.163 0.985 0.976 0.024
#> ERR342833 1 0.000 0.988 1.000 0.000
#> ERR342817 1 0.163 0.985 0.976 0.024
#> ERR342810 1 0.000 0.988 1.000 0.000
#> ERR342867 1 0.163 0.985 0.976 0.024
#> ERR342847 1 0.000 0.988 1.000 0.000
#> ERR342855 2 0.000 1.000 0.000 1.000
#> ERR342851 1 0.163 0.985 0.976 0.024
#> ERR342813 1 0.000 0.988 1.000 0.000
#> ERR342883 1 0.163 0.985 0.976 0.024
#> ERR342856 1 0.163 0.985 0.976 0.024
#> ERR342822 1 0.000 0.988 1.000 0.000
#> ERR342892 2 0.000 1.000 0.000 1.000
#> ERR342842 2 0.000 1.000 0.000 1.000
#> ERR342902 1 0.000 0.988 1.000 0.000
#> ERR342900 1 0.000 0.988 1.000 0.000
#> ERR342888 1 0.000 0.988 1.000 0.000
#> ERR342812 2 0.000 1.000 0.000 1.000
#> ERR342853 1 0.000 0.988 1.000 0.000
#> ERR342866 1 0.000 0.988 1.000 0.000
#> ERR342820 1 0.163 0.985 0.976 0.024
#> ERR342895 2 0.000 1.000 0.000 1.000
#> ERR342825 1 0.163 0.985 0.976 0.024
#> ERR342826 1 0.163 0.985 0.976 0.024
#> ERR342875 1 0.000 0.988 1.000 0.000
#> ERR342834 1 0.163 0.985 0.976 0.024
#> ERR342898 1 0.163 0.985 0.976 0.024
#> ERR342886 1 0.000 0.988 1.000 0.000
#> ERR342838 2 0.000 1.000 0.000 1.000
#> ERR342882 2 0.000 1.000 0.000 1.000
#> ERR342807 1 0.000 0.988 1.000 0.000
#> ERR342873 1 0.163 0.985 0.976 0.024
#> ERR342844 1 0.163 0.985 0.976 0.024
#> ERR342874 1 0.000 0.988 1.000 0.000
#> ERR342893 1 0.163 0.985 0.976 0.024
#> ERR342859 1 0.163 0.985 0.976 0.024
#> ERR342830 1 0.000 0.988 1.000 0.000
#> ERR342880 1 0.163 0.985 0.976 0.024
#> ERR342887 2 0.000 1.000 0.000 1.000
#> ERR342854 2 0.000 1.000 0.000 1.000
#> ERR342904 1 0.163 0.985 0.976 0.024
#> ERR342881 1 0.000 0.988 1.000 0.000
#> ERR342858 1 0.163 0.985 0.976 0.024
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342843 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342896 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342827 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342871 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342863 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342839 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342906 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342905 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342816 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342865 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342824 1 0.5986 0.692 0.736 0.024 0.240
#> ERR342841 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342835 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342899 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342829 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342850 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342849 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342811 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342837 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342857 3 0.0848 0.994 0.008 0.008 0.984
#> ERR342869 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342903 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342819 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342885 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342889 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342864 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342860 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342808 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342823 1 0.5986 0.692 0.736 0.024 0.240
#> ERR342907 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342852 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342832 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342868 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342821 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342878 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342876 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342809 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342846 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342872 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342828 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342840 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342831 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342818 2 0.9636 0.583 0.284 0.468 0.248
#> ERR342862 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342894 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342884 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342891 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342890 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342836 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342879 2 0.9636 0.583 0.284 0.468 0.248
#> ERR342848 2 0.9636 0.583 0.284 0.468 0.248
#> ERR342861 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342814 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342870 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342901 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342908 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342815 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342897 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342833 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342817 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342810 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342867 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342847 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342855 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342851 2 0.9636 0.583 0.284 0.468 0.248
#> ERR342813 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342883 2 0.9636 0.583 0.284 0.468 0.248
#> ERR342856 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342822 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342892 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342842 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342902 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342900 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342888 2 0.5365 0.659 0.252 0.744 0.004
#> ERR342812 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342853 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342866 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342820 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342895 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342825 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342826 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342875 2 0.4834 0.661 0.004 0.792 0.204
#> ERR342834 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342898 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342886 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342838 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342882 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342807 2 0.6107 0.703 0.100 0.784 0.116
#> ERR342873 2 0.9636 0.583 0.284 0.468 0.248
#> ERR342844 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342874 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342893 2 0.9636 0.583 0.284 0.468 0.248
#> ERR342859 2 0.6057 0.548 0.004 0.656 0.340
#> ERR342830 2 0.2056 0.713 0.024 0.952 0.024
#> ERR342880 2 0.9636 0.583 0.284 0.468 0.248
#> ERR342887 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342854 1 0.2356 0.971 0.928 0.000 0.072
#> ERR342904 3 0.0661 1.000 0.008 0.004 0.988
#> ERR342881 2 0.6451 0.574 0.436 0.560 0.004
#> ERR342858 2 0.9636 0.583 0.284 0.468 0.248
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342843 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342896 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342827 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342871 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342863 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342839 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342906 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342905 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342816 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342865 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342824 1 0.2101 0.731 0.928 0.000 0.012 0.060
#> ERR342841 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342835 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342899 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342829 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342850 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342849 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342811 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342837 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342857 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342869 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342903 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342819 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342885 3 0.7493 0.180 0.000 0.200 0.480 0.320
#> ERR342889 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342864 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342860 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342808 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342823 1 0.2101 0.731 0.928 0.000 0.012 0.060
#> ERR342907 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342852 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342832 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342868 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342821 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342878 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342876 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342846 3 0.7469 0.181 0.000 0.200 0.488 0.312
#> ERR342872 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342828 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342840 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342831 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342818 1 0.8714 0.247 0.420 0.224 0.048 0.308
#> ERR342862 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342894 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342884 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342891 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342890 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342836 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342879 1 0.8714 0.247 0.420 0.224 0.048 0.308
#> ERR342848 1 0.8709 0.255 0.428 0.232 0.048 0.292
#> ERR342861 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342814 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342870 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342901 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342908 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342815 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342897 3 0.7469 0.181 0.000 0.200 0.488 0.312
#> ERR342833 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342817 3 0.7493 0.180 0.000 0.200 0.480 0.320
#> ERR342810 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342867 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342847 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342855 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342851 1 0.8714 0.247 0.420 0.224 0.048 0.308
#> ERR342813 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342883 1 0.8714 0.247 0.420 0.224 0.048 0.308
#> ERR342856 3 0.7469 0.181 0.000 0.200 0.488 0.312
#> ERR342822 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342892 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342902 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342900 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342888 3 0.2197 0.563 0.024 0.048 0.928 0.000
#> ERR342812 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342853 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342866 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342820 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342895 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342825 3 0.7493 0.180 0.000 0.200 0.480 0.320
#> ERR342826 3 0.7493 0.180 0.000 0.200 0.480 0.320
#> ERR342875 2 0.3088 0.875 0.008 0.864 0.000 0.128
#> ERR342834 3 0.7493 0.180 0.000 0.200 0.480 0.320
#> ERR342898 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342886 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342838 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342807 4 0.7403 0.437 0.120 0.384 0.012 0.484
#> ERR342873 1 0.8714 0.247 0.420 0.224 0.048 0.308
#> ERR342844 4 0.0000 0.787 0.000 0.000 0.000 1.000
#> ERR342874 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342893 1 0.8714 0.247 0.420 0.224 0.048 0.308
#> ERR342859 3 0.7469 0.181 0.000 0.200 0.488 0.312
#> ERR342830 2 0.2153 0.885 0.008 0.936 0.036 0.020
#> ERR342880 1 0.8714 0.247 0.420 0.224 0.048 0.308
#> ERR342887 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.765 1.000 0.000 0.000 0.000
#> ERR342904 4 0.0336 0.786 0.000 0.000 0.008 0.992
#> ERR342881 3 0.6044 0.301 0.044 0.428 0.528 0.000
#> ERR342858 1 0.8714 0.247 0.420 0.224 0.048 0.308
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342843 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342896 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342871 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342863 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342839 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342906 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342905 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342816 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342865 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342824 1 0.0609 0.971 0.980 0.020 0.000 0.000 0.000
#> ERR342841 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342835 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342899 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342829 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342849 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342811 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342837 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342857 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342869 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342903 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342885 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342889 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342864 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342860 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342808 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342823 1 0.0609 0.971 0.980 0.020 0.000 0.000 0.000
#> ERR342907 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342852 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342832 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342868 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342821 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342878 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342876 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342872 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342828 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342840 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342831 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342818 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
#> ERR342862 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342894 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342884 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342891 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342836 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342879 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
#> ERR342848 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
#> ERR342861 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342870 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342901 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342815 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342897 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342833 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342817 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342810 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342867 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342847 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342855 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342851 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
#> ERR342813 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342883 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
#> ERR342856 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342822 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342892 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342900 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342888 5 0.3930 0.920 0.000 0.152 0.056 0.000 0.792
#> ERR342812 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342866 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342820 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342895 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342826 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342875 2 0.0566 0.698 0.004 0.984 0.000 0.012 0.000
#> ERR342834 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342898 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342886 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342838 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.5583 0.590 0.000 0.640 0.000 0.208 0.152
#> ERR342873 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
#> ERR342844 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342874 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342893 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
#> ERR342859 3 0.0404 1.000 0.000 0.000 0.988 0.012 0.000
#> ERR342830 2 0.2516 0.659 0.000 0.860 0.000 0.000 0.140
#> ERR342880 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
#> ERR342887 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.997 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.3109 1.000 0.000 0.000 0.200 0.800 0.000
#> ERR342881 5 0.3242 0.914 0.000 0.216 0.000 0.000 0.784
#> ERR342858 2 0.8151 0.498 0.064 0.524 0.200 0.112 0.100
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342843 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342896 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342827 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342871 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342863 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342839 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342906 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342905 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342816 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342865 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342824 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342841 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342835 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342899 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342829 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342850 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342849 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342811 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342837 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342857 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342869 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342903 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342819 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342885 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342889 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342864 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342860 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342808 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342823 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342907 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342852 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342832 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342868 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342821 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342878 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342876 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342809 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342846 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342872 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342828 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342840 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342831 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342818 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
#> ERR342862 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342894 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342884 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342891 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342890 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342836 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342879 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
#> ERR342848 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
#> ERR342861 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342814 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342870 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342901 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342908 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342815 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342897 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342833 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342817 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342810 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342867 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342847 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342855 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342851 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
#> ERR342813 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342883 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
#> ERR342856 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342822 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342892 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342842 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342902 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342900 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342888 5 0.000 0.876 0.000 0.000 0 0.000 1.000 0.000
#> ERR342812 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342853 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342866 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342820 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342895 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342825 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342826 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342875 2 0.230 0.687 0.000 0.856 0 0.000 0.000 0.144
#> ERR342834 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342898 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342886 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342838 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342882 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342807 6 0.000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342873 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
#> ERR342844 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342874 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342893 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
#> ERR342859 3 0.000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342830 2 0.000 0.745 0.000 1.000 0 0.000 0.000 0.000
#> ERR342880 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
#> ERR342887 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342854 1 0.000 1.000 1.000 0.000 0 0.000 0.000 0.000
#> ERR342904 4 0.000 1.000 0.000 0.000 0 1.000 0.000 0.000
#> ERR342881 5 0.273 0.870 0.000 0.192 0 0.000 0.808 0.000
#> ERR342858 2 0.593 0.477 0.016 0.512 0 0.316 0.156 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "NMF"]
# you can also extract it by
# res = res_list["MAD:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.772 0.945 0.972 0.4639 0.531 0.531
#> 3 3 0.643 0.756 0.883 0.3866 0.740 0.542
#> 4 4 0.699 0.853 0.879 0.1483 0.748 0.403
#> 5 5 0.892 0.930 0.941 0.0565 0.902 0.652
#> 6 6 0.818 0.798 0.822 0.0426 0.913 0.652
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 0.978 1.000 0.000
#> ERR342843 1 0.000 0.978 1.000 0.000
#> ERR342896 1 0.000 0.978 1.000 0.000
#> ERR342827 2 0.000 0.955 0.000 1.000
#> ERR342871 1 0.000 0.978 1.000 0.000
#> ERR342863 2 0.000 0.955 0.000 1.000
#> ERR342839 1 0.000 0.978 1.000 0.000
#> ERR342906 1 0.482 0.884 0.896 0.104
#> ERR342905 2 0.000 0.955 0.000 1.000
#> ERR342816 1 0.482 0.884 0.896 0.104
#> ERR342865 2 0.000 0.955 0.000 1.000
#> ERR342824 1 0.000 0.978 1.000 0.000
#> ERR342841 2 0.000 0.955 0.000 1.000
#> ERR342835 1 0.000 0.978 1.000 0.000
#> ERR342899 2 0.000 0.955 0.000 1.000
#> ERR342829 1 0.000 0.978 1.000 0.000
#> ERR342850 1 0.000 0.978 1.000 0.000
#> ERR342849 2 0.000 0.955 0.000 1.000
#> ERR342811 1 0.000 0.978 1.000 0.000
#> ERR342837 1 0.000 0.978 1.000 0.000
#> ERR342857 1 0.767 0.720 0.776 0.224
#> ERR342869 1 0.000 0.978 1.000 0.000
#> ERR342903 1 0.000 0.978 1.000 0.000
#> ERR342819 1 0.000 0.978 1.000 0.000
#> ERR342885 2 0.722 0.790 0.200 0.800
#> ERR342889 2 0.000 0.955 0.000 1.000
#> ERR342864 1 0.506 0.875 0.888 0.112
#> ERR342860 2 0.000 0.955 0.000 1.000
#> ERR342808 1 0.000 0.978 1.000 0.000
#> ERR342823 1 0.000 0.978 1.000 0.000
#> ERR342907 2 0.000 0.955 0.000 1.000
