Date: 2019-12-25 21:30:38 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 31589 rows and 108 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, anno = anno)
Dimension of the input matrix:
mat = get_matrix(res_list)
dim(mat)
#> [1] 31589 108
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, top_annotation = HeatmapAnnotation(df = get_anno(res_list),
col = get_anno_col(res_list)), 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 | ||
|---|---|---|---|---|---|
| SD:kmeans | 2 | 1.000 | 0.995 | 0.998 | ** |
| SD:skmeans | 2 | 1.000 | 0.974 | 0.989 | ** |
| SD:mclust | 2 | 1.000 | 0.995 | 0.998 | ** |
| MAD:mclust | 2 | 1.000 | 0.989 | 0.995 | ** |
| ATC:kmeans | 2 | 1.000 | 0.986 | 0.994 | ** |
| ATC:skmeans | 2 | 1.000 | 0.999 | 0.999 | ** |
| ATC:pam | 2 | 1.000 | 0.972 | 0.989 | ** |
| ATC:mclust | 2 | 1.000 | 0.990 | 0.993 | ** |
| ATC:NMF | 2 | 1.000 | 0.970 | 0.987 | ** |
| SD:NMF | 2 | 0.999 | 0.955 | 0.981 | ** |
| CV:mclust | 2 | 0.980 | 0.962 | 0.983 | ** |
| ATC:hclust | 2 | 0.978 | 0.949 | 0.974 | ** |
| MAD:kmeans | 2 | 0.923 | 0.936 | 0.970 | * |
| MAD:skmeans | 2 | 0.923 | 0.940 | 0.975 | * |
| MAD:NMF | 2 | 0.867 | 0.918 | 0.965 | |
| CV:skmeans | 2 | 0.830 | 0.886 | 0.954 | |
| CV:NMF | 2 | 0.813 | 0.883 | 0.952 | |
| CV:kmeans | 3 | 0.772 | 0.853 | 0.915 | |
| SD:pam | 3 | 0.697 | 0.865 | 0.927 | |
| MAD:pam | 2 | 0.642 | 0.893 | 0.927 | |
| CV:pam | 3 | 0.484 | 0.727 | 0.873 | |
| SD:hclust | 4 | 0.327 | 0.583 | 0.729 | |
| CV:hclust | 4 | 0.313 | 0.586 | 0.733 | |
| MAD:hclust | 3 | 0.302 | 0.638 | 0.791 |
**: 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 0.999 0.955 0.981 0.446 0.551 0.551
#> CV:NMF 2 0.813 0.883 0.952 0.459 0.551 0.551
#> MAD:NMF 2 0.867 0.918 0.965 0.462 0.534 0.534
#> ATC:NMF 2 1.000 0.970 0.987 0.447 0.558 0.558
#> SD:skmeans 2 1.000 0.974 0.989 0.481 0.520 0.520
#> CV:skmeans 2 0.830 0.886 0.954 0.496 0.502 0.502
#> MAD:skmeans 2 0.923 0.940 0.975 0.490 0.516 0.516
#> ATC:skmeans 2 1.000 0.999 0.999 0.476 0.525 0.525
#> SD:mclust 2 1.000 0.995 0.998 0.347 0.651 0.651
#> CV:mclust 2 0.980 0.962 0.983 0.315 0.695 0.695
#> MAD:mclust 2 1.000 0.989 0.995 0.348 0.651 0.651
#> ATC:mclust 2 1.000 0.990 0.993 0.354 0.651 0.651
#> SD:kmeans 2 1.000 0.995 0.998 0.352 0.651 0.651
#> CV:kmeans 2 0.799 0.898 0.954 0.390 0.641 0.641
#> MAD:kmeans 2 0.923 0.936 0.970 0.378 0.651 0.651
#> ATC:kmeans 2 1.000 0.986 0.994 0.370 0.631 0.631
#> SD:pam 2 0.681 0.830 0.909 0.371 0.565 0.565
#> CV:pam 2 0.506 0.880 0.853 0.318 0.732 0.732
#> MAD:pam 2 0.642 0.893 0.927 0.448 0.551 0.551
#> ATC:pam 2 1.000 0.972 0.989 0.384 0.612 0.612
#> SD:hclust 2 0.760 0.863 0.940 0.325 0.720 0.720
#> CV:hclust 2 0.430 0.814 0.886 0.362 0.662 0.662
#> MAD:hclust 2 0.719 0.849 0.934 0.335 0.707 0.707
#> ATC:hclust 2 0.978 0.949 0.974 0.341 0.684 0.684
get_stats(res_list, k = 3)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 3 0.794 0.871 0.942 0.262 0.861 0.758
#> CV:NMF 3 0.592 0.737 0.876 0.296 0.797 0.655
#> MAD:NMF 3 0.749 0.795 0.914 0.279 0.802 0.658
#> ATC:NMF 3 0.657 0.748 0.887 0.392 0.747 0.566
#> SD:skmeans 3 0.860 0.874 0.945 0.379 0.750 0.547
#> CV:skmeans 3 0.693 0.779 0.898 0.334 0.748 0.538
#> MAD:skmeans 3 0.811 0.871 0.940 0.360 0.771 0.575
#> ATC:skmeans 3 0.896 0.886 0.952 0.263 0.877 0.771
#> SD:mclust 3 0.556 0.746 0.812 0.645 0.745 0.608
#> CV:mclust 3 0.414 0.716 0.818 0.877 0.648 0.503
#> MAD:mclust 3 0.598 0.799 0.847 0.669 0.709 0.553
#> ATC:mclust 3 0.470 0.629 0.803 0.745 0.695 0.531
#> SD:kmeans 3 0.680 0.847 0.904 0.816 0.695 0.531
#> CV:kmeans 3 0.772 0.853 0.915 0.655 0.693 0.526
#> MAD:kmeans 3 0.783 0.915 0.938 0.720 0.695 0.531
#> ATC:kmeans 3 0.866 0.889 0.952 0.709 0.695 0.528
#> SD:pam 3 0.697 0.865 0.927 0.650 0.701 0.523
#> CV:pam 3 0.484 0.727 0.873 0.858 0.669 0.548
#> MAD:pam 3 0.514 0.774 0.857 0.372 0.714 0.534
#> ATC:pam 3 0.899 0.925 0.969 0.539 0.745 0.603
#> SD:hclust 3 0.272 0.498 0.728 0.828 0.634 0.496
#> CV:hclust 3 0.259 0.544 0.712 0.595 0.690 0.538
#> MAD:hclust 3 0.302 0.638 0.791 0.834 0.641 0.497
#> ATC:hclust 3 0.432 0.726 0.821 0.625 0.760 0.649
get_stats(res_list, k = 4)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 4 0.614 0.722 0.863 0.2209 0.729 0.472
#> CV:NMF 4 0.591 0.699 0.858 0.1790 0.778 0.529
#> MAD:NMF 4 0.589 0.660 0.846 0.1716 0.776 0.528
#> ATC:NMF 4 0.491 0.435 0.687 0.1376 0.868 0.664
#> SD:skmeans 4 0.620 0.534 0.737 0.1192 0.916 0.758
#> CV:skmeans 4 0.533 0.594 0.776 0.1297 0.853 0.599
#> MAD:skmeans 4 0.588 0.536 0.739 0.1181 0.940 0.825
#> ATC:skmeans 4 0.757 0.836 0.894 0.1852 0.828 0.597
#> SD:mclust 4 0.604 0.768 0.845 0.1866 0.824 0.603
#> CV:mclust 4 0.304 0.586 0.752 0.1281 0.858 0.647
#> MAD:mclust 4 0.639 0.761 0.877 0.1847 0.896 0.733
#> ATC:mclust 4 0.585 0.674 0.805 0.1036 0.811 0.543
#> SD:kmeans 4 0.598 0.636 0.806 0.1483 0.882 0.678
#> CV:kmeans 4 0.555 0.585 0.775 0.1358 0.855 0.624
#> MAD:kmeans 4 0.586 0.615 0.795 0.1375 0.892 0.702
#> ATC:kmeans 4 0.594 0.608 0.766 0.1292 0.930 0.811
#> SD:pam 4 0.763 0.826 0.918 0.1621 0.893 0.731
#> CV:pam 4 0.488 0.635 0.797 0.2016 0.734 0.442
#> MAD:pam 4 0.678 0.772 0.883 0.1680 0.861 0.663
#> ATC:pam 4 0.718 0.790 0.841 0.0973 0.958 0.902
#> SD:hclust 4 0.327 0.583 0.729 0.1813 0.794 0.516
#> CV:hclust 4 0.313 0.586 0.733 0.1725 0.848 0.638
#> MAD:hclust 4 0.348 0.533 0.712 0.1398 0.918 0.783
#> ATC:hclust 4 0.471 0.660 0.784 0.1730 0.971 0.935
get_stats(res_list, k = 5)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 5 0.531 0.539 0.752 0.0942 0.877 0.637
#> CV:NMF 5 0.536 0.553 0.747 0.0962 0.866 0.588
#> MAD:NMF 5 0.550 0.559 0.756 0.0920 0.862 0.605
#> ATC:NMF 5 0.532 0.506 0.715 0.0659 0.774 0.431
#> SD:skmeans 5 0.624 0.488 0.729 0.0602 0.868 0.575
#> CV:skmeans 5 0.531 0.438 0.656 0.0595 0.955 0.828
#> MAD:skmeans 5 0.596 0.468 0.704 0.0616 0.854 0.552
#> ATC:skmeans 5 0.745 0.746 0.848 0.0551 0.911 0.690
#> SD:mclust 5 0.603 0.744 0.822 0.0820 0.842 0.568
#> CV:mclust 5 0.452 0.524 0.688 0.1040 0.909 0.720
#> MAD:mclust 5 0.613 0.693 0.798 0.0690 0.845 0.570
#> ATC:mclust 5 0.587 0.664 0.768 0.0610 0.768 0.453
#> SD:kmeans 5 0.614 0.550 0.751 0.0747 0.902 0.659
#> CV:kmeans 5 0.555 0.468 0.695 0.0726 0.893 0.645
#> MAD:kmeans 5 0.599 0.529 0.711 0.0699 0.889 0.619
#> ATC:kmeans 5 0.627 0.600 0.754 0.0762 0.877 0.639
#> SD:pam 5 0.614 0.554 0.784 0.0610 0.927 0.763
#> CV:pam 5 0.480 0.520 0.716 0.0597 0.962 0.872
#> MAD:pam 5 0.631 0.609 0.789 0.0515 0.907 0.710
#> ATC:pam 5 0.701 0.707 0.858 0.1372 0.862 0.655
#> SD:hclust 5 0.438 0.514 0.682 0.0857 0.944 0.804
#> CV:hclust 5 0.393 0.525 0.681 0.0905 0.956 0.867
#> MAD:hclust 5 0.419 0.486 0.668 0.0875 0.890 0.668
#> ATC:hclust 5 0.463 0.419 0.615 0.0772 0.783 0.516
get_stats(res_list, k = 6)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 6 0.558 0.432 0.687 0.0594 0.834 0.469
#> CV:NMF 6 0.551 0.457 0.676 0.0550 0.925 0.692
#> MAD:NMF 6 0.545 0.425 0.679 0.0592 0.877 0.580
#> ATC:NMF 6 0.572 0.476 0.705 0.0352 0.876 0.611
#> SD:skmeans 6 0.618 0.397 0.633 0.0374 0.920 0.681
#> CV:skmeans 6 0.537 0.372 0.597 0.0398 0.898 0.612
#> MAD:skmeans 6 0.609 0.403 0.654 0.0400 0.898 0.591
#> ATC:skmeans 6 0.725 0.669 0.772 0.0279 0.946 0.775
#> SD:mclust 6 0.577 0.582 0.771 0.0504 0.915 0.697
#> CV:mclust 6 0.473 0.432 0.624 0.0570 0.820 0.438
#> MAD:mclust 6 0.558 0.565 0.755 0.0514 0.917 0.695
#> ATC:mclust 6 0.611 0.660 0.789 0.0275 0.923 0.765
#> SD:kmeans 6 0.626 0.468 0.668 0.0440 0.897 0.573
#> CV:kmeans 6 0.589 0.417 0.648 0.0468 0.884 0.532
#> MAD:kmeans 6 0.614 0.480 0.676 0.0443 0.907 0.602
#> ATC:kmeans 6 0.656 0.473 0.658 0.0490 0.873 0.558
#> SD:pam 6 0.705 0.679 0.838 0.0488 0.920 0.708
#> CV:pam 6 0.510 0.520 0.721 0.0443 0.906 0.669
#> MAD:pam 6 0.711 0.735 0.861 0.0521 0.929 0.734
#> ATC:pam 6 0.799 0.730 0.877 0.0701 0.864 0.549
#> SD:hclust 6 0.481 0.407 0.644 0.0440 0.986 0.939
#> CV:hclust 6 0.444 0.324 0.609 0.0495 0.958 0.870
#> MAD:hclust 6 0.490 0.435 0.645 0.0531 0.927 0.718
#> ATC:hclust 6 0.547 0.589 0.748 0.0704 0.876 0.592
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res_list, k = 2)
#> n genotype/variation(p) k
#> SD:NMF 106 0.1703 2
#> CV:NMF 101 0.2989 2
#> MAD:NMF 104 0.1517 2
#> ATC:NMF 107 0.3054 2
#> SD:skmeans 107 0.0967 2
#> CV:skmeans 101 0.4818 2
#> MAD:skmeans 104 0.1161 2
#> ATC:skmeans 108 0.1127 2
#> SD:mclust 108 0.9101 2
#> CV:mclust 108 0.7818 2
#> MAD:mclust 108 0.9101 2
#> ATC:mclust 108 0.9101 2
#> SD:kmeans 108 0.9101 2
#> CV:kmeans 104 0.8866 2
#> MAD:kmeans 107 0.9119 2
#> ATC:kmeans 108 0.7470 2
#> SD:pam 106 0.4059 2
#> CV:pam 107 0.7068 2
#> MAD:pam 107 0.5658 2
#> ATC:pam 106 0.7408 2
#> SD:hclust 103 0.9795 2
#> CV:hclust 100 0.9401 2
#> MAD:hclust 102 0.9727 2
#> ATC:hclust 106 0.8237 2
test_to_known_factors(res_list, k = 3)
#> n genotype/variation(p) k
#> SD:NMF 103 0.6063 3
#> CV:NMF 93 0.5810 3
#> MAD:NMF 95 0.5170 3
#> ATC:NMF 94 0.9274 3
#> SD:skmeans 102 0.5557 3
#> CV:skmeans 93 0.9101 3
#> MAD:skmeans 104 0.6209 3
#> ATC:skmeans 99 0.0945 3
#> SD:mclust 99 0.7376 3
#> CV:mclust 95 0.9285 3
#> MAD:mclust 100 0.9540 3
#> ATC:mclust 78 0.7427 3
#> SD:kmeans 107 0.9822 3
#> CV:kmeans 103 0.9627 3
#> MAD:kmeans 107 0.9822 3
#> ATC:kmeans 103 0.5524 3
#> SD:pam 104 0.5352 3
#> CV:pam 93 0.8518 3
#> MAD:pam 102 0.4210 3
#> ATC:pam 105 0.1090 3
#> SD:hclust 69 0.9949 3
#> CV:hclust 79 0.9990 3
#> MAD:hclust 84 0.9654 3
#> ATC:hclust 99 0.1951 3
test_to_known_factors(res_list, k = 4)
#> n genotype/variation(p) k
#> SD:NMF 94 0.907 4
#> CV:NMF 90 0.653 4
#> MAD:NMF 85 0.878 4
#> ATC:NMF 51 0.792 4
#> SD:skmeans 66 0.790 4
#> CV:skmeans 76 0.831 4
#> MAD:skmeans 64 0.844 4
#> ATC:skmeans 102 0.138 4
#> SD:mclust 100 0.763 4
#> CV:mclust 79 0.797 4
#> MAD:mclust 95 0.840 4
#> ATC:mclust 86 0.866 4
#> SD:kmeans 84 0.630 4
#> CV:kmeans 82 0.870 4
#> MAD:kmeans 83 0.673 4
#> ATC:kmeans 86 0.863 4
#> SD:pam 100 0.558 4
#> CV:pam 86 0.458 4
#> MAD:pam 96 0.290 4
#> ATC:pam 98 0.102 4
#> SD:hclust 83 0.888 4
#> CV:hclust 78 0.956 4
#> MAD:hclust 77 0.978 4
#> ATC:hclust 89 0.148 4
test_to_known_factors(res_list, k = 5)
#> n genotype/variation(p) k
#> SD:NMF 70 0.8109 5
#> CV:NMF 68 0.6960 5
#> MAD:NMF 76 0.4894 5
#> ATC:NMF 56 0.2711 5
#> SD:skmeans 55 0.5412 5
#> CV:skmeans 43 0.9809 5
#> MAD:skmeans 55 0.6989 5
#> ATC:skmeans 95 0.2010 5
#> SD:mclust 94 0.8831 5
#> CV:mclust 70 0.6162 5
#> MAD:mclust 92 0.7667 5
#> ATC:mclust 93 0.0901 5
#> SD:kmeans 69 0.5907 5
#> CV:kmeans 55 0.9848 5
#> MAD:kmeans 63 0.5201 5
#> ATC:kmeans 90 0.5543 5
#> SD:pam 77 0.3166 5
#> CV:pam 77 0.1401 5
#> MAD:pam 80 0.1433 5
#> ATC:pam 86 0.3476 5
#> SD:hclust 63 0.8169 5
#> CV:hclust 75 0.9425 5
#> MAD:hclust 60 0.9389 5
#> ATC:hclust 61 0.5502 5
test_to_known_factors(res_list, k = 6)
#> n genotype/variation(p) k
#> SD:NMF 41 0.651 6
#> CV:NMF 52 0.439 6
#> MAD:NMF 40 0.767 6
#> ATC:NMF 57 0.059 6
#> SD:skmeans 36 0.477 6
#> CV:skmeans 36 0.623 6
#> MAD:skmeans 38 0.346 6
#> ATC:skmeans 87 0.759 6
#> SD:mclust 83 0.716 6
#> CV:mclust 67 0.296 6
#> MAD:mclust 79 0.481 6
#> ATC:mclust 84 0.179 6
#> SD:kmeans 50 0.459 6
#> CV:kmeans 50 0.596 6
#> MAD:kmeans 54 0.466 6
#> ATC:kmeans 65 0.248 6
#> SD:pam 93 0.829 6
#> CV:pam 67 0.200 6
#> MAD:pam 97 0.584 6
#> ATC:pam 90 0.154 6
#> SD:hclust 46 0.898 6
#> CV:hclust 17 0.499 6
#> MAD:hclust 42 0.920 6
#> ATC:hclust 77 0.241 6
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 31589 rows and 108 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 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 0.760 0.863 0.940 0.3245 0.720 0.720
#> 3 3 0.272 0.498 0.728 0.8276 0.634 0.496
#> 4 4 0.327 0.583 0.729 0.1813 0.794 0.516
#> 5 5 0.438 0.514 0.682 0.0857 0.944 0.804
#> 6 6 0.481 0.407 0.644 0.0440 0.986 0.939
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
#> GSM955002 2 0.2236 0.9144 0.036 0.964
#> GSM955008 2 0.0000 0.9347 0.000 1.000
#> GSM955016 2 0.9922 0.2588 0.448 0.552
#> GSM955019 2 0.0000 0.9347 0.000 1.000
#> GSM955022 2 0.0376 0.9334 0.004 0.996
#> GSM955023 2 0.0376 0.9334 0.004 0.996
#> GSM955027 2 0.0000 0.9347 0.000 1.000
#> GSM955043 2 0.0000 0.9347 0.000 1.000
#> GSM955048 1 0.0000 0.9357 1.000 0.000
#> GSM955049 2 0.0000 0.9347 0.000 1.000
#> GSM955054 2 0.0000 0.9347 0.000 1.000
#> GSM955064 2 0.0000 0.9347 0.000 1.000
#> GSM955072 2 0.0000 0.9347 0.000 1.000
#> GSM955075 2 0.0000 0.9347 0.000 1.000
#> GSM955079 2 0.0672 0.9316 0.008 0.992
#> GSM955087 1 0.0000 0.9357 1.000 0.000
#> GSM955088 2 0.0000 0.9347 0.000 1.000
#> GSM955089 1 0.0376 0.9337 0.996 0.004
#> GSM955095 2 0.0000 0.9347 0.000 1.000
#> GSM955097 2 0.1843 0.9208 0.028 0.972
#> GSM955101 2 0.0000 0.9347 0.000 1.000
#> GSM954999 2 0.8955 0.5956 0.312 0.688
#> GSM955001 2 0.0000 0.9347 0.000 1.000
#> GSM955003 2 0.0000 0.9347 0.000 1.000
#> GSM955004 2 0.0376 0.9332 0.004 0.996
#> GSM955005 2 0.6148 0.8138 0.152 0.848
#> GSM955009 2 0.0000 0.9347 0.000 1.000
#> GSM955011 2 0.9286 0.5329 0.344 0.656
#> GSM955012 2 0.0000 0.9347 0.000 1.000
#> GSM955013 2 0.3114 0.9004 0.056 0.944
#> GSM955015 2 0.0000 0.9347 0.000 1.000
#> GSM955017 1 0.4022 0.8736 0.920 0.080
#> GSM955021 2 0.0000 0.9347 0.000 1.000
#> GSM955025 2 0.1184 0.9274 0.016 0.984
#> GSM955028 1 0.0000 0.9357 1.000 0.000
#> GSM955029 2 0.0000 0.9347 0.000 1.000
#> GSM955030 2 0.6623 0.7917 0.172 0.828
#> GSM955032 2 0.0672 0.9316 0.008 0.992
#> GSM955033 2 0.5737 0.8293 0.136 0.864
#> GSM955034 1 0.0000 0.9357 1.000 0.000
#> GSM955035 2 0.0000 0.9347 0.000 1.000
#> GSM955036 2 0.0376 0.9334 0.004 0.996
#> GSM955037 2 0.9983 0.1000 0.476 0.524
#> GSM955039 2 0.3114 0.9001 0.056 0.944
#> GSM955041 2 0.0000 0.9347 0.000 1.000
#> GSM955042 2 0.9000 0.5883 0.316 0.684
#> GSM955045 2 0.0000 0.9347 0.000 1.000
#> GSM955046 2 0.0376 0.9334 0.004 0.996
#> GSM955047 1 0.1184 0.9262 0.984 0.016
#> GSM955050 2 0.8608 0.6436 0.284 0.716
#> GSM955052 2 0.0000 0.9347 0.000 1.000
#> GSM955053 1 0.0000 0.9357 1.000 0.000
#> GSM955056 2 0.0000 0.9347 0.000 1.000
#> GSM955058 2 0.0000 0.9347 0.000 1.000
#> GSM955059 2 0.0376 0.9334 0.004 0.996
#> GSM955060 1 0.3733 0.8814 0.928 0.072
#> GSM955061 2 0.0000 0.9347 0.000 1.000
#> GSM955065 1 0.0000 0.9357 1.000 0.000
#> GSM955066 2 0.1633 0.9235 0.024 0.976
#> GSM955067 1 0.0000 0.9357 1.000 0.000
#> GSM955073 2 0.0000 0.9347 0.000 1.000
#> GSM955074 1 0.9754 0.2366 0.592 0.408
#> GSM955076 2 0.0000 0.9347 0.000 1.000
#> GSM955078 2 0.0000 0.9347 0.000 1.000
#> GSM955083 2 0.7299 0.7552 0.204 0.796
#> GSM955084 2 0.0000 0.9347 0.000 1.000
#> GSM955086 2 0.1184 0.9276 0.016 0.984
#> GSM955091 2 0.0000 0.9347 0.000 1.000
#> GSM955092 2 0.0000 0.9347 0.000 1.000
#> GSM955093 2 0.0000 0.9347 0.000 1.000
#> GSM955098 2 0.0000 0.9347 0.000 1.000
#> GSM955099 2 0.0000 0.9347 0.000 1.000
#> GSM955100 2 0.9087 0.5731 0.324 0.676
#> GSM955103 2 0.0376 0.9334 0.004 0.996
#> GSM955104 2 0.2778 0.9072 0.048 0.952
#> GSM955106 2 0.0376 0.9333 0.004 0.996
#> GSM955000 1 0.9754 0.2785 0.592 0.408
#> GSM955006 2 1.0000 0.0735 0.500 0.500
#> GSM955007 2 0.0000 0.9347 0.000 1.000
#> GSM955010 2 0.7815 0.7187 0.232 0.768
#> GSM955014 1 0.0000 0.9357 1.000 0.000
#> GSM955018 2 0.0672 0.9316 0.008 0.992
#> GSM955020 1 0.0000 0.9357 1.000 0.000
#> GSM955024 2 0.0000 0.9347 0.000 1.000
#> GSM955026 2 0.0000 0.9347 0.000 1.000
#> GSM955031 2 0.8713 0.6280 0.292 0.708
#> GSM955038 2 0.8499 0.6558 0.276 0.724
#> GSM955040 2 0.8661 0.6367 0.288 0.712
#> GSM955044 2 0.0000 0.9347 0.000 1.000
#> GSM955051 1 0.0000 0.9357 1.000 0.000
#> GSM955055 2 0.0000 0.9347 0.000 1.000
#> GSM955057 1 0.0000 0.9357 1.000 0.000
#> GSM955062 2 0.0000 0.9347 0.000 1.000
#> GSM955063 2 0.0000 0.9347 0.000 1.000
#> GSM955068 2 0.0000 0.9347 0.000 1.000
#> GSM955069 2 0.0000 0.9347 0.000 1.000
#> GSM955070 2 0.0000 0.9347 0.000 1.000
#> GSM955071 2 0.8081 0.6981 0.248 0.752
#> GSM955077 2 0.3431 0.8944 0.064 0.936
#> GSM955080 2 0.0000 0.9347 0.000 1.000
#> GSM955081 2 0.0000 0.9347 0.000 1.000
#> GSM955082 2 0.0000 0.9347 0.000 1.000
#> GSM955085 2 0.0000 0.9347 0.000 1.000
#> GSM955090 1 0.0000 0.9357 1.000 0.000
#> GSM955094 2 0.0672 0.9317 0.008 0.992
#> GSM955096 2 0.0000 0.9347 0.000 1.000
#> GSM955102 2 0.1843 0.9209 0.028 0.972
#> GSM955105 2 0.0672 0.9316 0.008 0.992
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.7207 0.2019 0.032 0.584 0.384
#> GSM955008 3 0.6126 0.4034 0.000 0.400 0.600
#> GSM955016 1 0.9776 0.0458 0.424 0.332 0.244
#> GSM955019 2 0.4235 0.6351 0.000 0.824 0.176
#> GSM955022 3 0.5760 0.5351 0.000 0.328 0.672
#> GSM955023 3 0.5760 0.5351 0.000 0.328 0.672
#> GSM955027 2 0.4121 0.6354 0.000 0.832 0.168
#> GSM955043 2 0.2261 0.6760 0.000 0.932 0.068
#> GSM955048 1 0.0237 0.8765 0.996 0.000 0.004
#> GSM955049 2 0.6235 0.0489 0.000 0.564 0.436
#> GSM955054 2 0.6168 0.1690 0.000 0.588 0.412
#> GSM955064 2 0.6140 0.2437 0.000 0.596 0.404
#> GSM955072 2 0.2165 0.6607 0.000 0.936 0.064
#> GSM955075 2 0.3038 0.6719 0.000 0.896 0.104
#> GSM955079 3 0.5178 0.5922 0.000 0.256 0.744
#> GSM955087 1 0.0237 0.8756 0.996 0.000 0.004
#> GSM955088 3 0.5760 0.5423 0.000 0.328 0.672
#> GSM955089 1 0.0475 0.8750 0.992 0.004 0.004
#> GSM955095 2 0.5098 0.5805 0.000 0.752 0.248
#> GSM955097 2 0.4663 0.6344 0.016 0.828 0.156
#> GSM955101 2 0.6180 0.2165 0.000 0.584 0.416
#> GSM954999 2 0.9871 -0.0488 0.280 0.412 0.308
#> GSM955001 2 0.4750 0.5931 0.000 0.784 0.216
#> GSM955003 2 0.6280 -0.0132 0.000 0.540 0.460
#> GSM955004 2 0.1163 0.6533 0.000 0.972 0.028
#> GSM955005 3 0.8967 0.3807 0.148 0.324 0.528
#> GSM955009 2 0.1163 0.6617 0.000 0.972 0.028
#> GSM955011 3 0.9980 0.1499 0.312 0.324 0.364
#> GSM955012 2 0.3267 0.6688 0.000 0.884 0.116
#> GSM955013 3 0.7831 0.3477 0.056 0.404 0.540
#> GSM955015 2 0.6215 0.1218 0.000 0.572 0.428
#> GSM955017 1 0.3459 0.8273 0.892 0.012 0.096
#> GSM955021 2 0.4796 0.5921 0.000 0.780 0.220
#> GSM955025 2 0.3377 0.6513 0.012 0.896 0.092
#> GSM955028 1 0.0237 0.8756 0.996 0.000 0.004
#> GSM955029 2 0.3267 0.6688 0.000 0.884 0.116
#> GSM955030 3 0.9256 0.3346 0.168 0.344 0.488
#> GSM955032 3 0.5327 0.5896 0.000 0.272 0.728
#> GSM955033 2 0.8814 0.0124 0.116 0.480 0.404
#> GSM955034 1 0.0237 0.8756 0.996 0.000 0.004
#> GSM955035 2 0.5497 0.4918 0.000 0.708 0.292
#> GSM955036 3 0.4062 0.5788 0.000 0.164 0.836
#> GSM955037 3 0.7657 -0.1630 0.448 0.044 0.508
#> GSM955039 3 0.7246 0.4997 0.052 0.300 0.648
#> GSM955041 3 0.6309 0.0904 0.000 0.496 0.504
#> GSM955042 2 0.9874 -0.0483 0.284 0.412 0.304
#> GSM955045 2 0.5650 0.4850 0.000 0.688 0.312
#> GSM955046 3 0.4062 0.5788 0.000 0.164 0.836
#> GSM955047 1 0.1585 0.8659 0.964 0.008 0.028
#> GSM955050 3 0.9870 0.1364 0.256 0.364 0.380
#> GSM955052 3 0.6140 0.3970 0.000 0.404 0.596
#> GSM955053 1 0.0237 0.8756 0.996 0.000 0.004
#> GSM955056 3 0.6215 0.3598 0.000 0.428 0.572
#> GSM955058 2 0.3267 0.6688 0.000 0.884 0.116
#> GSM955059 3 0.5650 0.5482 0.000 0.312 0.688
#> GSM955060 1 0.3213 0.8321 0.900 0.008 0.092
#> GSM955061 2 0.3267 0.6688 0.000 0.884 0.116
#> GSM955065 1 0.0424 0.8759 0.992 0.000 0.008
#> GSM955066 3 0.4413 0.5766 0.008 0.160 0.832
#> GSM955067 1 0.0424 0.8759 0.992 0.000 0.008
#> GSM955073 3 0.4062 0.5750 0.000 0.164 0.836
#> GSM955074 1 0.8702 0.3730 0.568 0.292 0.140
#> GSM955076 2 0.2261 0.6634 0.000 0.932 0.068
#> GSM955078 2 0.1529 0.6727 0.000 0.960 0.040
#> GSM955083 2 0.9267 0.1092 0.180 0.504 0.316
#> GSM955084 2 0.1031 0.6556 0.000 0.976 0.024
#> GSM955086 3 0.6102 0.5622 0.008 0.320 0.672
#> GSM955091 2 0.4399 0.6275 0.000 0.812 0.188
#> GSM955092 3 0.6309 0.1467 0.000 0.496 0.504
#> GSM955093 3 0.4178 0.5914 0.000 0.172 0.828
#> GSM955098 2 0.1964 0.6501 0.000 0.944 0.056
#> GSM955099 2 0.1529 0.6727 0.000 0.960 0.040
#> GSM955100 3 0.9941 0.1587 0.292 0.324 0.384
#> GSM955103 3 0.5902 0.5464 0.004 0.316 0.680
#> GSM955104 3 0.6423 0.5905 0.044 0.228 0.728
#> GSM955106 2 0.4465 0.6436 0.004 0.820 0.176
#> GSM955000 1 0.6973 0.3903 0.564 0.020 0.416
#> GSM955006 1 0.9613 0.0786 0.472 0.244 0.284
#> GSM955007 3 0.4750 0.5898 0.000 0.216 0.784
#> GSM955010 3 0.9621 0.1847 0.208 0.360 0.432
#> GSM955014 1 0.0237 0.8765 0.996 0.000 0.004
#> GSM955018 3 0.5138 0.5931 0.000 0.252 0.748
#> GSM955020 1 0.0000 0.8762 1.000 0.000 0.000
#> GSM955024 2 0.6305 -0.1018 0.000 0.516 0.484
#> GSM955026 2 0.2066 0.6560 0.000 0.940 0.060
#> GSM955031 2 0.9706 -0.0226 0.272 0.456 0.272
#> GSM955038 2 0.8734 0.2359 0.248 0.584 0.168
#> GSM955040 3 0.9884 0.1273 0.260 0.364 0.376
#> GSM955044 2 0.2066 0.6748 0.000 0.940 0.060
#> GSM955051 1 0.0424 0.8758 0.992 0.000 0.008
#> GSM955055 2 0.2066 0.6744 0.000 0.940 0.060
#> GSM955057 1 0.0237 0.8765 0.996 0.000 0.004
#> GSM955062 2 0.5497 0.4814 0.000 0.708 0.292
#> GSM955063 3 0.4178 0.5818 0.000 0.172 0.828
#> GSM955068 2 0.1860 0.6529 0.000 0.948 0.052
#> GSM955069 3 0.5291 0.5859 0.000 0.268 0.732
#> GSM955070 2 0.4887 0.5946 0.000 0.772 0.228
#> GSM955071 3 0.9734 0.1447 0.224 0.376 0.400
#> GSM955077 2 0.4887 0.6082 0.060 0.844 0.096
#> GSM955080 2 0.3619 0.6682 0.000 0.864 0.136
#> GSM955081 2 0.6308 -0.1565 0.000 0.508 0.492
#> GSM955082 3 0.6305 0.1873 0.000 0.484 0.516
#> GSM955085 2 0.3267 0.6783 0.000 0.884 0.116
#> GSM955090 1 0.0237 0.8763 0.996 0.000 0.004
#> GSM955094 2 0.4702 0.6084 0.000 0.788 0.212
#> GSM955096 3 0.5882 0.5093 0.000 0.348 0.652
#> GSM955102 3 0.2448 0.5458 0.000 0.076 0.924
#> GSM955105 3 0.5178 0.5947 0.000 0.256 0.744
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.8046 -0.05434 0.004 0.372 0.332 0.292
#> GSM955008 3 0.4567 0.58521 0.000 0.244 0.740 0.016
#> GSM955016 4 0.5919 0.58770 0.204 0.036 0.044 0.716
#> GSM955019 2 0.5690 0.63890 0.000 0.700 0.216 0.084
#> GSM955022 3 0.5568 0.65255 0.000 0.152 0.728 0.120
#> GSM955023 3 0.5568 0.65255 0.000 0.152 0.728 0.120
#> GSM955027 2 0.5298 0.63639 0.000 0.708 0.244 0.048
#> GSM955043 2 0.4150 0.71734 0.000 0.824 0.120 0.056
#> GSM955048 1 0.1792 0.85514 0.932 0.000 0.000 0.068
#> GSM955049 3 0.6079 0.26119 0.000 0.408 0.544 0.048
#> GSM955054 3 0.6114 0.13907 0.000 0.428 0.524 0.048
#> GSM955064 3 0.6242 0.13095 0.000 0.424 0.520 0.056
#> GSM955072 2 0.5757 0.61524 0.000 0.684 0.076 0.240
#> GSM955075 2 0.4656 0.70209 0.000 0.792 0.136 0.072
#> GSM955079 3 0.4307 0.61123 0.000 0.048 0.808 0.144
#> GSM955087 1 0.0000 0.86168 1.000 0.000 0.000 0.000
#> GSM955088 3 0.6115 0.64180 0.000 0.172 0.680 0.148
#> GSM955089 1 0.0921 0.86157 0.972 0.000 0.000 0.028
#> GSM955095 2 0.5901 0.58729 0.000 0.652 0.280 0.068
#> GSM955097 2 0.5705 0.64301 0.000 0.704 0.092 0.204
#> GSM955101 3 0.6278 0.17230 0.000 0.408 0.532 0.060
#> GSM954999 4 0.5398 0.71569 0.060 0.076 0.076 0.788
#> GSM955001 2 0.5599 0.56463 0.000 0.664 0.288 0.048
#> GSM955003 3 0.6009 0.33092 0.000 0.380 0.572 0.048
#> GSM955004 2 0.2589 0.68962 0.000 0.884 0.000 0.116
#> GSM955005 3 0.7710 -0.14939 0.044 0.084 0.452 0.420
#> GSM955009 2 0.2722 0.68474 0.000 0.904 0.032 0.064
#> GSM955011 4 0.7087 0.71839 0.108 0.068 0.156 0.668
#> GSM955012 2 0.4673 0.69420 0.000 0.792 0.132 0.076
#> GSM955013 3 0.7682 0.38652 0.012 0.212 0.528 0.248
#> GSM955015 3 0.5999 0.18102 0.000 0.404 0.552 0.044
#> GSM955017 1 0.4343 0.68230 0.732 0.000 0.004 0.264
#> GSM955021 2 0.5256 0.57695 0.000 0.692 0.272 0.036
#> GSM955025 2 0.5035 0.65166 0.000 0.748 0.056 0.196
#> GSM955028 1 0.0000 0.86168 1.000 0.000 0.000 0.000
#> GSM955029 2 0.4673 0.69420 0.000 0.792 0.132 0.076
#> GSM955030 4 0.7840 0.17932 0.052 0.084 0.424 0.440
#> GSM955032 3 0.4458 0.64132 0.000 0.076 0.808 0.116
#> GSM955033 4 0.7093 0.49405 0.000 0.212 0.220 0.568
#> GSM955034 1 0.0000 0.86168 1.000 0.000 0.000 0.000
#> GSM955035 2 0.5969 0.34349 0.000 0.564 0.392 0.044
#> GSM955036 3 0.4335 0.55850 0.000 0.036 0.796 0.168
#> GSM955037 1 0.7581 -0.00747 0.440 0.000 0.360 0.200
#> GSM955039 3 0.6701 0.34341 0.008 0.100 0.608 0.284
#> GSM955041 3 0.5973 0.38283 0.000 0.332 0.612 0.056
#> GSM955042 4 0.5471 0.71616 0.064 0.076 0.076 0.784
#> GSM955045 2 0.5936 0.38565 0.000 0.576 0.380 0.044
#> GSM955046 3 0.4335 0.55850 0.000 0.036 0.796 0.168
#> GSM955047 1 0.3610 0.75238 0.800 0.000 0.000 0.200
#> GSM955050 4 0.7387 0.70434 0.072 0.108 0.180 0.640
#> GSM955052 3 0.4675 0.58519 0.000 0.244 0.736 0.020
#> GSM955053 1 0.0188 0.86186 0.996 0.000 0.000 0.004
#> GSM955056 3 0.5256 0.58322 0.000 0.260 0.700 0.040
#> GSM955058 2 0.4673 0.69420 0.000 0.792 0.132 0.076
#> GSM955059 3 0.5432 0.65106 0.000 0.136 0.740 0.124
#> GSM955060 1 0.4134 0.69199 0.740 0.000 0.000 0.260
#> GSM955061 2 0.4673 0.69420 0.000 0.792 0.132 0.076
#> GSM955065 1 0.0188 0.86234 0.996 0.000 0.000 0.004
#> GSM955066 3 0.5050 0.44066 0.000 0.028 0.704 0.268
#> GSM955067 1 0.2081 0.85081 0.916 0.000 0.000 0.084
#> GSM955073 3 0.0927 0.63551 0.000 0.008 0.976 0.016
#> GSM955074 4 0.5712 0.24953 0.384 0.032 0.000 0.584
#> GSM955076 2 0.5910 0.59792 0.000 0.672 0.084 0.244
#> GSM955078 2 0.3796 0.72100 0.000 0.848 0.096 0.056
#> GSM955083 4 0.7018 0.59259 0.024 0.204 0.136 0.636
#> GSM955084 2 0.2266 0.69471 0.000 0.912 0.004 0.084
#> GSM955086 3 0.5759 0.57391 0.000 0.112 0.708 0.180
#> GSM955091 2 0.5820 0.62647 0.000 0.684 0.232 0.084
#> GSM955092 3 0.5368 0.46669 0.000 0.340 0.636 0.024
#> GSM955093 3 0.2255 0.62459 0.000 0.012 0.920 0.068
#> GSM955098 2 0.5799 0.57327 0.000 0.668 0.068 0.264
#> GSM955099 2 0.3652 0.71999 0.000 0.856 0.092 0.052
#> GSM955100 4 0.6772 0.71774 0.092 0.060 0.160 0.688
#> GSM955103 3 0.5208 0.65780 0.000 0.172 0.748 0.080
#> GSM955104 3 0.5322 0.50770 0.016 0.032 0.732 0.220
#> GSM955106 2 0.5690 0.66346 0.000 0.700 0.216 0.084
#> GSM955000 1 0.7220 0.26827 0.544 0.000 0.260 0.196
#> GSM955006 4 0.8009 0.50088 0.332 0.052 0.112 0.504
#> GSM955007 3 0.3687 0.64696 0.000 0.080 0.856 0.064
#> GSM955010 4 0.6924 0.62339 0.032 0.088 0.248 0.632
#> GSM955014 1 0.1867 0.85464 0.928 0.000 0.000 0.072
#> GSM955018 3 0.4307 0.61128 0.000 0.048 0.808 0.144
#> GSM955020 1 0.0592 0.86316 0.984 0.000 0.000 0.016
#> GSM955024 3 0.5954 0.40864 0.000 0.344 0.604 0.052
#> GSM955026 2 0.5799 0.57926 0.000 0.668 0.068 0.264
#> GSM955031 4 0.8523 0.60443 0.096 0.216 0.156 0.532
#> GSM955038 4 0.6075 0.55415 0.036 0.204 0.052 0.708
#> GSM955040 4 0.6729 0.72000 0.068 0.080 0.160 0.692
#> GSM955044 2 0.4780 0.72036 0.000 0.788 0.116 0.096
#> GSM955051 1 0.2345 0.83432 0.900 0.000 0.000 0.100
#> GSM955055 2 0.3505 0.70225 0.000 0.864 0.088 0.048
#> GSM955057 1 0.0817 0.86322 0.976 0.000 0.000 0.024
#> GSM955062 2 0.6052 0.31768 0.000 0.556 0.396 0.048
#> GSM955063 3 0.1624 0.64231 0.000 0.020 0.952 0.028
#> GSM955068 2 0.5478 0.59402 0.000 0.696 0.056 0.248
#> GSM955069 3 0.4469 0.65652 0.000 0.080 0.808 0.112
#> GSM955070 2 0.6745 0.55632 0.000 0.612 0.212 0.176
#> GSM955071 4 0.7511 0.67178 0.060 0.112 0.212 0.616
#> GSM955077 2 0.5880 0.53839 0.012 0.676 0.048 0.264
#> GSM955080 2 0.5265 0.69535 0.000 0.748 0.160 0.092
#> GSM955081 3 0.6074 0.42937 0.000 0.340 0.600 0.060
#> GSM955082 3 0.5548 0.45971 0.000 0.340 0.628 0.032
#> GSM955085 2 0.5222 0.70789 0.000 0.756 0.132 0.112
#> GSM955090 1 0.1022 0.85742 0.968 0.000 0.000 0.032
#> GSM955094 2 0.6585 0.58923 0.000 0.632 0.180 0.188
#> GSM955096 3 0.4446 0.64529 0.000 0.196 0.776 0.028
#> GSM955102 3 0.4155 0.42742 0.004 0.000 0.756 0.240
#> GSM955105 3 0.4332 0.59686 0.000 0.040 0.800 0.160
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 4 0.8549 -0.05257 0.000 0.192 0.252 0.280 0.276
#> GSM955008 3 0.5587 0.57224 0.000 0.100 0.688 0.028 0.184
#> GSM955016 4 0.5627 0.56441 0.148 0.084 0.020 0.720 0.028
#> GSM955019 5 0.6865 0.22617 0.000 0.352 0.184 0.016 0.448
#> GSM955022 3 0.5972 0.63308 0.000 0.060 0.680 0.124 0.136
#> GSM955023 3 0.5972 0.63308 0.000 0.060 0.680 0.124 0.136
#> GSM955027 5 0.6132 0.50510 0.000 0.200 0.212 0.004 0.584
#> GSM955043 5 0.4567 0.53425 0.000 0.164 0.080 0.004 0.752
#> GSM955048 1 0.2228 0.83615 0.908 0.012 0.000 0.076 0.004
#> GSM955049 3 0.6855 0.26588 0.000 0.160 0.500 0.028 0.312
#> GSM955054 3 0.7011 0.15232 0.000 0.184 0.476 0.028 0.312
#> GSM955064 3 0.6685 0.14538 0.000 0.160 0.488 0.016 0.336
#> GSM955072 2 0.5182 0.71651 0.000 0.704 0.032 0.048 0.216
#> GSM955075 5 0.3103 0.57136 0.000 0.044 0.072 0.012 0.872
#> GSM955079 3 0.4146 0.58882 0.000 0.024 0.780 0.176 0.020
#> GSM955087 1 0.0404 0.84830 0.988 0.012 0.000 0.000 0.000
#> GSM955088 3 0.6477 0.61589 0.000 0.092 0.636 0.168 0.104
#> GSM955089 1 0.0671 0.84855 0.980 0.004 0.000 0.016 0.000
#> GSM955095 5 0.5472 0.52307 0.000 0.076 0.220 0.024 0.680
#> GSM955097 5 0.4187 0.45190 0.000 0.048 0.040 0.100 0.812
#> GSM955101 3 0.6727 0.18534 0.000 0.160 0.500 0.020 0.320
#> GSM954999 4 0.3872 0.64022 0.012 0.072 0.028 0.844 0.044
#> GSM955001 5 0.6663 0.40929 0.000 0.224 0.244 0.012 0.520
#> GSM955003 3 0.6776 0.33151 0.000 0.148 0.540 0.036 0.276
#> GSM955004 5 0.3492 0.37878 0.000 0.188 0.000 0.016 0.796
#> GSM955005 4 0.7139 0.18624 0.020 0.068 0.368 0.484 0.060
#> GSM955009 2 0.4700 0.33948 0.000 0.516 0.008 0.004 0.472
#> GSM955011 4 0.4277 0.67678 0.052 0.044 0.076 0.820 0.008
#> GSM955012 5 0.1864 0.56302 0.000 0.004 0.068 0.004 0.924
#> GSM955013 3 0.7614 0.32787 0.000 0.076 0.460 0.268 0.196
#> GSM955015 3 0.6555 0.15708 0.000 0.160 0.508 0.012 0.320
#> GSM955017 1 0.4668 0.63793 0.684 0.044 0.000 0.272 0.000
#> GSM955021 5 0.6908 0.18206 0.000 0.324 0.244 0.008 0.424
#> GSM955025 2 0.6770 0.45873 0.004 0.484 0.024 0.124 0.364
#> GSM955028 1 0.0404 0.84830 0.988 0.012 0.000 0.000 0.000
#> GSM955029 5 0.1864 0.56302 0.000 0.004 0.068 0.004 0.924
#> GSM955030 4 0.7052 0.30542 0.024 0.072 0.324 0.528 0.052
#> GSM955032 3 0.4352 0.62373 0.000 0.040 0.792 0.132 0.036
#> GSM955033 4 0.6887 0.51271 0.000 0.108 0.152 0.600 0.140
#> GSM955034 1 0.0404 0.84830 0.988 0.012 0.000 0.000 0.000
#> GSM955035 5 0.6998 0.27158 0.000 0.232 0.356 0.012 0.400
#> GSM955036 3 0.5603 0.50935 0.000 0.072 0.704 0.164 0.060
#> GSM955037 1 0.7542 0.02498 0.420 0.052 0.308 0.220 0.000
#> GSM955039 3 0.6857 0.27310 0.000 0.064 0.524 0.316 0.096
#> GSM955041 3 0.6123 0.34545 0.000 0.108 0.576 0.016 0.300
#> GSM955042 4 0.3974 0.63992 0.016 0.072 0.028 0.840 0.044
#> GSM955045 5 0.5741 0.37111 0.000 0.088 0.340 0.004 0.568
#> GSM955046 3 0.5603 0.50935 0.000 0.072 0.704 0.164 0.060
#> GSM955047 1 0.4254 0.70968 0.740 0.040 0.000 0.220 0.000
#> GSM955050 4 0.4800 0.67695 0.016 0.076 0.100 0.784 0.024
#> GSM955052 3 0.5664 0.57221 0.000 0.100 0.684 0.032 0.184
#> GSM955053 1 0.0290 0.84857 0.992 0.008 0.000 0.000 0.000
#> GSM955056 3 0.5584 0.58689 0.000 0.132 0.696 0.028 0.144
#> GSM955058 5 0.1864 0.56302 0.000 0.004 0.068 0.004 0.924
#> GSM955059 3 0.5784 0.62932 0.000 0.048 0.692 0.128 0.132
#> GSM955060 1 0.4645 0.64670 0.688 0.044 0.000 0.268 0.000
#> GSM955061 5 0.1864 0.56302 0.000 0.004 0.068 0.004 0.924
#> GSM955065 1 0.0566 0.84860 0.984 0.012 0.000 0.004 0.000
#> GSM955066 3 0.6065 0.36976 0.000 0.084 0.596 0.292 0.028
#> GSM955067 1 0.2644 0.83065 0.888 0.012 0.000 0.088 0.012
#> GSM955073 3 0.1686 0.64181 0.000 0.020 0.944 0.008 0.028
#> GSM955074 4 0.6353 0.22135 0.344 0.080 0.004 0.544 0.028
#> GSM955076 2 0.4865 0.73374 0.000 0.748 0.040 0.044 0.168
#> GSM955078 5 0.5076 0.45450 0.000 0.252 0.068 0.004 0.676
#> GSM955083 4 0.6479 0.55167 0.004 0.092 0.100 0.648 0.156
#> GSM955084 5 0.4193 0.16307 0.000 0.304 0.000 0.012 0.684
#> GSM955086 3 0.5570 0.55235 0.000 0.100 0.684 0.192 0.024
#> GSM955091 5 0.6878 0.28152 0.000 0.324 0.196 0.016 0.464
#> GSM955092 3 0.6272 0.47589 0.000 0.152 0.608 0.024 0.216
#> GSM955093 3 0.3251 0.62356 0.000 0.040 0.864 0.080 0.016
#> GSM955098 2 0.4469 0.73590 0.000 0.776 0.020 0.056 0.148
#> GSM955099 5 0.4904 0.47307 0.000 0.240 0.072 0.000 0.688
#> GSM955100 4 0.3486 0.68009 0.028 0.036 0.072 0.860 0.004
#> GSM955103 3 0.5779 0.63832 0.000 0.072 0.696 0.080 0.152
#> GSM955104 3 0.5429 0.44593 0.004 0.036 0.656 0.276 0.028
#> GSM955106 5 0.4808 0.56508 0.000 0.064 0.152 0.028 0.756
#> GSM955000 1 0.7167 0.28910 0.520 0.052 0.220 0.208 0.000
#> GSM955006 4 0.5842 0.46982 0.288 0.036 0.048 0.624 0.004
#> GSM955007 3 0.4167 0.64483 0.000 0.040 0.812 0.044 0.104
#> GSM955010 4 0.5306 0.62466 0.016 0.056 0.176 0.728 0.024
#> GSM955014 1 0.2349 0.83434 0.900 0.012 0.000 0.084 0.004
#> GSM955018 3 0.4194 0.59254 0.000 0.028 0.780 0.172 0.020
#> GSM955020 1 0.0451 0.84888 0.988 0.008 0.000 0.004 0.000
#> GSM955024 3 0.6342 0.39246 0.000 0.092 0.556 0.032 0.320
#> GSM955026 2 0.4892 0.73879 0.000 0.744 0.020 0.076 0.160
#> GSM955031 4 0.7206 0.43467 0.028 0.280 0.124 0.536 0.032