#> ERR342852 1 0.753 0.733 0.784 0.216
#> ERR342832 2 0.000 0.955 0.000 1.000
#> ERR342868 1 0.000 0.978 1.000 0.000
#> ERR342821 1 0.456 0.892 0.904 0.096
#> ERR342878 2 0.000 0.955 0.000 1.000
#> ERR342876 1 0.000 0.978 1.000 0.000
#> ERR342809 1 0.000 0.978 1.000 0.000
#> ERR342846 2 0.552 0.867 0.128 0.872
#> ERR342872 2 0.000 0.955 0.000 1.000
#> ERR342828 2 0.000 0.955 0.000 1.000
#> ERR342840 1 0.000 0.978 1.000 0.000
#> ERR342831 1 0.000 0.978 1.000 0.000
#> ERR342818 1 0.000 0.978 1.000 0.000
#> ERR342862 1 0.000 0.978 1.000 0.000
#> ERR342894 1 0.000 0.978 1.000 0.000
#> ERR342884 2 0.000 0.955 0.000 1.000
#> ERR342891 1 0.000 0.978 1.000 0.000
#> ERR342890 1 0.000 0.978 1.000 0.000
#> ERR342836 2 0.000 0.955 0.000 1.000
#> ERR342879 1 0.000 0.978 1.000 0.000
#> ERR342848 1 0.000 0.978 1.000 0.000
#> ERR342861 1 0.000 0.978 1.000 0.000
#> ERR342814 2 0.000 0.955 0.000 1.000
#> ERR342870 1 0.000 0.978 1.000 0.000
#> ERR342901 1 0.000 0.978 1.000 0.000
#> ERR342908 1 0.000 0.978 1.000 0.000
#> ERR342815 2 0.000 0.955 0.000 1.000
#> ERR342897 2 0.625 0.841 0.156 0.844
#> ERR342833 2 0.000 0.955 0.000 1.000
#> ERR342817 2 0.706 0.800 0.192 0.808
#> ERR342810 2 0.000 0.955 0.000 1.000
#> ERR342867 1 0.482 0.884 0.896 0.104
#> ERR342847 1 0.000 0.978 1.000 0.000
#> ERR342855 1 0.000 0.978 1.000 0.000
#> ERR342851 1 0.000 0.978 1.000 0.000
#> ERR342813 1 0.000 0.978 1.000 0.000
#> ERR342883 1 0.000 0.978 1.000 0.000
#> ERR342856 2 0.563 0.864 0.132 0.868
#> ERR342822 2 0.000 0.955 0.000 1.000
#> ERR342892 1 0.000 0.978 1.000 0.000
#> ERR342842 1 0.000 0.978 1.000 0.000
#> ERR342902 2 0.000 0.955 0.000 1.000
#> ERR342900 2 0.000 0.955 0.000 1.000
#> ERR342888 1 0.000 0.978 1.000 0.000
#> ERR342812 1 0.000 0.978 1.000 0.000
#> ERR342853 2 0.000 0.955 0.000 1.000
#> ERR342866 1 0.000 0.978 1.000 0.000
#> ERR342820 1 0.000 0.978 1.000 0.000
#> ERR342895 1 0.000 0.978 1.000 0.000
#> ERR342825 2 0.722 0.790 0.200 0.800
#> ERR342826 2 0.680 0.814 0.180 0.820
#> ERR342875 2 0.000 0.955 0.000 1.000
#> ERR342834 2 0.722 0.790 0.200 0.800
#> ERR342898 1 0.634 0.816 0.840 0.160
#> ERR342886 2 0.000 0.955 0.000 1.000
#> ERR342838 1 0.000 0.978 1.000 0.000
#> ERR342882 1 0.000 0.978 1.000 0.000
#> ERR342807 2 0.000 0.955 0.000 1.000
#> ERR342873 1 0.000 0.978 1.000 0.000
#> ERR342844 1 0.671 0.794 0.824 0.176
#> ERR342874 1 0.000 0.978 1.000 0.000
#> ERR342893 1 0.000 0.978 1.000 0.000
#> ERR342859 2 0.574 0.860 0.136 0.864
#> ERR342830 2 0.000 0.955 0.000 1.000
#> ERR342880 1 0.000 0.978 1.000 0.000
#> ERR342887 1 0.000 0.978 1.000 0.000
#> ERR342854 1 0.000 0.978 1.000 0.000
#> ERR342904 1 0.000 0.978 1.000 0.000
#> ERR342881 1 0.000 0.978 1.000 0.000
#> ERR342858 1 0.000 0.978 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 3 0.5497 0.59731 0.292 0.000 0.708
#> ERR342843 3 0.3551 0.72993 0.132 0.000 0.868
#> ERR342896 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342827 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342871 1 0.6267 -0.07353 0.548 0.000 0.452
#> ERR342863 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342839 3 0.5098 0.64873 0.248 0.000 0.752
#> ERR342906 3 0.5397 0.67553 0.280 0.000 0.720
#> ERR342905 2 0.2356 0.93968 0.000 0.928 0.072
#> ERR342816 3 0.5591 0.65236 0.304 0.000 0.696
#> ERR342865 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342824 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342841 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342835 1 0.4702 0.67558 0.788 0.000 0.212
#> ERR342899 2 0.2711 0.93280 0.000 0.912 0.088
#> ERR342829 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342850 1 0.6286 -0.11257 0.536 0.000 0.464
#> ERR342849 2 0.2796 0.93014 0.000 0.908 0.092
#> ERR342811 1 0.6026 0.20008 0.624 0.000 0.376
#> ERR342837 1 0.4654 0.67920 0.792 0.000 0.208
#> ERR342857 3 0.4399 0.72986 0.188 0.000 0.812
#> ERR342869 3 0.6111 0.48624 0.396 0.000 0.604
#> ERR342903 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342819 1 0.4750 0.67098 0.784 0.000 0.216
#> ERR342885 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342889 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342864 3 0.6627 0.60589 0.336 0.020 0.644
#> ERR342860 2 0.3267 0.90940 0.000 0.884 0.116
#> ERR342808 1 0.5810 0.32215 0.664 0.000 0.336
#> ERR342823 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342907 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342852 3 0.6357 0.65437 0.296 0.020 0.684
#> ERR342832 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342868 3 0.3340 0.73337 0.120 0.000 0.880
#> ERR342821 3 0.5810 0.61273 0.336 0.000 0.664
#> ERR342878 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342876 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342809 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342846 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342872 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342828 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342840 1 0.4750 0.67098 0.784 0.000 0.216
#> ERR342831 3 0.5650 0.56485 0.312 0.000 0.688
#> ERR342818 1 0.0237 0.84464 0.996 0.000 0.004
#> ERR342862 1 0.4750 0.67098 0.784 0.000 0.216
#> ERR342894 3 0.4750 0.67909 0.216 0.000 0.784
#> ERR342884 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342891 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342890 3 0.5254 0.63275 0.264 0.000 0.736
#> ERR342836 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342879 1 0.0237 0.84464 0.996 0.000 0.004
#> ERR342848 1 0.0237 0.84464 0.996 0.000 0.004
#> ERR342861 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342814 2 0.2625 0.93513 0.000 0.916 0.084
#> ERR342870 3 0.6252 0.35986 0.444 0.000 0.556
#> ERR342901 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342908 1 0.5706 0.36208 0.680 0.000 0.320
#> ERR342815 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342897 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342833 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342817 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342810 2 0.2448 0.93842 0.000 0.924 0.076
#> ERR342867 3 0.5733 0.63080 0.324 0.000 0.676
#> ERR342847 1 0.4750 0.67098 0.784 0.000 0.216
#> ERR342855 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342851 1 0.0237 0.84464 0.996 0.000 0.004
#> ERR342813 3 0.4654 0.68173 0.208 0.000 0.792
#> ERR342883 1 0.0237 0.84464 0.996 0.000 0.004
#> ERR342856 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342822 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342892 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342842 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342902 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342900 2 0.2625 0.93513 0.000 0.916 0.084
#> ERR342888 3 0.3340 0.73349 0.120 0.000 0.880
#> ERR342812 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342853 2 0.2356 0.93968 0.000 0.928 0.072
#> ERR342866 1 0.4750 0.67098 0.784 0.000 0.216
#> ERR342820 1 0.6308 -0.20602 0.508 0.000 0.492
#> ERR342895 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342825 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342826 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342875 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342834 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342898 3 0.5982 0.62398 0.328 0.004 0.668
#> ERR342886 2 0.3340 0.90516 0.000 0.880 0.120
#> ERR342838 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342882 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342807 2 0.0000 0.96622 0.000 1.000 0.000
#> ERR342873 1 0.0237 0.84464 0.996 0.000 0.004
#> ERR342844 3 0.5178 0.69333 0.256 0.000 0.744
#> ERR342874 1 0.4750 0.67098 0.784 0.000 0.216
#> ERR342893 1 0.0237 0.84464 0.996 0.000 0.004
#> ERR342859 3 0.2486 0.75087 0.008 0.060 0.932
#> ERR342830 2 0.3038 0.92072 0.000 0.896 0.104
#> ERR342880 1 0.0237 0.84464 0.996 0.000 0.004
#> ERR342887 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342854 1 0.0000 0.84562 1.000 0.000 0.000
#> ERR342904 1 0.6235 -0.00503 0.564 0.000 0.436
#> ERR342881 1 0.4702 0.67558 0.788 0.000 0.212
#> ERR342858 1 0.0237 0.84464 0.996 0.000 0.004
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 3 0.0927 0.874 0.008 0.000 0.976 0.016
#> ERR342843 3 0.0707 0.871 0.000 0.000 0.980 0.020
#> ERR342896 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342827 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342871 4 0.5410 0.809 0.192 0.000 0.080 0.728
#> ERR342863 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342839 3 0.0895 0.872 0.004 0.000 0.976 0.020
#> ERR342906 4 0.4701 0.827 0.164 0.000 0.056 0.780
#> ERR342905 3 0.3870 0.812 0.004 0.208 0.788 0.000
#> ERR342816 4 0.4996 0.819 0.192 0.000 0.056 0.752
#> ERR342865 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342824 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342841 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342835 3 0.2494 0.872 0.048 0.000 0.916 0.036
#> ERR342899 3 0.4018 0.800 0.004 0.224 0.772 0.000
#> ERR342829 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342850 4 0.5332 0.813 0.184 0.000 0.080 0.736
#> ERR342849 3 0.4122 0.787 0.004 0.236 0.760 0.000
#> ERR342811 4 0.5850 0.769 0.244 0.000 0.080 0.676
#> ERR342837 3 0.2565 0.870 0.056 0.000 0.912 0.032
#> ERR342857 4 0.3796 0.824 0.096 0.000 0.056 0.848
#> ERR342869 4 0.4581 0.825 0.120 0.000 0.080 0.800
#> ERR342903 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342819 3 0.2494 0.872 0.048 0.000 0.916 0.036
#> ERR342885 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342889 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342864 4 0.5489 0.792 0.240 0.000 0.060 0.700
#> ERR342860 3 0.4053 0.796 0.004 0.228 0.768 0.000
#> ERR342808 4 0.6180 0.704 0.296 0.000 0.080 0.624
#> ERR342823 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342907 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342852 4 0.5221 0.812 0.208 0.000 0.060 0.732
#> ERR342832 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342868 3 0.0817 0.869 0.000 0.000 0.976 0.024
#> ERR342821 4 0.5426 0.798 0.232 0.000 0.060 0.708
#> ERR342878 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342876 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342809 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342846 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342872 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342828 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342840 3 0.2494 0.872 0.048 0.000 0.916 0.036
#> ERR342831 3 0.0672 0.875 0.008 0.000 0.984 0.008
#> ERR342818 1 0.5593 0.721 0.708 0.000 0.212 0.080
#> ERR342862 3 0.2494 0.872 0.048 0.000 0.916 0.036
#> ERR342894 3 0.0895 0.872 0.004 0.000 0.976 0.020
#> ERR342884 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342891 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342890 3 0.0895 0.872 0.004 0.000 0.976 0.020
#> ERR342836 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342879 1 0.6065 0.668 0.644 0.000 0.276 0.080
#> ERR342848 1 0.4469 0.763 0.808 0.000 0.112 0.080
#> ERR342861 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342814 3 0.4053 0.796 0.004 0.228 0.768 0.000
#> ERR342870 4 0.4841 0.824 0.140 0.000 0.080 0.780
#> ERR342901 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342908 4 0.6242 0.687 0.308 0.000 0.080 0.612
#> ERR342815 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342897 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342833 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342817 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342810 3 0.3831 0.814 0.004 0.204 0.792 0.000
#> ERR342867 4 0.5321 0.801 0.228 0.000 0.056 0.716
#> ERR342847 3 0.2494 0.872 0.048 0.000 0.916 0.036
#> ERR342855 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342851 1 0.5989 0.682 0.656 0.000 0.264 0.080
#> ERR342813 3 0.0895 0.872 0.004 0.000 0.976 0.020
#> ERR342883 1 0.5935 0.690 0.664 0.000 0.256 0.080
#> ERR342856 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342822 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342892 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342842 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342902 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342900 3 0.4343 0.751 0.004 0.264 0.732 0.000
#> ERR342888 3 0.0817 0.869 0.000 0.000 0.976 0.024
#> ERR342812 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342853 3 0.3908 0.809 0.004 0.212 0.784 0.000
#> ERR342866 3 0.2494 0.872 0.048 0.000 0.916 0.036
#> ERR342820 4 0.5143 0.819 0.172 0.000 0.076 0.752
#> ERR342895 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342825 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342826 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342875 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342834 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342898 4 0.5361 0.804 0.224 0.000 0.060 0.716
#> ERR342886 3 0.3945 0.806 0.004 0.216 0.780 0.000
#> ERR342838 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342882 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342807 2 0.0000 1.000 0.000 1.000 0.000 0.000
#> ERR342873 1 0.5694 0.715 0.696 0.000 0.224 0.080
#> ERR342844 4 0.4541 0.829 0.144 0.000 0.060 0.796
#> ERR342874 3 0.2494 0.872 0.048 0.000 0.916 0.036
#> ERR342893 1 0.6065 0.669 0.644 0.000 0.276 0.080
#> ERR342859 4 0.2011 0.774 0.000 0.000 0.080 0.920
#> ERR342830 3 0.3870 0.812 0.004 0.208 0.788 0.000
#> ERR342880 1 0.5879 0.697 0.672 0.000 0.248 0.080
#> ERR342887 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342854 1 0.0188 0.883 0.996 0.000 0.004 0.000
#> ERR342904 4 0.5371 0.810 0.188 0.000 0.080 0.732
#> ERR342881 3 0.2578 0.871 0.052 0.000 0.912 0.036
#> ERR342858 1 0.5727 0.712 0.692 0.000 0.228 0.080
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.2069 0.838 0.000 0.000 0.012 0.076 0.912
#> ERR342843 5 0.2270 0.836 0.000 0.000 0.020 0.076 0.904
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342871 4 0.0807 0.964 0.012 0.000 0.012 0.976 0.000
#> ERR342863 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342839 5 0.2270 0.836 0.000 0.000 0.020 0.076 0.904
#> ERR342906 4 0.1074 0.962 0.016 0.000 0.012 0.968 0.004
#> ERR342905 5 0.2624 0.815 0.000 0.116 0.000 0.012 0.872
#> ERR342816 4 0.1121 0.962 0.016 0.004 0.008 0.968 0.004
#> ERR342865 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342835 5 0.3519 0.793 0.008 0.000 0.000 0.216 0.776
#> ERR342899 5 0.2674 0.812 0.000 0.120 0.000 0.012 0.868
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.0807 0.964 0.012 0.000 0.012 0.976 0.000
#> ERR342849 5 0.2674 0.812 0.000 0.120 0.000 0.012 0.868
#> ERR342811 4 0.0807 0.964 0.012 0.000 0.012 0.976 0.000
#> ERR342837 5 0.3551 0.790 0.008 0.000 0.000 0.220 0.772
#> ERR342857 4 0.1235 0.960 0.012 0.004 0.016 0.964 0.004
#> ERR342869 4 0.0854 0.964 0.008 0.000 0.012 0.976 0.004
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.3519 0.793 0.008 0.000 0.000 0.216 0.776
#> ERR342885 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342889 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342864 4 0.1467 0.955 0.016 0.016 0.008 0.956 0.004
#> ERR342860 5 0.2522 0.816 0.000 0.108 0.000 0.012 0.880
#> ERR342808 4 0.0798 0.964 0.016 0.000 0.008 0.976 0.000
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342852 4 0.1467 0.955 0.016 0.016 0.008 0.956 0.004
#> ERR342832 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342868 5 0.2270 0.836 0.000 0.000 0.020 0.076 0.904
#> ERR342821 4 0.1121 0.962 0.016 0.004 0.008 0.968 0.004
#> ERR342878 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342872 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342828 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342840 5 0.3487 0.796 0.008 0.000 0.000 0.212 0.780
#> ERR342831 5 0.2069 0.838 0.000 0.000 0.012 0.076 0.912
#> ERR342818 4 0.1444 0.944 0.012 0.000 0.000 0.948 0.040
#> ERR342862 5 0.3809 0.752 0.008 0.000 0.000 0.256 0.736
#> ERR342894 5 0.2270 0.836 0.000 0.000 0.020 0.076 0.904
#> ERR342884 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.2270 0.836 0.000 0.000 0.020 0.076 0.904
#> ERR342836 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342879 4 0.1569 0.942 0.008 0.004 0.000 0.944 0.044
#> ERR342848 4 0.1668 0.943 0.028 0.000 0.000 0.940 0.032
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342814 5 0.2674 0.812 0.000 0.120 0.000 0.012 0.868
#> ERR342870 4 0.0740 0.963 0.008 0.000 0.008 0.980 0.004
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.0798 0.964 0.016 0.000 0.008 0.976 0.000
#> ERR342815 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342897 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342833 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342817 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342810 5 0.2624 0.815 0.000 0.116 0.000 0.012 0.872
#> ERR342867 4 0.1248 0.960 0.016 0.008 0.008 0.964 0.004
#> ERR342847 5 0.3388 0.802 0.008 0.000 0.000 0.200 0.792
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.1569 0.942 0.008 0.004 0.000 0.944 0.044
#> ERR342813 5 0.2270 0.836 0.000 0.000 0.020 0.076 0.904
#> ERR342883 4 0.1569 0.942 0.008 0.004 0.000 0.944 0.044
#> ERR342856 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342822 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342900 5 0.2818 0.803 0.000 0.132 0.000 0.012 0.856
#> ERR342888 5 0.2270 0.836 0.000 0.000 0.020 0.076 0.904
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342853 5 0.2674 0.812 0.000 0.120 0.000 0.012 0.868
#> ERR342866 5 0.3487 0.796 0.008 0.000 0.000 0.212 0.780
#> ERR342820 4 0.0807 0.964 0.012 0.000 0.012 0.976 0.000
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342826 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342875 2 0.1121 0.969 0.000 0.956 0.000 0.000 0.044
#> ERR342834 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342898 4 0.1248 0.960 0.016 0.008 0.008 0.964 0.004
#> ERR342886 5 0.2574 0.816 0.000 0.112 0.000 0.012 0.876
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.0451 0.969 0.000 0.988 0.008 0.004 0.000
#> ERR342873 4 0.1444 0.944 0.012 0.000 0.000 0.948 0.040
#> ERR342844 4 0.1121 0.962 0.016 0.004 0.008 0.968 0.004
#> ERR342874 5 0.3809 0.752 0.008 0.000 0.000 0.256 0.736
#> ERR342893 4 0.1569 0.942 0.008 0.004 0.000 0.944 0.044
#> ERR342859 3 0.0510 1.000 0.000 0.000 0.984 0.016 0.000
#> ERR342830 5 0.2574 0.816 0.000 0.112 0.000 0.012 0.876
#> ERR342880 4 0.1492 0.943 0.008 0.004 0.000 0.948 0.040
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.0693 0.964 0.012 0.000 0.008 0.980 0.000
#> ERR342881 5 0.3861 0.741 0.008 0.000 0.000 0.264 0.728
#> ERR342858 4 0.1492 0.943 0.008 0.004 0.000 0.948 0.040
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342843 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342896 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342871 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342863 2 0.0146 0.6563 0.000 0.996 0.000 0.000 0.000 0.004
#> ERR342839 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342906 4 0.0870 0.8759 0.004 0.000 0.000 0.972 0.012 0.012
#> ERR342905 2 0.6101 0.0386 0.000 0.424 0.000 0.004 0.236 0.336
#> ERR342816 4 0.0870 0.8759 0.004 0.000 0.000 0.972 0.012 0.012
#> ERR342865 2 0.0146 0.6563 0.000 0.996 0.000 0.000 0.000 0.004
#> ERR342824 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342835 6 0.5411 0.9834 0.000 0.000 0.000 0.124 0.364 0.512
#> ERR342899 2 0.6053 0.0844 0.000 0.440 0.000 0.004 0.224 0.332
#> ERR342829 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342849 2 0.6053 0.0844 0.000 0.440 0.000 0.004 0.224 0.332
#> ERR342811 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342837 6 0.5411 0.9834 0.000 0.000 0.000 0.124 0.364 0.512
#> ERR342857 4 0.0870 0.8759 0.004 0.000 0.000 0.972 0.012 0.012
#> ERR342869 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342903 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342819 6 0.5425 0.9818 0.000 0.000 0.000 0.124 0.372 0.504
#> ERR342885 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342889 2 0.0146 0.6563 0.000 0.996 0.000 0.000 0.000 0.004
#> ERR342864 4 0.1053 0.8755 0.004 0.000 0.000 0.964 0.012 0.020
#> ERR342860 2 0.6082 0.0666 0.000 0.432 0.000 0.004 0.232 0.332
#> ERR342808 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342823 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342852 4 0.0964 0.8759 0.004 0.000 0.000 0.968 0.012 0.016
#> ERR342832 2 0.0146 0.6563 0.000 0.996 0.000 0.000 0.000 0.004
#> ERR342868 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342821 4 0.0870 0.8759 0.004 0.000 0.000 0.972 0.012 0.012
#> ERR342878 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342876 1 0.0146 0.9964 0.996 0.000 0.000 0.000 0.000 0.004
#> ERR342809 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342872 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342828 2 0.0000 0.6565 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342840 6 0.5432 0.9786 0.000 0.000 0.000 0.124 0.376 0.500
#> ERR342831 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342818 4 0.3641 0.7886 0.000 0.000 0.000 0.748 0.028 0.224
#> ERR342862 6 0.5434 0.9814 0.000 0.000 0.000 0.128 0.360 0.512
#> ERR342894 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342884 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342891 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342836 2 0.0146 0.6563 0.000 0.996 0.000 0.000 0.000 0.004
#> ERR342879 4 0.3614 0.7883 0.000 0.000 0.000 0.752 0.028 0.220
#> ERR342848 4 0.3915 0.7797 0.008 0.000 0.000 0.736 0.028 0.228
#> ERR342861 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.6053 0.0844 0.000 0.440 0.000 0.004 0.224 0.332
#> ERR342870 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342901 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342815 2 0.0000 0.6565 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342897 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342833 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342817 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342810 2 0.6101 0.0386 0.000 0.424 0.000 0.004 0.236 0.336
#> ERR342867 4 0.0870 0.8759 0.004 0.000 0.000 0.972 0.012 0.012
#> ERR342847 6 0.5380 0.9653 0.000 0.000 0.000 0.116 0.384 0.500
#> ERR342855 1 0.0146 0.9964 0.996 0.000 0.000 0.000 0.000 0.004
#> ERR342851 4 0.3641 0.7849 0.000 0.000 0.000 0.748 0.028 0.224
#> ERR342813 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342883 4 0.3511 0.7938 0.000 0.000 0.000 0.760 0.024 0.216
#> ERR342856 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342822 2 0.0000 0.6565 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342900 2 0.6005 0.1062 0.000 0.452 0.000 0.004 0.212 0.332
#> ERR342888 5 0.0622 1.0000 0.000 0.000 0.012 0.008 0.980 0.000
#> ERR342812 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.6053 0.0831 0.000 0.440 0.000 0.004 0.224 0.332
#> ERR342866 6 0.5432 0.9786 0.000 0.000 0.000 0.124 0.376 0.500
#> ERR342820 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342895 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342826 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342875 2 0.0000 0.6565 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342834 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342898 4 0.1053 0.8757 0.004 0.000 0.000 0.964 0.012 0.020
#> ERR342886 2 0.6073 0.0644 0.000 0.432 0.000 0.004 0.228 0.336
#> ERR342838 1 0.0146 0.9964 0.996 0.000 0.000 0.000 0.000 0.004
#> ERR342882 1 0.0000 0.9987 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.3349 0.5998 0.000 0.748 0.000 0.000 0.008 0.244
#> ERR342873 4 0.3614 0.7883 0.000 0.000 0.000 0.752 0.028 0.220
#> ERR342844 4 0.0964 0.8759 0.004 0.000 0.000 0.968 0.012 0.016
#> ERR342874 6 0.5434 0.9814 0.000 0.000 0.000 0.128 0.360 0.512
#> ERR342893 4 0.3641 0.7849 0.000 0.000 0.000 0.748 0.028 0.224
#> ERR342859 3 0.0000 1.0000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342830 2 0.6068 0.0747 0.000 0.436 0.000 0.004 0.228 0.332
#> ERR342880 4 0.3511 0.7938 0.000 0.000 0.000 0.760 0.024 0.216
#> ERR342887 1 0.0146 0.9964 0.996 0.000 0.000 0.000 0.000 0.004
#> ERR342854 1 0.0146 0.9964 0.996 0.000 0.000 0.000 0.000 0.004
#> ERR342904 4 0.1501 0.8661 0.000 0.000 0.000 0.924 0.000 0.076
#> ERR342881 6 0.5434 0.9814 0.000 0.000 0.000 0.128 0.360 0.512
#> ERR342858 4 0.3539 0.7938 0.000 0.000 0.000 0.756 0.024 0.220
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "hclust"]
# you can also extract it by
# res = res_list["ATC:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 4.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.820 0.897 0.958 0.3422 0.704 0.704
#> 3 3 0.718 0.768 0.834 0.6111 0.663 0.521
#> 4 4 0.770 0.914 0.932 0.2013 0.947 0.854
#> 5 5 0.800 0.854 0.862 0.1674 0.900 0.682
#> 6 6 0.832 0.522 0.698 0.0379 0.848 0.465
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 4
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.000 0.946 1.00 0.00
#> ERR342843 1 0.000 0.946 1.00 0.00
#> ERR342896 1 0.000 0.946 1.00 0.00
#> ERR342827 2 0.000 1.000 0.00 1.00
#> ERR342871 1 0.000 0.946 1.00 0.00
#> ERR342863 2 0.000 1.000 0.00 1.00
#> ERR342839 1 0.000 0.946 1.00 0.00
#> ERR342906 1 0.000 0.946 1.00 0.00
#> ERR342905 1 0.981 0.355 0.58 0.42
#> ERR342816 1 0.000 0.946 1.00 0.00
#> ERR342865 2 0.000 1.000 0.00 1.00
#> ERR342824 1 0.000 0.946 1.00 0.00
#> ERR342841 2 0.000 1.000 0.00 1.00
#> ERR342835 1 0.000 0.946 1.00 0.00
#> ERR342899 1 0.981 0.355 0.58 0.42
#> ERR342829 1 0.000 0.946 1.00 0.00
#> ERR342850 1 0.000 0.946 1.00 0.00
#> ERR342849 1 0.981 0.355 0.58 0.42
#> ERR342811 1 0.000 0.946 1.00 0.00
#> ERR342837 1 0.000 0.946 1.00 0.00
#> ERR342857 1 0.000 0.946 1.00 0.00
#> ERR342869 1 0.000 0.946 1.00 0.00
#> ERR342903 1 0.000 0.946 1.00 0.00
#> ERR342819 1 0.000 0.946 1.00 0.00
#> ERR342885 1 0.000 0.946 1.00 0.00
#> ERR342889 2 0.000 1.000 0.00 1.00
#> ERR342864 1 0.000 0.946 1.00 0.00
#> ERR342860 1 0.981 0.355 0.58 0.42
#> ERR342808 1 0.000 0.946 1.00 0.00
#> ERR342823 1 0.000 0.946 1.00 0.00