#> GSM955038 4 0.5895 0.36764 0.004 0.352 0.008 0.560 0.076
#> GSM955040 4 0.4103 0.68107 0.016 0.064 0.076 0.828 0.016
#> GSM955044 5 0.5094 0.45741 0.000 0.220 0.076 0.008 0.696
#> GSM955051 1 0.2886 0.81249 0.864 0.016 0.000 0.116 0.004
#> GSM955055 5 0.5566 -0.00678 0.000 0.416 0.060 0.004 0.520
#> GSM955057 1 0.0671 0.84969 0.980 0.004 0.000 0.016 0.000
#> GSM955062 5 0.6894 0.25872 0.000 0.204 0.364 0.012 0.420
#> GSM955063 3 0.2060 0.64492 0.000 0.024 0.928 0.012 0.036
#> GSM955068 2 0.4745 0.73940 0.000 0.740 0.020 0.048 0.192
#> GSM955069 3 0.4933 0.63209 0.000 0.048 0.756 0.140 0.056
#> GSM955070 5 0.7860 0.28098 0.000 0.228 0.156 0.148 0.468
#> GSM955071 4 0.5805 0.64643 0.020 0.096 0.128 0.716 0.040
#> GSM955077 2 0.6838 0.48535 0.004 0.488 0.016 0.164 0.328
#> GSM955080 5 0.3894 0.57473 0.000 0.056 0.092 0.024 0.828
#> GSM955081 3 0.6943 0.43468 0.000 0.156 0.548 0.052 0.244
#> GSM955082 3 0.6445 0.48394 0.000 0.128 0.600 0.040 0.232
#> GSM955085 5 0.6340 0.15168 0.000 0.316 0.076 0.044 0.564
#> GSM955090 1 0.1612 0.83923 0.948 0.016 0.000 0.024 0.012
#> GSM955094 5 0.7674 0.29724 0.000 0.224 0.120 0.164 0.492
#> GSM955096 3 0.4876 0.63101 0.000 0.076 0.764 0.040 0.120
#> GSM955102 3 0.5446 0.38186 0.000 0.072 0.648 0.268 0.012
#> GSM955105 3 0.4088 0.57954 0.000 0.036 0.780 0.176 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 4 0.8193 -0.0357 0.000 0.168 0.220 0.308 0.268 0.036
#> GSM955008 3 0.5934 0.5397 0.000 0.096 0.648 0.040 0.180 0.036
#> GSM955016 4 0.5568 -0.4453 0.104 0.004 0.004 0.480 0.000 0.408
#> GSM955019 5 0.6395 0.1602 0.000 0.400 0.152 0.008 0.416 0.024
#> GSM955022 3 0.5840 0.5785 0.000 0.040 0.672 0.128 0.116 0.044
#> GSM955023 3 0.5840 0.5785 0.000 0.040 0.672 0.128 0.116 0.044
#> GSM955027 5 0.6293 0.4662 0.000 0.204 0.160 0.008 0.576 0.052
#> GSM955043 5 0.4584 0.5306 0.000 0.180 0.040 0.008 0.736 0.036
#> GSM955048 1 0.3417 0.6997 0.812 0.004 0.000 0.052 0.000 0.132
#> GSM955049 3 0.6842 0.2526 0.000 0.176 0.460 0.028 0.308 0.028
#> GSM955054 3 0.6924 0.1357 0.000 0.196 0.448 0.028 0.300 0.028
#> GSM955064 3 0.6614 0.0829 0.000 0.176 0.448 0.012 0.336 0.028
#> GSM955072 2 0.3532 0.6254 0.000 0.816 0.012 0.024 0.136 0.012
#> GSM955075 5 0.2266 0.5757 0.000 0.052 0.024 0.004 0.908 0.012
#> GSM955079 3 0.5065 0.5232 0.000 0.008 0.688 0.196 0.020 0.088
#> GSM955087 1 0.0653 0.7406 0.980 0.004 0.000 0.000 0.004 0.012
#> GSM955088 3 0.7052 0.5361 0.000 0.052 0.544 0.212 0.092 0.100
#> GSM955089 1 0.1148 0.7366 0.960 0.004 0.000 0.016 0.000 0.020
#> GSM955095 5 0.5044 0.5105 0.000 0.068 0.180 0.024 0.708 0.020
#> GSM955097 5 0.3875 0.4677 0.000 0.012 0.012 0.088 0.808 0.080
#> GSM955101 3 0.6663 0.1244 0.000 0.176 0.460 0.016 0.320 0.028
#> GSM954999 4 0.3996 -0.0232 0.000 0.000 0.004 0.604 0.004 0.388
#> GSM955001 5 0.6706 0.3213 0.000 0.256 0.212 0.012 0.484 0.036
#> GSM955003 3 0.6753 0.2993 0.000 0.160 0.508 0.036 0.268 0.028
#> GSM955004 5 0.4258 0.4039 0.000 0.204 0.000 0.004 0.724 0.068
#> GSM955005 4 0.6457 0.1976 0.020 0.032 0.316 0.544 0.052 0.036
#> GSM955009 2 0.4616 0.4194 0.000 0.596 0.004 0.000 0.360 0.040
#> GSM955011 4 0.2632 0.3902 0.032 0.028 0.020 0.900 0.004 0.016
#> GSM955012 5 0.0806 0.5700 0.000 0.000 0.020 0.000 0.972 0.008
#> GSM955013 3 0.7248 0.2605 0.000 0.044 0.416 0.304 0.204 0.032
#> GSM955015 3 0.6489 0.1267 0.000 0.172 0.476 0.012 0.316 0.024
#> GSM955017 1 0.5316 0.4705 0.644 0.008 0.000 0.228 0.012 0.108
#> GSM955021 2 0.6812 -0.0598 0.000 0.368 0.216 0.000 0.364 0.052
#> GSM955025 2 0.6615 0.4459 0.004 0.540 0.020 0.104 0.276 0.056
#> GSM955028 1 0.0653 0.7406 0.980 0.004 0.000 0.000 0.004 0.012
#> GSM955029 5 0.0806 0.5700 0.000 0.000 0.020 0.000 0.972 0.008
#> GSM955030 4 0.6372 0.3103 0.024 0.040 0.256 0.596 0.044 0.040
#> GSM955032 3 0.5258 0.5625 0.000 0.024 0.708 0.152 0.036 0.080
#> GSM955033 4 0.7287 0.2766 0.000 0.080 0.104 0.548 0.132 0.136
#> GSM955034 1 0.0508 0.7411 0.984 0.004 0.000 0.000 0.000 0.012
#> GSM955035 5 0.6888 0.2617 0.000 0.256 0.320 0.012 0.384 0.028
#> GSM955036 3 0.6418 0.3789 0.000 0.024 0.572 0.120 0.048 0.236
#> GSM955037 1 0.7710 -0.0853 0.416 0.012 0.220 0.168 0.004 0.180
#> GSM955039 3 0.6778 0.2201 0.000 0.024 0.468 0.348 0.092 0.068
#> GSM955041 3 0.6485 0.2355 0.000 0.112 0.504 0.008 0.316 0.060
#> GSM955042 4 0.4131 -0.0274 0.004 0.000 0.004 0.600 0.004 0.388
#> GSM955045 5 0.5688 0.3657 0.000 0.088 0.300 0.008 0.580 0.024
#> GSM955046 3 0.6418 0.3789 0.000 0.024 0.572 0.120 0.048 0.236
#> GSM955047 1 0.5288 0.5362 0.660 0.012 0.000 0.188 0.008 0.132
#> GSM955050 4 0.3344 0.4317 0.008 0.052 0.048 0.860 0.012 0.020
#> GSM955052 3 0.5995 0.5394 0.000 0.096 0.644 0.044 0.180 0.036
#> GSM955053 1 0.0363 0.7421 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM955056 3 0.6053 0.5587 0.000 0.112 0.656 0.048 0.136 0.048
#> GSM955058 5 0.0806 0.5700 0.000 0.000 0.020 0.000 0.972 0.008
#> GSM955059 3 0.5802 0.5740 0.000 0.032 0.672 0.136 0.112 0.048
#> GSM955060 1 0.5308 0.4799 0.648 0.008 0.000 0.220 0.012 0.112
#> GSM955061 5 0.0806 0.5700 0.000 0.000 0.020 0.000 0.972 0.008
#> GSM955065 1 0.0748 0.7397 0.976 0.004 0.000 0.000 0.004 0.016
#> GSM955066 3 0.6579 0.2598 0.000 0.028 0.484 0.284 0.012 0.192
#> GSM955067 1 0.4017 0.6694 0.764 0.012 0.000 0.056 0.000 0.168
#> GSM955073 3 0.2520 0.5962 0.000 0.012 0.888 0.000 0.032 0.068
#> GSM955074 6 0.6443 0.0000 0.292 0.008 0.004 0.336 0.000 0.360
#> GSM955076 2 0.3446 0.6400 0.000 0.840 0.024 0.020 0.096 0.020
#> GSM955078 5 0.4896 0.4487 0.000 0.280 0.028 0.004 0.652 0.036
#> GSM955083 4 0.6389 0.0769 0.000 0.008 0.048 0.504 0.116 0.324
#> GSM955084 5 0.4255 0.1226 0.000 0.380 0.000 0.004 0.600 0.016
#> GSM955086 3 0.6280 0.4892 0.000 0.080 0.604 0.208 0.020 0.088
#> GSM955091 5 0.6447 0.2138 0.000 0.372 0.164 0.008 0.432 0.024
#> GSM955092 3 0.6554 0.4554 0.000 0.156 0.568 0.040 0.204 0.032
#> GSM955093 3 0.3851 0.5750 0.000 0.008 0.812 0.080 0.020 0.080
#> GSM955098 2 0.2308 0.6354 0.000 0.904 0.004 0.028 0.056 0.008
#> GSM955099 5 0.5016 0.4654 0.000 0.264 0.036 0.004 0.656 0.040
#> GSM955100 4 0.1337 0.4067 0.008 0.012 0.016 0.956 0.000 0.008
#> GSM955103 3 0.6115 0.5900 0.000 0.032 0.644 0.092 0.160 0.072
#> GSM955104 3 0.5799 0.3749 0.000 0.004 0.588 0.260 0.028 0.120
#> GSM955106 5 0.4149 0.5657 0.000 0.064 0.100 0.016 0.796 0.024
#> GSM955000 1 0.7349 0.1130 0.500 0.012 0.152 0.152 0.008 0.176
#> GSM955006 4 0.4374 -0.0373 0.264 0.016 0.012 0.696 0.004 0.008
#> GSM955007 3 0.4984 0.5791 0.000 0.016 0.724 0.024 0.108 0.128
#> GSM955010 4 0.5346 0.3570 0.008 0.024 0.112 0.704 0.016 0.136
#> GSM955014 1 0.3851 0.6779 0.776 0.008 0.000 0.056 0.000 0.160
#> GSM955018 3 0.5113 0.5290 0.000 0.008 0.688 0.192 0.024 0.088
#> GSM955020 1 0.1155 0.7379 0.956 0.004 0.000 0.004 0.000 0.036
#> GSM955024 3 0.6425 0.3577 0.000 0.088 0.532 0.040 0.308 0.032
#> GSM955026 2 0.2873 0.6403 0.000 0.872 0.004 0.044 0.068 0.012
#> GSM955031 4 0.6781 0.1971 0.004 0.248 0.084 0.528 0.008 0.128
#> GSM955038 4 0.6543 -0.1384 0.000 0.328 0.008 0.352 0.008 0.304
#> GSM955040 4 0.1877 0.4231 0.000 0.024 0.024 0.932 0.008 0.012
#> GSM955044 5 0.4930 0.4697 0.000 0.248 0.040 0.004 0.672 0.036
#> GSM955051 1 0.4048 0.6758 0.776 0.012 0.000 0.112 0.000 0.100
#> GSM955055 2 0.5475 0.0885 0.000 0.472 0.040 0.000 0.444 0.044
#> GSM955057 1 0.0692 0.7441 0.976 0.000 0.000 0.004 0.000 0.020
#> GSM955062 5 0.6894 0.2491 0.000 0.216 0.328 0.012 0.408 0.036
#> GSM955063 3 0.2971 0.5977 0.000 0.020 0.868 0.004 0.036 0.072
#> GSM955068 2 0.3178 0.6381 0.000 0.848 0.008 0.024 0.104 0.016
#> GSM955069 3 0.5174 0.5741 0.000 0.020 0.716 0.148 0.044 0.072
#> GSM955070 5 0.7762 0.2614 0.000 0.240 0.124 0.140 0.444 0.052
#> GSM955071 4 0.4190 0.4373 0.008 0.056 0.080 0.808 0.032 0.016
#> GSM955077 2 0.7073 0.4631 0.004 0.504 0.012 0.132 0.244 0.104
#> GSM955080 5 0.3447 0.5738 0.000 0.048 0.036 0.020 0.852 0.044
#> GSM955081 3 0.7091 0.4276 0.000 0.164 0.508 0.068 0.228 0.032
#> GSM955082 3 0.6470 0.4648 0.000 0.136 0.572 0.048 0.220 0.024
#> GSM955085 5 0.6391 0.0572 0.000 0.340 0.052 0.044 0.516 0.048
#> GSM955090 1 0.3121 0.6644 0.804 0.012 0.000 0.004 0.000 0.180
#> GSM955094 5 0.7545 0.2731 0.000 0.232 0.084 0.172 0.464 0.048
#> GSM955096 3 0.5675 0.5941 0.000 0.064 0.700 0.072 0.108 0.056
#> GSM955102 3 0.6103 0.2787 0.000 0.020 0.520 0.216 0.000 0.244
#> GSM955105 3 0.4999 0.5168 0.000 0.012 0.688 0.204 0.012 0.084
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> SD:hclust 103 0.979 2
#> SD:hclust 69 0.995 3
#> SD:hclust 83 0.888 4
#> SD:hclust 63 0.817 5
#> SD:hclust 46 0.898 6
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 31589 rows and 108 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 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 0.995 0.998 0.3520 0.651 0.651
#> 3 3 0.680 0.847 0.904 0.8157 0.695 0.531
#> 4 4 0.598 0.636 0.806 0.1483 0.882 0.678
#> 5 5 0.614 0.550 0.751 0.0747 0.902 0.659
#> 6 6 0.626 0.468 0.668 0.0440 0.897 0.573
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
#> GSM955002 2 0.0000 0.997 0.000 1.000
#> GSM955008 2 0.0000 0.997 0.000 1.000
#> GSM955016 1 0.0000 1.000 1.000 0.000
#> GSM955019 2 0.0000 0.997 0.000 1.000
#> GSM955022 2 0.0000 0.997 0.000 1.000
#> GSM955023 2 0.0000 0.997 0.000 1.000
#> GSM955027 2 0.0000 0.997 0.000 1.000
#> GSM955043 2 0.0000 0.997 0.000 1.000
#> GSM955048 1 0.0000 1.000 1.000 0.000
#> GSM955049 2 0.0000 0.997 0.000 1.000
#> GSM955054 2 0.0000 0.997 0.000 1.000
#> GSM955064 2 0.0000 0.997 0.000 1.000
#> GSM955072 2 0.0000 0.997 0.000 1.000
#> GSM955075 2 0.0000 0.997 0.000 1.000
#> GSM955079 2 0.0000 0.997 0.000 1.000
#> GSM955087 1 0.0000 1.000 1.000 0.000
#> GSM955088 2 0.0000 0.997 0.000 1.000
#> GSM955089 1 0.0000 1.000 1.000 0.000
#> GSM955095 2 0.0000 0.997 0.000 1.000
#> GSM955097 2 0.0000 0.997 0.000 1.000
#> GSM955101 2 0.0000 0.997 0.000 1.000
#> GSM954999 2 0.0376 0.994 0.004 0.996
#> GSM955001 2 0.0000 0.997 0.000 1.000
#> GSM955003 2 0.0000 0.997 0.000 1.000
#> GSM955004 2 0.0000 0.997 0.000 1.000
#> GSM955005 2 0.0000 0.997 0.000 1.000
#> GSM955009 2 0.0000 0.997 0.000 1.000
#> GSM955011 1 0.0000 1.000 1.000 0.000
#> GSM955012 2 0.0000 0.997 0.000 1.000
#> GSM955013 2 0.0000 0.997 0.000 1.000
#> GSM955015 2 0.0000 0.997 0.000 1.000
#> GSM955017 1 0.0000 1.000 1.000 0.000
#> GSM955021 2 0.0000 0.997 0.000 1.000
#> GSM955025 2 0.0000 0.997 0.000 1.000
#> GSM955028 1 0.0000 1.000 1.000 0.000
#> GSM955029 2 0.0000 0.997 0.000 1.000
#> GSM955030 2 0.0376 0.994 0.004 0.996
#> GSM955032 2 0.0000 0.997 0.000 1.000
#> GSM955033 2 0.0376 0.994 0.004 0.996
#> GSM955034 1 0.0000 1.000 1.000 0.000
#> GSM955035 2 0.0000 0.997 0.000 1.000
#> GSM955036 2 0.0376 0.994 0.004 0.996
#> GSM955037 1 0.0000 1.000 1.000 0.000
#> GSM955039 2 0.0000 0.997 0.000 1.000
#> GSM955041 2 0.0000 0.997 0.000 1.000
#> GSM955042 1 0.0000 1.000 1.000 0.000
#> GSM955045 2 0.0000 0.997 0.000 1.000
#> GSM955046 2 0.0000 0.997 0.000 1.000
#> GSM955047 1 0.0000 1.000 1.000 0.000
#> GSM955050 2 0.0376 0.994 0.004 0.996
#> GSM955052 2 0.0000 0.997 0.000 1.000
#> GSM955053 1 0.0000 1.000 1.000 0.000
#> GSM955056 2 0.0000 0.997 0.000 1.000
#> GSM955058 2 0.0000 0.997 0.000 1.000
#> GSM955059 2 0.0000 0.997 0.000 1.000
#> GSM955060 1 0.0000 1.000 1.000 0.000
#> GSM955061 2 0.0000 0.997 0.000 1.000
#> GSM955065 1 0.0000 1.000 1.000 0.000
#> GSM955066 2 0.0376 0.994 0.004 0.996
#> GSM955067 1 0.0000 1.000 1.000 0.000
#> GSM955073 2 0.0000 0.997 0.000 1.000
#> GSM955074 1 0.0000 1.000 1.000 0.000
#> GSM955076 2 0.0000 0.997 0.000 1.000
#> GSM955078 2 0.0000 0.997 0.000 1.000
#> GSM955083 2 0.0376 0.994 0.004 0.996
#> GSM955084 2 0.0000 0.997 0.000 1.000
#> GSM955086 2 0.0000 0.997 0.000 1.000
#> GSM955091 2 0.0000 0.997 0.000 1.000
#> GSM955092 2 0.0000 0.997 0.000 1.000
#> GSM955093 2 0.0000 0.997 0.000 1.000
#> GSM955098 2 0.0000 0.997 0.000 1.000
#> GSM955099 2 0.0000 0.997 0.000 1.000
#> GSM955100 1 0.0000 1.000 1.000 0.000
#> GSM955103 2 0.0000 0.997 0.000 1.000
#> GSM955104 2 0.0000 0.997 0.000 1.000
#> GSM955106 2 0.0000 0.997 0.000 1.000
#> GSM955000 1 0.0000 1.000 1.000 0.000
#> GSM955006 1 0.0000 1.000 1.000 0.000
#> GSM955007 2 0.0000 0.997 0.000 1.000
#> GSM955010 2 0.0376 0.994 0.004 0.996
#> GSM955014 1 0.0000 1.000 1.000 0.000
#> GSM955018 2 0.0000 0.997 0.000 1.000
#> GSM955020 1 0.0000 1.000 1.000 0.000
#> GSM955024 2 0.0000 0.997 0.000 1.000
#> GSM955026 2 0.0000 0.997 0.000 1.000
#> GSM955031 2 0.0000 0.997 0.000 1.000
#> GSM955038 2 0.7299 0.745 0.204 0.796
#> GSM955040 2 0.0376 0.994 0.004 0.996
#> GSM955044 2 0.0000 0.997 0.000 1.000
#> GSM955051 1 0.0000 1.000 1.000 0.000
#> GSM955055 2 0.0000 0.997 0.000 1.000
#> GSM955057 1 0.0000 1.000 1.000 0.000
#> GSM955062 2 0.0000 0.997 0.000 1.000
#> GSM955063 2 0.0000 0.997 0.000 1.000
#> GSM955068 2 0.0000 0.997 0.000 1.000
#> GSM955069 2 0.0000 0.997 0.000 1.000
#> GSM955070 2 0.0000 0.997 0.000 1.000
#> GSM955071 2 0.0376 0.994 0.004 0.996
#> GSM955077 2 0.0000 0.997 0.000 1.000
#> GSM955080 2 0.0000 0.997 0.000 1.000
#> GSM955081 2 0.0000 0.997 0.000 1.000
#> GSM955082 2 0.0000 0.997 0.000 1.000
#> GSM955085 2 0.0000 0.997 0.000 1.000
#> GSM955090 1 0.0000 1.000 1.000 0.000
#> GSM955094 2 0.0000 0.997 0.000 1.000
#> GSM955096 2 0.0000 0.997 0.000 1.000
#> GSM955102 2 0.1184 0.983 0.016 0.984
#> GSM955105 2 0.0000 0.997 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.6126 0.5662 0.000 0.400 0.600
#> GSM955008 3 0.5397 0.7428 0.000 0.280 0.720
#> GSM955016 1 0.5216 0.7743 0.740 0.000 0.260
#> GSM955019 2 0.0237 0.9310 0.000 0.996 0.004
#> GSM955022 3 0.4750 0.7934 0.000 0.216 0.784
#> GSM955023 3 0.5431 0.7393 0.000 0.284 0.716
#> GSM955027 2 0.0892 0.9314 0.000 0.980 0.020
#> GSM955043 2 0.1031 0.9306 0.000 0.976 0.024
#> GSM955048 1 0.0237 0.9375 0.996 0.000 0.004
#> GSM955049 2 0.1529 0.9263 0.000 0.960 0.040
#> GSM955054 3 0.5988 0.6487 0.000 0.368 0.632
#> GSM955064 2 0.1860 0.9218 0.000 0.948 0.052
#> GSM955072 2 0.0237 0.9293 0.000 0.996 0.004
#> GSM955075 2 0.1643 0.9247 0.000 0.956 0.044
#> GSM955079 3 0.2448 0.8447 0.000 0.076 0.924
#> GSM955087 1 0.0000 0.9378 1.000 0.000 0.000
#> GSM955088 3 0.1411 0.8437 0.000 0.036 0.964
#> GSM955089 1 0.0000 0.9378 1.000 0.000 0.000
#> GSM955095 2 0.2796 0.8848 0.000 0.908 0.092
#> GSM955097 2 0.4452 0.7844 0.000 0.808 0.192
#> GSM955101 3 0.5254 0.7618 0.000 0.264 0.736
#> GSM954999 3 0.0424 0.8247 0.000 0.008 0.992
#> GSM955001 2 0.0424 0.9317 0.000 0.992 0.008
#> GSM955003 3 0.5905 0.6742 0.000 0.352 0.648
#> GSM955004 2 0.1031 0.9189 0.000 0.976 0.024
#> GSM955005 3 0.1031 0.8401 0.000 0.024 0.976
#> GSM955009 2 0.0237 0.9310 0.000 0.996 0.004
#> GSM955011 1 0.5058 0.7838 0.756 0.000 0.244
#> GSM955012 2 0.1643 0.9247 0.000 0.956 0.044
#> GSM955013 3 0.1163 0.8417 0.000 0.028 0.972
#> GSM955015 3 0.6204 0.5270 0.000 0.424 0.576
#> GSM955017 1 0.1860 0.9177 0.948 0.000 0.052
#> GSM955021 2 0.0424 0.9317 0.000 0.992 0.008
#> GSM955025 2 0.1411 0.9164 0.000 0.964 0.036
#> GSM955028 1 0.0000 0.9378 1.000 0.000 0.000
#> GSM955029 2 0.1643 0.9247 0.000 0.956 0.044
#> GSM955030 3 0.1031 0.8401 0.000 0.024 0.976
#> GSM955032 3 0.4291 0.8157 0.000 0.180 0.820
#> GSM955033 3 0.4504 0.7231 0.000 0.196 0.804
#> GSM955034 1 0.0000 0.9378 1.000 0.000 0.000
#> GSM955035 2 0.0592 0.9319 0.000 0.988 0.012
#> GSM955036 3 0.1163 0.8390 0.000 0.028 0.972
#> GSM955037 1 0.4887 0.7947 0.772 0.000 0.228
#> GSM955039 3 0.1163 0.8417 0.000 0.028 0.972
#> GSM955041 2 0.3340 0.8506 0.000 0.880 0.120
#> GSM955042 1 0.5178 0.7785 0.744 0.000 0.256
#> GSM955045 2 0.1860 0.9217 0.000 0.948 0.052
#> GSM955046 3 0.1289 0.8423 0.000 0.032 0.968
#> GSM955047 1 0.0237 0.9375 0.996 0.000 0.004
#> GSM955050 3 0.3482 0.7889 0.000 0.128 0.872
#> GSM955052 3 0.5138 0.7692 0.000 0.252 0.748
#> GSM955053 1 0.0000 0.9378 1.000 0.000 0.000
#> GSM955056 3 0.5529 0.7342 0.000 0.296 0.704
#> GSM955058 2 0.1643 0.9247 0.000 0.956 0.044
#> GSM955059 3 0.1411 0.8437 0.000 0.036 0.964
#> GSM955060 1 0.0000 0.9378 1.000 0.000 0.000
#> GSM955061 2 0.1643 0.9247 0.000 0.956 0.044
#> GSM955065 1 0.0000 0.9378 1.000 0.000 0.000
#> GSM955066 3 0.1163 0.8412 0.000 0.028 0.972
#> GSM955067 1 0.0424 0.9372 0.992 0.000 0.008
#> GSM955073 3 0.4974 0.7810 0.000 0.236 0.764
#> GSM955074 1 0.3816 0.8649 0.852 0.000 0.148
#> GSM955076 2 0.0424 0.9313 0.000 0.992 0.008
#> GSM955078 2 0.0000 0.9302 0.000 1.000 0.000
#> GSM955083 3 0.2959 0.7986 0.000 0.100 0.900
#> GSM955084 2 0.1031 0.9189 0.000 0.976 0.024
#> GSM955086 3 0.1860 0.8434 0.000 0.052 0.948
#> GSM955091 2 0.0237 0.9310 0.000 0.996 0.004
#> GSM955092 2 0.2711 0.8792 0.000 0.912 0.088
#> GSM955093 3 0.1529 0.8443 0.000 0.040 0.960
#> GSM955098 2 0.1163 0.9203 0.000 0.972 0.028
#> GSM955099 2 0.0237 0.9310 0.000 0.996 0.004
#> GSM955100 1 0.5138 0.7754 0.748 0.000 0.252
#> GSM955103 3 0.5363 0.7493 0.000 0.276 0.724
#> GSM955104 3 0.1031 0.8401 0.000 0.024 0.976
#> GSM955106 2 0.1753 0.9251 0.000 0.952 0.048
#> GSM955000 1 0.1860 0.9177 0.948 0.000 0.052
#> GSM955006 1 0.0000 0.9378 1.000 0.000 0.000
#> GSM955007 3 0.5098 0.7724 0.000 0.248 0.752
#> GSM955010 3 0.0424 0.8294 0.000 0.008 0.992
#> GSM955014 1 0.0424 0.9372 0.992 0.000 0.008
#> GSM955018 3 0.1753 0.8452 0.000 0.048 0.952
#> GSM955020 1 0.0424 0.9372 0.992 0.000 0.008
#> GSM955024 3 0.6062 0.5828 0.000 0.384 0.616
#> GSM955026 2 0.1163 0.9203 0.000 0.972 0.028
#> GSM955031 3 0.2165 0.8173 0.000 0.064 0.936
#> GSM955038 2 0.9790 0.0519 0.272 0.436 0.292
#> GSM955040 3 0.3038 0.8009 0.000 0.104 0.896
#> GSM955044 2 0.0892 0.9306 0.000 0.980 0.020
#> GSM955051 1 0.0424 0.9372 0.992 0.000 0.008
#> GSM955055 2 0.0424 0.9317 0.000 0.992 0.008
#> GSM955057 1 0.0237 0.9375 0.996 0.000 0.004
#> GSM955062 2 0.0892 0.9314 0.000 0.980 0.020
#> GSM955063 3 0.4931 0.7838 0.000 0.232 0.768
#> GSM955068 2 0.1031 0.9189 0.000 0.976 0.024
#> GSM955069 3 0.1289 0.8423 0.000 0.032 0.968
#> GSM955070 2 0.2356 0.9030 0.000 0.928 0.072
#> GSM955071 3 0.0592 0.8280 0.000 0.012 0.988
#> GSM955077 2 0.5058 0.6506 0.000 0.756 0.244
#> GSM955080 2 0.1529 0.9262 0.000 0.960 0.040
#> GSM955081 3 0.5178 0.7721 0.000 0.256 0.744
#> GSM955082 2 0.5363 0.5780 0.000 0.724 0.276
#> GSM955085 2 0.0237 0.9310 0.000 0.996 0.004
#> GSM955090 1 0.0424 0.9372 0.992 0.000 0.008
#> GSM955094 2 0.2878 0.8861 0.000 0.904 0.096
#> GSM955096 3 0.5216 0.7701 0.000 0.260 0.740
#> GSM955102 3 0.1289 0.8423 0.000 0.032 0.968
#> GSM955105 3 0.1753 0.8424 0.000 0.048 0.952
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 4 0.7867 -0.0720 0.000 0.292 0.316 0.392
#> GSM955008 3 0.2522 0.7340 0.000 0.076 0.908 0.016
#> GSM955016 4 0.5203 0.3698 0.348 0.000 0.016 0.636
#> GSM955019 2 0.5662 0.6938 0.000 0.692 0.072 0.236
#> GSM955022 3 0.3009 0.7409 0.000 0.056 0.892 0.052
#> GSM955023 3 0.2871 0.7309 0.000 0.072 0.896 0.032
#> GSM955027 2 0.1302 0.8032 0.000 0.956 0.044 0.000
#> GSM955043 2 0.2002 0.7945 0.000 0.936 0.020 0.044
#> GSM955048 1 0.0188 0.9256 0.996 0.000 0.004 0.000
#> GSM955049 2 0.5386 0.6885 0.000 0.708 0.236 0.056
#> GSM955054 3 0.5624 0.5951 0.000 0.128 0.724 0.148
#> GSM955064 2 0.5559 0.6868 0.000 0.696 0.240 0.064
#> GSM955072 2 0.4105 0.7629 0.000 0.812 0.032 0.156
#> GSM955075 2 0.2408 0.7940 0.000 0.920 0.036 0.044
#> GSM955079 3 0.1767 0.7379 0.000 0.012 0.944 0.044
#> GSM955087 1 0.0188 0.9261 0.996 0.000 0.004 0.000
#> GSM955088 3 0.1302 0.7277 0.000 0.000 0.956 0.044
#> GSM955089 1 0.0188 0.9261 0.996 0.000 0.004 0.000
#> GSM955095 2 0.2840 0.7888 0.000 0.900 0.044 0.056
#> GSM955097 2 0.5130 0.4832 0.000 0.668 0.020 0.312
#> GSM955101 3 0.2845 0.7297 0.000 0.076 0.896 0.028
#> GSM954999 4 0.4535 0.4732 0.000 0.004 0.292 0.704
#> GSM955001 2 0.1724 0.8040 0.000 0.948 0.032 0.020
#> GSM955003 3 0.5361 0.6149 0.000 0.108 0.744 0.148
#> GSM955004 2 0.1867 0.7787 0.000 0.928 0.000 0.072
#> GSM955005 3 0.5050 0.1543 0.000 0.004 0.588 0.408
#> GSM955009 2 0.3760 0.7696 0.000 0.836 0.028 0.136
#> GSM955011 4 0.5807 0.3557 0.364 0.000 0.040 0.596
#> GSM955012 2 0.2408 0.7940 0.000 0.920 0.036 0.044
#> GSM955013 4 0.5294 0.0535 0.000 0.008 0.484 0.508
#> GSM955015 3 0.5972 0.4430 0.000 0.292 0.640 0.068
#> GSM955017 1 0.4562 0.6734 0.764 0.000 0.028 0.208
#> GSM955021 2 0.6080 0.6514 0.000 0.664 0.236 0.100
#> GSM955025 2 0.5712 0.5366 0.000 0.584 0.032 0.384
#> GSM955028 1 0.0188 0.9261 0.996 0.000 0.004 0.000
#> GSM955029 2 0.2408 0.7940 0.000 0.920 0.036 0.044
#> GSM955030 3 0.5163 -0.0733 0.000 0.004 0.516 0.480
#> GSM955032 3 0.2021 0.7391 0.000 0.024 0.936 0.040
#> GSM955033 4 0.2198 0.6071 0.000 0.008 0.072 0.920
#> GSM955034 1 0.0188 0.9261 0.996 0.000 0.004 0.000
#> GSM955035 2 0.6025 0.6584 0.000 0.668 0.236 0.096
#> GSM955036 4 0.4973 0.3904 0.000 0.008 0.348 0.644
#> GSM955037 1 0.6083 0.2061 0.584 0.000 0.056 0.360
#> GSM955039 3 0.5167 -0.0495 0.000 0.004 0.508 0.488
#> GSM955041 2 0.6016 0.3400 0.000 0.544 0.412 0.044
#> GSM955042 4 0.5237 0.3544 0.356 0.000 0.016 0.628
#> GSM955045 2 0.3821 0.7617 0.000 0.840 0.120 0.040
#> GSM955046 3 0.4313 0.4779 0.000 0.004 0.736 0.260
#> GSM955047 1 0.1109 0.9214 0.968 0.000 0.004 0.028
#> GSM955050 4 0.2021 0.5983 0.000 0.040 0.024 0.936
#> GSM955052 3 0.1474 0.7435 0.000 0.052 0.948 0.000
#> GSM955053 1 0.0188 0.9261 0.996 0.000 0.004 0.000
#> GSM955056 3 0.3128 0.7277 0.000 0.076 0.884 0.040
#> GSM955058 2 0.2408 0.7940 0.000 0.920 0.036 0.044
#> GSM955059 3 0.1557 0.7178 0.000 0.000 0.944 0.056
#> GSM955060 1 0.0657 0.9254 0.984 0.000 0.004 0.012
#> GSM955061 2 0.2408 0.7940 0.000 0.920 0.036 0.044
#> GSM955065 1 0.0188 0.9261 0.996 0.000 0.004 0.000
#> GSM955066 3 0.4800 0.3249 0.000 0.004 0.656 0.340
#> GSM955067 1 0.1489 0.9179 0.952 0.000 0.004 0.044
#> GSM955073 3 0.1854 0.7446 0.000 0.048 0.940 0.012
#> GSM955074 4 0.5039 0.2392 0.404 0.000 0.004 0.592
#> GSM955076 2 0.7331 0.5464 0.000 0.528 0.212 0.260
#> GSM955078 2 0.1004 0.7977 0.000 0.972 0.004 0.024
#> GSM955083 4 0.4098 0.5525 0.000 0.012 0.204 0.784
#> GSM955084 2 0.2281 0.7736 0.000 0.904 0.000 0.096
#> GSM955086 3 0.2198 0.7308 0.000 0.008 0.920 0.072
#> GSM955091 2 0.2483 0.7996 0.000 0.916 0.032 0.052
#> GSM955092 2 0.4838 0.6618 0.000 0.724 0.252 0.024
#> GSM955093 3 0.1545 0.7292 0.000 0.008 0.952 0.040
#> GSM955098 2 0.6295 0.5743 0.000 0.580 0.072 0.348
#> GSM955099 2 0.2399 0.8010 0.000 0.920 0.032 0.048
#> GSM955100 4 0.5713 0.3976 0.340 0.000 0.040 0.620
#> GSM955103 3 0.5354 0.5765 0.000 0.232 0.712 0.056
#> GSM955104 3 0.5165 -0.0864 0.000 0.004 0.512 0.484
#> GSM955106 2 0.2313 0.7935 0.000 0.924 0.032 0.044
#> GSM955000 1 0.3907 0.7664 0.828 0.000 0.032 0.140
#> GSM955006 1 0.2125 0.8902 0.920 0.000 0.004 0.076
#> GSM955007 3 0.2222 0.7426 0.000 0.060 0.924 0.016
#> GSM955010 4 0.4950 0.3726 0.000 0.004 0.376 0.620
#> GSM955014 1 0.1489 0.9179 0.952 0.000 0.004 0.044
#> GSM955018 3 0.1452 0.7304 0.000 0.008 0.956 0.036
#> GSM955020 1 0.0779 0.9228 0.980 0.000 0.004 0.016
#> GSM955024 3 0.4671 0.6049 0.000 0.220 0.752 0.028
#> GSM955026 2 0.6295 0.5743 0.000 0.580 0.072 0.348
#> GSM955031 4 0.6362 0.1061 0.000 0.072 0.368 0.560
#> GSM955038 4 0.2048 0.5913 0.008 0.064 0.000 0.928
#> GSM955040 4 0.2751 0.6039 0.000 0.040 0.056 0.904
#> GSM955044 2 0.2466 0.8049 0.000 0.916 0.028 0.056
#> GSM955051 1 0.1489 0.9179 0.952 0.000 0.004 0.044
#> GSM955055 2 0.2124 0.8031 0.000 0.932 0.040 0.028
#> GSM955057 1 0.0000 0.9260 1.000 0.000 0.000 0.000
#> GSM955062 2 0.5537 0.6606 0.000 0.688 0.256 0.056
#> GSM955063 3 0.1767 0.7451 0.000 0.044 0.944 0.012
#> GSM955068 2 0.5297 0.6624 0.000 0.676 0.032 0.292
#> GSM955069 3 0.3266 0.6076 0.000 0.000 0.832 0.168
#> GSM955070 2 0.6457 0.6324 0.000 0.604 0.100 0.296
#> GSM955071 4 0.3668 0.5741 0.000 0.004 0.188 0.808
#> GSM955077 4 0.5596 0.1032 0.000 0.332 0.036 0.632
#> GSM955080 2 0.2565 0.7897 0.000 0.912 0.032 0.056
#> GSM955081 3 0.5174 0.6414 0.000 0.092 0.756 0.152
#> GSM955082 3 0.5353 0.1298 0.000 0.432 0.556 0.012
#> GSM955085 2 0.1182 0.8017 0.000 0.968 0.016 0.016
#> GSM955090 1 0.1398 0.9190 0.956 0.000 0.004 0.040
#> GSM955094 2 0.5773 0.6179 0.000 0.620 0.044 0.336
#> GSM955096 3 0.2313 0.7404 0.000 0.044 0.924 0.032
#> GSM955102 3 0.4382 0.4221 0.000 0.000 0.704 0.296
#> GSM955105 3 0.2053 0.7272 0.000 0.004 0.924 0.072
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.6894 0.43223 0.000 0.572 0.104 0.236 0.088
#> GSM955008 3 0.3246 0.65168 0.000 0.184 0.808 0.000 0.008
#> GSM955016 4 0.4075 0.67231 0.100 0.096 0.000 0.800 0.004
#> GSM955019 2 0.4532 0.47469 0.000 0.672 0.020 0.004 0.304
#> GSM955022 3 0.5258 0.63215 0.000 0.060 0.740 0.124 0.076
#> GSM955023 3 0.4096 0.63109 0.000 0.200 0.760 0.000 0.040
#> GSM955027 5 0.4284 0.51376 0.000 0.204 0.040 0.004 0.752
#> GSM955043 5 0.0693 0.64461 0.000 0.012 0.008 0.000 0.980
#> GSM955048 1 0.0865 0.90001 0.972 0.024 0.000 0.004 0.000
#> GSM955049 5 0.6615 -0.15291 0.000 0.356 0.220 0.000 0.424
#> GSM955054 3 0.4565 0.32621 0.000 0.408 0.580 0.000 0.012
#> GSM955064 5 0.6608 0.01920 0.000 0.276 0.228 0.004 0.492
#> GSM955072 2 0.4562 0.20615 0.000 0.548 0.004 0.004 0.444
#> GSM955075 5 0.0324 0.64517 0.000 0.004 0.004 0.000 0.992
#> GSM955079 3 0.1725 0.72626 0.000 0.044 0.936 0.020 0.000
#> GSM955087 1 0.0290 0.89776 0.992 0.008 0.000 0.000 0.000
#> GSM955088 3 0.2989 0.69255 0.000 0.060 0.868 0.072 0.000
#> GSM955089 1 0.1195 0.89892 0.960 0.012 0.000 0.028 0.000
#> GSM955095 5 0.2931 0.59483 0.000 0.028 0.040 0.044 0.888
#> GSM955097 5 0.3573 0.48354 0.000 0.036 0.000 0.152 0.812
#> GSM955101 3 0.4065 0.61682 0.000 0.224 0.752 0.008 0.016
#> GSM954999 4 0.2876 0.73778 0.000 0.044 0.052 0.888 0.016
#> GSM955001 5 0.4295 0.47315 0.000 0.248 0.024 0.004 0.724
#> GSM955003 3 0.4565 0.33875 0.000 0.408 0.580 0.000 0.012
#> GSM955004 5 0.3086 0.54997 0.000 0.180 0.000 0.004 0.816
#> GSM955005 3 0.5447 0.11746 0.000 0.064 0.536 0.400 0.000
#> GSM955009 2 0.4891 0.17281 0.000 0.532 0.012 0.008 0.448
#> GSM955011 4 0.4450 0.66096 0.152 0.080 0.004 0.764 0.000
#> GSM955012 5 0.0162 0.64546 0.000 0.000 0.004 0.000 0.996
#> GSM955013 4 0.6439 0.43461 0.000 0.048 0.300 0.568 0.084
#> GSM955015 3 0.6626 0.11304 0.000 0.364 0.476 0.016 0.144
#> GSM955017 1 0.4840 0.60134 0.688 0.064 0.000 0.248 0.000
#> GSM955021 2 0.6636 0.33309 0.000 0.488 0.244 0.004 0.264
#> GSM955025 2 0.5530 0.51596 0.000 0.664 0.004 0.160 0.172
#> GSM955028 1 0.0290 0.89776 0.992 0.008 0.000 0.000 0.000
#> GSM955029 5 0.0613 0.64478 0.000 0.008 0.004 0.004 0.984
#> GSM955030 4 0.5218 0.47660 0.000 0.068 0.308 0.624 0.000
#> GSM955032 3 0.1628 0.72600 0.000 0.056 0.936 0.008 0.000
#> GSM955033 4 0.3658 0.70878 0.000 0.112 0.012 0.832 0.044
#> GSM955034 1 0.0290 0.89776 0.992 0.008 0.000 0.000 0.000
#> GSM955035 2 0.6811 0.25388 0.000 0.432 0.256 0.004 0.308
#> GSM955036 4 0.5209 0.66569 0.000 0.056 0.136 0.740 0.068
#> GSM955037 4 0.6496 0.28943 0.396 0.048 0.068 0.488 0.000
#> GSM955039 4 0.6132 0.46669 0.000 0.096 0.276 0.600 0.028
#> GSM955041 5 0.6626 0.00957 0.000 0.200 0.332 0.004 0.464
#> GSM955042 4 0.4366 0.64918 0.124 0.096 0.000 0.776 0.004
#> GSM955045 5 0.2550 0.59964 0.000 0.020 0.084 0.004 0.892
#> GSM955046 3 0.5995 0.42101 0.000 0.076 0.620 0.268 0.036
#> GSM955047 1 0.2888 0.88574 0.880 0.060 0.000 0.056 0.004
#> GSM955050 4 0.3561 0.61252 0.000 0.260 0.000 0.740 0.000
#> GSM955052 3 0.1952 0.71636 0.000 0.084 0.912 0.004 0.000
#> GSM955053 1 0.0162 0.89811 0.996 0.004 0.000 0.000 0.000
#> GSM955056 3 0.2629 0.68958 0.000 0.136 0.860 0.000 0.004
#> GSM955058 5 0.0162 0.64546 0.000 0.000 0.004 0.000 0.996
#> GSM955059 3 0.3201 0.66609 0.000 0.052 0.852 0.096 0.000
#> GSM955060 1 0.1907 0.89319 0.928 0.044 0.000 0.028 0.000
#> GSM955061 5 0.0162 0.64546 0.000 0.000 0.004 0.000 0.996
#> GSM955065 1 0.0290 0.89776 0.992 0.008 0.000 0.000 0.000
#> GSM955066 3 0.5328 0.26678 0.000 0.064 0.584 0.352 0.000
#> GSM955067 1 0.4006 0.85231 0.804 0.112 0.000 0.080 0.004
#> GSM955073 3 0.1770 0.72607 0.000 0.048 0.936 0.008 0.008
#> GSM955074 4 0.4634 0.62549 0.144 0.100 0.000 0.752 0.004
#> GSM955076 2 0.5104 0.53597 0.000 0.704 0.088 0.008 0.200
#> GSM955078 5 0.3838 0.43253 0.000 0.280 0.000 0.004 0.716
#> GSM955083 4 0.2930 0.73423 0.000 0.048 0.032 0.888 0.032
#> GSM955084 5 0.3885 0.42911 0.000 0.268 0.000 0.008 0.724
#> GSM955086 3 0.2426 0.72191 0.000 0.064 0.900 0.036 0.000
#> GSM955091 5 0.4574 0.14965 0.000 0.412 0.012 0.000 0.576
#> GSM955092 5 0.6745 0.11800 0.000 0.228 0.284 0.008 0.480
#> GSM955093 3 0.1579 0.72222 0.000 0.032 0.944 0.024 0.000
#> GSM955098 2 0.4850 0.55675 0.000 0.728 0.016 0.056 0.200
#> GSM955099 5 0.4789 0.16606 0.000 0.400 0.016 0.004 0.580
#> GSM955100 4 0.3683 0.71463 0.096 0.072 0.004 0.828 0.000
#> GSM955103 3 0.6670 0.24988 0.000 0.096 0.480 0.040 0.384
#> GSM955104 4 0.5492 0.41806 0.000 0.068 0.340 0.588 0.004
#> GSM955106 5 0.1179 0.63497 0.000 0.016 0.004 0.016 0.964
#> GSM955000 1 0.4681 0.69299 0.744 0.060 0.012 0.184 0.000
#> GSM955006 1 0.4459 0.76238 0.744 0.052 0.000 0.200 0.004
#> GSM955007 3 0.3742 0.70050 0.000 0.064 0.844 0.044 0.048
#> GSM955010 4 0.3507 0.69947 0.000 0.052 0.120 0.828 0.000
#> GSM955014 1 0.3317 0.87692 0.852 0.088 0.000 0.056 0.004
#> GSM955018 3 0.1300 0.71621 0.000 0.016 0.956 0.028 0.000
#> GSM955020 1 0.2313 0.88940 0.912 0.044 0.000 0.040 0.004
#> GSM955024 3 0.5535 0.46126 0.000 0.116 0.628 0.000 0.256
#> GSM955026 2 0.4895 0.55608 0.000 0.728 0.012 0.072 0.188
#> GSM955031 2 0.5618 0.32403 0.000 0.628 0.136 0.236 0.000
#> GSM955038 4 0.4182 0.54830 0.000 0.352 0.000 0.644 0.004
#> GSM955040 4 0.2891 0.68785 0.000 0.176 0.000 0.824 0.000
#> GSM955044 5 0.3289 0.55531 0.000 0.172 0.008 0.004 0.816
#> GSM955051 1 0.3517 0.87028 0.840 0.084 0.000 0.072 0.004
#> GSM955055 5 0.4774 0.31152 0.000 0.340 0.024 0.004 0.632
#> GSM955057 1 0.0000 0.89837 1.000 0.000 0.000 0.000 0.000
#> GSM955062 2 0.6745 0.25072 0.000 0.408 0.280 0.000 0.312
#> GSM955063 3 0.1695 0.72552 0.000 0.044 0.940 0.008 0.008
#> GSM955068 2 0.4829 0.47684 0.000 0.660 0.004 0.036 0.300
#> GSM955069 3 0.4238 0.55590 0.000 0.052 0.756 0.192 0.000
#> GSM955070 2 0.7101 0.31205 0.000 0.484 0.072 0.104 0.340
#> GSM955071 4 0.3193 0.71960 0.000 0.132 0.028 0.840 0.000
#> GSM955077 2 0.5878 0.22833 0.000 0.576 0.028 0.340 0.056
#> GSM955080 5 0.0613 0.64404 0.000 0.008 0.004 0.004 0.984
#> GSM955081 3 0.5411 0.34416 0.000 0.396 0.552 0.044 0.008
#> GSM955082 3 0.6418 0.06131 0.000 0.112 0.468 0.016 0.404
#> GSM955085 5 0.3439 0.55509 0.000 0.188 0.004 0.008 0.800
#> GSM955090 1 0.3693 0.85977 0.828 0.088 0.000 0.080 0.004
#> GSM955094 5 0.6664 -0.21543 0.000 0.412 0.012 0.156 0.420
#> GSM955096 3 0.2077 0.71712 0.000 0.084 0.908 0.008 0.000
#> GSM955102 3 0.5027 0.37967 0.000 0.056 0.640 0.304 0.000
#> GSM955105 3 0.2359 0.71712 0.000 0.060 0.904 0.036 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.8067 0.263176 0.000 0.388 0.240 0.092 0.072 0.208
#> GSM955008 3 0.1745 0.500265 0.000 0.068 0.920 0.000 0.012 0.000
#> GSM955016 4 0.1555 0.653193 0.040 0.008 0.000 0.940 0.000 0.012
#> GSM955019 2 0.3913 0.556206 0.000 0.784 0.040 0.012 0.156 0.008
#> GSM955022 3 0.5679 -0.091594 0.000 0.012 0.484 0.004 0.096 0.404
#> GSM955023 3 0.4894 0.481826 0.000 0.112 0.736 0.004 0.064 0.084
#> GSM955027 5 0.5365 0.270899 0.000 0.308 0.084 0.000 0.588 0.020
#> GSM955043 5 0.2002 0.716616 0.000 0.040 0.012 0.000 0.920 0.028
#> GSM955048 1 0.1269 0.838020 0.956 0.012 0.000 0.012 0.000 0.020
#> GSM955049 3 0.6876 -0.172681 0.000 0.352 0.372 0.004 0.228 0.044
#> GSM955054 3 0.5095 0.228111 0.000 0.352 0.576 0.000 0.016 0.056
#> GSM955064 3 0.7018 0.000779 0.000 0.224 0.416 0.004 0.292 0.064
#> GSM955072 2 0.4419 0.490719 0.000 0.724 0.020 0.004 0.212 0.040
#> GSM955075 5 0.0881 0.735463 0.000 0.012 0.008 0.000 0.972 0.008
#> GSM955079 3 0.4076 0.343727 0.000 0.024 0.724 0.016 0.000 0.236
#> GSM955087 1 0.1799 0.830359 0.928 0.008 0.000 0.008 0.004 0.052
#> GSM955088 3 0.4858 0.171505 0.000 0.060 0.588 0.004 0.000 0.348
#> GSM955089 1 0.1938 0.838161 0.920 0.008 0.000 0.052 0.000 0.020
#> GSM955095 5 0.3453 0.672481 0.000 0.032 0.064 0.000 0.836 0.068
#> GSM955097 5 0.3237 0.640937 0.000 0.016 0.004 0.112 0.840 0.028
#> GSM955101 3 0.3325 0.495606 0.000 0.120 0.832 0.004 0.016 0.028
#> GSM954999 4 0.3135 0.633797 0.000 0.004 0.008 0.816 0.008 0.164
#> GSM955001 5 0.5585 0.069474 0.000 0.392 0.072 0.000 0.508 0.028
#> GSM955003 3 0.4750 0.303041 0.000 0.316 0.628 0.000 0.016 0.040
#> GSM955004 5 0.3244 0.557997 0.000 0.268 0.000 0.000 0.732 0.000