#> ERR342907 2 0.000 1.000 0.00 1.00
#> ERR342852 1 0.000 0.946 1.00 0.00
#> ERR342832 2 0.000 1.000 0.00 1.00
#> ERR342868 1 0.000 0.946 1.00 0.00
#> ERR342821 1 0.000 0.946 1.00 0.00
#> ERR342878 2 0.000 1.000 0.00 1.00
#> ERR342876 1 0.000 0.946 1.00 0.00
#> ERR342809 1 0.000 0.946 1.00 0.00
#> ERR342846 1 0.000 0.946 1.00 0.00
#> ERR342872 2 0.000 1.000 0.00 1.00
#> ERR342828 2 0.000 1.000 0.00 1.00
#> ERR342840 1 0.000 0.946 1.00 0.00
#> ERR342831 1 0.000 0.946 1.00 0.00
#> ERR342818 1 0.000 0.946 1.00 0.00
#> ERR342862 1 0.000 0.946 1.00 0.00
#> ERR342894 1 0.000 0.946 1.00 0.00
#> ERR342884 2 0.000 1.000 0.00 1.00
#> ERR342891 1 0.000 0.946 1.00 0.00
#> ERR342890 1 0.000 0.946 1.00 0.00
#> ERR342836 2 0.000 1.000 0.00 1.00
#> ERR342879 1 0.000 0.946 1.00 0.00
#> ERR342848 1 0.000 0.946 1.00 0.00
#> ERR342861 1 0.000 0.946 1.00 0.00
#> ERR342814 1 0.981 0.355 0.58 0.42
#> ERR342870 1 0.000 0.946 1.00 0.00
#> ERR342901 1 0.000 0.946 1.00 0.00
#> ERR342908 1 0.000 0.946 1.00 0.00
#> ERR342815 2 0.000 1.000 0.00 1.00
#> ERR342897 1 0.000 0.946 1.00 0.00
#> ERR342833 2 0.000 1.000 0.00 1.00
#> ERR342817 1 0.000 0.946 1.00 0.00
#> ERR342810 1 0.981 0.355 0.58 0.42
#> ERR342867 1 0.000 0.946 1.00 0.00
#> ERR342847 1 0.000 0.946 1.00 0.00
#> ERR342855 1 0.000 0.946 1.00 0.00
#> ERR342851 1 0.000 0.946 1.00 0.00
#> ERR342813 1 0.000 0.946 1.00 0.00
#> ERR342883 1 0.000 0.946 1.00 0.00
#> ERR342856 1 0.000 0.946 1.00 0.00
#> ERR342822 2 0.000 1.000 0.00 1.00
#> ERR342892 1 0.000 0.946 1.00 0.00
#> ERR342842 1 0.000 0.946 1.00 0.00
#> ERR342902 2 0.000 1.000 0.00 1.00
#> ERR342900 1 0.981 0.355 0.58 0.42
#> ERR342888 1 0.000 0.946 1.00 0.00
#> ERR342812 1 0.000 0.946 1.00 0.00
#> ERR342853 1 0.981 0.355 0.58 0.42
#> ERR342866 1 0.000 0.946 1.00 0.00
#> ERR342820 1 0.000 0.946 1.00 0.00
#> ERR342895 1 0.000 0.946 1.00 0.00
#> ERR342825 1 0.000 0.946 1.00 0.00
#> ERR342826 1 0.000 0.946 1.00 0.00
#> ERR342875 2 0.000 1.000 0.00 1.00
#> ERR342834 1 0.000 0.946 1.00 0.00
#> ERR342898 1 0.000 0.946 1.00 0.00
#> ERR342886 1 0.981 0.355 0.58 0.42
#> ERR342838 1 0.000 0.946 1.00 0.00
#> ERR342882 1 0.000 0.946 1.00 0.00
#> ERR342807 2 0.000 1.000 0.00 1.00
#> ERR342873 1 0.000 0.946 1.00 0.00
#> ERR342844 1 0.000 0.946 1.00 0.00
#> ERR342874 1 0.000 0.946 1.00 0.00
#> ERR342893 1 0.000 0.946 1.00 0.00
#> ERR342859 1 0.000 0.946 1.00 0.00
#> ERR342830 1 0.981 0.355 0.58 0.42
#> ERR342880 1 0.000 0.946 1.00 0.00
#> ERR342887 1 0.000 0.946 1.00 0.00
#> ERR342854 1 0.000 0.946 1.00 0.00
#> ERR342904 1 0.000 0.946 1.00 0.00
#> ERR342881 1 0.000 0.946 1.00 0.00
#> ERR342858 1 0.000 0.946 1.00 0.00
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.000 1.000 1.000 0.0 0.000
#> ERR342843 1 0.000 1.000 1.000 0.0 0.000
#> ERR342896 1 0.000 1.000 1.000 0.0 0.000
#> ERR342827 2 0.000 1.000 0.000 1.0 0.000
#> ERR342871 3 0.627 0.621 0.452 0.0 0.548
#> ERR342863 2 0.000 1.000 0.000 1.0 0.000
#> ERR342839 1 0.000 1.000 1.000 0.0 0.000
#> ERR342906 3 0.627 0.621 0.452 0.0 0.548
#> ERR342905 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342816 3 0.627 0.621 0.452 0.0 0.548
#> ERR342865 2 0.000 1.000 0.000 1.0 0.000
#> ERR342824 1 0.000 1.000 1.000 0.0 0.000
#> ERR342841 2 0.000 1.000 0.000 1.0 0.000
#> ERR342835 1 0.000 1.000 1.000 0.0 0.000
#> ERR342899 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342829 1 0.000 1.000 1.000 0.0 0.000
#> ERR342850 3 0.627 0.621 0.452 0.0 0.548
#> ERR342849 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342811 3 0.627 0.621 0.452 0.0 0.548
#> ERR342837 1 0.000 1.000 1.000 0.0 0.000
#> ERR342857 3 0.627 0.621 0.452 0.0 0.548
#> ERR342869 3 0.627 0.621 0.452 0.0 0.548
#> ERR342903 1 0.000 1.000 1.000 0.0 0.000
#> ERR342819 1 0.000 1.000 1.000 0.0 0.000
#> ERR342885 3 0.627 0.621 0.452 0.0 0.548
#> ERR342889 2 0.000 1.000 0.000 1.0 0.000
#> ERR342864 3 0.627 0.621 0.452 0.0 0.548
#> ERR342860 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342808 3 0.627 0.621 0.452 0.0 0.548
#> ERR342823 1 0.000 1.000 1.000 0.0 0.000
#> ERR342907 2 0.000 1.000 0.000 1.0 0.000
#> ERR342852 3 0.627 0.621 0.452 0.0 0.548
#> ERR342832 2 0.000 1.000 0.000 1.0 0.000
#> ERR342868 1 0.000 1.000 1.000 0.0 0.000
#> ERR342821 3 0.627 0.621 0.452 0.0 0.548
#> ERR342878 2 0.000 1.000 0.000 1.0 0.000
#> ERR342876 1 0.000 1.000 1.000 0.0 0.000
#> ERR342809 1 0.000 1.000 1.000 0.0 0.000
#> ERR342846 3 0.627 0.621 0.452 0.0 0.548
#> ERR342872 2 0.000 1.000 0.000 1.0 0.000
#> ERR342828 2 0.000 1.000 0.000 1.0 0.000
#> ERR342840 1 0.000 1.000 1.000 0.0 0.000
#> ERR342831 1 0.000 1.000 1.000 0.0 0.000
#> ERR342818 1 0.000 1.000 1.000 0.0 0.000
#> ERR342862 1 0.000 1.000 1.000 0.0 0.000
#> ERR342894 1 0.000 1.000 1.000 0.0 0.000
#> ERR342884 2 0.000 1.000 0.000 1.0 0.000
#> ERR342891 1 0.000 1.000 1.000 0.0 0.000
#> ERR342890 1 0.000 1.000 1.000 0.0 0.000
#> ERR342836 2 0.000 1.000 0.000 1.0 0.000
#> ERR342879 1 0.000 1.000 1.000 0.0 0.000
#> ERR342848 1 0.000 1.000 1.000 0.0 0.000
#> ERR342861 1 0.000 1.000 1.000 0.0 0.000
#> ERR342814 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342870 3 0.627 0.621 0.452 0.0 0.548
#> ERR342901 1 0.000 1.000 1.000 0.0 0.000
#> ERR342908 3 0.627 0.621 0.452 0.0 0.548
#> ERR342815 2 0.000 1.000 0.000 1.0 0.000
#> ERR342897 3 0.627 0.621 0.452 0.0 0.548
#> ERR342833 2 0.000 1.000 0.000 1.0 0.000
#> ERR342817 3 0.627 0.621 0.452 0.0 0.548
#> ERR342810 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342867 3 0.627 0.621 0.452 0.0 0.548
#> ERR342847 1 0.000 1.000 1.000 0.0 0.000
#> ERR342855 1 0.000 1.000 1.000 0.0 0.000
#> ERR342851 1 0.000 1.000 1.000 0.0 0.000
#> ERR342813 1 0.000 1.000 1.000 0.0 0.000
#> ERR342883 1 0.000 1.000 1.000 0.0 0.000
#> ERR342856 3 0.627 0.621 0.452 0.0 0.548
#> ERR342822 2 0.000 1.000 0.000 1.0 0.000
#> ERR342892 1 0.000 1.000 1.000 0.0 0.000
#> ERR342842 1 0.000 1.000 1.000 0.0 0.000
#> ERR342902 2 0.000 1.000 0.000 1.0 0.000
#> ERR342900 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342888 1 0.000 1.000 1.000 0.0 0.000
#> ERR342812 1 0.000 1.000 1.000 0.0 0.000
#> ERR342853 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342866 1 0.000 1.000 1.000 0.0 0.000
#> ERR342820 3 0.627 0.621 0.452 0.0 0.548
#> ERR342895 1 0.000 1.000 1.000 0.0 0.000
#> ERR342825 3 0.627 0.621 0.452 0.0 0.548
#> ERR342826 3 0.627 0.621 0.452 0.0 0.548
#> ERR342875 2 0.000 1.000 0.000 1.0 0.000
#> ERR342834 3 0.627 0.621 0.452 0.0 0.548
#> ERR342898 3 0.627 0.621 0.452 0.0 0.548
#> ERR342886 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342838 1 0.000 1.000 1.000 0.0 0.000
#> ERR342882 1 0.000 1.000 1.000 0.0 0.000
#> ERR342807 2 0.000 1.000 0.000 1.0 0.000
#> ERR342873 1 0.000 1.000 1.000 0.0 0.000
#> ERR342844 3 0.627 0.621 0.452 0.0 0.548
#> ERR342874 1 0.000 1.000 1.000 0.0 0.000
#> ERR342893 1 0.000 1.000 1.000 0.0 0.000
#> ERR342859 3 0.627 0.621 0.452 0.0 0.548
#> ERR342830 3 0.790 -0.324 0.060 0.4 0.540
#> ERR342880 1 0.000 1.000 1.000 0.0 0.000
#> ERR342887 1 0.000 1.000 1.000 0.0 0.000
#> ERR342854 1 0.000 1.000 1.000 0.0 0.000
#> ERR342904 3 0.627 0.621 0.452 0.0 0.548
#> ERR342881 1 0.000 1.000 1.000 0.0 0.000
#> ERR342858 1 0.000 1.000 1.000 0.0 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342843 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342896 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342827 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342871 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342863 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342839 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342906 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342905 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342816 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342865 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342824 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342841 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342835 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342899 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342829 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342850 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342849 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342811 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342837 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342857 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342869 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342903 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342819 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342885 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342889 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342864 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342860 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342808 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342823 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342907 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342852 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342832 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342868 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342821 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342878 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342876 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342809 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342846 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342872 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342828 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342840 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342831 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342818 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342862 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342894 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342884 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342891 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342890 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342836 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342879 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342848 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342861 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342814 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342870 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342901 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342908 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342815 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342897 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342833 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342817 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342810 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342867 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342847 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342855 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342851 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342813 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342883 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342856 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342822 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342892 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342842 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342902 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342900 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342888 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342812 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342853 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342866 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342820 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342895 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342825 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342826 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342875 2 0.485 0.647 0.00 0.6 0.4 0.00
#> ERR342834 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342898 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342886 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342838 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342882 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342807 2 0.000 0.745 0.00 1.0 0.0 0.00
#> ERR342873 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342844 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342874 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342893 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342859 4 0.000 0.813 0.00 0.0 0.0 1.00
#> ERR342830 3 0.000 1.000 0.00 0.0 1.0 0.00
#> ERR342880 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342887 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342854 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342904 4 0.340 0.912 0.18 0.0 0.0 0.82
#> ERR342881 1 0.000 1.000 1.00 0.0 0.0 0.00
#> ERR342858 1 0.000 1.000 1.00 0.0 0.0 0.00
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342843 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342896 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342827 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342871 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342863 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342839 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342906 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342905 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342816 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342865 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342824 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342841 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342835 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342899 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342829 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342850 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342849 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342811 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342837 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342857 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342869 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342903 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342819 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342885 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342889 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342864 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342860 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342808 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342823 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342907 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342852 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342832 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342868 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342821 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342878 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342876 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342809 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342846 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342872 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342828 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342840 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342831 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342818 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
#> ERR342862 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342894 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342884 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342891 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342890 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342836 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342879 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
#> ERR342848 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
#> ERR342861 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342814 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342870 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342901 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342908 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342815 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342897 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342833 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342817 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342810 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342867 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342847 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342855 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342851 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
#> ERR342813 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342883 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
#> ERR342856 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342822 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342892 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342842 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342902 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342900 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342888 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342812 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342853 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342866 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342820 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342895 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342825 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342826 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342875 2 0.418 0.647 0.000 0.6 0.4 0.00 0.000
#> ERR342834 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342898 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342886 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342838 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342882 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342807 2 0.000 0.745 0.000 1.0 0.0 0.00 0.000
#> ERR342873 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
#> ERR342844 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342874 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342893 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
#> ERR342859 4 0.000 0.869 0.000 0.0 0.0 1.00 0.000
#> ERR342830 3 0.000 1.000 0.000 0.0 1.0 0.00 0.000
#> ERR342880 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
#> ERR342887 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342854 1 0.000 0.797 1.000 0.0 0.0 0.00 0.000
#> ERR342904 4 0.293 0.938 0.000 0.0 0.0 0.82 0.180
#> ERR342881 5 0.409 1.000 0.368 0.0 0.0 0.00 0.632
#> ERR342858 1 0.409 0.657 0.632 0.0 0.0 0.00 0.368
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342843 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342896 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342827 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342871 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342863 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342839 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342906 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342905 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342816 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342865 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342824 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342841 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342835 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342899 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342829 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342850 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342849 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342811 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342837 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342857 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342869 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342903 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342819 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342885 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342889 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342864 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342860 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342808 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342823 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342907 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342852 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342832 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342868 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342821 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342878 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342876 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342809 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342846 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342872 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342828 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342840 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342831 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342818 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
#> ERR342862 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342894 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342884 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342891 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342890 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342836 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342879 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
#> ERR342848 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
#> ERR342861 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342814 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342870 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342901 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342908 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342815 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342897 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342833 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342817 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342810 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342867 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342847 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342855 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342851 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
#> ERR342813 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342883 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
#> ERR342856 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342822 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342892 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342842 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342902 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342900 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342888 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342812 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342853 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342866 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342820 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342895 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342825 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342826 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342875 2 0.000 1.000 0.0 1.000 0.00 0.000 0.000 0.000
#> ERR342834 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342898 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342886 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342838 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342882 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342807 4 0.380 -0.260 0.0 0.424 0.00 0.576 0.000 0.000
#> ERR342873 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
#> ERR342844 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342874 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342893 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
#> ERR342859 3 0.000 1.000 0.0 0.000 1.00 0.000 0.000 0.000
#> ERR342830 1 0.376 -0.290 0.6 0.400 0.00 0.000 0.000 0.000
#> ERR342880 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
#> ERR342887 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342854 1 0.599 0.136 0.4 0.000 0.00 0.000 0.368 0.232
#> ERR342904 4 0.570 0.574 0.0 0.000 0.16 0.424 0.000 0.416
#> ERR342881 5 0.000 1.000 0.0 0.000 0.00 0.000 1.000 0.000
#> ERR342858 6 0.376 1.000 0.4 0.000 0.00 0.000 0.000 0.600
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "kmeans"]
# you can also extract it by
# res = res_list["ATC:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.722 0.938 0.941 0.3798 0.595 0.595
#> 3 3 0.449 0.583 0.772 0.5237 0.804 0.671
#> 4 4 0.469 0.672 0.732 0.1648 0.804 0.577
#> 5 5 0.569 0.599 0.670 0.1012 0.902 0.704
#> 6 6 0.646 0.576 0.661 0.0576 0.936 0.745
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.1633 0.963 0.976 0.024
#> ERR342843 1 0.1633 0.963 0.976 0.024
#> ERR342896 1 0.1184 0.965 0.984 0.016
#> ERR342827 2 0.2948 0.916 0.052 0.948
#> ERR342871 1 0.2603 0.962 0.956 0.044
#> ERR342863 2 0.2603 0.917 0.044 0.956
#> ERR342839 1 0.1633 0.963 0.976 0.024
#> ERR342906 1 0.3114 0.955 0.944 0.056
#> ERR342905 2 0.7815 0.823 0.232 0.768
#> ERR342816 1 0.3114 0.955 0.944 0.056