#> GSM955005 6 0.5258 0.577747 0.000 0.004 0.188 0.184 0.000 0.624
#> GSM955009 2 0.3514 0.489574 0.000 0.768 0.004 0.000 0.208 0.020
#> GSM955011 4 0.4702 0.611400 0.084 0.024 0.000 0.716 0.000 0.176
#> GSM955012 5 0.0405 0.735640 0.000 0.000 0.004 0.000 0.988 0.008
#> GSM955013 6 0.7513 0.312588 0.000 0.008 0.264 0.268 0.104 0.356
#> GSM955015 3 0.6739 0.116732 0.000 0.284 0.496 0.004 0.100 0.116
#> GSM955017 1 0.6357 0.354639 0.500 0.024 0.000 0.224 0.004 0.248
#> GSM955021 2 0.6148 0.311219 0.000 0.508 0.328 0.000 0.120 0.044
#> GSM955025 2 0.4568 0.538816 0.000 0.764 0.004 0.084 0.088 0.060
#> GSM955028 1 0.1542 0.831126 0.936 0.008 0.000 0.000 0.004 0.052
#> GSM955029 5 0.0653 0.735682 0.000 0.012 0.004 0.000 0.980 0.004
#> GSM955030 6 0.5156 0.349692 0.000 0.000 0.112 0.308 0.000 0.580
#> GSM955032 3 0.4439 0.375935 0.000 0.064 0.692 0.000 0.004 0.240
#> GSM955033 4 0.5098 0.589625 0.000 0.052 0.004 0.644 0.028 0.272
#> GSM955034 1 0.1542 0.831126 0.936 0.008 0.000 0.000 0.004 0.052
#> GSM955035 3 0.6668 -0.222827 0.000 0.384 0.404 0.004 0.160 0.048
#> GSM955036 4 0.5794 0.199972 0.000 0.004 0.044 0.480 0.056 0.416
#> GSM955037 6 0.6652 -0.065264 0.264 0.008 0.012 0.300 0.004 0.412
#> GSM955039 6 0.7337 0.278823 0.000 0.028 0.312 0.248 0.044 0.368
#> GSM955041 3 0.6485 0.231957 0.000 0.128 0.524 0.004 0.276 0.068
#> GSM955042 4 0.1152 0.653288 0.044 0.004 0.000 0.952 0.000 0.000
#> GSM955045 5 0.4026 0.632335 0.000 0.048 0.112 0.000 0.792 0.048
#> GSM955046 6 0.5680 0.485986 0.000 0.004 0.356 0.088 0.020 0.532
#> GSM955047 1 0.3931 0.803439 0.800 0.036 0.000 0.100 0.000 0.064
#> GSM955050 4 0.5395 0.577024 0.000 0.220 0.000 0.584 0.000 0.196
#> GSM955052 3 0.1700 0.460480 0.000 0.004 0.916 0.000 0.000 0.080
#> GSM955053 1 0.1542 0.831126 0.936 0.008 0.000 0.000 0.004 0.052
#> GSM955056 3 0.3985 0.457680 0.000 0.088 0.768 0.000 0.004 0.140
#> GSM955058 5 0.0436 0.736410 0.000 0.004 0.004 0.000 0.988 0.004
#> GSM955059 6 0.4103 0.244193 0.000 0.004 0.448 0.004 0.000 0.544
#> GSM955060 1 0.3557 0.810920 0.828 0.032 0.000 0.080 0.000 0.060
#> GSM955061 5 0.0436 0.736410 0.000 0.004 0.004 0.000 0.988 0.004
#> GSM955065 1 0.1799 0.830359 0.928 0.008 0.000 0.008 0.004 0.052
#> GSM955066 6 0.4894 0.577134 0.000 0.004 0.180 0.144 0.000 0.672
#> GSM955067 1 0.4030 0.774902 0.752 0.020 0.000 0.196 0.000 0.032
#> GSM955073 3 0.2573 0.417579 0.000 0.004 0.856 0.000 0.008 0.132
#> GSM955074 4 0.2058 0.631743 0.072 0.008 0.000 0.908 0.000 0.012
#> GSM955076 2 0.3361 0.573014 0.000 0.844 0.040 0.004 0.084 0.028
#> GSM955078 5 0.3659 0.402334 0.000 0.364 0.000 0.000 0.636 0.000
#> GSM955083 4 0.3023 0.641919 0.000 0.004 0.000 0.808 0.008 0.180
#> GSM955084 5 0.3737 0.372409 0.000 0.392 0.000 0.000 0.608 0.000
#> GSM955086 3 0.4531 0.317175 0.000 0.044 0.672 0.012 0.000 0.272
#> GSM955091 2 0.5084 0.316804 0.000 0.580 0.056 0.000 0.348 0.016
#> GSM955092 3 0.6769 0.184189 0.000 0.192 0.448 0.000 0.296 0.064
#> GSM955093 3 0.2964 0.367949 0.000 0.000 0.792 0.000 0.004 0.204
#> GSM955098 2 0.3556 0.571288 0.000 0.840 0.008 0.044 0.060 0.048
#> GSM955099 2 0.5340 0.291920 0.000 0.552 0.068 0.000 0.360 0.020
#> GSM955100 4 0.4684 0.622149 0.048 0.024 0.000 0.684 0.000 0.244
#> GSM955103 3 0.6169 0.307637 0.000 0.044 0.516 0.000 0.312 0.128
#> GSM955104 6 0.5724 0.480112 0.000 0.000 0.180 0.260 0.008 0.552
#> GSM955106 5 0.1821 0.714327 0.000 0.008 0.024 0.000 0.928 0.040
#> GSM955000 1 0.6067 0.440765 0.540 0.024 0.000 0.152 0.004 0.280
#> GSM955006 1 0.5118 0.573578 0.612 0.028 0.000 0.308 0.000 0.052
#> GSM955007 3 0.4876 0.213357 0.000 0.008 0.620 0.000 0.064 0.308
#> GSM955010 4 0.4361 0.376423 0.000 0.004 0.016 0.544 0.000 0.436
#> GSM955014 1 0.3386 0.813569 0.824 0.020 0.000 0.124 0.000 0.032
#> GSM955018 3 0.4180 0.290939 0.000 0.024 0.680 0.008 0.000 0.288
#> GSM955020 1 0.2247 0.832182 0.904 0.012 0.000 0.060 0.000 0.024
#> GSM955024 3 0.4987 0.453081 0.000 0.048 0.720 0.004 0.140 0.088
#> GSM955026 2 0.3496 0.571414 0.000 0.844 0.008 0.044 0.056 0.048
#> GSM955031 2 0.6887 0.087095 0.000 0.452 0.088 0.172 0.000 0.288
#> GSM955038 4 0.4117 0.554765 0.000 0.228 0.000 0.716 0.000 0.056
#> GSM955040 4 0.4932 0.633396 0.000 0.128 0.000 0.644 0.000 0.228
#> GSM955044 5 0.5915 0.166114 0.000 0.320 0.096 0.000 0.540 0.044
#> GSM955051 1 0.3700 0.800793 0.792 0.020 0.000 0.156 0.000 0.032
#> GSM955055 2 0.5658 0.030902 0.000 0.464 0.064 0.000 0.436 0.036
#> GSM955057 1 0.0692 0.837049 0.976 0.004 0.000 0.000 0.000 0.020
#> GSM955062 2 0.6483 0.245060 0.000 0.436 0.360 0.004 0.168 0.032
#> GSM955063 3 0.2734 0.417380 0.000 0.004 0.840 0.000 0.008 0.148
#> GSM955068 2 0.3492 0.559025 0.000 0.824 0.004 0.012 0.112 0.048
#> GSM955069 6 0.4746 0.298007 0.000 0.004 0.424 0.040 0.000 0.532
#> GSM955070 2 0.8114 0.317312 0.000 0.372 0.252 0.048 0.168 0.160
#> GSM955071 4 0.4698 0.620798 0.000 0.064 0.008 0.660 0.000 0.268
#> GSM955077 2 0.6068 0.140779 0.000 0.556 0.032 0.200 0.000 0.212
#> GSM955080 5 0.1275 0.731767 0.000 0.016 0.012 0.000 0.956 0.016
#> GSM955081 3 0.5822 0.370780 0.000 0.284 0.532 0.004 0.004 0.176
#> GSM955082 3 0.6508 0.341187 0.000 0.104 0.524 0.000 0.264 0.108
#> GSM955085 5 0.4416 0.392451 0.000 0.340 0.016 0.000 0.628 0.016
#> GSM955090 1 0.3673 0.790290 0.780 0.016 0.000 0.180 0.000 0.024
#> GSM955094 2 0.7850 0.316599 0.000 0.396 0.072 0.060 0.232 0.240
#> GSM955096 3 0.4329 0.358974 0.000 0.056 0.700 0.004 0.000 0.240
#> GSM955102 6 0.5090 0.597210 0.000 0.004 0.232 0.128 0.000 0.636
#> GSM955105 3 0.4656 0.307002 0.000 0.048 0.668 0.016 0.000 0.268
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> SD:kmeans 108 0.910 2
#> SD:kmeans 107 0.982 3
#> SD:kmeans 84 0.630 4
#> SD:kmeans 69 0.591 5
#> SD:kmeans 50 0.459 6
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 31589 rows and 108 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 1.000 0.974 0.989 0.4811 0.520 0.520
#> 3 3 0.860 0.874 0.945 0.3791 0.750 0.547
#> 4 4 0.620 0.534 0.737 0.1192 0.916 0.758
#> 5 5 0.624 0.488 0.729 0.0602 0.868 0.575
#> 6 6 0.618 0.397 0.633 0.0374 0.920 0.681
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
#> GSM955002 2 0.0000 0.989 0.000 1.000
#> GSM955008 2 0.0000 0.989 0.000 1.000
#> GSM955016 1 0.0000 0.989 1.000 0.000
#> GSM955019 2 0.0000 0.989 0.000 1.000
#> GSM955022 2 0.0000 0.989 0.000 1.000
#> GSM955023 2 0.0000 0.989 0.000 1.000
#> GSM955027 2 0.0000 0.989 0.000 1.000
#> GSM955043 2 0.0000 0.989 0.000 1.000
#> GSM955048 1 0.0000 0.989 1.000 0.000
#> GSM955049 2 0.0000 0.989 0.000 1.000
#> GSM955054 2 0.0000 0.989 0.000 1.000
#> GSM955064 2 0.0000 0.989 0.000 1.000
#> GSM955072 2 0.0000 0.989 0.000 1.000
#> GSM955075 2 0.0000 0.989 0.000 1.000
#> GSM955079 2 0.2236 0.955 0.036 0.964
#> GSM955087 1 0.0000 0.989 1.000 0.000
#> GSM955088 2 0.0000 0.989 0.000 1.000
#> GSM955089 1 0.0000 0.989 1.000 0.000
#> GSM955095 2 0.0000 0.989 0.000 1.000
#> GSM955097 2 0.9635 0.362 0.388 0.612
#> GSM955101 2 0.0000 0.989 0.000 1.000
#> GSM954999 1 0.0000 0.989 1.000 0.000
#> GSM955001 2 0.0000 0.989 0.000 1.000
#> GSM955003 2 0.0000 0.989 0.000 1.000
#> GSM955004 2 0.0000 0.989 0.000 1.000
#> GSM955005 1 0.0000 0.989 1.000 0.000
#> GSM955009 2 0.0000 0.989 0.000 1.000
#> GSM955011 1 0.0000 0.989 1.000 0.000
#> GSM955012 2 0.0000 0.989 0.000 1.000
#> GSM955013 2 0.0000 0.989 0.000 1.000
#> GSM955015 2 0.0000 0.989 0.000 1.000
#> GSM955017 1 0.0000 0.989 1.000 0.000
#> GSM955021 2 0.0000 0.989 0.000 1.000
#> GSM955025 2 0.1843 0.963 0.028 0.972
#> GSM955028 1 0.0000 0.989 1.000 0.000
#> GSM955029 2 0.0000 0.989 0.000 1.000
#> GSM955030 1 0.0000 0.989 1.000 0.000
#> GSM955032 2 0.0000 0.989 0.000 1.000
#> GSM955033 1 0.1633 0.967 0.976 0.024
#> GSM955034 1 0.0000 0.989 1.000 0.000
#> GSM955035 2 0.0000 0.989 0.000 1.000
#> GSM955036 1 0.0672 0.982 0.992 0.008
#> GSM955037 1 0.0000 0.989 1.000 0.000
#> GSM955039 2 0.0000 0.989 0.000 1.000
#> GSM955041 2 0.0000 0.989 0.000 1.000
#> GSM955042 1 0.0000 0.989 1.000 0.000
#> GSM955045 2 0.0000 0.989 0.000 1.000
#> GSM955046 2 0.0000 0.989 0.000 1.000
#> GSM955047 1 0.0000 0.989 1.000 0.000
#> GSM955050 1 0.0000 0.989 1.000 0.000
#> GSM955052 2 0.0000 0.989 0.000 1.000
#> GSM955053 1 0.0000 0.989 1.000 0.000
#> GSM955056 2 0.0000 0.989 0.000 1.000
#> GSM955058 2 0.0000 0.989 0.000 1.000
#> GSM955059 2 0.0672 0.982 0.008 0.992
#> GSM955060 1 0.0000 0.989 1.000 0.000
#> GSM955061 2 0.0000 0.989 0.000 1.000
#> GSM955065 1 0.0000 0.989 1.000 0.000
#> GSM955066 1 0.0000 0.989 1.000 0.000
#> GSM955067 1 0.0000 0.989 1.000 0.000
#> GSM955073 2 0.0000 0.989 0.000 1.000
#> GSM955074 1 0.0000 0.989 1.000 0.000
#> GSM955076 2 0.0000 0.989 0.000 1.000
#> GSM955078 2 0.0000 0.989 0.000 1.000
#> GSM955083 1 0.0000 0.989 1.000 0.000
#> GSM955084 2 0.0000 0.989 0.000 1.000
#> GSM955086 2 0.7883 0.690 0.236 0.764
#> GSM955091 2 0.0000 0.989 0.000 1.000
#> GSM955092 2 0.0000 0.989 0.000 1.000
#> GSM955093 2 0.0000 0.989 0.000 1.000
#> GSM955098 2 0.0000 0.989 0.000 1.000
#> GSM955099 2 0.0000 0.989 0.000 1.000
#> GSM955100 1 0.0000 0.989 1.000 0.000
#> GSM955103 2 0.0000 0.989 0.000 1.000
#> GSM955104 1 0.0000 0.989 1.000 0.000
#> GSM955106 2 0.0000 0.989 0.000 1.000
#> GSM955000 1 0.0000 0.989 1.000 0.000
#> GSM955006 1 0.0000 0.989 1.000 0.000
#> GSM955007 2 0.0000 0.989 0.000 1.000
#> GSM955010 1 0.0000 0.989 1.000 0.000
#> GSM955014 1 0.0000 0.989 1.000 0.000
#> GSM955018 2 0.1633 0.967 0.024 0.976
#> GSM955020 1 0.0000 0.989 1.000 0.000
#> GSM955024 2 0.0000 0.989 0.000 1.000
#> GSM955026 2 0.0000 0.989 0.000 1.000
#> GSM955031 1 0.0000 0.989 1.000 0.000
#> GSM955038 1 0.0000 0.989 1.000 0.000
#> GSM955040 1 0.0000 0.989 1.000 0.000
#> GSM955044 2 0.0000 0.989 0.000 1.000
#> GSM955051 1 0.0000 0.989 1.000 0.000
#> GSM955055 2 0.0000 0.989 0.000 1.000
#> GSM955057 1 0.0000 0.989 1.000 0.000
#> GSM955062 2 0.0000 0.989 0.000 1.000
#> GSM955063 2 0.0000 0.989 0.000 1.000
#> GSM955068 2 0.0000 0.989 0.000 1.000
#> GSM955069 1 0.9044 0.520 0.680 0.320
#> GSM955070 2 0.0000 0.989 0.000 1.000
#> GSM955071 1 0.0000 0.989 1.000 0.000
#> GSM955077 1 0.0000 0.989 1.000 0.000
#> GSM955080 2 0.0000 0.989 0.000 1.000
#> GSM955081 2 0.0000 0.989 0.000 1.000
#> GSM955082 2 0.0000 0.989 0.000 1.000
#> GSM955085 2 0.0000 0.989 0.000 1.000
#> GSM955090 1 0.0000 0.989 1.000 0.000
#> GSM955094 2 0.0000 0.989 0.000 1.000
#> GSM955096 2 0.0000 0.989 0.000 1.000
#> GSM955102 1 0.0000 0.989 1.000 0.000
#> GSM955105 1 0.4815 0.880 0.896 0.104
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.2625 0.8786 0.000 0.916 0.084
#> GSM955008 3 0.2537 0.8385 0.000 0.080 0.920
#> GSM955016 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955019 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955022 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955023 3 0.5178 0.6463 0.000 0.256 0.744
#> GSM955027 2 0.0237 0.9402 0.000 0.996 0.004
#> GSM955043 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955048 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955049 2 0.0424 0.9385 0.000 0.992 0.008
#> GSM955054 3 0.6180 0.3046 0.000 0.416 0.584
#> GSM955064 2 0.0747 0.9343 0.000 0.984 0.016
#> GSM955072 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955075 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955079 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955087 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955088 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955089 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955095 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955097 2 0.2625 0.8618 0.084 0.916 0.000
#> GSM955101 3 0.3752 0.7868 0.000 0.144 0.856
#> GSM954999 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955001 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955003 3 0.6274 0.1731 0.000 0.456 0.544
#> GSM955004 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955005 3 0.2711 0.8331 0.088 0.000 0.912
#> GSM955009 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955011 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955012 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955013 3 0.4178 0.7590 0.000 0.172 0.828
#> GSM955015 2 0.6305 -0.0271 0.000 0.516 0.484
#> GSM955017 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955021 2 0.2066 0.9036 0.000 0.940 0.060
#> GSM955025 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955028 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955029 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955030 3 0.6192 0.3017 0.420 0.000 0.580
#> GSM955032 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955033 1 0.4293 0.7819 0.832 0.164 0.004
#> GSM955034 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955035 2 0.1753 0.9135 0.000 0.952 0.048
#> GSM955036 3 0.5244 0.6630 0.240 0.004 0.756
#> GSM955037 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955039 3 0.3816 0.7901 0.000 0.148 0.852
#> GSM955041 2 0.4062 0.7882 0.000 0.836 0.164
#> GSM955042 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955045 2 0.1529 0.9181 0.000 0.960 0.040
#> GSM955046 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955047 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955050 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955052 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955053 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955056 3 0.2261 0.8460 0.000 0.068 0.932
#> GSM955058 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955059 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955060 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955061 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955065 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955066 3 0.3116 0.8154 0.108 0.000 0.892
#> GSM955067 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955073 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955074 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955076 2 0.1964 0.9069 0.000 0.944 0.056
#> GSM955078 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955083 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955084 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955086 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955091 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955092 2 0.2878 0.8677 0.000 0.904 0.096
#> GSM955093 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955098 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955099 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955100 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955103 2 0.5650 0.5469 0.000 0.688 0.312
#> GSM955104 3 0.5591 0.5520 0.304 0.000 0.696
#> GSM955106 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955000 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955006 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955007 3 0.0237 0.8763 0.000 0.004 0.996
#> GSM955010 1 0.1753 0.9419 0.952 0.000 0.048
#> GSM955014 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955018 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955020 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955024 3 0.6180 0.2986 0.000 0.416 0.584
#> GSM955026 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955031 1 0.0237 0.9870 0.996 0.000 0.004
#> GSM955038 1 0.0592 0.9787 0.988 0.012 0.000
#> GSM955040 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955044 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955051 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955055 2 0.0237 0.9402 0.000 0.996 0.004
#> GSM955057 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955062 2 0.1411 0.9218 0.000 0.964 0.036
#> GSM955063 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955068 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955069 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955070 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955071 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955077 1 0.1411 0.9532 0.964 0.036 0.000
#> GSM955080 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955081 2 0.6154 0.2849 0.000 0.592 0.408
#> GSM955082 2 0.5621 0.5568 0.000 0.692 0.308