#> ERR342865 2 0.2603 0.917 0.044 0.956
#> ERR342824 1 0.1184 0.965 0.984 0.016
#> ERR342841 2 0.2948 0.916 0.052 0.948
#> ERR342835 1 0.0938 0.965 0.988 0.012
#> ERR342899 2 0.7815 0.823 0.232 0.768
#> ERR342829 1 0.1184 0.965 0.984 0.016
#> ERR342850 1 0.2603 0.962 0.956 0.044
#> ERR342849 2 0.7815 0.823 0.232 0.768
#> ERR342811 1 0.2603 0.962 0.956 0.044
#> ERR342837 1 0.0938 0.965 0.988 0.012
#> ERR342857 1 0.3114 0.955 0.944 0.056
#> ERR342869 1 0.2603 0.962 0.956 0.044
#> ERR342903 1 0.1184 0.965 0.984 0.016
#> ERR342819 1 0.0938 0.965 0.988 0.012
#> ERR342885 1 0.4431 0.939 0.908 0.092
#> ERR342889 2 0.2603 0.917 0.044 0.956
#> ERR342864 1 0.3114 0.955 0.944 0.056
#> ERR342860 2 0.7815 0.823 0.232 0.768
#> ERR342808 1 0.2603 0.962 0.956 0.044
#> ERR342823 1 0.1184 0.965 0.984 0.016
#> ERR342907 2 0.2948 0.916 0.052 0.948
#> ERR342852 1 0.3114 0.955 0.944 0.056
#> ERR342832 2 0.2603 0.917 0.044 0.956
#> ERR342868 1 0.1633 0.963 0.976 0.024
#> ERR342821 1 0.3114 0.955 0.944 0.056
#> ERR342878 2 0.2948 0.916 0.052 0.948
#> ERR342876 1 0.1184 0.965 0.984 0.016
#> ERR342809 1 0.1184 0.965 0.984 0.016
#> ERR342846 1 0.4431 0.939 0.908 0.092
#> ERR342872 2 0.2948 0.916 0.052 0.948
#> ERR342828 2 0.2603 0.917 0.044 0.956
#> ERR342840 1 0.0938 0.965 0.988 0.012
#> ERR342831 1 0.1633 0.963 0.976 0.024
#> ERR342818 1 0.2778 0.962 0.952 0.048
#> ERR342862 1 0.0938 0.965 0.988 0.012
#> ERR342894 1 0.1633 0.963 0.976 0.024
#> ERR342884 2 0.2948 0.916 0.052 0.948
#> ERR342891 1 0.1184 0.965 0.984 0.016
#> ERR342890 1 0.1633 0.963 0.976 0.024
#> ERR342836 2 0.2603 0.917 0.044 0.956
#> ERR342879 1 0.2778 0.962 0.952 0.048
#> ERR342848 1 0.2778 0.962 0.952 0.048
#> ERR342861 1 0.1184 0.965 0.984 0.016
#> ERR342814 2 0.7815 0.823 0.232 0.768
#> ERR342870 1 0.2603 0.962 0.956 0.044
#> ERR342901 1 0.1184 0.965 0.984 0.016
#> ERR342908 1 0.2603 0.962 0.956 0.044
#> ERR342815 2 0.2603 0.917 0.044 0.956
#> ERR342897 1 0.4431 0.939 0.908 0.092
#> ERR342833 2 0.2948 0.916 0.052 0.948
#> ERR342817 1 0.4431 0.939 0.908 0.092
#> ERR342810 2 0.7815 0.823 0.232 0.768
#> ERR342867 1 0.3114 0.955 0.944 0.056
#> ERR342847 1 0.0938 0.965 0.988 0.012
#> ERR342855 1 0.1184 0.965 0.984 0.016
#> ERR342851 1 0.2778 0.962 0.952 0.048
#> ERR342813 1 0.1633 0.963 0.976 0.024
#> ERR342883 1 0.2778 0.962 0.952 0.048
#> ERR342856 1 0.4431 0.939 0.908 0.092
#> ERR342822 2 0.2603 0.917 0.044 0.956
#> ERR342892 1 0.1184 0.965 0.984 0.016
#> ERR342842 1 0.1184 0.965 0.984 0.016
#> ERR342902 2 0.2948 0.916 0.052 0.948
#> ERR342900 2 0.7815 0.823 0.232 0.768
#> ERR342888 1 0.1633 0.963 0.976 0.024
#> ERR342812 1 0.1184 0.965 0.984 0.016
#> ERR342853 2 0.7815 0.823 0.232 0.768
#> ERR342866 1 0.0938 0.965 0.988 0.012
#> ERR342820 1 0.2603 0.962 0.956 0.044
#> ERR342895 1 0.1184 0.965 0.984 0.016
#> ERR342825 1 0.4431 0.939 0.908 0.092
#> ERR342826 1 0.4431 0.939 0.908 0.092
#> ERR342875 2 0.2603 0.917 0.044 0.956
#> ERR342834 1 0.4431 0.939 0.908 0.092
#> ERR342898 1 0.3114 0.955 0.944 0.056
#> ERR342886 2 0.7815 0.823 0.232 0.768
#> ERR342838 1 0.1184 0.965 0.984 0.016
#> ERR342882 1 0.1184 0.965 0.984 0.016
#> ERR342807 2 0.2948 0.916 0.052 0.948
#> ERR342873 1 0.2778 0.962 0.952 0.048
#> ERR342844 1 0.3114 0.955 0.944 0.056
#> ERR342874 1 0.0938 0.965 0.988 0.012
#> ERR342893 1 0.2778 0.962 0.952 0.048
#> ERR342859 1 0.4431 0.939 0.908 0.092
#> ERR342830 2 0.7815 0.823 0.232 0.768
#> ERR342880 1 0.2778 0.962 0.952 0.048
#> ERR342887 1 0.1184 0.965 0.984 0.016
#> ERR342854 1 0.1184 0.965 0.984 0.016
#> ERR342904 1 0.2603 0.962 0.956 0.044
#> ERR342881 1 0.0938 0.965 0.988 0.012
#> ERR342858 1 0.2778 0.962 0.952 0.048
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342843 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342896 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342827 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342871 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342863 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342839 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342906 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342905 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342816 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342865 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342824 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342841 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342835 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342899 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342829 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342850 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342849 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342811 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342837 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342857 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342869 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342903 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342819 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342885 3 0.6703 0.780 0.268 0.040 0.692
#> ERR342889 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342864 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342860 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342808 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342823 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342907 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342852 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342832 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342868 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342821 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342878 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342876 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342809 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342846 3 0.6805 0.780 0.268 0.044 0.688
#> ERR342872 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342828 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342840 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342831 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342818 1 0.6651 0.210 0.656 0.024 0.320
#> ERR342862 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342894 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342884 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342891 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342890 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342836 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342879 1 0.6651 0.210 0.656 0.024 0.320
#> ERR342848 1 0.6651 0.210 0.656 0.024 0.320
#> ERR342861 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342814 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342870 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342901 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342908 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342815 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342897 3 0.6805 0.780 0.268 0.044 0.688
#> ERR342833 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342817 3 0.6703 0.780 0.268 0.040 0.692
#> ERR342810 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342867 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342847 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342855 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342851 1 0.6651 0.210 0.656 0.024 0.320
#> ERR342813 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342883 1 0.6651 0.210 0.656 0.024 0.320
#> ERR342856 3 0.6805 0.780 0.268 0.044 0.688
#> ERR342822 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342892 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342842 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342902 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342900 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342888 1 0.5864 0.521 0.704 0.008 0.288
#> ERR342812 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342853 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342866 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342820 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342895 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342825 3 0.6703 0.780 0.268 0.040 0.692
#> ERR342826 3 0.6703 0.780 0.268 0.040 0.692
#> ERR342875 2 0.0592 0.894 0.012 0.988 0.000
#> ERR342834 3 0.6703 0.780 0.268 0.040 0.692
#> ERR342898 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342886 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342838 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342882 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342807 2 0.3459 0.880 0.012 0.892 0.096
#> ERR342873 1 0.6651 0.210 0.656 0.024 0.320
#> ERR342844 3 0.7671 0.734 0.408 0.048 0.544
#> ERR342874 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342893 1 0.6651 0.210 0.656 0.024 0.320
#> ERR342859 3 0.6805 0.780 0.268 0.044 0.688
#> ERR342830 2 0.6348 0.823 0.048 0.740 0.212
#> ERR342880 1 0.6651 0.210 0.656 0.024 0.320
#> ERR342887 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342854 1 0.0592 0.641 0.988 0.012 0.000
#> ERR342904 1 0.7240 -0.320 0.540 0.028 0.432
#> ERR342881 1 0.4842 0.579 0.776 0.000 0.224
#> ERR342858 1 0.6651 0.210 0.656 0.024 0.320
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.7044 0.579 0.516 0.004 NA 0.112
#> ERR342843 1 0.7044 0.579 0.516 0.004 NA 0.112
#> ERR342896 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342827 2 0.4050 0.829 0.000 0.820 NA 0.036
#> ERR342871 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342863 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342839 1 0.7110 0.579 0.516 0.004 NA 0.120
#> ERR342906 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342905 2 0.6400 0.772 0.016 0.688 NA 0.164
#> ERR342816 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342865 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342824 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342841 2 0.3853 0.829 0.000 0.820 NA 0.020
#> ERR342835 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342899 2 0.6393 0.772 0.016 0.688 NA 0.168
#> ERR342829 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342850 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342849 2 0.6393 0.772 0.016 0.688 NA 0.168
#> ERR342811 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342837 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342857 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342869 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342903 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342819 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342885 4 0.6703 0.562 0.108 0.012 NA 0.632
#> ERR342889 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342864 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342860 2 0.6393 0.772 0.016 0.688 NA 0.168
#> ERR342808 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342823 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342907 2 0.3853 0.829 0.000 0.820 NA 0.020
#> ERR342852 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342832 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342868 1 0.7110 0.579 0.516 0.004 NA 0.120
#> ERR342821 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342878 2 0.3853 0.829 0.000 0.820 NA 0.020
#> ERR342876 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342809 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342846 4 0.6854 0.562 0.108 0.012 NA 0.608
#> ERR342872 2 0.3853 0.829 0.000 0.820 NA 0.020
#> ERR342828 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342840 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342831 1 0.7044 0.579 0.516 0.004 NA 0.112
#> ERR342818 4 0.7169 0.470 0.424 0.004 NA 0.456
#> ERR342862 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342894 1 0.7044 0.579 0.516 0.004 NA 0.112
#> ERR342884 2 0.3853 0.829 0.000 0.820 NA 0.020
#> ERR342891 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342890 1 0.7110 0.579 0.516 0.004 NA 0.120
#> ERR342836 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342879 4 0.7169 0.470 0.424 0.004 NA 0.456
#> ERR342848 4 0.7169 0.470 0.424 0.004 NA 0.456
#> ERR342861 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342814 2 0.6393 0.772 0.016 0.688 NA 0.168
#> ERR342870 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342901 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342908 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342815 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342897 4 0.6830 0.562 0.108 0.012 NA 0.612
#> ERR342833 2 0.3853 0.829 0.000 0.820 NA 0.020
#> ERR342817 4 0.6703 0.562 0.108 0.012 NA 0.632
#> ERR342810 2 0.6400 0.772 0.016 0.688 NA 0.164
#> ERR342867 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342847 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342855 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342851 4 0.7169 0.470 0.424 0.004 NA 0.456
#> ERR342813 1 0.7044 0.579 0.516 0.004 NA 0.112
#> ERR342883 4 0.7169 0.470 0.424 0.004 NA 0.456
#> ERR342856 4 0.6830 0.562 0.108 0.012 NA 0.612
#> ERR342822 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342892 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342842 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342902 2 0.3853 0.829 0.000 0.820 NA 0.020
#> ERR342900 2 0.6393 0.772 0.016 0.688 NA 0.168
#> ERR342888 1 0.7110 0.579 0.516 0.004 NA 0.120
#> ERR342812 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342853 2 0.6400 0.772 0.016 0.688 NA 0.164
#> ERR342866 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342820 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342895 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342825 4 0.6703 0.562 0.108 0.012 NA 0.632
#> ERR342826 4 0.6703 0.562 0.108 0.012 NA 0.632
#> ERR342875 2 0.0188 0.852 0.000 0.996 NA 0.000
#> ERR342834 4 0.6703 0.562 0.108 0.012 NA 0.632
#> ERR342898 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342886 2 0.6393 0.772 0.016 0.688 NA 0.168
#> ERR342838 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342882 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342807 2 0.3853 0.829 0.000 0.820 NA 0.020
#> ERR342873 4 0.7169 0.470 0.424 0.004 NA 0.456
#> ERR342844 4 0.4507 0.676 0.200 0.012 NA 0.776
#> ERR342874 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342893 4 0.7169 0.470 0.424 0.004 NA 0.456
#> ERR342859 4 0.6854 0.562 0.108 0.012 NA 0.608
#> ERR342830 2 0.6393 0.772 0.016 0.688 NA 0.168
#> ERR342880 4 0.7169 0.470 0.424 0.004 NA 0.456
#> ERR342887 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342854 1 0.0000 0.722 1.000 0.000 NA 0.000
#> ERR342904 4 0.6596 0.590 0.368 0.012 NA 0.560
#> ERR342881 1 0.6689 0.598 0.620 0.000 NA 0.184
#> ERR342858 4 0.7169 0.470 0.424 0.004 NA 0.456
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.5143 0.990 0.364 0.012 0.004 0.020 0.600
#> ERR342843 5 0.5041 0.991 0.364 0.008 0.004 0.020 0.604
#> ERR342896 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.5417 0.730 0.000 0.712 0.088 0.036 0.164
#> ERR342871 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342863 2 0.0324 0.760 0.000 0.992 0.000 0.004 0.004
#> ERR342839 5 0.5539 0.988 0.364 0.012 0.020 0.020 0.584
#> ERR342906 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342905 2 0.7413 0.645 0.008 0.512 0.284 0.108 0.088
#> ERR342816 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342865 2 0.0324 0.760 0.000 0.992 0.000 0.004 0.004
#> ERR342824 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.5298 0.730 0.000 0.712 0.080 0.028 0.180
#> ERR342835 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342899 2 0.7319 0.645 0.008 0.512 0.296 0.108 0.076
#> ERR342829 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342849 2 0.7319 0.645 0.008 0.512 0.296 0.108 0.076
#> ERR342811 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342837 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342857 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342869 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342903 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342819 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342885 3 0.6099 0.993 0.048 0.004 0.588 0.316 0.044
#> ERR342889 2 0.0324 0.760 0.000 0.992 0.000 0.004 0.004
#> ERR342864 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342860 2 0.7319 0.645 0.008 0.512 0.296 0.108 0.076
#> ERR342808 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342823 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.5298 0.730 0.000 0.712 0.080 0.028 0.180
#> ERR342852 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342832 2 0.0324 0.760 0.000 0.992 0.000 0.004 0.004
#> ERR342868 5 0.5438 0.989 0.364 0.008 0.020 0.020 0.588
#> ERR342821 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342878 2 0.5298 0.730 0.000 0.712 0.080 0.028 0.180
#> ERR342876 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.6192 0.992 0.048 0.004 0.576 0.324 0.048
#> ERR342872 2 0.5342 0.730 0.000 0.712 0.080 0.032 0.176
#> ERR342828 2 0.0324 0.760 0.000 0.992 0.000 0.004 0.004
#> ERR342840 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342831 5 0.5143 0.990 0.364 0.012 0.004 0.020 0.600
#> ERR342818 4 0.5548 0.491 0.216 0.000 0.032 0.680 0.072
#> ERR342862 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342894 5 0.5041 0.991 0.364 0.008 0.004 0.020 0.604
#> ERR342884 2 0.5298 0.730 0.000 0.712 0.080 0.028 0.180
#> ERR342891 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.5539 0.988 0.364 0.012 0.020 0.020 0.584
#> ERR342836 2 0.0324 0.760 0.000 0.992 0.000 0.004 0.004
#> ERR342879 4 0.5548 0.491 0.216 0.000 0.032 0.680 0.072
#> ERR342848 4 0.5603 0.490 0.216 0.000 0.032 0.676 0.076
#> ERR342861 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.7319 0.645 0.008 0.512 0.296 0.108 0.076
#> ERR342870 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342901 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342815 2 0.0613 0.760 0.000 0.984 0.004 0.008 0.004
#> ERR342897 3 0.6192 0.992 0.048 0.004 0.576 0.324 0.048
#> ERR342833 2 0.5298 0.730 0.000 0.712 0.080 0.028 0.180
#> ERR342817 3 0.6099 0.993 0.048 0.004 0.588 0.316 0.044
#> ERR342810 2 0.7413 0.645 0.008 0.512 0.284 0.108 0.088
#> ERR342867 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342847 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342855 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.5548 0.491 0.216 0.000 0.032 0.680 0.072
#> ERR342813 5 0.5041 0.991 0.364 0.008 0.004 0.020 0.604
#> ERR342883 4 0.5548 0.491 0.216 0.000 0.032 0.680 0.072
#> ERR342856 3 0.6192 0.992 0.048 0.004 0.576 0.324 0.048
#> ERR342822 2 0.0324 0.760 0.000 0.992 0.000 0.004 0.004
#> ERR342892 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.5298 0.730 0.000 0.712 0.080 0.028 0.180
#> ERR342900 2 0.7319 0.645 0.008 0.512 0.296 0.108 0.076
#> ERR342888 5 0.5438 0.989 0.364 0.008 0.020 0.020 0.588
#> ERR342812 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.7413 0.645 0.008 0.512 0.284 0.108 0.088
#> ERR342866 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342820 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342895 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.6099 0.993 0.048 0.004 0.588 0.316 0.044
#> ERR342826 3 0.6099 0.993 0.048 0.004 0.588 0.316 0.044
#> ERR342875 2 0.0324 0.760 0.000 0.992 0.000 0.004 0.004
#> ERR342834 3 0.6099 0.993 0.048 0.004 0.588 0.316 0.044
#> ERR342898 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342886 2 0.7430 0.645 0.008 0.512 0.280 0.116 0.084
#> ERR342838 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.5317 0.730 0.000 0.712 0.084 0.028 0.176
#> ERR342873 4 0.5548 0.491 0.216 0.000 0.032 0.680 0.072
#> ERR342844 4 0.5243 0.363 0.080 0.004 0.212 0.696 0.008
#> ERR342874 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342893 4 0.5548 0.491 0.216 0.000 0.032 0.680 0.072
#> ERR342859 3 0.6192 0.992 0.048 0.004 0.576 0.324 0.048
#> ERR342830 2 0.7430 0.645 0.008 0.512 0.280 0.116 0.084
#> ERR342880 4 0.5548 0.491 0.216 0.000 0.032 0.680 0.072
#> ERR342887 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.694 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.7436 0.361 0.196 0.000 0.208 0.512 0.084
#> ERR342881 1 0.7481 -0.150 0.440 0.000 0.112 0.100 0.348
#> ERR342858 4 0.5548 0.491 0.216 0.000 0.032 0.680 0.072
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.3915 0.859 0.284 0.000 0.008 0.012 0.696 0.000
#> ERR342843 5 0.3808 0.860 0.284 0.000 0.004 0.012 0.700 0.000
#> ERR342896 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.4852 0.705 0.000 0.716 0.180 0.004 0.048 0.052
#> ERR342871 4 0.3867 0.532 0.104 0.000 0.024 0.800 0.072 0.000
#> ERR342863 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342839 5 0.4682 0.857 0.284 0.000 0.020 0.020 0.664 0.012
#> ERR342906 4 0.5095 0.501 0.044 0.000 0.084 0.740 0.036 0.096
#> ERR342905 2 0.7137 0.603 0.000 0.476 0.096 0.036 0.092 0.300
#> ERR342816 4 0.5095 0.501 0.044 0.000 0.084 0.740 0.036 0.096
#> ERR342865 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342824 1 0.1442 0.690 0.944 0.000 0.040 0.000 0.004 0.012
#> ERR342841 2 0.4591 0.705 0.000 0.716 0.200 0.000 0.056 0.028
#> ERR342835 1 0.7840 -0.346 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342899 2 0.7020 0.603 0.000 0.476 0.096 0.036 0.076 0.316
#> ERR342829 1 0.0146 0.729 0.996 0.000 0.004 0.000 0.000 0.000
#> ERR342850 4 0.3840 0.533 0.104 0.000 0.020 0.800 0.076 0.000
#> ERR342849 2 0.7020 0.603 0.000 0.476 0.096 0.036 0.076 0.316
#> ERR342811 4 0.3840 0.533 0.104 0.000 0.020 0.800 0.076 0.000
#> ERR342837 1 0.7840 -0.346 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342857 4 0.5075 0.501 0.044 0.000 0.088 0.740 0.032 0.096
#> ERR342869 4 0.3840 0.533 0.104 0.000 0.020 0.800 0.076 0.000
#> ERR342903 1 0.0146 0.729 0.996 0.000 0.004 0.000 0.000 0.000
#> ERR342819 1 0.7840 -0.346 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342885 3 0.5089 0.999 0.016 0.000 0.496 0.444 0.044 0.000
#> ERR342889 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342864 4 0.5095 0.501 0.044 0.000 0.084 0.740 0.036 0.096
#> ERR342860 2 0.6965 0.603 0.000 0.476 0.088 0.036 0.076 0.324
#> ERR342808 4 0.3867 0.532 0.104 0.000 0.024 0.800 0.072 0.000
#> ERR342823 1 0.1442 0.690 0.944 0.000 0.040 0.000 0.004 0.012
#> ERR342907 2 0.4591 0.705 0.000 0.716 0.200 0.000 0.056 0.028
#> ERR342852 4 0.5095 0.501 0.044 0.000 0.084 0.740 0.036 0.096
#> ERR342832 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342868 5 0.4602 0.857 0.284 0.000 0.016 0.020 0.668 0.012
#> ERR342821 4 0.5095 0.501 0.044 0.000 0.084 0.740 0.036 0.096
#> ERR342878 2 0.4591 0.705 0.000 0.716 0.200 0.000 0.056 0.028
#> ERR342876 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0146 0.729 0.996 0.000 0.004 0.000 0.000 0.000
#> ERR342846 4 0.6233 -0.912 0.016 0.000 0.416 0.452 0.072 0.044
#> ERR342872 2 0.4644 0.705 0.000 0.716 0.196 0.000 0.052 0.036
#> ERR342828 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342840 5 0.7840 0.252 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342831 5 0.3915 0.859 0.284 0.000 0.008 0.012 0.696 0.000
#> ERR342818 6 0.5721 0.997 0.144 0.000 0.004 0.320 0.004 0.528
#> ERR342862 1 0.7840 -0.346 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342894 5 0.3808 0.860 0.284 0.000 0.004 0.012 0.700 0.000
#> ERR342884 2 0.4591 0.705 0.000 0.716 0.200 0.000 0.056 0.028
#> ERR342891 1 0.0146 0.729 0.996 0.000 0.004 0.000 0.000 0.000
#> ERR342890 5 0.4682 0.857 0.284 0.000 0.020 0.020 0.664 0.012
#> ERR342836 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342879 6 0.5721 0.997 0.144 0.000 0.004 0.320 0.004 0.528
#> ERR342848 6 0.6333 0.973 0.144 0.000 0.020 0.320 0.016 0.500
#> ERR342861 1 0.0146 0.729 0.996 0.000 0.004 0.000 0.000 0.000
#> ERR342814 2 0.6965 0.603 0.000 0.476 0.088 0.036 0.076 0.324
#> ERR342870 4 0.3840 0.533 0.104 0.000 0.020 0.800 0.076 0.000
#> ERR342901 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.3867 0.532 0.104 0.000 0.024 0.800 0.072 0.000
#> ERR342815 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342897 4 0.6047 -0.929 0.016 0.000 0.436 0.448 0.064 0.036
#> ERR342833 2 0.4591 0.705 0.000 0.716 0.200 0.000 0.056 0.028
#> ERR342817 3 0.5089 0.999 0.016 0.000 0.496 0.444 0.044 0.000
#> ERR342810 2 0.7137 0.603 0.000 0.476 0.096 0.036 0.092 0.300
#> ERR342867 4 0.5095 0.501 0.044 0.000 0.084 0.740 0.036 0.096
#> ERR342847 1 0.7840 -0.346 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342855 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 6 0.5721 0.997 0.144 0.000 0.004 0.320 0.004 0.528
#> ERR342813 5 0.3808 0.860 0.284 0.000 0.004 0.012 0.700 0.000
#> ERR342883 6 0.5721 0.997 0.144 0.000 0.004 0.320 0.004 0.528
#> ERR342856 4 0.6047 -0.929 0.016 0.000 0.436 0.448 0.064 0.036
#> ERR342822 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0146 0.729 0.996 0.000 0.004 0.000 0.000 0.000
#> ERR342902 2 0.4591 0.705 0.000 0.716 0.200 0.000 0.056 0.028
#> ERR342900 2 0.6965 0.603 0.000 0.476 0.088 0.036 0.076 0.324
#> ERR342888 5 0.4602 0.857 0.284 0.000 0.016 0.020 0.668 0.012
#> ERR342812 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.7137 0.603 0.000 0.476 0.096 0.036 0.092 0.300
#> ERR342866 5 0.7840 0.252 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342820 4 0.3840 0.533 0.104 0.000 0.020 0.800 0.076 0.000
#> ERR342895 1 0.0146 0.729 0.996 0.000 0.004 0.000 0.000 0.000
#> ERR342825 3 0.5089 0.999 0.016 0.000 0.496 0.444 0.044 0.000
#> ERR342826 3 0.5142 0.996 0.016 0.000 0.492 0.444 0.048 0.000
#> ERR342875 2 0.0000 0.740 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342834 3 0.5089 0.999 0.016 0.000 0.496 0.444 0.044 0.000
#> ERR342898 4 0.5095 0.501 0.044 0.000 0.084 0.740 0.036 0.096
#> ERR342886 2 0.7224 0.602 0.000 0.476 0.100 0.044 0.088 0.292
#> ERR342838 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0146 0.729 0.996 0.000 0.004 0.000 0.000 0.000