#> GSM955085 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955090 1 0.0000 0.9906 1.000 0.000 0.000
#> GSM955094 2 0.0000 0.9419 0.000 1.000 0.000
#> GSM955096 3 0.0000 0.8775 0.000 0.000 1.000
#> GSM955102 3 0.2711 0.8309 0.088 0.000 0.912
#> GSM955105 3 0.0237 0.8763 0.004 0.000 0.996
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 4 0.6392 -0.1106 0.000 0.452 0.064 0.484
#> GSM955008 3 0.4046 0.6518 0.000 0.124 0.828 0.048
#> GSM955016 1 0.0336 0.9248 0.992 0.000 0.000 0.008
#> GSM955019 2 0.3325 0.5236 0.000 0.864 0.024 0.112
#> GSM955022 4 0.5793 0.0652 0.000 0.040 0.360 0.600
#> GSM955023 3 0.7188 0.2599 0.000 0.308 0.528 0.164
#> GSM955027 2 0.3271 0.5448 0.000 0.856 0.012 0.132
#> GSM955043 2 0.4961 0.1749 0.000 0.552 0.000 0.448
#> GSM955048 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955049 2 0.5457 0.4977 0.000 0.728 0.088 0.184
#> GSM955054 3 0.7043 0.1190 0.000 0.424 0.456 0.120
#> GSM955064 2 0.6495 0.2857 0.000 0.560 0.084 0.356
#> GSM955072 2 0.2408 0.5431 0.000 0.896 0.000 0.104
#> GSM955075 2 0.4977 0.1521 0.000 0.540 0.000 0.460
#> GSM955079 3 0.2002 0.7214 0.000 0.020 0.936 0.044
#> GSM955087 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955088 3 0.2053 0.7185 0.000 0.004 0.924 0.072
#> GSM955089 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955095 4 0.4999 -0.1326 0.000 0.492 0.000 0.508
#> GSM955097 4 0.5402 -0.1016 0.012 0.472 0.000 0.516
#> GSM955101 3 0.5566 0.5222 0.000 0.224 0.704 0.072
#> GSM954999 1 0.2839 0.8555 0.884 0.004 0.004 0.108
#> GSM955001 2 0.3757 0.5388 0.000 0.828 0.020 0.152
#> GSM955003 3 0.7107 0.1514 0.000 0.408 0.464 0.128
#> GSM955004 2 0.3610 0.4999 0.000 0.800 0.000 0.200
#> GSM955005 3 0.6172 0.5146 0.084 0.000 0.632 0.284
#> GSM955009 2 0.1890 0.5528 0.000 0.936 0.008 0.056
#> GSM955011 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955012 2 0.4985 0.1335 0.000 0.532 0.000 0.468
#> GSM955013 4 0.4898 0.4246 0.000 0.072 0.156 0.772
#> GSM955015 2 0.7540 0.0424 0.000 0.444 0.364 0.192
#> GSM955017 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955021 2 0.5100 0.4134 0.000 0.756 0.168 0.076
#> GSM955025 2 0.3266 0.5051 0.000 0.832 0.000 0.168
#> GSM955028 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955029 2 0.4955 0.1808 0.000 0.556 0.000 0.444
#> GSM955030 1 0.7906 -0.1987 0.356 0.000 0.344 0.300
#> GSM955032 3 0.2319 0.7201 0.000 0.036 0.924 0.040
#> GSM955033 4 0.5608 0.3385 0.148 0.080 0.020 0.752
#> GSM955034 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955035 2 0.5628 0.4326 0.000 0.724 0.144 0.132
#> GSM955036 4 0.5061 0.2971 0.048 0.004 0.196 0.752
#> GSM955037 1 0.1174 0.9118 0.968 0.000 0.012 0.020
#> GSM955039 4 0.5877 0.1073 0.000 0.068 0.276 0.656
#> GSM955041 2 0.7368 0.0998 0.000 0.460 0.164 0.376
#> GSM955042 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955045 2 0.6332 0.1679 0.000 0.532 0.064 0.404
#> GSM955046 3 0.4888 0.4433 0.000 0.000 0.588 0.412
#> GSM955047 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955050 1 0.3224 0.8468 0.864 0.016 0.000 0.120
#> GSM955052 3 0.1520 0.7266 0.000 0.020 0.956 0.024
#> GSM955053 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955056 3 0.4562 0.6205 0.000 0.152 0.792 0.056
#> GSM955058 2 0.4961 0.1765 0.000 0.552 0.000 0.448
#> GSM955059 3 0.3486 0.6594 0.000 0.000 0.812 0.188
#> GSM955060 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955061 2 0.4977 0.1521 0.000 0.540 0.000 0.460
#> GSM955065 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955066 3 0.5859 0.5366 0.064 0.000 0.652 0.284
#> GSM955067 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955073 3 0.1118 0.7274 0.000 0.000 0.964 0.036
#> GSM955074 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955076 2 0.5619 0.4021 0.000 0.724 0.124 0.152
#> GSM955078 2 0.2345 0.5539 0.000 0.900 0.000 0.100
#> GSM955083 1 0.3751 0.7724 0.800 0.004 0.000 0.196
#> GSM955084 2 0.3219 0.5303 0.000 0.836 0.000 0.164
#> GSM955086 3 0.1406 0.7270 0.000 0.024 0.960 0.016
#> GSM955091 2 0.2593 0.5608 0.000 0.892 0.004 0.104
#> GSM955092 2 0.6854 0.2973 0.000 0.596 0.232 0.172
#> GSM955093 3 0.1637 0.7234 0.000 0.000 0.940 0.060
#> GSM955098 2 0.4332 0.4599 0.000 0.792 0.032 0.176
#> GSM955099 2 0.2589 0.5591 0.000 0.884 0.000 0.116
#> GSM955100 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955103 4 0.7341 0.1632 0.000 0.292 0.192 0.516
#> GSM955104 3 0.7745 0.2158 0.240 0.000 0.420 0.340
#> GSM955106 4 0.4999 -0.1464 0.000 0.492 0.000 0.508
#> GSM955000 1 0.0188 0.9263 0.996 0.000 0.004 0.000
#> GSM955006 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955007 3 0.4908 0.5538 0.000 0.016 0.692 0.292
#> GSM955010 1 0.6499 0.5125 0.612 0.000 0.112 0.276
#> GSM955014 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955018 3 0.0921 0.7254 0.000 0.000 0.972 0.028
#> GSM955020 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955024 4 0.7874 0.1452 0.000 0.280 0.348 0.372
#> GSM955026 2 0.4677 0.4539 0.000 0.776 0.048 0.176
#> GSM955031 1 0.5941 0.6904 0.740 0.144 0.036 0.080
#> GSM955038 1 0.3754 0.8254 0.852 0.064 0.000 0.084
#> GSM955040 1 0.2125 0.8876 0.920 0.004 0.000 0.076
#> GSM955044 2 0.4697 0.4411 0.000 0.696 0.008 0.296
#> GSM955051 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955055 2 0.2563 0.5605 0.000 0.908 0.020 0.072
#> GSM955057 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955062 2 0.4514 0.4826 0.000 0.800 0.136 0.064
#> GSM955063 3 0.1389 0.7274 0.000 0.000 0.952 0.048
#> GSM955068 2 0.3257 0.5081 0.000 0.844 0.004 0.152
#> GSM955069 3 0.3528 0.6564 0.000 0.000 0.808 0.192
#> GSM955070 2 0.5237 0.3453 0.000 0.628 0.016 0.356
#> GSM955071 1 0.2593 0.8668 0.892 0.000 0.004 0.104
#> GSM955077 1 0.5675 0.6517 0.720 0.188 0.004 0.088
#> GSM955080 2 0.4994 0.1040 0.000 0.520 0.000 0.480
#> GSM955081 2 0.7340 -0.0392 0.000 0.436 0.408 0.156
#> GSM955082 2 0.7908 -0.1150 0.000 0.360 0.336 0.304
#> GSM955085 2 0.3024 0.5341 0.000 0.852 0.000 0.148
#> GSM955090 1 0.0000 0.9282 1.000 0.000 0.000 0.000
#> GSM955094 4 0.4961 -0.0682 0.000 0.448 0.000 0.552
#> GSM955096 3 0.1975 0.7198 0.000 0.048 0.936 0.016
#> GSM955102 3 0.5393 0.5728 0.044 0.000 0.688 0.268
#> GSM955105 3 0.1526 0.7273 0.012 0.016 0.960 0.012
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.6460 0.318740 0.000 0.576 0.056 0.288 0.080
#> GSM955008 3 0.4715 0.581359 0.000 0.212 0.728 0.048 0.012
#> GSM955016 1 0.2305 0.824099 0.896 0.012 0.000 0.092 0.000
#> GSM955019 2 0.4715 0.426234 0.000 0.672 0.020 0.012 0.296
#> GSM955022 4 0.7368 0.328001 0.000 0.040 0.220 0.436 0.304
#> GSM955023 3 0.7840 0.131972 0.000 0.284 0.440 0.116 0.160
#> GSM955027 5 0.5536 0.233555 0.000 0.340 0.044 0.020 0.596
#> GSM955043 5 0.2727 0.560542 0.000 0.116 0.000 0.016 0.868
#> GSM955048 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955049 5 0.6736 -0.041485 0.000 0.372 0.136 0.024 0.468
#> GSM955054 2 0.5619 0.069010 0.000 0.516 0.428 0.032 0.024
#> GSM955064 5 0.7118 0.079444 0.000 0.320 0.128 0.060 0.492
#> GSM955072 2 0.4668 0.282204 0.000 0.600 0.008 0.008 0.384
#> GSM955075 5 0.0566 0.584207 0.000 0.012 0.000 0.004 0.984
#> GSM955079 3 0.3494 0.651015 0.000 0.096 0.840 0.060 0.004
#> GSM955087 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955088 3 0.4233 0.488581 0.000 0.044 0.748 0.208 0.000
#> GSM955089 1 0.0000 0.883075 1.000 0.000 0.000 0.000 0.000
#> GSM955095 5 0.2353 0.564589 0.000 0.028 0.004 0.060 0.908
#> GSM955097 5 0.2544 0.554254 0.008 0.028 0.000 0.064 0.900
#> GSM955101 3 0.5977 0.453166 0.000 0.264 0.620 0.088 0.028
#> GSM954999 1 0.5039 0.518057 0.648 0.020 0.004 0.312 0.016
#> GSM955001 5 0.5190 0.259652 0.000 0.344 0.020 0.024 0.612
#> GSM955003 3 0.5781 0.010179 0.000 0.464 0.472 0.036 0.028
#> GSM955004 5 0.4473 0.321252 0.000 0.324 0.000 0.020 0.656
#> GSM955005 4 0.5894 0.330385 0.056 0.016 0.380 0.544 0.004
#> GSM955009 2 0.4920 0.308414 0.000 0.620 0.008 0.024 0.348
#> GSM955011 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955012 5 0.1012 0.583967 0.000 0.012 0.000 0.020 0.968
#> GSM955013 4 0.6972 0.343529 0.000 0.052 0.116 0.484 0.348
#> GSM955015 2 0.7711 0.245744 0.000 0.432 0.324 0.124 0.120
#> GSM955017 1 0.0880 0.873191 0.968 0.000 0.000 0.032 0.000
#> GSM955021 2 0.6775 0.425345 0.000 0.560 0.196 0.036 0.208
#> GSM955025 2 0.5180 0.417821 0.000 0.696 0.004 0.112 0.188
#> GSM955028 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955029 5 0.1124 0.581051 0.000 0.036 0.000 0.004 0.960
#> GSM955030 4 0.6338 0.441283 0.232 0.008 0.196 0.564 0.000
#> GSM955032 3 0.2554 0.658463 0.000 0.072 0.892 0.036 0.000
#> GSM955033 4 0.5899 0.394124 0.024 0.232 0.000 0.640 0.104
#> GSM955034 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955035 2 0.7163 0.388003 0.000 0.524 0.168 0.060 0.248
#> GSM955036 4 0.4377 0.507511 0.000 0.024 0.024 0.760 0.192
#> GSM955037 1 0.1952 0.829960 0.912 0.000 0.004 0.084 0.000
#> GSM955039 4 0.6113 0.444175 0.000 0.120 0.112 0.676 0.092
#> GSM955041 5 0.7284 0.210930 0.000 0.176 0.204 0.084 0.536
#> GSM955042 1 0.0798 0.876513 0.976 0.008 0.000 0.016 0.000
#> GSM955045 5 0.2800 0.573104 0.000 0.052 0.040 0.016 0.892
#> GSM955046 4 0.5141 0.383151 0.000 0.012 0.320 0.632 0.036
#> GSM955047 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955050 1 0.5329 0.611014 0.672 0.184 0.000 0.144 0.000
#> GSM955052 3 0.2437 0.658577 0.000 0.060 0.904 0.032 0.004
#> GSM955053 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955056 3 0.5151 0.582836 0.000 0.228 0.696 0.056 0.020
#> GSM955058 5 0.0703 0.583481 0.000 0.024 0.000 0.000 0.976
#> GSM955059 3 0.4389 0.178732 0.000 0.004 0.624 0.368 0.004
#> GSM955060 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955061 5 0.0609 0.583788 0.000 0.020 0.000 0.000 0.980
#> GSM955065 1 0.0290 0.882396 0.992 0.000 0.000 0.008 0.000
#> GSM955066 4 0.4752 0.311321 0.020 0.000 0.412 0.568 0.000
#> GSM955067 1 0.0451 0.880871 0.988 0.004 0.000 0.008 0.000
#> GSM955073 3 0.2968 0.636289 0.000 0.028 0.872 0.092 0.008
#> GSM955074 1 0.0451 0.880498 0.988 0.004 0.000 0.008 0.000
#> GSM955076 2 0.4882 0.518100 0.000 0.756 0.100 0.024 0.120
#> GSM955078 5 0.4367 0.242276 0.000 0.372 0.000 0.008 0.620
#> GSM955083 1 0.5721 0.463144 0.612 0.040 0.000 0.308 0.040
#> GSM955084 5 0.4953 0.045965 0.000 0.440 0.000 0.028 0.532
#> GSM955086 3 0.3102 0.637793 0.000 0.084 0.860 0.056 0.000
#> GSM955091 2 0.4800 0.131033 0.000 0.528 0.008 0.008 0.456
#> GSM955092 5 0.7178 0.173925 0.000 0.228 0.252 0.036 0.484
#> GSM955093 3 0.3621 0.568844 0.000 0.020 0.788 0.192 0.000
#> GSM955098 2 0.2914 0.501724 0.000 0.872 0.000 0.052 0.076
#> GSM955099 2 0.5295 0.115023 0.000 0.504 0.008 0.032 0.456
#> GSM955100 1 0.0963 0.871379 0.964 0.000 0.000 0.036 0.000
#> GSM955103 5 0.6173 0.406389 0.000 0.080 0.128 0.124 0.668
#> GSM955104 4 0.7456 0.436075 0.156 0.020 0.240 0.532 0.052
#> GSM955106 5 0.2110 0.561563 0.000 0.016 0.000 0.072 0.912
#> GSM955000 1 0.0880 0.872042 0.968 0.000 0.000 0.032 0.000
#> GSM955006 1 0.0000 0.883075 1.000 0.000 0.000 0.000 0.000
#> GSM955007 3 0.7355 -0.005727 0.000 0.048 0.432 0.340 0.180
#> GSM955010 4 0.5599 0.242319 0.376 0.028 0.032 0.564 0.000
#> GSM955014 1 0.0000 0.883075 1.000 0.000 0.000 0.000 0.000
#> GSM955018 3 0.2389 0.599786 0.000 0.004 0.880 0.116 0.000
#> GSM955020 1 0.0162 0.882505 0.996 0.004 0.000 0.000 0.000
#> GSM955024 5 0.7803 0.023913 0.000 0.124 0.348 0.128 0.400
#> GSM955026 2 0.3133 0.498599 0.000 0.864 0.004 0.052 0.080
#> GSM955031 1 0.7115 0.310597 0.508 0.308 0.100 0.084 0.000
#> GSM955038 1 0.5574 0.565334 0.640 0.244 0.000 0.112 0.004
#> GSM955040 1 0.5741 0.565039 0.636 0.156 0.004 0.204 0.000
#> GSM955044 5 0.5636 0.149403 0.000 0.372 0.012 0.056 0.560
#> GSM955051 1 0.0000 0.883075 1.000 0.000 0.000 0.000 0.000
#> GSM955055 5 0.5687 -0.036466 0.000 0.444 0.040 0.020 0.496
#> GSM955057 1 0.0162 0.883472 0.996 0.000 0.000 0.004 0.000
#> GSM955062 2 0.7097 0.322461 0.000 0.476 0.176 0.036 0.312
#> GSM955063 3 0.3110 0.629498 0.000 0.028 0.856 0.112 0.004
#> GSM955068 2 0.4197 0.474331 0.000 0.752 0.004 0.032 0.212
#> GSM955069 3 0.4533 0.000202 0.000 0.008 0.544 0.448 0.000
#> GSM955070 2 0.7175 0.236891 0.000 0.484 0.044 0.176 0.296
#> GSM955071 1 0.5039 0.649815 0.708 0.100 0.004 0.188 0.000
#> GSM955077 1 0.7295 0.262609 0.480 0.352 0.020 0.100 0.048
#> GSM955080 5 0.1992 0.578477 0.000 0.032 0.000 0.044 0.924
#> GSM955081 2 0.7564 -0.023548 0.000 0.408 0.372 0.124 0.096
#> GSM955082 5 0.6246 0.286837 0.000 0.064 0.316 0.048 0.572
#> GSM955085 5 0.4843 0.302802 0.000 0.328 0.008 0.024 0.640
#> GSM955090 1 0.0162 0.882505 0.996 0.004 0.000 0.000 0.000
#> GSM955094 5 0.6707 -0.048311 0.000 0.368 0.000 0.244 0.388
#> GSM955096 3 0.3159 0.645292 0.000 0.088 0.856 0.056 0.000
#> GSM955102 4 0.5100 0.233624 0.036 0.000 0.448 0.516 0.000
#> GSM955105 3 0.3213 0.625815 0.004 0.064 0.860 0.072 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.7255 -0.00516 0.000 0.428 0.036 0.340 0.076 0.120
#> GSM955008 6 0.3913 0.46740 0.000 0.072 0.128 0.008 0.004 0.788
#> GSM955016 1 0.3432 0.73019 0.764 0.020 0.000 0.216 0.000 0.000
#> GSM955019 2 0.6095 0.27001 0.000 0.532 0.000 0.040 0.296 0.132
#> GSM955022 3 0.7782 -0.17800 0.000 0.016 0.372 0.160 0.260 0.192
#> GSM955023 6 0.7328 0.36041 0.000 0.168 0.160 0.040 0.116 0.516
#> GSM955027 5 0.5760 0.40451 0.000 0.180 0.000 0.028 0.600 0.192
#> GSM955043 5 0.3390 0.54818 0.000 0.104 0.004 0.028 0.836 0.028
#> GSM955048 1 0.0260 0.84123 0.992 0.000 0.000 0.008 0.000 0.000
#> GSM955049 5 0.6671 0.15624 0.000 0.224 0.004 0.032 0.424 0.316
#> GSM955054 6 0.5849 0.27349 0.000 0.332 0.044 0.036 0.028 0.560
#> GSM955064 5 0.6872 0.13507 0.000 0.112 0.008 0.088 0.400 0.392
#> GSM955072 2 0.5537 0.25228 0.000 0.572 0.004 0.024 0.324 0.076
#> GSM955075 5 0.1155 0.57056 0.000 0.004 0.000 0.036 0.956 0.004
#> GSM955079 6 0.6607 0.29217 0.008 0.056 0.208 0.148 0.012 0.568
#> GSM955087 1 0.0260 0.84070 0.992 0.000 0.000 0.008 0.000 0.000
#> GSM955088 3 0.6647 -0.02979 0.000 0.076 0.464 0.116 0.004 0.340
#> GSM955089 1 0.0458 0.84090 0.984 0.000 0.000 0.016 0.000 0.000
#> GSM955095 5 0.3482 0.53707 0.000 0.024 0.008 0.116 0.828 0.024
#> GSM955097 5 0.2890 0.51626 0.000 0.024 0.004 0.128 0.844 0.000
#> GSM955101 6 0.4817 0.46558 0.000 0.100 0.052 0.072 0.020 0.756
#> GSM954999 1 0.6516 0.39670 0.520 0.032 0.116 0.308 0.016 0.008
#> GSM955001 5 0.5706 0.38347 0.000 0.208 0.000 0.024 0.600 0.168
#> GSM955003 6 0.4498 0.38498 0.000 0.260 0.016 0.032 0.004 0.688
#> GSM955004 5 0.4012 0.34151 0.000 0.344 0.000 0.016 0.640 0.000
#> GSM955005 3 0.4346 0.42260 0.040 0.020 0.788 0.100 0.000 0.052
#> GSM955009 2 0.5997 0.21509 0.000 0.544 0.008 0.044 0.324 0.080
#> GSM955011 1 0.0405 0.84002 0.988 0.000 0.008 0.004 0.000 0.000
#> GSM955012 5 0.0665 0.57808 0.000 0.008 0.000 0.004 0.980 0.008
#> GSM955013 4 0.7889 0.28657 0.000 0.052 0.152 0.364 0.324 0.108
#> GSM955015 6 0.7212 0.27969 0.000 0.224 0.124 0.060 0.072 0.520
#> GSM955017 1 0.1995 0.81481 0.912 0.000 0.052 0.036 0.000 0.000
#> GSM955021 6 0.6549 -0.05212 0.000 0.360 0.012 0.032 0.148 0.448
#> GSM955025 2 0.4160 0.46438 0.000 0.780 0.012 0.108 0.092 0.008
#> GSM955028 1 0.0260 0.84070 0.992 0.000 0.000 0.008 0.000 0.000
#> GSM955029 5 0.0862 0.57807 0.000 0.016 0.000 0.004 0.972 0.008
#> GSM955030 3 0.6136 0.18399 0.240 0.004 0.544 0.188 0.000 0.024
#> GSM955032 6 0.5384 0.33976 0.000 0.060 0.316 0.036 0.000 0.588
#> GSM955033 4 0.6694 0.37336 0.020 0.144 0.192 0.576 0.060 0.008
#> GSM955034 1 0.0146 0.84082 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM955035 6 0.6741 -0.02347 0.000 0.336 0.008 0.048 0.164 0.444
#> GSM955036 3 0.5941 -0.31103 0.000 0.008 0.452 0.424 0.096 0.020
#> GSM955037 1 0.3010 0.75619 0.836 0.000 0.132 0.028 0.000 0.004
#> GSM955039 4 0.7618 0.29719 0.000 0.084 0.260 0.440 0.048 0.168
#> GSM955041 6 0.6837 -0.08100 0.000 0.076 0.048 0.052 0.392 0.432
#> GSM955042 1 0.2744 0.79429 0.840 0.016 0.000 0.144 0.000 0.000
#> GSM955045 5 0.4278 0.54483 0.000 0.044 0.004 0.084 0.784 0.084
#> GSM955046 3 0.3662 0.33937 0.000 0.000 0.800 0.128 0.008 0.064
#> GSM955047 1 0.1196 0.83569 0.952 0.000 0.008 0.040 0.000 0.000
#> GSM955050 1 0.6166 0.33853 0.484 0.212 0.016 0.288 0.000 0.000
#> GSM955052 6 0.4273 0.40539 0.000 0.036 0.248 0.012 0.000 0.704