#> ERR342807 2 0.4672 0.706 0.000 0.716 0.192 0.000 0.056 0.036
#> ERR342873 6 0.5721 0.997 0.144 0.000 0.004 0.320 0.004 0.528
#> ERR342844 4 0.5075 0.501 0.044 0.000 0.088 0.740 0.032 0.096
#> ERR342874 1 0.7840 -0.346 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342893 6 0.5721 0.997 0.144 0.000 0.004 0.320 0.004 0.528
#> ERR342859 4 0.6233 -0.912 0.016 0.000 0.416 0.452 0.072 0.044
#> ERR342830 2 0.7224 0.602 0.000 0.476 0.100 0.044 0.088 0.292
#> ERR342880 6 0.5721 0.997 0.144 0.000 0.004 0.320 0.004 0.528
#> ERR342887 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.729 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.3840 0.533 0.104 0.000 0.020 0.800 0.076 0.000
#> ERR342881 1 0.7840 -0.346 0.352 0.000 0.056 0.128 0.352 0.112
#> ERR342858 6 0.5721 0.997 0.144 0.000 0.004 0.320 0.004 0.528
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "skmeans"]
# you can also extract it by
# res = res_list["ATC:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.992 0.995 0.4084 0.595 0.595
#> 3 3 1.000 0.984 0.989 0.5893 0.754 0.587
#> 4 4 0.769 0.777 0.852 0.1221 0.940 0.828
#> 5 5 0.850 0.924 0.854 0.0593 0.923 0.736
#> 6 6 0.852 0.894 0.870 0.0470 0.968 0.851
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
#> attr(,"optional")
#> [1] 2
There is also optional best \(k\) = 2 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0.0000 0.993 1.000 0.000
#> ERR342843 1 0.0000 0.993 1.000 0.000
#> ERR342896 1 0.0000 0.993 1.000 0.000
#> ERR342827 2 0.0000 1.000 0.000 1.000
#> ERR342871 1 0.0000 0.993 1.000 0.000
#> ERR342863 2 0.0000 1.000 0.000 1.000
#> ERR342839 1 0.0000 0.993 1.000 0.000
#> ERR342906 1 0.0938 0.987 0.988 0.012
#> ERR342905 2 0.0000 1.000 0.000 1.000
#> ERR342816 1 0.0938 0.987 0.988 0.012
#> ERR342865 2 0.0000 1.000 0.000 1.000
#> ERR342824 1 0.0000 0.993 1.000 0.000
#> ERR342841 2 0.0000 1.000 0.000 1.000
#> ERR342835 1 0.0000 0.993 1.000 0.000
#> ERR342899 2 0.0000 1.000 0.000 1.000
#> ERR342829 1 0.0000 0.993 1.000 0.000
#> ERR342850 1 0.0000 0.993 1.000 0.000
#> ERR342849 2 0.0000 1.000 0.000 1.000
#> ERR342811 1 0.0000 0.993 1.000 0.000
#> ERR342837 1 0.0000 0.993 1.000 0.000
#> ERR342857 1 0.0938 0.987 0.988 0.012
#> ERR342869 1 0.0000 0.993 1.000 0.000
#> ERR342903 1 0.0000 0.993 1.000 0.000
#> ERR342819 1 0.0000 0.993 1.000 0.000
#> ERR342885 1 0.2603 0.962 0.956 0.044
#> ERR342889 2 0.0000 1.000 0.000 1.000
#> ERR342864 1 0.0938 0.987 0.988 0.012
#> ERR342860 2 0.0000 1.000 0.000 1.000
#> ERR342808 1 0.0000 0.993 1.000 0.000
#> ERR342823 1 0.0000 0.993 1.000 0.000
#> ERR342907 2 0.0000 1.000 0.000 1.000
#> ERR342852 1 0.0938 0.987 0.988 0.012
#> ERR342832 2 0.0000 1.000 0.000 1.000
#> ERR342868 1 0.0000 0.993 1.000 0.000
#> ERR342821 1 0.0938 0.987 0.988 0.012
#> ERR342878 2 0.0000 1.000 0.000 1.000
#> ERR342876 1 0.0000 0.993 1.000 0.000
#> ERR342809 1 0.0000 0.993 1.000 0.000
#> ERR342846 1 0.2603 0.962 0.956 0.044
#> ERR342872 2 0.0000 1.000 0.000 1.000
#> ERR342828 2 0.0000 1.000 0.000 1.000
#> ERR342840 1 0.0000 0.993 1.000 0.000
#> ERR342831 1 0.0000 0.993 1.000 0.000
#> ERR342818 1 0.0000 0.993 1.000 0.000
#> ERR342862 1 0.0000 0.993 1.000 0.000
#> ERR342894 1 0.0000 0.993 1.000 0.000
#> ERR342884 2 0.0000 1.000 0.000 1.000
#> ERR342891 1 0.0000 0.993 1.000 0.000
#> ERR342890 1 0.0000 0.993 1.000 0.000
#> ERR342836 2 0.0000 1.000 0.000 1.000
#> ERR342879 1 0.0000 0.993 1.000 0.000
#> ERR342848 1 0.0000 0.993 1.000 0.000
#> ERR342861 1 0.0000 0.993 1.000 0.000
#> ERR342814 2 0.0000 1.000 0.000 1.000
#> ERR342870 1 0.0000 0.993 1.000 0.000
#> ERR342901 1 0.0000 0.993 1.000 0.000
#> ERR342908 1 0.0000 0.993 1.000 0.000
#> ERR342815 2 0.0000 1.000 0.000 1.000
#> ERR342897 1 0.2603 0.962 0.956 0.044
#> ERR342833 2 0.0000 1.000 0.000 1.000
#> ERR342817 1 0.2603 0.962 0.956 0.044
#> ERR342810 2 0.0000 1.000 0.000 1.000
#> ERR342867 1 0.0938 0.987 0.988 0.012
#> ERR342847 1 0.0000 0.993 1.000 0.000
#> ERR342855 1 0.0000 0.993 1.000 0.000
#> ERR342851 1 0.0000 0.993 1.000 0.000
#> ERR342813 1 0.0000 0.993 1.000 0.000
#> ERR342883 1 0.0000 0.993 1.000 0.000
#> ERR342856 1 0.2603 0.962 0.956 0.044
#> ERR342822 2 0.0000 1.000 0.000 1.000
#> ERR342892 1 0.0000 0.993 1.000 0.000
#> ERR342842 1 0.0000 0.993 1.000 0.000
#> ERR342902 2 0.0000 1.000 0.000 1.000
#> ERR342900 2 0.0000 1.000 0.000 1.000
#> ERR342888 1 0.0000 0.993 1.000 0.000
#> ERR342812 1 0.0000 0.993 1.000 0.000
#> ERR342853 2 0.0000 1.000 0.000 1.000
#> ERR342866 1 0.0000 0.993 1.000 0.000
#> ERR342820 1 0.0000 0.993 1.000 0.000
#> ERR342895 1 0.0000 0.993 1.000 0.000
#> ERR342825 1 0.2603 0.962 0.956 0.044
#> ERR342826 1 0.2603 0.962 0.956 0.044
#> ERR342875 2 0.0000 1.000 0.000 1.000
#> ERR342834 1 0.2603 0.962 0.956 0.044
#> ERR342898 1 0.0938 0.987 0.988 0.012
#> ERR342886 2 0.0000 1.000 0.000 1.000
#> ERR342838 1 0.0000 0.993 1.000 0.000
#> ERR342882 1 0.0000 0.993 1.000 0.000
#> ERR342807 2 0.0000 1.000 0.000 1.000
#> ERR342873 1 0.0000 0.993 1.000 0.000
#> ERR342844 1 0.0938 0.987 0.988 0.012
#> ERR342874 1 0.0000 0.993 1.000 0.000
#> ERR342893 1 0.0000 0.993 1.000 0.000
#> ERR342859 1 0.2603 0.962 0.956 0.044
#> ERR342830 2 0.0000 1.000 0.000 1.000
#> ERR342880 1 0.0000 0.993 1.000 0.000
#> ERR342887 1 0.0000 0.993 1.000 0.000
#> ERR342854 1 0.0000 0.993 1.000 0.000
#> ERR342904 1 0.0000 0.993 1.000 0.000
#> ERR342881 1 0.0000 0.993 1.000 0.000
#> ERR342858 1 0.0000 0.993 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.0747 0.985 0.984 0 0.016
#> ERR342843 1 0.0747 0.985 0.984 0 0.016
#> ERR342896 1 0.0000 0.986 1.000 0 0.000
#> ERR342827 2 0.0000 1.000 0.000 1 0.000
#> ERR342871 3 0.1860 0.958 0.052 0 0.948
#> ERR342863 2 0.0000 1.000 0.000 1 0.000
#> ERR342839 1 0.0747 0.985 0.984 0 0.016
#> ERR342906 3 0.0000 0.979 0.000 0 1.000
#> ERR342905 2 0.0000 1.000 0.000 1 0.000
#> ERR342816 3 0.0000 0.979 0.000 0 1.000
#> ERR342865 2 0.0000 1.000 0.000 1 0.000
#> ERR342824 1 0.0000 0.986 1.000 0 0.000
#> ERR342841 2 0.0000 1.000 0.000 1 0.000
#> ERR342835 1 0.0747 0.985 0.984 0 0.016
#> ERR342899 2 0.0000 1.000 0.000 1 0.000
#> ERR342829 1 0.0000 0.986 1.000 0 0.000
#> ERR342850 3 0.1860 0.958 0.052 0 0.948
#> ERR342849 2 0.0000 1.000 0.000 1 0.000
#> ERR342811 3 0.1860 0.958 0.052 0 0.948
#> ERR342837 1 0.0747 0.985 0.984 0 0.016
#> ERR342857 3 0.0000 0.979 0.000 0 1.000
#> ERR342869 3 0.1860 0.958 0.052 0 0.948
#> ERR342903 1 0.0000 0.986 1.000 0 0.000
#> ERR342819 1 0.0747 0.985 0.984 0 0.016
#> ERR342885 3 0.0000 0.979 0.000 0 1.000
#> ERR342889 2 0.0000 1.000 0.000 1 0.000
#> ERR342864 3 0.0000 0.979 0.000 0 1.000
#> ERR342860 2 0.0000 1.000 0.000 1 0.000
#> ERR342808 3 0.1860 0.958 0.052 0 0.948
#> ERR342823 1 0.0000 0.986 1.000 0 0.000
#> ERR342907 2 0.0000 1.000 0.000 1 0.000
#> ERR342852 3 0.0000 0.979 0.000 0 1.000
#> ERR342832 2 0.0000 1.000 0.000 1 0.000
#> ERR342868 1 0.0747 0.985 0.984 0 0.016
#> ERR342821 3 0.0000 0.979 0.000 0 1.000
#> ERR342878 2 0.0000 1.000 0.000 1 0.000
#> ERR342876 1 0.0000 0.986 1.000 0 0.000
#> ERR342809 1 0.0000 0.986 1.000 0 0.000
#> ERR342846 3 0.0000 0.979 0.000 0 1.000
#> ERR342872 2 0.0000 1.000 0.000 1 0.000
#> ERR342828 2 0.0000 1.000 0.000 1 0.000
#> ERR342840 1 0.0747 0.985 0.984 0 0.016
#> ERR342831 1 0.0747 0.985 0.984 0 0.016
#> ERR342818 1 0.1411 0.968 0.964 0 0.036
#> ERR342862 1 0.0747 0.985 0.984 0 0.016
#> ERR342894 1 0.0747 0.985 0.984 0 0.016
#> ERR342884 2 0.0000 1.000 0.000 1 0.000
#> ERR342891 1 0.0000 0.986 1.000 0 0.000
#> ERR342890 1 0.0747 0.985 0.984 0 0.016
#> ERR342836 2 0.0000 1.000 0.000 1 0.000
#> ERR342879 1 0.1411 0.968 0.964 0 0.036
#> ERR342848 1 0.1411 0.968 0.964 0 0.036
#> ERR342861 1 0.0000 0.986 1.000 0 0.000
#> ERR342814 2 0.0000 1.000 0.000 1 0.000
#> ERR342870 3 0.1860 0.958 0.052 0 0.948
#> ERR342901 1 0.0000 0.986 1.000 0 0.000
#> ERR342908 3 0.1860 0.958 0.052 0 0.948
#> ERR342815 2 0.0000 1.000 0.000 1 0.000
#> ERR342897 3 0.0000 0.979 0.000 0 1.000
#> ERR342833 2 0.0000 1.000 0.000 1 0.000
#> ERR342817 3 0.0000 0.979 0.000 0 1.000
#> ERR342810 2 0.0000 1.000 0.000 1 0.000
#> ERR342867 3 0.0000 0.979 0.000 0 1.000
#> ERR342847 1 0.0747 0.985 0.984 0 0.016
#> ERR342855 1 0.0000 0.986 1.000 0 0.000
#> ERR342851 1 0.1411 0.968 0.964 0 0.036
#> ERR342813 1 0.0747 0.985 0.984 0 0.016
#> ERR342883 1 0.1411 0.968 0.964 0 0.036
#> ERR342856 3 0.0000 0.979 0.000 0 1.000
#> ERR342822 2 0.0000 1.000 0.000 1 0.000
#> ERR342892 1 0.0000 0.986 1.000 0 0.000
#> ERR342842 1 0.0000 0.986 1.000 0 0.000
#> ERR342902 2 0.0000 1.000 0.000 1 0.000
#> ERR342900 2 0.0000 1.000 0.000 1 0.000
#> ERR342888 1 0.0747 0.985 0.984 0 0.016
#> ERR342812 1 0.0000 0.986 1.000 0 0.000
#> ERR342853 2 0.0000 1.000 0.000 1 0.000
#> ERR342866 1 0.0747 0.985 0.984 0 0.016
#> ERR342820 3 0.1860 0.958 0.052 0 0.948
#> ERR342895 1 0.0000 0.986 1.000 0 0.000
#> ERR342825 3 0.0000 0.979 0.000 0 1.000
#> ERR342826 3 0.0000 0.979 0.000 0 1.000
#> ERR342875 2 0.0000 1.000 0.000 1 0.000
#> ERR342834 3 0.0000 0.979 0.000 0 1.000
#> ERR342898 3 0.0000 0.979 0.000 0 1.000
#> ERR342886 2 0.0000 1.000 0.000 1 0.000
#> ERR342838 1 0.0000 0.986 1.000 0 0.000
#> ERR342882 1 0.0000 0.986 1.000 0 0.000
#> ERR342807 2 0.0000 1.000 0.000 1 0.000
#> ERR342873 1 0.1411 0.968 0.964 0 0.036
#> ERR342844 3 0.0000 0.979 0.000 0 1.000
#> ERR342874 1 0.0747 0.985 0.984 0 0.016
#> ERR342893 1 0.1411 0.968 0.964 0 0.036
#> ERR342859 3 0.0000 0.979 0.000 0 1.000
#> ERR342830 2 0.0000 1.000 0.000 1 0.000
#> ERR342880 1 0.1411 0.968 0.964 0 0.036
#> ERR342887 1 0.0000 0.986 1.000 0 0.000
#> ERR342854 1 0.0000 0.986 1.000 0 0.000
#> ERR342904 3 0.1860 0.958 0.052 0 0.948
#> ERR342881 1 0.0747 0.985 0.984 0 0.016
#> ERR342858 1 0.1411 0.968 0.964 0 0.036
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342843 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342896 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342827 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342871 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342863 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342839 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342906 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342905 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342816 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342865 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342824 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342841 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342835 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342899 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342829 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342850 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342849 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342811 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342837 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342857 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342869 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342903 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342819 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342885 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342889 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342864 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342860 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342808 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342823 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342907 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342852 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342832 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342868 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342821 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342878 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342876 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342846 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342872 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342828 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342840 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342831 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342818 3 0.5168 1.000 0.496 0.000 0.500 0.004
#> ERR342862 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342894 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342884 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342891 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342890 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342836 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342879 3 0.5168 1.000 0.496 0.000 0.500 0.004
#> ERR342848 1 0.5000 -0.992 0.500 0.000 0.500 0.000
#> ERR342861 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342814 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342870 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342901 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342908 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342815 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342897 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342833 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342817 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342810 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342867 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342847 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342855 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342851 3 0.5168 1.000 0.496 0.000 0.500 0.004
#> ERR342813 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342883 3 0.5168 1.000 0.496 0.000 0.500 0.004
#> ERR342856 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342822 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342892 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342902 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342900 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342888 1 0.5503 0.619 0.516 0.000 0.468 0.016
#> ERR342812 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342853 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342866 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342820 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342895 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342825 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342826 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342875 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342834 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342898 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342886 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342838 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342807 2 0.0000 0.999 0.000 1.000 0.000 0.000
#> ERR342873 3 0.5168 1.000 0.496 0.000 0.500 0.004
#> ERR342844 4 0.2647 0.860 0.000 0.000 0.120 0.880
#> ERR342874 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342893 3 0.5168 1.000 0.496 0.000 0.500 0.004
#> ERR342859 4 0.0707 0.879 0.000 0.000 0.020 0.980
#> ERR342830 2 0.0188 0.998 0.000 0.996 0.004 0.000
#> ERR342880 3 0.5168 1.000 0.496 0.000 0.500 0.004
#> ERR342887 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.494 1.000 0.000 0.000 0.000
#> ERR342904 4 0.4469 0.814 0.112 0.000 0.080 0.808
#> ERR342881 1 0.5506 0.618 0.512 0.000 0.472 0.016
#> ERR342858 3 0.5168 1.000 0.496 0.000 0.500 0.004
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342843 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342896 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342827 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342871 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342863 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342839 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342906 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342905 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342816 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342865 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342824 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342841 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342835 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342899 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342829 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342850 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342849 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342811 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342837 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342857 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342869 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342903 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342819 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342885 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342889 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342864 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342860 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342808 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342823 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342907 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342852 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342832 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342868 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342821 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342878 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342876 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342809 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342846 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342872 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342828 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342840 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342831 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342818 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
#> ERR342862 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342894 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342884 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342891 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342890 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342836 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342879 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
#> ERR342848 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
#> ERR342861 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342814 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342870 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342901 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342908 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342815 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342897 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342833 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342817 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342810 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342867 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342847 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342855 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342851 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
#> ERR342813 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342883 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
#> ERR342856 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342822 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342892 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342842 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342902 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342900 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342888 5 0.0290 0.962 0.008 0.00 0.000 0.000 0.992
#> ERR342812 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342853 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342866 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342820 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342895 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342825 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342826 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342875 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342834 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342898 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342886 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342838 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342882 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342807 2 0.0000 0.994 0.000 1.00 0.000 0.000 0.000
#> ERR342873 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
#> ERR342844 3 0.3532 0.748 0.092 0.00 0.832 0.076 0.000
#> ERR342874 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342893 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
#> ERR342859 3 0.4960 0.744 0.104 0.00 0.728 0.160 0.008
#> ERR342830 2 0.0693 0.988 0.008 0.98 0.000 0.012 0.000
#> ERR342880 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
#> ERR342887 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342854 1 0.3636 1.000 0.728 0.00 0.000 0.000 0.272
#> ERR342904 3 0.4563 0.754 0.084 0.00 0.792 0.048 0.076
#> ERR342881 5 0.1630 0.961 0.036 0.00 0.004 0.016 0.944
#> ERR342858 4 0.4495 1.000 0.196 0.00 0.024 0.752 0.028
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342843 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342871 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342863 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342839 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342906 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342905 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342816 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342865 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342835 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342899 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342849 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342811 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342837 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342857 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342869 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342885 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342889 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342864 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342860 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342808 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342852 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342832 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342868 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342821 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342878 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342872 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342828 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342840 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342831 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342818 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
#> ERR342862 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342894 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342884 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342836 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342879 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
#> ERR342848 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342870 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342815 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342897 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342833 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342817 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342810 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342867 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342847 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342851 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
#> ERR342813 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342883 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
#> ERR342856 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342822 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342900 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342888 5 0.4700 0.907 0.112 0.000 0.016 0.104 0.748 0.020
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342866 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342820 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342875 2 0.0000 0.983 0.000 1.000 0.000 0.000 0.000 0.000
#> ERR342834 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342898 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342886 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.0405 0.982 0.000 0.988 0.000 0.004 0.000 0.008
#> ERR342873 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
#> ERR342844 4 0.3171 0.564 0.000 0.000 0.204 0.784 0.000 0.012
#> ERR342874 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342893 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
#> ERR342859 3 0.0000 1.000 0.000 0.000 1.000 0.000 0.000 0.000
#> ERR342830 2 0.1167 0.975 0.000 0.960 0.000 0.012 0.020 0.008
#> ERR342880 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.7012 0.493 0.016 0.000 0.332 0.388 0.228 0.036
#> ERR342881 5 0.2378 0.906 0.152 0.000 0.000 0.000 0.848 0.000
#> ERR342858 6 0.1364 1.000 0.048 0.000 0.000 0.004 0.004 0.944
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "pam"]
# you can also extract it by
# res = res_list["ATC:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 1.000 1.000 0.4053 0.595 0.595
#> 3 3 0.878 0.847 0.942 0.6409 0.745 0.571
#> 4 4 0.747 0.745 0.825 0.0647 0.958 0.884
#> 5 5 0.739 0.736 0.810 0.0668 0.862 0.610
#> 6 6 0.834 0.757 0.874 0.0552 0.908 0.652
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0 1 1 0
#> ERR342843 1 0 1 1 0
#> ERR342896 1 0 1 1 0
#> ERR342827 2 0 1 0 1
#> ERR342871 1 0 1 1 0
#> ERR342863 2 0 1 0 1
#> ERR342839 1 0 1 1 0
#> ERR342906 1 0 1 1 0
#> ERR342905 2 0 1 0 1
#> ERR342816 1 0 1 1 0
#> ERR342865 2 0 1 0 1
#> ERR342824 1 0 1 1 0
#> ERR342841 2 0 1 0 1
#> ERR342835 1 0 1 1 0
#> ERR342899 2 0 1 0 1
#> ERR342829 1 0 1 1 0
#> ERR342850 1 0 1 1 0
#> ERR342849 2 0 1 0 1
#> ERR342811 1 0 1 1 0
#> ERR342837 1 0 1 1 0
#> ERR342857 1 0 1 1 0
#> ERR342869 1 0 1 1 0
#> ERR342903 1 0 1 1 0
#> ERR342819 1 0 1 1 0
#> ERR342885 1 0 1 1 0
#> ERR342889 2 0 1 0 1
#> ERR342864 1 0 1 1 0
#> ERR342860 2 0 1 0 1
#> ERR342808 1 0 1 1 0
#> ERR342823 1 0 1 1 0
#> ERR342907 2 0 1 0 1
#> ERR342852 1 0 1 1 0
#> ERR342832 2 0 1 0 1
#> ERR342868 1 0 1 1 0
#> ERR342821 1 0 1 1 0
#> ERR342878 2 0 1 0 1
#> ERR342876 1 0 1 1 0
#> ERR342809 1 0 1 1 0
#> ERR342846 1 0 1 1 0
#> ERR342872 2 0 1 0 1
#> ERR342828 2 0 1 0 1
#> ERR342840 1 0 1 1 0
#> ERR342831 1 0 1 1 0
#> ERR342818 1 0 1 1 0
#> ERR342862 1 0 1 1 0
#> ERR342894 1 0 1 1 0
#> ERR342884 2 0 1 0 1
#> ERR342891 1 0 1 1 0
#> ERR342890 1 0 1 1 0
#> ERR342836 2 0 1 0 1
#> ERR342879 1 0 1 1 0
#> ERR342848 1 0 1 1 0
#> ERR342861 1 0 1 1 0
#> ERR342814 2 0 1 0 1
#> ERR342870 1 0 1 1 0
#> ERR342901 1 0 1 1 0
#> ERR342908 1 0 1 1 0
#> ERR342815 2 0 1 0 1
#> ERR342897 1 0 1 1 0
#> ERR342833 2 0 1 0 1
#> ERR342817 1 0 1 1 0
#> ERR342810 2 0 1 0 1
#> ERR342867 1 0 1 1 0
#> ERR342847 1 0 1 1 0
#> ERR342855 1 0 1 1 0
#> ERR342851 1 0 1 1 0
#> ERR342813 1 0 1 1 0
#> ERR342883 1 0 1 1 0
#> ERR342856 1 0 1 1 0
#> ERR342822 2 0 1 0 1
#> ERR342892 1 0 1 1 0
#> ERR342842 1 0 1 1 0
#> ERR342902 2 0 1 0 1
#> ERR342900 2 0 1 0 1
#> ERR342888 1 0 1 1 0
#> ERR342812 1 0 1 1 0
#> ERR342853 2 0 1 0 1
#> ERR342866 1 0 1 1 0
#> ERR342820 1 0 1 1 0
#> ERR342895 1 0 1 1 0
#> ERR342825 1 0 1 1 0
#> ERR342826 1 0 1 1 0
#> ERR342875 2 0 1 0 1
#> ERR342834 1 0 1 1 0
#> ERR342898 1 0 1 1 0
#> ERR342886 2 0 1 0 1
#> ERR342838 1 0 1 1 0
#> ERR342882 1 0 1 1 0
#> ERR342807 2 0 1 0 1
#> ERR342873 1 0 1 1 0
#> ERR342844 1 0 1 1 0
#> ERR342874 1 0 1 1 0
#> ERR342893 1 0 1 1 0
#> ERR342859 1 0 1 1 0
#> ERR342830 2 0 1 0 1
#> ERR342880 1 0 1 1 0
#> ERR342887 1 0 1 1 0
#> ERR342854 1 0 1 1 0
#> ERR342904 1 0 1 1 0
#> ERR342881 1 0 1 1 0
#> ERR342858 1 0 1 1 0
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342843 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342896 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342827 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342871 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342863 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342839 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342906 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342905 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342816 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342865 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342824 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342841 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342835 1 0.0892 0.8671 0.980 0.000 0.020
#> ERR342899 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342829 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342850 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342849 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342811 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342837 1 0.0592 0.8721 0.988 0.000 0.012
#> ERR342857 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342869 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342903 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342819 1 0.0747 0.8697 0.984 0.000 0.016
#> ERR342885 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342889 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342864 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342860 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342808 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342823 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342907 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342852 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342832 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342868 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342821 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342878 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342876 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342809 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342846 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342872 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342828 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342840 1 0.6192 0.2910 0.580 0.000 0.420
#> ERR342831 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342818 1 0.6280 0.2227 0.540 0.000 0.460
#> ERR342862 1 0.6309 0.0701 0.504 0.000 0.496
#> ERR342894 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342884 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342891 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342890 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342836 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342879 1 0.6168 0.3497 0.588 0.000 0.412
#> ERR342848 1 0.4291 0.7189 0.820 0.000 0.180
#> ERR342861 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342814 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342870 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342901 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342908 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342815 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342897 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342833 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342817 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342810 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342867 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342847 1 0.1529 0.8538 0.960 0.000 0.040
#> ERR342855 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342851 1 0.6045 0.4187 0.620 0.000 0.380
#> ERR342813 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342883 3 0.6274 0.0159 0.456 0.000 0.544
#> ERR342856 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342822 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342892 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342842 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342902 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342900 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342888 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342812 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342853 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342866 3 0.6267 0.0633 0.452 0.000 0.548
#> ERR342820 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342895 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342825 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342826 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342875 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342834 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342898 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342886 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342838 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342882 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342807 2 0.0000 0.9969 0.000 1.000 0.000
#> ERR342873 1 0.5859 0.4810 0.656 0.000 0.344
#> ERR342844 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342874 1 0.6291 0.1597 0.532 0.000 0.468
#> ERR342893 1 0.6126 0.3776 0.600 0.000 0.400
#> ERR342859 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342830 2 0.0424 0.9943 0.000 0.992 0.008
#> ERR342880 3 0.5882 0.3588 0.348 0.000 0.652
#> ERR342887 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342854 1 0.0000 0.8787 1.000 0.000 0.000
#> ERR342904 3 0.0000 0.9483 0.000 0.000 1.000
#> ERR342881 1 0.6215 0.2711 0.572 0.000 0.428
#> ERR342858 1 0.6286 0.2128 0.536 0.000 0.464
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342843 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342896 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342827 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342871 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342863 2 0.443 0.8868 0.000 0.696 NA 0.000
#> ERR342839 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342906 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342905 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342816 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342865 2 0.438 0.8864 0.000 0.704 NA 0.000
#> ERR342824 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342841 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342835 1 0.273 0.8150 0.896 0.000 NA 0.016
#> ERR342899 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342829 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342850 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342849 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342811 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342837 1 0.172 0.8363 0.944 0.000 NA 0.008
#> ERR342857 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342869 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342903 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342819 1 0.220 0.8308 0.920 0.000 NA 0.008
#> ERR342885 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342889 2 0.443 0.8868 0.000 0.696 NA 0.000
#> ERR342864 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342860 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342808 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342823 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342907 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342852 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342832 2 0.394 0.8784 0.000 0.764 NA 0.000
#> ERR342868 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342821 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342878 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342876 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342809 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342846 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342872 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342828 2 0.443 0.8868 0.000 0.696 NA 0.000
#> ERR342840 1 0.648 0.4105 0.564 0.000 NA 0.084
#> ERR342831 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342818 1 0.737 -0.2532 0.432 0.000 NA 0.408
#> ERR342862 1 0.676 0.3598 0.536 0.000 NA 0.104
#> ERR342894 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342884 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342891 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342890 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342836 2 0.443 0.8868 0.000 0.696 NA 0.000
#> ERR342879 4 0.741 0.3155 0.388 0.000 NA 0.444
#> ERR342848 1 0.364 0.6718 0.820 0.000 NA 0.172
#> ERR342861 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342814 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342870 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342901 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342908 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342815 2 0.443 0.8868 0.000 0.696 NA 0.000
#> ERR342897 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342833 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342817 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342810 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342867 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342847 1 0.400 0.7631 0.812 0.000 NA 0.024
#> ERR342855 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342851 1 0.720 -0.0959 0.484 0.000 NA 0.372
#> ERR342813 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342883 4 0.757 0.4153 0.340 0.000 NA 0.456
#> ERR342856 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342822 2 0.443 0.8868 0.000 0.696 NA 0.000
#> ERR342892 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342842 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342902 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342900 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342888 1 0.276 0.8205 0.872 0.000 NA 0.000
#> ERR342812 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342853 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342866 1 0.676 0.3598 0.536 0.000 NA 0.104
#> ERR342820 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342895 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342825 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342826 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342875 2 0.443 0.8868 0.000 0.696 NA 0.000
#> ERR342834 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342898 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342886 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342838 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342882 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342807 2 0.479 0.8752 0.000 0.620 NA 0.000
#> ERR342873 1 0.634 0.2329 0.600 0.000 NA 0.316
#> ERR342844 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342874 1 0.671 0.3685 0.540 0.000 NA 0.100
#> ERR342893 1 0.731 -0.2332 0.436 0.000 NA 0.412
#> ERR342859 4 0.000 0.6575 0.000 0.000 NA 1.000
#> ERR342830 2 0.000 0.8223 0.000 1.000 NA 0.000
#> ERR342880 4 0.761 0.5509 0.264 0.000 NA 0.476
#> ERR342887 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342854 1 0.000 0.8457 1.000 0.000 NA 0.000
#> ERR342904 4 0.500 0.8158 0.000 0.000 NA 0.508
#> ERR342881 1 0.631 0.4291 0.576 0.000 NA 0.072
#> ERR342858 4 0.743 0.3333 0.380 0.000 NA 0.448
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342843 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342896 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342871 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342863 2 0.000 0.8050 0.000 1.000 0.000 0.000 0.000
#> ERR342839 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342906 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342905 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342816 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342865 2 0.029 0.8048 0.000 0.992 0.000 0.000 0.008
#> ERR342824 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342835 1 0.601 0.0624 0.528 0.000 0.000 0.344 0.128
#> ERR342899 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342829 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342849 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342811 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342837 1 0.512 0.2102 0.692 0.000 0.000 0.188 0.120
#> ERR342857 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342869 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342903 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342819 1 0.592 0.0740 0.564 0.000 0.000 0.304 0.132
#> ERR342885 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342889 2 0.000 0.8050 0.000 1.000 0.000 0.000 0.000
#> ERR342864 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342860 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342808 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342823 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342852 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342832 2 0.167 0.7975 0.000 0.924 0.000 0.000 0.076
#> ERR342868 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342821 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342878 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342876 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342872 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342828 2 0.000 0.8050 0.000 1.000 0.000 0.000 0.000
#> ERR342840 1 0.610 0.0378 0.480 0.000 0.000 0.392 0.128
#> ERR342831 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342818 4 0.393 0.5022 0.328 0.000 0.000 0.672 0.000
#> ERR342862 1 0.613 0.0259 0.456 0.000 0.000 0.416 0.128
#> ERR342894 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342884 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342891 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342836 2 0.000 0.8050 0.000 1.000 0.000 0.000 0.000
#> ERR342879 4 0.345 0.6144 0.244 0.000 0.000 0.756 0.000
#> ERR342848 1 0.297 0.4224 0.816 0.000 0.000 0.184 0.000
#> ERR342861 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342870 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342901 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342815 2 0.000 0.8050 0.000 1.000 0.000 0.000 0.000
#> ERR342897 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342833 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342817 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342810 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342867 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342847 1 0.615 0.0282 0.488 0.000 0.000 0.376 0.136
#> ERR342855 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.393 0.5040 0.328 0.000 0.000 0.672 0.000
#> ERR342813 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342883 4 0.112 0.8405 0.044 0.000 0.000 0.956 0.000
#> ERR342856 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342822 2 0.000 0.8050 0.000 1.000 0.000 0.000 0.000
#> ERR342892 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342900 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342888 5 0.423 1.0000 0.424 0.000 0.000 0.000 0.576
#> ERR342812 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342866 1 0.613 0.0259 0.456 0.000 0.000 0.416 0.128
#> ERR342820 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342895 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342826 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342875 2 0.000 0.8050 0.000 1.000 0.000 0.000 0.000
#> ERR342834 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342898 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342886 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342838 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.511 0.7628 0.000 0.680 0.224 0.000 0.096
#> ERR342873 4 0.425 0.3377 0.432 0.000 0.000 0.568 0.000
#> ERR342844 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342874 1 0.612 0.0261 0.460 0.000 0.000 0.412 0.128
#> ERR342893 4 0.389 0.5141 0.320 0.000 0.000 0.680 0.000
#> ERR342859 3 0.331 1.0000 0.000 0.000 0.776 0.224 0.000
#> ERR342830 2 0.393 0.7820 0.000 0.672 0.000 0.000 0.328
#> ERR342880 4 0.029 0.8726 0.008 0.000 0.000 0.992 0.000
#> ERR342887 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.000 0.6755 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.000 0.8787 0.000 0.000 0.000 1.000 0.000
#> ERR342881 1 0.604 0.0516 0.488 0.000 0.000 0.392 0.120
#> ERR342858 4 0.321 0.6546 0.212 0.000 0.000 0.788 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342843 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342896 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342827 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342871 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342863 2 0.1556 0.811 0.000 0.920 0 0.000 0.000 0.080
#> ERR342839 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342906 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342905 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342816 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342865 2 0.1501 0.812 0.000 0.924 0 0.000 0.000 0.076
#> ERR342824 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342841 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342835 1 0.6103 -0.309 0.368 0.000 0 0.344 0.288 0.000
#> ERR342899 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342829 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342850 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342849 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342811 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342837 1 0.5602 -0.133 0.536 0.000 0 0.188 0.276 0.000
#> ERR342857 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342869 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342903 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342819 1 0.6062 -0.289 0.408 0.000 0 0.304 0.288 0.000
#> ERR342885 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342889 2 0.1556 0.811 0.000 0.920 0 0.000 0.000 0.080
#> ERR342864 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342860 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342808 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342823 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342907 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342852 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342832 2 0.0713 0.819 0.000 0.972 0 0.000 0.000 0.028
#> ERR342868 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342821 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342878 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342876 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342872 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342828 2 0.1556 0.811 0.000 0.920 0 0.000 0.000 0.080
#> ERR342840 4 0.6080 -0.254 0.316 0.000 0 0.396 0.288 0.000
#> ERR342831 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342818 4 0.3499 0.497 0.320 0.000 0 0.680 0.000 0.000
#> ERR342862 4 0.6069 -0.241 0.308 0.000 0 0.404 0.288 0.000
#> ERR342894 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342884 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342891 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342890 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342836 2 0.1556 0.811 0.000 0.920 0 0.000 0.000 0.080
#> ERR342879 4 0.3101 0.597 0.244 0.000 0 0.756 0.000 0.000
#> ERR342848 1 0.2597 0.604 0.824 0.000 0 0.176 0.000 0.000
#> ERR342861 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342814 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342870 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342901 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342908 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342815 2 0.1556 0.811 0.000 0.920 0 0.000 0.000 0.080
#> ERR342897 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342833 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342817 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342810 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342867 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342847 4 0.6099 -0.286 0.328 0.000 0 0.380 0.292 0.000
#> ERR342855 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342851 4 0.3482 0.503 0.316 0.000 0 0.684 0.000 0.000
#> ERR342813 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342883 4 0.1007 0.764 0.044 0.000 0 0.956 0.000 0.000
#> ERR342856 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342822 2 0.1556 0.811 0.000 0.920 0 0.000 0.000 0.080
#> ERR342892 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342902 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342900 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342888 5 0.3198 1.000 0.260 0.000 0 0.000 0.740 0.000
#> ERR342812 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342853 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342866 4 0.6069 -0.241 0.308 0.000 0 0.404 0.288 0.000
#> ERR342820 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342895 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342875 2 0.1556 0.811 0.000 0.920 0 0.000 0.000 0.080
#> ERR342834 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342898 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342886 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342838 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342807 6 0.0000 1.000 0.000 0.000 0 0.000 0.000 1.000
#> ERR342873 4 0.3774 0.337 0.408 0.000 0 0.592 0.000 0.000
#> ERR342844 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342874 4 0.6069 -0.241 0.308 0.000 0 0.404 0.288 0.000
#> ERR342893 4 0.3464 0.509 0.312 0.000 0 0.688 0.000 0.000
#> ERR342859 3 0.0000 1.000 0.000 0.000 1 0.000 0.000 0.000
#> ERR342830 2 0.3198 0.846 0.000 0.740 0 0.000 0.260 0.000
#> ERR342880 4 0.0260 0.783 0.008 0.000 0 0.992 0.000 0.000
#> ERR342887 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.872 1.000 0.000 0 0.000 0.000 0.000
#> ERR342904 4 0.0000 0.787 0.000 0.000 0 1.000 0.000 0.000
#> ERR342881 4 0.6067 -0.242 0.324 0.000 0 0.400 0.276 0.000
#> ERR342858 4 0.2883 0.633 0.212 0.000 0 0.788 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "mclust"]
# you can also extract it by
# res = res_list["ATC:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 6.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.836 0.954 0.966 0.4888 0.499 0.499
#> 3 3 0.587 0.866 0.849 0.2876 0.836 0.682
#> 4 4 0.720 0.700 0.769 0.1274 0.852 0.629
#> 5 5 0.866 0.916 0.922 0.0724 0.968 0.887
#> 6 6 1.000 0.999 0.999 0.0731 0.932 0.730
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 6
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 2 0.0000 0.972 0.000 1.000
#> ERR342843 2 0.0000 0.972 0.000 1.000
#> ERR342896 1 0.0000 0.955 1.000 0.000
#> ERR342827 2 0.0000 0.972 0.000 1.000
#> ERR342871 1 0.4022 0.955 0.920 0.080
#> ERR342863 2 0.0000 0.972 0.000 1.000
#> ERR342839 2 0.0000 0.972 0.000 1.000
#> ERR342906 1 0.4022 0.955 0.920 0.080
#> ERR342905 2 0.0000 0.972 0.000 1.000
#> ERR342816 1 0.4022 0.955 0.920 0.080
#> ERR342865 2 0.0000 0.972 0.000 1.000
#> ERR342824 1 0.0376 0.956 0.996 0.004
#> ERR342841 2 0.0000 0.972 0.000 1.000
#> ERR342835 2 0.5519 0.870 0.128 0.872
#> ERR342899 2 0.0000 0.972 0.000 1.000
#> ERR342829 1 0.0000 0.955 1.000 0.000
#> ERR342850 1 0.4022 0.955 0.920 0.080
#> ERR342849 2 0.0000 0.972 0.000 1.000
#> ERR342811 1 0.4022 0.955 0.920 0.080
#> ERR342837 2 0.5519 0.870 0.128 0.872
#> ERR342857 1 0.4022 0.955 0.920 0.080
#> ERR342869 1 0.4022 0.955 0.920 0.080
#> ERR342903 1 0.0000 0.955 1.000 0.000