#> GSM955053 1 0.0363 0.84085 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM955056 6 0.6289 0.41859 0.000 0.128 0.196 0.068 0.012 0.596
#> GSM955058 5 0.0767 0.57810 0.000 0.012 0.000 0.004 0.976 0.008
#> GSM955059 3 0.3231 0.37625 0.000 0.000 0.784 0.016 0.000 0.200
#> GSM955060 1 0.0806 0.83856 0.972 0.000 0.008 0.020 0.000 0.000
#> GSM955061 5 0.0551 0.57626 0.000 0.004 0.000 0.008 0.984 0.004
#> GSM955065 1 0.0520 0.84046 0.984 0.000 0.008 0.008 0.000 0.000
#> GSM955066 3 0.2859 0.43177 0.024 0.008 0.880 0.056 0.000 0.032
#> GSM955067 1 0.1901 0.83054 0.912 0.008 0.004 0.076 0.000 0.000
#> GSM955073 6 0.4194 0.33957 0.000 0.004 0.320 0.016 0.004 0.656
#> GSM955074 1 0.2664 0.79859 0.848 0.016 0.000 0.136 0.000 0.000
#> GSM955076 2 0.4902 0.45947 0.000 0.696 0.004 0.012 0.112 0.176
#> GSM955078 5 0.4450 0.27946 0.000 0.380 0.000 0.012 0.592 0.016
#> GSM955083 1 0.6748 0.27586 0.468 0.040 0.076 0.360 0.056 0.000
#> GSM955084 5 0.4432 0.17097 0.000 0.432 0.000 0.020 0.544 0.004
#> GSM955086 6 0.6379 0.25742 0.000 0.076 0.308 0.108 0.000 0.508
#> GSM955091 5 0.5777 0.09339 0.000 0.412 0.000 0.024 0.468 0.096
#> GSM955092 5 0.7406 0.19934 0.000 0.164 0.028 0.080 0.416 0.312
#> GSM955093 6 0.5279 0.16267 0.000 0.012 0.384 0.072 0.000 0.532
#> GSM955098 2 0.3029 0.50969 0.000 0.868 0.004 0.028 0.040 0.060
#> GSM955099 5 0.5901 0.24129 0.000 0.340 0.000 0.032 0.520 0.108
#> GSM955100 1 0.1686 0.82519 0.924 0.000 0.012 0.064 0.000 0.000
#> GSM955103 5 0.6858 0.10741 0.000 0.032 0.044 0.184 0.524 0.216
#> GSM955104 3 0.7229 0.18471 0.152 0.004 0.484 0.260 0.024 0.076
#> GSM955106 5 0.2458 0.55120 0.000 0.016 0.004 0.084 0.888 0.008
#> GSM955000 1 0.2060 0.80309 0.900 0.000 0.084 0.016 0.000 0.000
#> GSM955006 1 0.0405 0.84097 0.988 0.000 0.004 0.008 0.000 0.000
#> GSM955007 3 0.6183 -0.00135 0.000 0.008 0.500 0.032 0.112 0.348
#> GSM955010 3 0.6671 -0.06320 0.316 0.028 0.336 0.320 0.000 0.000
#> GSM955014 1 0.1493 0.83607 0.936 0.004 0.004 0.056 0.000 0.000
#> GSM955018 6 0.5614 0.05049 0.000 0.016 0.440 0.092 0.000 0.452
#> GSM955020 1 0.1152 0.83758 0.952 0.004 0.000 0.044 0.000 0.000
#> GSM955024 5 0.7596 0.03657 0.000 0.056 0.104 0.100 0.396 0.344
#> GSM955026 2 0.2825 0.49785 0.000 0.884 0.008 0.040 0.036 0.032
#> GSM955031 1 0.7843 0.01880 0.376 0.328 0.088 0.140 0.000 0.068
#> GSM955038 1 0.5894 0.37720 0.500 0.280 0.004 0.216 0.000 0.000
#> GSM955040 1 0.6335 0.38017 0.512 0.144 0.052 0.292 0.000 0.000
#> GSM955044 5 0.6407 0.22507 0.000 0.312 0.004 0.072 0.512 0.100
#> GSM955051 1 0.0790 0.84127 0.968 0.000 0.000 0.032 0.000 0.000
#> GSM955055 5 0.6828 0.09433 0.000 0.320 0.004 0.048 0.420 0.208
#> GSM955057 1 0.0363 0.84118 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM955062 6 0.7162 -0.12682 0.000 0.236 0.012 0.056 0.300 0.396
#> GSM955063 6 0.4118 0.30877 0.000 0.000 0.352 0.020 0.000 0.628
#> GSM955068 2 0.4659 0.42821 0.000 0.700 0.000 0.020 0.216 0.064
#> GSM955069 3 0.5410 0.31720 0.004 0.004 0.616 0.124 0.004 0.248
#> GSM955070 2 0.7993 0.17790 0.000 0.304 0.016 0.252 0.240 0.188
#> GSM955071 1 0.6021 0.45266 0.568 0.064 0.080 0.284 0.000 0.004
#> GSM955077 2 0.7206 0.03615 0.308 0.440 0.028 0.184 0.016 0.024
#> GSM955080 5 0.2265 0.56685 0.000 0.024 0.000 0.076 0.896 0.004
#> GSM955081 2 0.8041 -0.06776 0.000 0.340 0.108 0.168 0.060 0.324
#> GSM955082 5 0.7307 0.13616 0.000 0.056 0.044 0.152 0.440 0.308
#> GSM955085 5 0.4924 0.40970 0.000 0.288 0.004 0.040 0.644 0.024
#> GSM955090 1 0.2039 0.82605 0.908 0.016 0.004 0.072 0.000 0.000
#> GSM955094 2 0.8083 -0.00495 0.000 0.308 0.096 0.252 0.292 0.052
#> GSM955096 6 0.6085 0.30526 0.000 0.072 0.268 0.096 0.000 0.564
#> GSM955102 3 0.2642 0.45286 0.032 0.000 0.884 0.020 0.000 0.064
#> GSM955105 6 0.7057 0.19692 0.032 0.060 0.248 0.160 0.000 0.500
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> SD:skmeans 107 0.0967 2
#> SD:skmeans 102 0.5557 3
#> SD:skmeans 66 0.7902 4
#> SD:skmeans 55 0.5412 5
#> SD:skmeans 36 0.4767 6
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 31589 rows and 108 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 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 0.681 0.830 0.909 0.3715 0.565 0.565
#> 3 3 0.697 0.865 0.927 0.6498 0.701 0.523
#> 4 4 0.763 0.826 0.918 0.1621 0.893 0.731
#> 5 5 0.614 0.554 0.784 0.0610 0.927 0.763
#> 6 6 0.705 0.679 0.838 0.0488 0.920 0.708
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
#> GSM955002 2 0.1633 0.948 0.024 0.976
#> GSM955008 2 0.0672 0.959 0.008 0.992
#> GSM955016 1 0.9775 0.614 0.588 0.412
#> GSM955019 2 0.0000 0.959 0.000 1.000
#> GSM955022 2 0.1414 0.952 0.020 0.980
#> GSM955023 2 0.0938 0.958 0.012 0.988
#> GSM955027 2 0.0000 0.959 0.000 1.000
#> GSM955043 2 0.0376 0.959 0.004 0.996
#> GSM955048 1 0.0000 0.734 1.000 0.000
#> GSM955049 2 0.0000 0.959 0.000 1.000
#> GSM955054 2 0.0376 0.959 0.004 0.996
#> GSM955064 2 0.0000 0.959 0.000 1.000
#> GSM955072 2 0.0000 0.959 0.000 1.000
#> GSM955075 2 0.0000 0.959 0.000 1.000
#> GSM955079 2 0.1843 0.942 0.028 0.972
#> GSM955087 1 0.0000 0.734 1.000 0.000
#> GSM955088 2 0.0938 0.958 0.012 0.988
#> GSM955089 1 0.0000 0.734 1.000 0.000
#> GSM955095 2 0.0000 0.959 0.000 1.000
#> GSM955097 2 0.9983 -0.376 0.476 0.524
#> GSM955101 2 0.0000 0.959 0.000 1.000
#> GSM954999 1 0.9775 0.614 0.588 0.412
#> GSM955001 2 0.0000 0.959 0.000 1.000
#> GSM955003 2 0.0000 0.959 0.000 1.000
#> GSM955004 2 0.5519 0.795 0.128 0.872
#> GSM955005 2 0.6048 0.776 0.148 0.852
#> GSM955009 2 0.0000 0.959 0.000 1.000
#> GSM955011 1 0.9775 0.614 0.588 0.412
#> GSM955012 2 0.0938 0.958 0.012 0.988
#> GSM955013 2 0.3114 0.911 0.056 0.944
#> GSM955015 2 0.0938 0.958 0.012 0.988
#> GSM955017 1 0.9775 0.614 0.588 0.412
#> GSM955021 2 0.0000 0.959 0.000 1.000
#> GSM955025 2 0.1184 0.956 0.016 0.984
#> GSM955028 1 0.0000 0.734 1.000 0.000
#> GSM955029 2 0.0000 0.959 0.000 1.000
#> GSM955030 1 0.9833 0.594 0.576 0.424
#> GSM955032 2 0.0938 0.958 0.012 0.988
#> GSM955033 1 0.9963 0.514 0.536 0.464
#> GSM955034 1 0.0000 0.734 1.000 0.000
#> GSM955035 2 0.0000 0.959 0.000 1.000
#> GSM955036 1 0.9775 0.614 0.588 0.412
#> GSM955037 1 0.9775 0.614 0.588 0.412
#> GSM955039 2 0.0938 0.958 0.012 0.988
#> GSM955041 2 0.0938 0.958 0.012 0.988
#> GSM955042 1 0.9775 0.614 0.588 0.412
#> GSM955045 2 0.0000 0.959 0.000 1.000
#> GSM955046 2 0.0938 0.958 0.012 0.988
#> GSM955047 1 0.0000 0.734 1.000 0.000
#> GSM955050 1 0.9850 0.599 0.572 0.428
#> GSM955052 2 0.0938 0.958 0.012 0.988
#> GSM955053 1 0.0000 0.734 1.000 0.000
#> GSM955056 2 0.0938 0.958 0.012 0.988
#> GSM955058 2 0.0000 0.959 0.000 1.000
#> GSM955059 2 0.0938 0.958 0.012 0.988
#> GSM955060 1 0.0000 0.734 1.000 0.000
#> GSM955061 2 0.0000 0.959 0.000 1.000
#> GSM955065 1 0.0000 0.734 1.000 0.000
#> GSM955066 1 0.9866 0.580 0.568 0.432
#> GSM955067 1 0.0000 0.734 1.000 0.000
#> GSM955073 2 0.0938 0.958 0.012 0.988
#> GSM955074 1 0.9775 0.614 0.588 0.412
#> GSM955076 2 0.0000 0.959 0.000 1.000
#> GSM955078 2 0.0000 0.959 0.000 1.000
#> GSM955083 1 0.9795 0.608 0.584 0.416
#> GSM955084 2 0.0000 0.959 0.000 1.000
#> GSM955086 2 0.0938 0.958 0.012 0.988
#> GSM955091 2 0.0000 0.959 0.000 1.000
#> GSM955092 2 0.0000 0.959 0.000 1.000
#> GSM955093 2 0.0938 0.958 0.012 0.988
#> GSM955098 2 0.0938 0.958 0.012 0.988
#> GSM955099 2 0.0000 0.959 0.000 1.000
#> GSM955100 1 0.9775 0.614 0.588 0.412
#> GSM955103 2 0.0000 0.959 0.000 1.000
#> GSM955104 2 0.6048 0.776 0.148 0.852
#> GSM955106 2 0.0938 0.958 0.012 0.988
#> GSM955000 1 0.9775 0.614 0.588 0.412
#> GSM955006 1 0.0000 0.734 1.000 0.000
#> GSM955007 2 0.0672 0.959 0.008 0.992
#> GSM955010 2 0.4022 0.879 0.080 0.920
#> GSM955014 1 0.0000 0.734 1.000 0.000
#> GSM955018 2 0.1184 0.955 0.016 0.984
#> GSM955020 1 0.0000 0.734 1.000 0.000
#> GSM955024 2 0.0376 0.959 0.004 0.996
#> GSM955026 2 0.0376 0.959 0.004 0.996
#> GSM955031 2 0.0672 0.958 0.008 0.992
#> GSM955038 2 0.6712 0.724 0.176 0.824
#> GSM955040 1 0.9944 0.533 0.544 0.456
#> GSM955044 2 0.0000 0.959 0.000 1.000
#> GSM955051 1 0.0000 0.734 1.000 0.000
#> GSM955055 2 0.0000 0.959 0.000 1.000
#> GSM955057 1 0.0000 0.734 1.000 0.000
#> GSM955062 2 0.0000 0.959 0.000 1.000
#> GSM955063 2 0.0938 0.958 0.012 0.988
#> GSM955068 2 0.0000 0.959 0.000 1.000
#> GSM955069 2 0.6048 0.776 0.148 0.852
#> GSM955070 2 0.0000 0.959 0.000 1.000
#> GSM955071 2 0.9963 -0.300 0.464 0.536
#> GSM955077 1 0.9970 0.506 0.532 0.468
#> GSM955080 2 0.0000 0.959 0.000 1.000
#> GSM955081 2 0.0938 0.958 0.012 0.988
#> GSM955082 2 0.0000 0.959 0.000 1.000
#> GSM955085 2 0.0000 0.959 0.000 1.000
#> GSM955090 1 0.0000 0.734 1.000 0.000
#> GSM955094 2 0.0938 0.958 0.012 0.988
#> GSM955096 2 0.0938 0.958 0.012 0.988
#> GSM955102 1 0.9909 0.554 0.556 0.444
#> GSM955105 2 0.1414 0.952 0.020 0.980
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.5138 7.70e-01 0.000 0.748 0.252
#> GSM955008 2 0.3267 8.63e-01 0.000 0.884 0.116
#> GSM955016 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955019 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955022 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955023 2 0.4702 8.10e-01 0.000 0.788 0.212
#> GSM955027 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955043 2 0.6307 7.87e-03 0.000 0.512 0.488
#> GSM955048 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955049 2 0.1411 8.94e-01 0.000 0.964 0.036
#> GSM955054 2 0.1529 8.94e-01 0.000 0.960 0.040
#> GSM955064 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955072 2 0.0892 8.93e-01 0.000 0.980 0.020
#> GSM955075 2 0.1289 8.90e-01 0.000 0.968 0.032
#> GSM955079 3 0.2537 8.88e-01 0.000 0.080 0.920
#> GSM955087 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955088 2 0.6095 4.83e-01 0.000 0.608 0.392
#> GSM955089 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955095 2 0.2711 8.67e-01 0.000 0.912 0.088
#> GSM955097 3 0.4291 7.55e-01 0.000 0.180 0.820
#> GSM955101 2 0.0237 8.96e-01 0.000 0.996 0.004
#> GSM954999 3 0.1163 9.16e-01 0.028 0.000 0.972
#> GSM955001 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955003 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955004 2 0.1289 8.90e-01 0.000 0.968 0.032
#> GSM955005 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955009 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955011 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955012 3 0.2356 8.78e-01 0.000 0.072 0.928
#> GSM955013 3 0.1411 9.00e-01 0.000 0.036 0.964
#> GSM955015 2 0.1529 8.94e-01 0.000 0.960 0.040
#> GSM955017 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955021 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955025 3 0.1411 9.09e-01 0.000 0.036 0.964
#> GSM955028 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955029 2 0.1529 8.89e-01 0.000 0.960 0.040
#> GSM955030 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955032 3 0.5621 5.41e-01 0.000 0.308 0.692
#> GSM955033 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955034 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955035 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955036 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955037 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955039 3 0.5760 4.28e-01 0.000 0.328 0.672
#> GSM955041 2 0.2878 8.74e-01 0.000 0.904 0.096
#> GSM955042 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955045 2 0.4504 7.56e-01 0.000 0.804 0.196
#> GSM955046 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955047 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955050 3 0.3966 8.46e-01 0.024 0.100 0.876
#> GSM955052 2 0.4291 8.20e-01 0.000 0.820 0.180
#> GSM955053 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955056 2 0.4291 8.20e-01 0.000 0.820 0.180
#> GSM955058 2 0.1289 8.91e-01 0.000 0.968 0.032
#> GSM955059 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955060 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955061 3 0.4291 7.55e-01 0.000 0.180 0.820
#> GSM955065 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955066 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955067 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955073 2 0.4291 8.20e-01 0.000 0.820 0.180
#> GSM955074 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955076 2 0.1163 8.95e-01 0.000 0.972 0.028
#> GSM955078 2 0.0424 8.95e-01 0.000 0.992 0.008
#> GSM955083 3 0.1031 9.16e-01 0.024 0.000 0.976
#> GSM955084 2 0.1529 8.91e-01 0.000 0.960 0.040
#> GSM955086 2 0.5859 5.90e-01 0.000 0.656 0.344
#> GSM955091 2 0.0237 8.96e-01 0.000 0.996 0.004
#> GSM955092 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955093 2 0.4291 8.20e-01 0.000 0.820 0.180
#> GSM955098 2 0.4291 8.20e-01 0.000 0.820 0.180
#> GSM955099 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955100 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955103 2 0.1529 8.94e-01 0.000 0.960 0.040
#> GSM955104 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955106 3 0.6252 6.26e-05 0.000 0.444 0.556
#> GSM955000 3 0.1529 9.11e-01 0.040 0.000 0.960
#> GSM955006 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955007 3 0.3038 8.45e-01 0.000 0.104 0.896
#> GSM955010 3 0.3879 7.81e-01 0.000 0.152 0.848
#> GSM955014 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955018 3 0.1964 8.98e-01 0.000 0.056 0.944
#> GSM955020 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955024 2 0.2356 8.87e-01 0.000 0.928 0.072
#> GSM955026 2 0.3412 8.63e-01 0.000 0.876 0.124
#> GSM955031 2 0.2959 8.74e-01 0.000 0.900 0.100
#> GSM955038 3 0.1905 9.14e-01 0.028 0.016 0.956
#> GSM955040 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955044 2 0.0892 8.93e-01 0.000 0.980 0.020
#> GSM955051 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955055 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955057 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955062 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955063 2 0.4291 8.21e-01 0.000 0.820 0.180
#> GSM955068 2 0.4555 7.33e-01 0.000 0.800 0.200
#> GSM955069 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955070 2 0.0237 8.95e-01 0.000 0.996 0.004
#> GSM955071 3 0.1529 9.07e-01 0.000 0.040 0.960
#> GSM955077 3 0.1289 9.15e-01 0.032 0.000 0.968
#> GSM955080 2 0.1289 8.90e-01 0.000 0.968 0.032
#> GSM955081 2 0.4346 8.18e-01 0.000 0.816 0.184
#> GSM955082 2 0.2711 8.86e-01 0.000 0.912 0.088
#> GSM955085 2 0.0000 8.95e-01 0.000 1.000 0.000
#> GSM955090 1 0.0000 1.00e+00 1.000 0.000 0.000
#> GSM955094 2 0.5363 7.42e-01 0.000 0.724 0.276
#> GSM955096 2 0.5431 7.01e-01 0.000 0.716 0.284
#> GSM955102 3 0.0000 9.16e-01 0.000 0.000 1.000
#> GSM955105 2 0.4452 8.13e-01 0.000 0.808 0.192
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.3636 0.7443 0.000 0.820 0.172 0.008
#> GSM955008 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955016 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955019 2 0.1792 0.8427 0.000 0.932 0.000 0.068
#> GSM955022 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955023 2 0.0804 0.8539 0.000 0.980 0.012 0.008
#> GSM955027 4 0.4994 0.0274 0.000 0.480 0.000 0.520
#> GSM955043 4 0.3205 0.7822 0.000 0.104 0.024 0.872
#> GSM955048 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955049 2 0.0188 0.8551 0.000 0.996 0.004 0.000
#> GSM955054 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955064 2 0.3486 0.7704 0.000 0.812 0.000 0.188
#> GSM955072 2 0.4356 0.6725 0.000 0.708 0.000 0.292
#> GSM955075 4 0.0000 0.8447 0.000 0.000 0.000 1.000
#> GSM955079 3 0.2522 0.8726 0.000 0.016 0.908 0.076
#> GSM955087 1 0.0188 0.9961 0.996 0.000 0.004 0.000
#> GSM955088 2 0.4356 0.5619 0.000 0.708 0.292 0.000
#> GSM955089 1 0.0188 0.9961 0.996 0.000 0.004 0.000
#> GSM955095 4 0.5108 0.4087 0.000 0.308 0.020 0.672
#> GSM955097 4 0.0000 0.8447 0.000 0.000 0.000 1.000
#> GSM955101 2 0.0469 0.8552 0.000 0.988 0.000 0.012
#> GSM954999 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955001 2 0.4304 0.6805 0.000 0.716 0.000 0.284
#> GSM955003 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955004 4 0.0000 0.8447 0.000 0.000 0.000 1.000
#> GSM955005 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955009 2 0.4304 0.6805 0.000 0.716 0.000 0.284
#> GSM955011 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955012 4 0.3942 0.6413 0.000 0.000 0.236 0.764