#> ERR342819 2 0.5519 0.870 0.128 0.872
#> ERR342885 1 0.4022 0.955 0.920 0.080
#> ERR342889 2 0.0000 0.972 0.000 1.000
#> ERR342864 1 0.4022 0.955 0.920 0.080
#> ERR342860 2 0.0000 0.972 0.000 1.000
#> ERR342808 1 0.4022 0.955 0.920 0.080
#> ERR342823 1 0.0376 0.956 0.996 0.004
#> ERR342907 2 0.0000 0.972 0.000 1.000
#> ERR342852 1 0.4022 0.955 0.920 0.080
#> ERR342832 2 0.0000 0.972 0.000 1.000
#> ERR342868 2 0.0000 0.972 0.000 1.000
#> ERR342821 1 0.4022 0.955 0.920 0.080
#> ERR342878 2 0.0000 0.972 0.000 1.000
#> ERR342876 1 0.0000 0.955 1.000 0.000
#> ERR342809 1 0.0000 0.955 1.000 0.000
#> ERR342846 1 0.4022 0.955 0.920 0.080
#> ERR342872 2 0.0000 0.972 0.000 1.000
#> ERR342828 2 0.0000 0.972 0.000 1.000
#> ERR342840 2 0.5519 0.870 0.128 0.872
#> ERR342831 2 0.0000 0.972 0.000 1.000
#> ERR342818 1 0.0376 0.956 0.996 0.004
#> ERR342862 2 0.5519 0.870 0.128 0.872
#> ERR342894 2 0.0000 0.972 0.000 1.000
#> ERR342884 2 0.0000 0.972 0.000 1.000
#> ERR342891 1 0.0000 0.955 1.000 0.000
#> ERR342890 2 0.0000 0.972 0.000 1.000
#> ERR342836 2 0.0000 0.972 0.000 1.000
#> ERR342879 1 0.0376 0.956 0.996 0.004
#> ERR342848 1 0.3114 0.956 0.944 0.056
#> ERR342861 1 0.0000 0.955 1.000 0.000
#> ERR342814 2 0.0000 0.972 0.000 1.000
#> ERR342870 1 0.4022 0.955 0.920 0.080
#> ERR342901 1 0.0000 0.955 1.000 0.000
#> ERR342908 1 0.4022 0.955 0.920 0.080
#> ERR342815 2 0.0000 0.972 0.000 1.000
#> ERR342897 1 0.4022 0.955 0.920 0.080
#> ERR342833 2 0.0000 0.972 0.000 1.000
#> ERR342817 1 0.4022 0.955 0.920 0.080
#> ERR342810 2 0.0000 0.972 0.000 1.000
#> ERR342867 1 0.4022 0.955 0.920 0.080
#> ERR342847 2 0.5519 0.870 0.128 0.872
#> ERR342855 1 0.0000 0.955 1.000 0.000
#> ERR342851 1 0.0376 0.956 0.996 0.004
#> ERR342813 2 0.0000 0.972 0.000 1.000
#> ERR342883 1 0.0376 0.956 0.996 0.004
#> ERR342856 1 0.4022 0.955 0.920 0.080
#> ERR342822 2 0.0000 0.972 0.000 1.000
#> ERR342892 1 0.0000 0.955 1.000 0.000
#> ERR342842 1 0.0000 0.955 1.000 0.000
#> ERR342902 2 0.0000 0.972 0.000 1.000
#> ERR342900 2 0.0000 0.972 0.000 1.000
#> ERR342888 2 0.0000 0.972 0.000 1.000
#> ERR342812 1 0.0000 0.955 1.000 0.000
#> ERR342853 2 0.0000 0.972 0.000 1.000
#> ERR342866 2 0.5519 0.870 0.128 0.872
#> ERR342820 1 0.4022 0.955 0.920 0.080
#> ERR342895 1 0.0000 0.955 1.000 0.000
#> ERR342825 1 0.4022 0.955 0.920 0.080
#> ERR342826 1 0.4022 0.955 0.920 0.080
#> ERR342875 2 0.0000 0.972 0.000 1.000
#> ERR342834 1 0.4022 0.955 0.920 0.080
#> ERR342898 1 0.4022 0.955 0.920 0.080
#> ERR342886 2 0.0000 0.972 0.000 1.000
#> ERR342838 1 0.0000 0.955 1.000 0.000
#> ERR342882 1 0.0000 0.955 1.000 0.000
#> ERR342807 2 0.0000 0.972 0.000 1.000
#> ERR342873 1 0.0376 0.956 0.996 0.004
#> ERR342844 1 0.4022 0.955 0.920 0.080
#> ERR342874 2 0.5519 0.870 0.128 0.872
#> ERR342893 1 0.0376 0.956 0.996 0.004
#> ERR342859 1 0.4022 0.955 0.920 0.080
#> ERR342830 2 0.0000 0.972 0.000 1.000
#> ERR342880 1 0.0376 0.956 0.996 0.004
#> ERR342887 1 0.0000 0.955 1.000 0.000
#> ERR342854 1 0.0000 0.955 1.000 0.000
#> ERR342904 1 0.4022 0.955 0.920 0.080
#> ERR342881 2 0.5519 0.870 0.128 0.872
#> ERR342858 1 0.0376 0.956 0.996 0.004
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342843 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342896 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342827 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342871 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342863 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342839 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342906 1 0.5016 0.795 0.760 0.000 0.240
#> ERR342905 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342816 1 0.5254 0.786 0.736 0.000 0.264
#> ERR342865 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342824 1 0.0000 0.850 1.000 0.000 0.000
#> ERR342841 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342835 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342899 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342829 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342850 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342849 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342811 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342837 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342857 1 0.5058 0.794 0.756 0.000 0.244
#> ERR342869 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342903 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342819 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342885 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342889 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342864 1 0.5016 0.795 0.760 0.000 0.240
#> ERR342860 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342808 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342823 1 0.0000 0.850 1.000 0.000 0.000
#> ERR342907 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342852 1 0.5098 0.793 0.752 0.000 0.248
#> ERR342832 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342868 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342821 1 0.5178 0.790 0.744 0.000 0.256
#> ERR342878 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342876 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342809 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342846 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342872 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342828 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342840 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342831 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342818 1 0.0237 0.850 0.996 0.000 0.004
#> ERR342862 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342894 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342884 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342891 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342890 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342836 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342879 1 0.0237 0.850 0.996 0.000 0.004
#> ERR342848 1 0.0237 0.850 0.996 0.000 0.004
#> ERR342861 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342814 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342870 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342901 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342908 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342815 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342897 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342833 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342817 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342810 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342867 1 0.5098 0.793 0.752 0.000 0.248
#> ERR342847 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342855 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342851 1 0.0237 0.850 0.996 0.000 0.004
#> ERR342813 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342883 1 0.0237 0.850 0.996 0.000 0.004
#> ERR342856 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342822 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342892 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342842 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342902 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342900 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342888 2 0.1031 0.921 0.000 0.976 0.024
#> ERR342812 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342853 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342866 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342820 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342895 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342825 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342826 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342875 2 0.2711 0.921 0.000 0.912 0.088
#> ERR342834 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342898 1 0.5058 0.794 0.756 0.000 0.244
#> ERR342886 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342838 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342882 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342807 3 0.4861 0.871 0.008 0.192 0.800
#> ERR342873 1 0.0237 0.850 0.996 0.000 0.004
#> ERR342844 1 0.5254 0.786 0.736 0.000 0.264
#> ERR342874 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342893 1 0.0237 0.850 0.996 0.000 0.004
#> ERR342859 3 0.8442 0.878 0.188 0.192 0.620
#> ERR342830 2 0.2448 0.926 0.000 0.924 0.076
#> ERR342880 1 0.0237 0.850 0.996 0.000 0.004
#> ERR342887 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342854 1 0.2448 0.843 0.924 0.076 0.000
#> ERR342904 1 0.5591 0.762 0.696 0.000 0.304
#> ERR342881 2 0.1765 0.914 0.004 0.956 0.040
#> ERR342858 1 0.0237 0.850 0.996 0.000 0.004
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342843 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342896 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342827 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342871 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342863 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342839 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342906 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342905 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342816 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342865 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342824 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342841 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342835 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342899 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342829 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342850 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342849 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342811 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342837 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342857 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342869 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342903 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342819 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342885 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342889 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342864 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342860 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342808 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342823 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342907 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342852 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342832 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342868 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342821 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342878 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342876 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342846 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342872 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342828 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342840 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342831 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342818 1 0.0592 0.988 0.984 0.000 0.000 0.016
#> ERR342862 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342894 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342884 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342891 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342890 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342836 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342879 1 0.0592 0.988 0.984 0.000 0.000 0.016
#> ERR342848 1 0.0707 0.984 0.980 0.000 0.000 0.020
#> ERR342861 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342814 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342870 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342901 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342908 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342815 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342897 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342833 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342817 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342810 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342867 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342847 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342855 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342851 1 0.0592 0.988 0.984 0.000 0.000 0.016
#> ERR342813 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342883 1 0.0592 0.988 0.984 0.000 0.000 0.016
#> ERR342856 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342822 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342892 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342902 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342900 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342888 2 0.6627 0.590 0.000 0.556 0.096 0.348
#> ERR342812 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342853 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342866 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342820 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342895 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342825 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342826 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342875 2 0.0469 0.829 0.000 0.988 0.012 0.000
#> ERR342834 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342898 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342886 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342838 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342807 3 0.5077 1.000 0.000 0.160 0.760 0.080
#> ERR342873 1 0.0592 0.988 0.984 0.000 0.000 0.016
#> ERR342844 4 0.4584 0.424 0.004 0.000 0.300 0.696
#> ERR342874 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342893 1 0.0592 0.988 0.984 0.000 0.000 0.016
#> ERR342859 4 0.7249 -0.236 0.000 0.412 0.144 0.444
#> ERR342830 2 0.0000 0.833 0.000 1.000 0.000 0.000
#> ERR342880 1 0.0592 0.988 0.984 0.000 0.000 0.016
#> ERR342887 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.994 1.000 0.000 0.000 0.000
#> ERR342904 4 0.4722 0.424 0.008 0.000 0.300 0.692
#> ERR342881 2 0.3634 0.812 0.000 0.856 0.096 0.048
#> ERR342858 1 0.0592 0.988 0.984 0.000 0.000 0.016
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342843 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342896 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342871 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342863 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342839 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342906 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342905 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342816 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342865 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342824 1 0.0162 0.992 0.996 0.000 0.000 0.004 0.000
#> ERR342841 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342835 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342899 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342829 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342849 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342811 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342837 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342857 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342869 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342903 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342885 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342889 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342864 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342860 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342808 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342823 1 0.0162 0.992 0.996 0.000 0.000 0.004 0.000
#> ERR342907 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342852 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342832 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342868 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342821 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342878 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342876 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342872 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342828 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342840 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342831 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342818 1 0.0404 0.988 0.988 0.000 0.000 0.012 0.000
#> ERR342862 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342894 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342884 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342891 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342836 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342879 1 0.0404 0.988 0.988 0.000 0.000 0.012 0.000
#> ERR342848 1 0.1043 0.958 0.960 0.000 0.000 0.040 0.000
#> ERR342861 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342814 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342870 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342901 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342815 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342897 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342833 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342817 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342810 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342867 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342847 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342855 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342851 1 0.0404 0.988 0.988 0.000 0.000 0.012 0.000
#> ERR342813 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342883 1 0.0404 0.988 0.988 0.000 0.000 0.012 0.000
#> ERR342856 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342822 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342892 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342900 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342888 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342812 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342853 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342866 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342820 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342895 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342826 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342875 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342834 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342898 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342886 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342838 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.5477 1.000 0.000 0.648 0.132 0.000 0.220
#> ERR342873 1 0.0404 0.988 0.988 0.000 0.000 0.012 0.000
#> ERR342844 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342874 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342893 1 0.0880 0.968 0.968 0.000 0.000 0.032 0.000
#> ERR342859 3 0.2424 1.000 0.000 0.000 0.868 0.132 0.000
#> ERR342830 5 0.0000 0.774 0.000 0.000 0.000 0.000 1.000
#> ERR342880 1 0.0404 0.988 0.988 0.000 0.000 0.012 0.000
#> ERR342887 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.993 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.0000 1.000 0.000 0.000 0.000 1.000 0.000
#> ERR342881 5 0.4030 0.786 0.000 0.352 0.000 0.000 0.648
#> ERR342858 1 0.0404 0.988 0.988 0.000 0.000 0.012 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342843 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342896 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342827 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342871 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342863 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342839 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342906 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342905 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342816 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342865 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342824 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342841 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342835 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342899 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342829 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342850 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342849 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342811 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342837 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342857 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342869 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342903 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342819 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342885 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342889 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342864 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342860 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342808 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342823 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342907 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342852 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342832 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342868 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342821 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342878 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342876 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342809 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342846 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342872 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342828 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342840 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342831 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342818 1 0.026 0.994 0.992 0 0 0.008 0 0
#> ERR342862 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342894 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342884 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342891 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342890 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342836 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342879 1 0.026 0.994 0.992 0 0 0.008 0 0
#> ERR342848 1 0.026 0.994 0.992 0 0 0.008 0 0
#> ERR342861 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342814 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342870 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342901 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342908 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342815 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342897 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342833 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342817 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342810 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342867 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342847 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342855 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342851 1 0.026 0.994 0.992 0 0 0.008 0 0
#> ERR342813 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342883 1 0.026 0.994 0.992 0 0 0.008 0 0
#> ERR342856 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342822 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342892 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342842 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342902 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342900 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342888 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342812 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342853 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342866 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342820 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342895 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342825 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342826 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342875 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342834 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342898 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342886 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342838 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342882 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342807 6 0.000 1.000 0.000 0 0 0.000 0 1
#> ERR342873 1 0.026 0.994 0.992 0 0 0.008 0 0
#> ERR342844 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342874 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342893 1 0.026 0.994 0.992 0 0 0.008 0 0
#> ERR342859 3 0.000 1.000 0.000 0 1 0.000 0 0
#> ERR342830 2 0.000 1.000 0.000 1 0 0.000 0 0
#> ERR342880 1 0.026 0.994 0.992 0 0 0.008 0 0
#> ERR342887 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342854 1 0.000 0.997 1.000 0 0 0.000 0 0
#> ERR342904 4 0.000 1.000 0.000 0 0 1.000 0 0
#> ERR342881 5 0.000 1.000 0.000 0 0 0.000 1 0
#> ERR342858 1 0.026 0.994 0.992 0 0 0.008 0 0
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "NMF"]
# you can also extract it by
# res = res_list["ATC:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 15144 rows and 101 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 1.000 1.000 0.4053 0.595 0.595
#> 3 3 1.000 0.998 0.997 0.6048 0.754 0.587
#> 4 4 0.827 0.926 0.915 0.1438 0.900 0.714
#> 5 5 0.863 0.926 0.929 0.0546 0.902 0.652
#> 6 6 0.887 0.837 0.857 0.0373 1.000 1.000
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
#> attr(,"optional")
#> [1] 2
There is also optional best \(k\) = 2 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> ERR342845 1 0 1 1 0
#> ERR342843 1 0 1 1 0
#> ERR342896 1 0 1 1 0
#> ERR342827 2 0 1 0 1
#> ERR342871 1 0 1 1 0
#> ERR342863 2 0 1 0 1
#> ERR342839 1 0 1 1 0
#> ERR342906 1 0 1 1 0
#> ERR342905 2 0 1 0 1
#> ERR342816 1 0 1 1 0
#> ERR342865 2 0 1 0 1
#> ERR342824 1 0 1 1 0
#> ERR342841 2 0 1 0 1
#> ERR342835 1 0 1 1 0
#> ERR342899 2 0 1 0 1
#> ERR342829 1 0 1 1 0
#> ERR342850 1 0 1 1 0
#> ERR342849 2 0 1 0 1
#> ERR342811 1 0 1 1 0
#> ERR342837 1 0 1 1 0
#> ERR342857 1 0 1 1 0
#> ERR342869 1 0 1 1 0
#> ERR342903 1 0 1 1 0
#> ERR342819 1 0 1 1 0
#> ERR342885 1 0 1 1 0
#> ERR342889 2 0 1 0 1
#> ERR342864 1 0 1 1 0
#> ERR342860 2 0 1 0 1
#> ERR342808 1 0 1 1 0
#> ERR342823 1 0 1 1 0
#> ERR342907 2 0 1 0 1
#> ERR342852 1 0 1 1 0
#> ERR342832 2 0 1 0 1
#> ERR342868 1 0 1 1 0
#> ERR342821 1 0 1 1 0
#> ERR342878 2 0 1 0 1
#> ERR342876 1 0 1 1 0
#> ERR342809 1 0 1 1 0
#> ERR342846 1 0 1 1 0
#> ERR342872 2 0 1 0 1
#> ERR342828 2 0 1 0 1
#> ERR342840 1 0 1 1 0
#> ERR342831 1 0 1 1 0
#> ERR342818 1 0 1 1 0
#> ERR342862 1 0 1 1 0
#> ERR342894 1 0 1 1 0
#> ERR342884 2 0 1 0 1
#> ERR342891 1 0 1 1 0
#> ERR342890 1 0 1 1 0
#> ERR342836 2 0 1 0 1
#> ERR342879 1 0 1 1 0
#> ERR342848 1 0 1 1 0
#> ERR342861 1 0 1 1 0
#> ERR342814 2 0 1 0 1
#> ERR342870 1 0 1 1 0
#> ERR342901 1 0 1 1 0
#> ERR342908 1 0 1 1 0
#> ERR342815 2 0 1 0 1
#> ERR342897 1 0 1 1 0
#> ERR342833 2 0 1 0 1
#> ERR342817 1 0 1 1 0
#> ERR342810 2 0 1 0 1
#> ERR342867 1 0 1 1 0
#> ERR342847 1 0 1 1 0
#> ERR342855 1 0 1 1 0
#> ERR342851 1 0 1 1 0
#> ERR342813 1 0 1 1 0
#> ERR342883 1 0 1 1 0
#> ERR342856 1 0 1 1 0
#> ERR342822 2 0 1 0 1
#> ERR342892 1 0 1 1 0
#> ERR342842 1 0 1 1 0
#> ERR342902 2 0 1 0 1
#> ERR342900 2 0 1 0 1
#> ERR342888 1 0 1 1 0
#> ERR342812 1 0 1 1 0
#> ERR342853 2 0 1 0 1
#> ERR342866 1 0 1 1 0
#> ERR342820 1 0 1 1 0
#> ERR342895 1 0 1 1 0
#> ERR342825 1 0 1 1 0
#> ERR342826 1 0 1 1 0
#> ERR342875 2 0 1 0 1
#> ERR342834 1 0 1 1 0
#> ERR342898 1 0 1 1 0
#> ERR342886 2 0 1 0 1
#> ERR342838 1 0 1 1 0
#> ERR342882 1 0 1 1 0
#> ERR342807 2 0 1 0 1
#> ERR342873 1 0 1 1 0
#> ERR342844 1 0 1 1 0
#> ERR342874 1 0 1 1 0
#> ERR342893 1 0 1 1 0
#> ERR342859 1 0 1 1 0
#> ERR342830 2 0 1 0 1
#> ERR342880 1 0 1 1 0
#> ERR342887 1 0 1 1 0
#> ERR342854 1 0 1 1 0
#> ERR342904 1 0 1 1 0
#> ERR342881 1 0 1 1 0
#> ERR342858 1 0 1 1 0
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> ERR342845 1 0.0000 0.997 1.000 0 0.000
#> ERR342843 1 0.0000 0.997 1.000 0 0.000
#> ERR342896 1 0.0237 0.997 0.996 0 0.004
#> ERR342827 2 0.0000 1.000 0.000 1 0.000
#> ERR342871 3 0.0237 1.000 0.004 0 0.996
#> ERR342863 2 0.0000 1.000 0.000 1 0.000
#> ERR342839 1 0.0000 0.997 1.000 0 0.000
#> ERR342906 3 0.0237 1.000 0.004 0 0.996
#> ERR342905 2 0.0000 1.000 0.000 1 0.000
#> ERR342816 3 0.0237 1.000 0.004 0 0.996
#> ERR342865 2 0.0000 1.000 0.000 1 0.000
#> ERR342824 1 0.0237 0.997 0.996 0 0.004
#> ERR342841 2 0.0000 1.000 0.000 1 0.000
#> ERR342835 1 0.0000 0.997 1.000 0 0.000
#> ERR342899 2 0.0000 1.000 0.000 1 0.000
#> ERR342829 1 0.0237 0.997 0.996 0 0.004
#> ERR342850 3 0.0237 1.000 0.004 0 0.996
#> ERR342849 2 0.0000 1.000 0.000 1 0.000
#> ERR342811 3 0.0237 1.000 0.004 0 0.996
#> ERR342837 1 0.0000 0.997 1.000 0 0.000
#> ERR342857 3 0.0237 1.000 0.004 0 0.996
#> ERR342869 3 0.0237 1.000 0.004 0 0.996
#> ERR342903 1 0.0237 0.997 0.996 0 0.004
#> ERR342819 1 0.0000 0.997 1.000 0 0.000
#> ERR342885 3 0.0237 1.000 0.004 0 0.996
#> ERR342889 2 0.0000 1.000 0.000 1 0.000
#> ERR342864 3 0.0237 1.000 0.004 0 0.996
#> ERR342860 2 0.0000 1.000 0.000 1 0.000
#> ERR342808 3 0.0237 1.000 0.004 0 0.996
#> ERR342823 1 0.0237 0.997 0.996 0 0.004
#> ERR342907 2 0.0000 1.000 0.000 1 0.000
#> ERR342852 3 0.0237 1.000 0.004 0 0.996
#> ERR342832 2 0.0000 1.000 0.000 1 0.000
#> ERR342868 1 0.0000 0.997 1.000 0 0.000
#> ERR342821 3 0.0237 1.000 0.004 0 0.996
#> ERR342878 2 0.0000 1.000 0.000 1 0.000
#> ERR342876 1 0.0237 0.997 0.996 0 0.004
#> ERR342809 1 0.0237 0.997 0.996 0 0.004
#> ERR342846 3 0.0237 1.000 0.004 0 0.996
#> ERR342872 2 0.0000 1.000 0.000 1 0.000
#> ERR342828 2 0.0000 1.000 0.000 1 0.000
#> ERR342840 1 0.0000 0.997 1.000 0 0.000
#> ERR342831 1 0.0000 0.997 1.000 0 0.000
#> ERR342818 1 0.0592 0.994 0.988 0 0.012
#> ERR342862 1 0.0000 0.997 1.000 0 0.000
#> ERR342894 1 0.0000 0.997 1.000 0 0.000
#> ERR342884 2 0.0000 1.000 0.000 1 0.000
#> ERR342891 1 0.0237 0.997 0.996 0 0.004
#> ERR342890 1 0.0000 0.997 1.000 0 0.000
#> ERR342836 2 0.0000 1.000 0.000 1 0.000
#> ERR342879 1 0.0592 0.994 0.988 0 0.012
#> ERR342848 1 0.0592 0.994 0.988 0 0.012
#> ERR342861 1 0.0237 0.997 0.996 0 0.004
#> ERR342814 2 0.0000 1.000 0.000 1 0.000
#> ERR342870 3 0.0237 1.000 0.004 0 0.996
#> ERR342901 1 0.0237 0.997 0.996 0 0.004
#> ERR342908 3 0.0237 1.000 0.004 0 0.996
#> ERR342815 2 0.0000 1.000 0.000 1 0.000
#> ERR342897 3 0.0237 1.000 0.004 0 0.996
#> ERR342833 2 0.0000 1.000 0.000 1 0.000
#> ERR342817 3 0.0237 1.000 0.004 0 0.996
#> ERR342810 2 0.0000 1.000 0.000 1 0.000
#> ERR342867 3 0.0237 1.000 0.004 0 0.996
#> ERR342847 1 0.0000 0.997 1.000 0 0.000
#> ERR342855 1 0.0237 0.997 0.996 0 0.004
#> ERR342851 1 0.0592 0.994 0.988 0 0.012
#> ERR342813 1 0.0000 0.997 1.000 0 0.000
#> ERR342883 1 0.0592 0.994 0.988 0 0.012
#> ERR342856 3 0.0237 1.000 0.004 0 0.996
#> ERR342822 2 0.0000 1.000 0.000 1 0.000
#> ERR342892 1 0.0237 0.997 0.996 0 0.004
#> ERR342842 1 0.0237 0.997 0.996 0 0.004
#> ERR342902 2 0.0000 1.000 0.000 1 0.000
#> ERR342900 2 0.0000 1.000 0.000 1 0.000
#> ERR342888 1 0.0000 0.997 1.000 0 0.000
#> ERR342812 1 0.0237 0.997 0.996 0 0.004
#> ERR342853 2 0.0000 1.000 0.000 1 0.000
#> ERR342866 1 0.0000 0.997 1.000 0 0.000
#> ERR342820 3 0.0237 1.000 0.004 0 0.996
#> ERR342895 1 0.0237 0.997 0.996 0 0.004
#> ERR342825 3 0.0237 1.000 0.004 0 0.996
#> ERR342826 3 0.0237 1.000 0.004 0 0.996
#> ERR342875 2 0.0000 1.000 0.000 1 0.000
#> ERR342834 3 0.0237 1.000 0.004 0 0.996
#> ERR342898 3 0.0237 1.000 0.004 0 0.996
#> ERR342886 2 0.0000 1.000 0.000 1 0.000
#> ERR342838 1 0.0237 0.997 0.996 0 0.004
#> ERR342882 1 0.0237 0.997 0.996 0 0.004
#> ERR342807 2 0.0000 1.000 0.000 1 0.000
#> ERR342873 1 0.0592 0.994 0.988 0 0.012
#> ERR342844 3 0.0237 1.000 0.004 0 0.996
#> ERR342874 1 0.0000 0.997 1.000 0 0.000
#> ERR342893 1 0.0592 0.994 0.988 0 0.012
#> ERR342859 3 0.0237 1.000 0.004 0 0.996
#> ERR342830 2 0.0000 1.000 0.000 1 0.000
#> ERR342880 1 0.0592 0.994 0.988 0 0.012
#> ERR342887 1 0.0237 0.997 0.996 0 0.004
#> ERR342854 1 0.0237 0.997 0.996 0 0.004
#> ERR342904 3 0.0237 1.000 0.004 0 0.996
#> ERR342881 1 0.0000 0.997 1.000 0 0.000
#> ERR342858 1 0.0747 0.991 0.984 0 0.016
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> ERR342845 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342843 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342896 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342827 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342871 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342863 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342839 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342906 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342905 2 0.1637 0.952 0.000 0.940 0.060 0.000
#> ERR342816 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342865 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342824 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342841 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342835 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342899 2 0.1637 0.952 0.000 0.940 0.060 0.000
#> ERR342829 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342850 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342849 2 0.1389 0.959 0.000 0.952 0.048 0.000
#> ERR342811 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342837 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342857 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342869 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342903 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342819 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342885 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342889 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342864 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342860 2 0.2868 0.874 0.000 0.864 0.136 0.000
#> ERR342808 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342823 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342907 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342852 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342832 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342868 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342821 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342878 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342876 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342846 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342872 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342828 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342840 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342831 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342818 1 0.4931 0.790 0.776 0.000 0.092 0.132
#> ERR342862 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342894 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342884 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342891 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342890 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342836 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342879 1 0.4931 0.790 0.776 0.000 0.092 0.132
#> ERR342848 1 0.4931 0.790 0.776 0.000 0.092 0.132
#> ERR342861 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342814 2 0.1022 0.967 0.000 0.968 0.032 0.000
#> ERR342870 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342901 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342908 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342815 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342897 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342833 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342817 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342810 2 0.1716 0.949 0.000 0.936 0.064 0.000
#> ERR342867 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342847 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342855 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342851 1 0.4931 0.790 0.776 0.000 0.092 0.132
#> ERR342813 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342883 1 0.4931 0.790 0.776 0.000 0.092 0.132
#> ERR342856 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342822 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342892 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342902 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342900 2 0.1022 0.967 0.000 0.968 0.032 0.000
#> ERR342888 3 0.3907 0.995 0.232 0.000 0.768 0.000
#> ERR342812 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342853 2 0.1022 0.967 0.000 0.968 0.032 0.000
#> ERR342866 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342820 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342895 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342825 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342826 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342875 2 0.0000 0.977 0.000 1.000 0.000 0.000
#> ERR342834 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342898 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342886 2 0.1716 0.949 0.000 0.936 0.064 0.000
#> ERR342838 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342807 2 0.0336 0.976 0.000 0.992 0.008 0.000
#> ERR342873 1 0.4931 0.790 0.776 0.000 0.092 0.132
#> ERR342844 4 0.2216 0.906 0.000 0.000 0.092 0.908
#> ERR342874 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342893 1 0.4931 0.790 0.776 0.000 0.092 0.132
#> ERR342859 4 0.2814 0.893 0.000 0.000 0.132 0.868
#> ERR342830 2 0.1716 0.949 0.000 0.936 0.064 0.000
#> ERR342880 1 0.4931 0.790 0.776 0.000 0.092 0.132
#> ERR342887 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 0.890 1.000 0.000 0.000 0.000
#> ERR342904 4 0.0188 0.928 0.004 0.000 0.000 0.996
#> ERR342881 3 0.3975 0.995 0.240 0.000 0.760 0.000
#> ERR342858 1 0.4931 0.790 0.776 0.000 0.092 0.132
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> ERR342845 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342843 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342827 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342871 4 0.4004 0.755 0.004 0.000 0.172 0.784 0.040
#> ERR342863 2 0.0000 0.960 0.000 1.000 0.000 0.000 0.000
#> ERR342839 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342906 4 0.0566 0.846 0.000 0.000 0.004 0.984 0.012
#> ERR342905 2 0.0404 0.957 0.000 0.988 0.000 0.000 0.012
#> ERR342816 4 0.0451 0.847 0.000 0.000 0.004 0.988 0.008
#> ERR342865 2 0.0000 0.960 0.000 1.000 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342841 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342835 5 0.2433 0.961 0.056 0.000 0.012 0.024 0.908
#> ERR342899 2 0.0290 0.959 0.000 0.992 0.000 0.000 0.008
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342850 4 0.4004 0.755 0.004 0.000 0.172 0.784 0.040
#> ERR342849 2 0.0290 0.959 0.000 0.992 0.000 0.000 0.008
#> ERR342811 4 0.4125 0.752 0.008 0.000 0.172 0.780 0.040
#> ERR342837 5 0.2341 0.962 0.056 0.000 0.012 0.020 0.912
#> ERR342857 4 0.0324 0.847 0.000 0.000 0.004 0.992 0.004
#> ERR342869 4 0.4004 0.755 0.004 0.000 0.172 0.784 0.040
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342819 5 0.2341 0.962 0.056 0.000 0.012 0.020 0.912
#> ERR342885 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342889 2 0.0000 0.960 0.000 1.000 0.000 0.000 0.000
#> ERR342864 4 0.0324 0.847 0.000 0.000 0.004 0.992 0.004
#> ERR342860 2 0.0794 0.946 0.000 0.972 0.000 0.000 0.028
#> ERR342808 4 0.4125 0.752 0.008 0.000 0.172 0.780 0.040
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342907 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342852 4 0.0451 0.847 0.000 0.000 0.004 0.988 0.008
#> ERR342832 2 0.0000 0.960 0.000 1.000 0.000 0.000 0.000
#> ERR342868 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342821 4 0.0451 0.847 0.000 0.000 0.004 0.988 0.008
#> ERR342878 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342846 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342872 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342828 2 0.0000 0.960 0.000 1.000 0.000 0.000 0.000
#> ERR342840 5 0.2270 0.961 0.052 0.000 0.012 0.020 0.916
#> ERR342831 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342818 4 0.2574 0.814 0.112 0.000 0.000 0.876 0.012
#> ERR342862 5 0.2536 0.955 0.052 0.000 0.012 0.032 0.904
#> ERR342894 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342884 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342890 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342836 2 0.0000 0.960 0.000 1.000 0.000 0.000 0.000
#> ERR342879 4 0.2574 0.814 0.112 0.000 0.000 0.876 0.012
#> ERR342848 4 0.3242 0.758 0.172 0.000 0.000 0.816 0.012
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342814 2 0.0290 0.959 0.000 0.992 0.000 0.000 0.008
#> ERR342870 4 0.4004 0.755 0.004 0.000 0.172 0.784 0.040
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342908 4 0.4125 0.752 0.008 0.000 0.172 0.780 0.040
#> ERR342815 2 0.0162 0.960 0.000 0.996 0.000 0.000 0.004
#> ERR342897 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342833 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342817 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342810 2 0.0510 0.955 0.000 0.984 0.000 0.000 0.016
#> ERR342867 4 0.0324 0.847 0.000 0.000 0.004 0.992 0.004
#> ERR342847 5 0.2341 0.962 0.056 0.000 0.012 0.020 0.912
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342851 4 0.2574 0.814 0.112 0.000 0.000 0.876 0.012
#> ERR342813 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342883 4 0.2574 0.814 0.112 0.000 0.000 0.876 0.012
#> ERR342856 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342822 2 0.0000 0.960 0.000 1.000 0.000 0.000 0.000
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342902 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342900 2 0.0162 0.960 0.000 0.996 0.000 0.000 0.004
#> ERR342888 5 0.1892 0.964 0.080 0.000 0.004 0.000 0.916
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342853 2 0.0290 0.959 0.000 0.992 0.000 0.000 0.008
#> ERR342866 5 0.2536 0.955 0.052 0.000 0.012 0.032 0.904
#> ERR342820 4 0.4004 0.755 0.004 0.000 0.172 0.784 0.040
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342825 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342826 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342875 2 0.0000 0.960 0.000 1.000 0.000 0.000 0.000
#> ERR342834 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342898 4 0.0324 0.847 0.000 0.000 0.004 0.992 0.004
#> ERR342886 2 0.0290 0.959 0.000 0.992 0.000 0.000 0.008
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342807 2 0.2685 0.922 0.000 0.880 0.092 0.000 0.028
#> ERR342873 4 0.2624 0.811 0.116 0.000 0.000 0.872 0.012
#> ERR342844 4 0.0324 0.847 0.000 0.000 0.004 0.992 0.004
#> ERR342874 5 0.2536 0.955 0.052 0.000 0.012 0.032 0.904
#> ERR342893 4 0.2574 0.814 0.112 0.000 0.000 0.876 0.012
#> ERR342859 3 0.2074 1.000 0.000 0.000 0.896 0.104 0.000
#> ERR342830 2 0.0290 0.959 0.000 0.992 0.000 0.000 0.008
#> ERR342880 4 0.2574 0.814 0.112 0.000 0.000 0.876 0.012
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.000 0.000 0.000
#> ERR342904 4 0.4125 0.752 0.008 0.000 0.172 0.780 0.040
#> ERR342881 5 0.2536 0.955 0.052 0.000 0.012 0.032 0.904
#> ERR342858 4 0.2574 0.814 0.112 0.000 0.000 0.876 0.012
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> ERR342845 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342843 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342896 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342827 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342871 4 0.5957 0.626 0.000 0.000 0.06 0.600 0.212 0.128
#> ERR342863 2 0.0000 0.898 0.000 1.000 0.00 0.000 0.000 0.000
#> ERR342839 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342906 4 0.0891 0.743 0.000 0.000 0.00 0.968 0.008 0.024
#> ERR342905 2 0.0520 0.895 0.000 0.984 0.00 0.000 0.008 0.008
#> ERR342816 4 0.0508 0.746 0.000 0.000 0.00 0.984 0.004 0.012
#> ERR342865 2 0.0000 0.898 0.000 1.000 0.00 0.000 0.000 0.000
#> ERR342824 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342841 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342835 5 0.1789 0.790 0.032 0.000 0.00 0.044 0.924 0.000
#> ERR342899 2 0.0405 0.896 0.000 0.988 0.00 0.000 0.008 0.004
#> ERR342829 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342850 4 0.5980 0.624 0.000 0.000 0.06 0.596 0.216 0.128
#> ERR342849 2 0.0405 0.896 0.000 0.988 0.00 0.000 0.008 0.004
#> ERR342811 4 0.5980 0.624 0.000 0.000 0.06 0.596 0.216 0.128
#> ERR342837 5 0.1789 0.790 0.032 0.000 0.00 0.044 0.924 0.000
#> ERR342857 4 0.0146 0.746 0.000 0.000 0.00 0.996 0.000 0.004
#> ERR342869 4 0.5980 0.624 0.000 0.000 0.06 0.596 0.216 0.128
#> ERR342903 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342819 5 0.1789 0.790 0.032 0.000 0.00 0.044 0.924 0.000
#> ERR342885 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342889 2 0.0000 0.898 0.000 1.000 0.00 0.000 0.000 0.000
#> ERR342864 4 0.0146 0.746 0.000 0.000 0.00 0.996 0.000 0.004
#> ERR342860 2 0.0622 0.893 0.000 0.980 0.00 0.000 0.012 0.008
#> ERR342808 4 0.5957 0.626 0.000 0.000 0.06 0.600 0.212 0.128
#> ERR342823 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342907 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342852 4 0.0146 0.746 0.000 0.000 0.00 0.996 0.000 0.004
#> ERR342832 2 0.0000 0.898 0.000 1.000 0.00 0.000 0.000 0.000
#> ERR342868 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342821 4 0.0603 0.745 0.000 0.000 0.00 0.980 0.004 0.016
#> ERR342878 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342876 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342809 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342846 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342872 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342828 2 0.0146 0.897 0.000 0.996 0.00 0.000 0.000 0.004
#> ERR342840 5 0.1713 0.791 0.028 0.000 0.00 0.044 0.928 0.000
#> ERR342831 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342818 4 0.4363 0.682 0.024 0.000 0.00 0.684 0.020 0.272
#> ERR342862 5 0.2846 0.737 0.024 0.000 0.00 0.084 0.868 0.024
#> ERR342894 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342884 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342891 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342890 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342836 2 0.0000 0.898 0.000 1.000 0.00 0.000 0.000 0.000
#> ERR342879 4 0.4363 0.682 0.024 0.000 0.00 0.684 0.020 0.272
#> ERR342848 4 0.5773 0.569 0.144 0.000 0.00 0.564 0.020 0.272
#> ERR342861 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342814 2 0.0405 0.896 0.000 0.988 0.00 0.000 0.004 0.008
#> ERR342870 4 0.5980 0.624 0.000 0.000 0.06 0.596 0.216 0.128
#> ERR342901 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342908 4 0.5957 0.626 0.000 0.000 0.06 0.600 0.212 0.128
#> ERR342815 2 0.0260 0.897 0.000 0.992 0.00 0.000 0.000 0.008
#> ERR342897 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342833 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342817 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342810 2 0.0405 0.896 0.000 0.988 0.00 0.000 0.004 0.008
#> ERR342867 4 0.0000 0.746 0.000 0.000 0.00 1.000 0.000 0.000
#> ERR342847 5 0.1644 0.792 0.028 0.000 0.00 0.040 0.932 0.000
#> ERR342855 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342851 4 0.4363 0.682 0.024 0.000 0.00 0.684 0.020 0.272
#> ERR342813 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342883 4 0.4363 0.682 0.024 0.000 0.00 0.684 0.020 0.272
#> ERR342856 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342822 2 0.0146 0.897 0.000 0.996 0.00 0.000 0.000 0.004
#> ERR342892 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342842 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342902 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342900 2 0.0405 0.896 0.000 0.988 0.00 0.000 0.008 0.004
#> ERR342888 5 0.4152 0.798 0.032 0.000 0.00 0.000 0.664 0.304
#> ERR342812 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342853 2 0.0520 0.895 0.000 0.984 0.00 0.000 0.008 0.008
#> ERR342866 5 0.2358 0.774 0.028 0.000 0.00 0.056 0.900 0.016
#> ERR342820 4 0.5980 0.624 0.000 0.000 0.06 0.596 0.216 0.128
#> ERR342895 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342825 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342826 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342875 2 0.0146 0.897 0.000 0.996 0.00 0.000 0.000 0.004
#> ERR342834 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342898 4 0.0000 0.746 0.000 0.000 0.00 1.000 0.000 0.000
#> ERR342886 2 0.0405 0.896 0.000 0.988 0.00 0.000 0.008 0.004
#> ERR342838 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342882 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342807 2 0.3464 0.776 0.000 0.688 0.00 0.000 0.000 0.312
#> ERR342873 4 0.4436 0.680 0.028 0.000 0.00 0.680 0.020 0.272
#> ERR342844 4 0.0146 0.746 0.000 0.000 0.00 0.996 0.000 0.004
#> ERR342874 5 0.2763 0.749 0.028 0.000 0.00 0.072 0.876 0.024
#> ERR342893 4 0.4363 0.682 0.024 0.000 0.00 0.684 0.020 0.272
#> ERR342859 3 0.0000 1.000 0.000 0.000 1.00 0.000 0.000 0.000
#> ERR342830 2 0.0405 0.896 0.000 0.988 0.00 0.000 0.008 0.004
#> ERR342880 4 0.4363 0.682 0.024 0.000 0.00 0.684 0.020 0.272
#> ERR342887 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342854 1 0.0000 1.000 1.000 0.000 0.00 0.000 0.000 0.000
#> ERR342904 4 0.5980 0.624 0.000 0.000 0.06 0.596 0.216 0.128
#> ERR342881 5 0.2917 0.751 0.032 0.000 0.00 0.072 0.868 0.028
#> ERR342858 4 0.4363 0.682 0.024 0.000 0.00 0.684 0.020 0.272
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
sessionInfo()
#> R version 3.6.0 (2019-04-26)
#> Platform: x86_64-pc-linux-gnu (64-bit)
#> Running under: CentOS Linux 7 (Core)
#>
#> Matrix products: default
#> BLAS: /usr/lib64/libblas.so.3.4.2
#> LAPACK: /usr/lib64/liblapack.so.3.4.2
#>
#> locale:
#> [1] LC_CTYPE=en_GB.UTF-8 LC_NUMERIC=C LC_TIME=en_GB.UTF-8
#> [4] LC_COLLATE=en_GB.UTF-8 LC_MONETARY=en_GB.UTF-8 LC_MESSAGES=en_GB.UTF-8
#> [7] LC_PAPER=en_GB.UTF-8 LC_NAME=C LC_ADDRESS=C
#> [10] LC_TELEPHONE=C LC_MEASUREMENT=en_GB.UTF-8 LC_IDENTIFICATION=C
#>
#> attached base packages:
#> [1] grid stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] genefilter_1.66.0 ComplexHeatmap_2.3.1 markdown_1.1 knitr_1.26
#> [5] GetoptLong_0.1.7 cola_1.3.2
#>
#> loaded via a namespace (and not attached):
#> [1] circlize_0.4.8 shape_1.4.4 xfun_0.11 slam_0.1-46
#> [5] lattice_0.20-38 splines_3.6.0 colorspace_1.4-1 vctrs_0.2.0
#> [9] stats4_3.6.0 blob_1.2.0 XML_3.98-1.20 survival_2.44-1.1
#> [13] rlang_0.4.2 pillar_1.4.2 DBI_1.0.0 BiocGenerics_0.30.0
#> [17] bit64_0.9-7 RColorBrewer_1.1-2 matrixStats_0.55.0 stringr_1.4.0
#> [21] GlobalOptions_0.1.1 evaluate_0.14 memoise_1.1.0 Biobase_2.44.0
#> [25] IRanges_2.18.3 parallel_3.6.0 AnnotationDbi_1.46.1 highr_0.8
#> [29] Rcpp_1.0.3 xtable_1.8-4 backports_1.1.5 S4Vectors_0.22.1
#> [33] annotate_1.62.0 skmeans_0.2-11 bit_1.1-14 microbenchmark_1.4-7
#> [37] brew_1.0-6 impute_1.58.0 rjson_0.2.20 png_0.1-7
#> [41] digest_0.6.23 stringi_1.4.3 polyclip_1.10-0 clue_0.3-57
#> [45] tools_3.6.0 bitops_1.0-6 magrittr_1.5 eulerr_6.0.0
#> [49] RCurl_1.95-4.12 RSQLite_2.1.4 tibble_2.1.3 cluster_2.1.0
#> [53] crayon_1.3.4 pkgconfig_2.0.3 zeallot_0.1.0 Matrix_1.2-17
#> [57] xml2_1.2.2 httr_1.4.1 R6_2.4.1 mclust_5.4.5
#> [61] compiler_3.6.0