#> GSM955013 3 0.1452 0.9110 0.000 0.036 0.956 0.008
#> GSM955015 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955017 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955021 2 0.3907 0.7361 0.000 0.768 0.000 0.232
#> GSM955025 3 0.0672 0.9333 0.000 0.008 0.984 0.008
#> GSM955028 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955029 4 0.0000 0.8447 0.000 0.000 0.000 1.000
#> GSM955030 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955032 3 0.4907 0.3230 0.000 0.420 0.580 0.000
#> GSM955033 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955034 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955035 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955036 3 0.0921 0.9268 0.000 0.000 0.972 0.028
#> GSM955037 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955039 3 0.5172 0.3188 0.000 0.404 0.588 0.008
#> GSM955041 2 0.4967 -0.0171 0.000 0.548 0.000 0.452
#> GSM955042 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955045 2 0.7188 0.3955 0.000 0.528 0.164 0.308
#> GSM955046 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955047 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955050 3 0.3123 0.7849 0.000 0.000 0.844 0.156
#> GSM955052 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955053 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955056 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955058 4 0.0000 0.8447 0.000 0.000 0.000 1.000
#> GSM955059 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955060 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955061 4 0.0000 0.8447 0.000 0.000 0.000 1.000
#> GSM955065 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955066 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955067 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955073 2 0.0188 0.8552 0.000 0.996 0.004 0.000
#> GSM955074 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955076 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955078 2 0.4955 0.2751 0.000 0.556 0.000 0.444
#> GSM955083 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955084 4 0.0000 0.8447 0.000 0.000 0.000 1.000
#> GSM955086 2 0.3942 0.6457 0.000 0.764 0.236 0.000
#> GSM955091 2 0.2530 0.8267 0.000 0.888 0.000 0.112
#> GSM955092 2 0.2081 0.8353 0.000 0.916 0.000 0.084
#> GSM955093 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955098 2 0.0000 0.8545 0.000 1.000 0.000 0.000
#> GSM955099 2 0.3123 0.7958 0.000 0.844 0.000 0.156
#> GSM955100 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955103 2 0.3208 0.8056 0.000 0.848 0.004 0.148
#> GSM955104 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955106 4 0.5041 0.6361 0.000 0.040 0.232 0.728
#> GSM955000 3 0.0336 0.9342 0.008 0.000 0.992 0.000
#> GSM955006 1 0.0336 0.9930 0.992 0.000 0.008 0.000
#> GSM955007 3 0.3024 0.8080 0.000 0.000 0.852 0.148
#> GSM955010 3 0.3852 0.7271 0.000 0.192 0.800 0.008
#> GSM955014 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955018 3 0.2011 0.8773 0.000 0.080 0.920 0.000
#> GSM955020 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955024 2 0.3958 0.7873 0.000 0.816 0.024 0.160
#> GSM955026 2 0.1109 0.8498 0.000 0.968 0.028 0.004
#> GSM955031 2 0.0817 0.8503 0.000 0.976 0.024 0.000
#> GSM955038 3 0.0469 0.9326 0.000 0.012 0.988 0.000
#> GSM955040 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955044 4 0.3486 0.7129 0.000 0.188 0.000 0.812
#> GSM955051 1 0.0336 0.9930 0.992 0.000 0.008 0.000
#> GSM955055 2 0.4304 0.6805 0.000 0.716 0.000 0.284
#> GSM955057 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955062 2 0.2081 0.8395 0.000 0.916 0.000 0.084
#> GSM955063 2 0.0336 0.8551 0.000 0.992 0.008 0.000
#> GSM955068 2 0.7110 0.4651 0.000 0.564 0.200 0.236
#> GSM955069 3 0.0188 0.9376 0.000 0.000 0.996 0.004
#> GSM955070 2 0.0469 0.8554 0.000 0.988 0.000 0.012
#> GSM955071 3 0.1118 0.9157 0.000 0.036 0.964 0.000
#> GSM955077 3 0.0000 0.9374 0.000 0.000 1.000 0.000
#> GSM955080 4 0.0000 0.8447 0.000 0.000 0.000 1.000
#> GSM955081 2 0.0336 0.8548 0.000 0.992 0.008 0.000
#> GSM955082 2 0.1406 0.8512 0.000 0.960 0.024 0.016
#> GSM955085 2 0.2589 0.8173 0.000 0.884 0.000 0.116
#> GSM955090 1 0.0000 0.9984 1.000 0.000 0.000 0.000
#> GSM955094 2 0.3401 0.7611 0.000 0.840 0.152 0.008
#> GSM955096 2 0.2814 0.7701 0.000 0.868 0.132 0.000
#> GSM955102 3 0.0336 0.9375 0.000 0.000 0.992 0.008
#> GSM955105 2 0.0336 0.8550 0.000 0.992 0.008 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.3231 0.71764 0.000 0.004 0.800 0.196 0.000
#> GSM955008 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955016 1 0.4283 -0.31056 0.544 0.000 0.000 0.456 0.000
#> GSM955019 3 0.1544 0.81815 0.000 0.000 0.932 0.000 0.068
#> GSM955022 4 0.0162 0.81197 0.000 0.004 0.000 0.996 0.000
#> GSM955023 3 0.1831 0.81172 0.000 0.004 0.920 0.076 0.000
#> GSM955027 5 0.5546 0.11692 0.000 0.068 0.436 0.000 0.496
#> GSM955043 5 0.3334 0.62984 0.000 0.004 0.080 0.064 0.852
#> GSM955048 2 0.4278 -0.36582 0.452 0.548 0.000 0.000 0.000
#> GSM955049 3 0.0162 0.83842 0.000 0.000 0.996 0.004 0.000
#> GSM955054 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955064 3 0.3074 0.71940 0.000 0.000 0.804 0.000 0.196
#> GSM955072 2 0.6657 0.12673 0.000 0.424 0.340 0.000 0.236
#> GSM955075 5 0.0451 0.68405 0.000 0.004 0.000 0.008 0.988
#> GSM955079 4 0.2464 0.78532 0.000 0.000 0.016 0.888 0.096
#> GSM955087 1 0.4291 0.35423 0.536 0.464 0.000 0.000 0.000
#> GSM955088 3 0.3586 0.58602 0.000 0.000 0.736 0.264 0.000
#> GSM955089 1 0.1410 0.53439 0.940 0.060 0.000 0.000 0.000
#> GSM955095 2 0.6992 -0.38201 0.000 0.428 0.104 0.056 0.412
#> GSM955097 5 0.4235 0.48405 0.000 0.424 0.000 0.000 0.576
#> GSM955101 3 0.0404 0.83761 0.000 0.000 0.988 0.000 0.012
#> GSM954999 4 0.1197 0.81220 0.048 0.000 0.000 0.952 0.000
#> GSM955001 2 0.6657 0.12673 0.000 0.424 0.340 0.000 0.236
#> GSM955003 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955004 5 0.4235 0.48405 0.000 0.424 0.000 0.000 0.576
#> GSM955005 4 0.0000 0.81293 0.000 0.000 0.000 1.000 0.000
#> GSM955009 2 0.6657 0.12673 0.000 0.424 0.340 0.000 0.236
#> GSM955011 4 0.4287 0.43422 0.460 0.000 0.000 0.540 0.000
#> GSM955012 5 0.3366 0.57302 0.000 0.004 0.000 0.212 0.784
#> GSM955013 4 0.1124 0.79931 0.000 0.004 0.036 0.960 0.000
#> GSM955015 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955017 4 0.3561 0.70889 0.260 0.000 0.000 0.740 0.000
#> GSM955021 3 0.4732 0.61790 0.000 0.076 0.716 0.000 0.208
#> GSM955025 4 0.1753 0.80733 0.000 0.000 0.032 0.936 0.032
#> GSM955028 2 0.4242 -0.35250 0.428 0.572 0.000 0.000 0.000
#> GSM955029 5 0.0000 0.68240 0.000 0.000 0.000 0.000 1.000
#> GSM955030 4 0.0290 0.81459 0.008 0.000 0.000 0.992 0.000
#> GSM955032 4 0.4227 0.36088 0.000 0.000 0.420 0.580 0.000
#> GSM955033 4 0.2806 0.73701 0.152 0.004 0.000 0.844 0.000
#> GSM955034 2 0.4242 -0.35250 0.428 0.572 0.000 0.000 0.000
#> GSM955035 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955036 4 0.0955 0.80517 0.000 0.004 0.000 0.968 0.028
#> GSM955037 4 0.5348 0.63770 0.232 0.112 0.000 0.656 0.000
#> GSM955039 4 0.4161 0.33581 0.000 0.000 0.392 0.608 0.000
#> GSM955041 3 0.4294 0.03193 0.000 0.000 0.532 0.000 0.468
#> GSM955042 1 0.4278 -0.30291 0.548 0.000 0.000 0.452 0.000
#> GSM955045 2 0.8217 -0.00493 0.000 0.396 0.260 0.168 0.176
#> GSM955046 4 0.0000 0.81293 0.000 0.000 0.000 1.000 0.000
#> GSM955047 1 0.3305 0.53861 0.776 0.224 0.000 0.000 0.000
#> GSM955050 4 0.3750 0.72357 0.232 0.000 0.000 0.756 0.012
#> GSM955052 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955053 2 0.4256 -0.35881 0.436 0.564 0.000 0.000 0.000
#> GSM955056 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955058 5 0.0000 0.68240 0.000 0.000 0.000 0.000 1.000
#> GSM955059 4 0.0162 0.81197 0.000 0.004 0.000 0.996 0.000
#> GSM955060 1 0.3210 0.54183 0.788 0.212 0.000 0.000 0.000
#> GSM955061 5 0.0609 0.68220 0.000 0.000 0.000 0.020 0.980
#> GSM955065 1 0.4256 0.38106 0.564 0.436 0.000 0.000 0.000
#> GSM955066 4 0.0162 0.81399 0.004 0.000 0.000 0.996 0.000
#> GSM955067 1 0.4060 0.51084 0.640 0.360 0.000 0.000 0.000
#> GSM955073 3 0.0162 0.83859 0.000 0.000 0.996 0.004 0.000
#> GSM955074 4 0.3480 0.71762 0.248 0.000 0.000 0.752 0.000
#> GSM955076 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955078 3 0.5864 0.25593 0.000 0.056 0.528 0.020 0.396
#> GSM955083 4 0.1410 0.80577 0.060 0.000 0.000 0.940 0.000
#> GSM955084 5 0.4235 0.48405 0.000 0.424 0.000 0.000 0.576
#> GSM955086 3 0.3366 0.63512 0.000 0.000 0.768 0.232 0.000
#> GSM955091 3 0.2230 0.79612 0.000 0.000 0.884 0.000 0.116
#> GSM955092 3 0.5068 0.31848 0.000 0.364 0.592 0.000 0.044
#> GSM955093 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955098 3 0.0000 0.83814 0.000 0.000 1.000 0.000 0.000
#> GSM955099 3 0.2773 0.74998 0.000 0.000 0.836 0.000 0.164
#> GSM955100 1 0.4283 -0.30919 0.544 0.000 0.000 0.456 0.000
#> GSM955103 3 0.3781 0.76608 0.000 0.016 0.828 0.048 0.108
#> GSM955104 4 0.0162 0.81410 0.004 0.000 0.000 0.996 0.000
#> GSM955106 5 0.3585 0.56463 0.000 0.004 0.004 0.220 0.772
#> GSM955000 4 0.3039 0.75744 0.192 0.000 0.000 0.808 0.000
#> GSM955006 1 0.0000 0.51296 1.000 0.000 0.000 0.000 0.000
#> GSM955007 4 0.4847 0.49685 0.000 0.240 0.000 0.692 0.068
#> GSM955010 4 0.3167 0.68970 0.004 0.004 0.172 0.820 0.000
#> GSM955014 1 0.4060 0.51084 0.640 0.360 0.000 0.000 0.000
#> GSM955018 4 0.2127 0.77568 0.000 0.000 0.108 0.892 0.000
#> GSM955020 2 0.4278 -0.36582 0.452 0.548 0.000 0.000 0.000
#> GSM955024 3 0.4349 0.73286 0.000 0.012 0.788 0.088 0.112
#> GSM955026 3 0.0992 0.83380 0.000 0.000 0.968 0.024 0.008
#> GSM955031 3 0.0703 0.83353 0.000 0.000 0.976 0.024 0.000
#> GSM955038 4 0.2414 0.80725 0.080 0.000 0.012 0.900 0.008
#> GSM955040 4 0.4341 0.48708 0.364 0.000 0.008 0.628 0.000
#> GSM955044 5 0.2818 0.59994 0.000 0.000 0.132 0.012 0.856
#> GSM955051 1 0.2690 0.52671 0.844 0.156 0.000 0.000 0.000
#> GSM955055 2 0.6657 0.12673 0.000 0.424 0.340 0.000 0.236
#> GSM955057 1 0.4060 0.51084 0.640 0.360 0.000 0.000 0.000
#> GSM955062 3 0.3442 0.75282 0.000 0.104 0.836 0.000 0.060
#> GSM955063 3 0.0290 0.83840 0.000 0.000 0.992 0.008 0.000
#> GSM955068 3 0.8028 -0.03956 0.000 0.288 0.400 0.112 0.200
#> GSM955069 4 0.3300 0.74639 0.204 0.004 0.000 0.792 0.000
#> GSM955070 3 0.0451 0.83837 0.000 0.000 0.988 0.004 0.008
#> GSM955071 4 0.4489 0.49036 0.420 0.000 0.008 0.572 0.000
#> GSM955077 4 0.1845 0.81046 0.056 0.000 0.016 0.928 0.000
#> GSM955080 5 0.4630 0.50392 0.000 0.396 0.000 0.016 0.588
#> GSM955081 3 0.0290 0.83774 0.000 0.000 0.992 0.008 0.000
#> GSM955082 3 0.2295 0.80607 0.000 0.004 0.900 0.088 0.008
#> GSM955085 3 0.5309 0.28592 0.000 0.364 0.576 0.000 0.060
#> GSM955090 1 0.4060 0.51084 0.640 0.360 0.000 0.000 0.000
#> GSM955094 3 0.3196 0.72231 0.000 0.004 0.804 0.192 0.000
#> GSM955096 3 0.2329 0.76111 0.000 0.000 0.876 0.124 0.000
#> GSM955102 4 0.0510 0.81506 0.016 0.000 0.000 0.984 0.000
#> GSM955105 3 0.0609 0.83689 0.000 0.000 0.980 0.020 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.3655 0.7614 0.000 0.792 0.096 0.000 0.112 0.000
#> GSM955008 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955016 1 0.1753 0.5748 0.912 0.000 0.084 0.000 0.004 0.000
#> GSM955019 2 0.1387 0.8325 0.000 0.932 0.000 0.068 0.000 0.000
#> GSM955022 3 0.2562 0.7590 0.000 0.000 0.828 0.000 0.172 0.000
#> GSM955023 2 0.2912 0.7690 0.000 0.816 0.012 0.000 0.172 0.000
#> GSM955027 2 0.5832 -0.1131 0.000 0.428 0.000 0.188 0.384 0.000
#> GSM955043 5 0.2009 0.8271 0.000 0.040 0.004 0.040 0.916 0.000
#> GSM955048 6 0.1845 0.7576 0.072 0.000 0.000 0.004 0.008 0.916
#> GSM955049 2 0.0146 0.8536 0.000 0.996 0.004 0.000 0.000 0.000
#> GSM955054 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955064 2 0.2762 0.7354 0.000 0.804 0.000 0.196 0.000 0.000
#> GSM955072 4 0.3076 0.6044 0.000 0.240 0.000 0.760 0.000 0.000
#> GSM955075 5 0.2871 0.8459 0.000 0.000 0.004 0.192 0.804 0.000
#> GSM955079 3 0.1812 0.7804 0.000 0.008 0.912 0.080 0.000 0.000
#> GSM955087 6 0.1910 0.7186 0.108 0.000 0.000 0.000 0.000 0.892
#> GSM955088 2 0.3371 0.5914 0.000 0.708 0.292 0.000 0.000 0.000
#> GSM955089 1 0.2051 0.5790 0.896 0.000 0.000 0.004 0.004 0.096
#> GSM955095 4 0.2631 0.7127 0.000 0.012 0.004 0.856 0.128 0.000
#> GSM955097 4 0.0458 0.7777 0.000 0.000 0.000 0.984 0.016 0.000
#> GSM955101 2 0.0363 0.8527 0.000 0.988 0.000 0.012 0.000 0.000
#> GSM954999 3 0.0146 0.7971 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM955001 4 0.0458 0.7892 0.000 0.016 0.000 0.984 0.000 0.000
#> GSM955003 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955004 4 0.0146 0.7803 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM955005 3 0.0000 0.7980 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955009 4 0.0458 0.7892 0.000 0.016 0.000 0.984 0.000 0.000
#> GSM955011 1 0.3881 0.0282 0.600 0.000 0.396 0.000 0.004 0.000
#> GSM955012 5 0.0458 0.8020 0.000 0.000 0.016 0.000 0.984 0.000
#> GSM955013 3 0.3210 0.7560 0.000 0.036 0.812 0.000 0.152 0.000
#> GSM955015 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955017 3 0.3756 0.5646 0.352 0.000 0.644 0.000 0.004 0.000
#> GSM955021 2 0.3464 0.5739 0.000 0.688 0.000 0.312 0.000 0.000
#> GSM955025 3 0.0405 0.7978 0.000 0.004 0.988 0.008 0.000 0.000
#> GSM955028 6 0.0000 0.7965 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955029 5 0.2697 0.8460 0.000 0.000 0.000 0.188 0.812 0.000
#> GSM955030 3 0.0000 0.7980 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955032 3 0.3797 0.3667 0.000 0.420 0.580 0.000 0.000 0.000
#> GSM955033 3 0.4300 0.5975 0.208 0.000 0.712 0.000 0.080 0.000
#> GSM955034 6 0.0000 0.7965 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955035 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955036 3 0.2697 0.7543 0.000 0.000 0.812 0.000 0.188 0.000
#> GSM955037 6 0.6108 0.1259 0.292 0.000 0.264 0.000 0.004 0.440
#> GSM955039 3 0.5312 0.3335 0.000 0.364 0.524 0.000 0.112 0.000
#> GSM955041 2 0.3866 0.0236 0.000 0.516 0.000 0.000 0.484 0.000
#> GSM955042 1 0.1444 0.5810 0.928 0.000 0.072 0.000 0.000 0.000
#> GSM955045 4 0.3590 0.7087 0.000 0.076 0.004 0.804 0.116 0.000
#> GSM955046 3 0.0000 0.7980 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955047 1 0.3767 0.4943 0.708 0.000 0.000 0.004 0.012 0.276
#> GSM955050 3 0.3646 0.6355 0.292 0.000 0.700 0.004 0.004 0.000
#> GSM955052 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955053 6 0.0260 0.7959 0.008 0.000 0.000 0.000 0.000 0.992
#> GSM955056 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955058 5 0.2697 0.8460 0.000 0.000 0.000 0.188 0.812 0.000
#> GSM955059 3 0.2454 0.7646 0.000 0.000 0.840 0.000 0.160 0.000
#> GSM955060 1 0.3702 0.5072 0.720 0.000 0.000 0.004 0.012 0.264
#> GSM955061 5 0.2340 0.8603 0.000 0.000 0.000 0.148 0.852 0.000
#> GSM955065 6 0.2340 0.6716 0.148 0.000 0.000 0.000 0.000 0.852
#> GSM955066 3 0.0000 0.7980 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955067 1 0.4268 0.3852 0.556 0.000 0.000 0.004 0.012 0.428
#> GSM955073 2 0.0291 0.8542 0.000 0.992 0.004 0.000 0.004 0.000
#> GSM955074 3 0.3565 0.6249 0.304 0.000 0.692 0.000 0.004 0.000
#> GSM955076 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955078 2 0.5547 0.2130 0.000 0.508 0.000 0.148 0.344 0.000
#> GSM955083 3 0.2301 0.7514 0.096 0.000 0.884 0.000 0.020 0.000
#> GSM955084 4 0.0146 0.7803 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM955086 2 0.3076 0.6589 0.000 0.760 0.240 0.000 0.000 0.000
#> GSM955091 2 0.2301 0.8115 0.000 0.884 0.000 0.096 0.020 0.000
#> GSM955092 4 0.3371 0.5994 0.000 0.292 0.000 0.708 0.000 0.000
#> GSM955093 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955098 2 0.0000 0.8535 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955099 2 0.2491 0.7661 0.000 0.836 0.000 0.164 0.000 0.000
#> GSM955100 1 0.1501 0.5816 0.924 0.000 0.076 0.000 0.000 0.000
#> GSM955103 2 0.3673 0.7728 0.000 0.804 0.008 0.088 0.100 0.000
#> GSM955104 3 0.0000 0.7980 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955106 5 0.0458 0.8020 0.000 0.000 0.016 0.000 0.984 0.000
#> GSM955000 3 0.2994 0.7116 0.208 0.000 0.788 0.000 0.004 0.000
#> GSM955006 1 0.0146 0.5804 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM955007 3 0.5759 0.1352 0.000 0.000 0.436 0.392 0.172 0.000
#> GSM955010 3 0.4074 0.6739 0.000 0.160 0.748 0.000 0.092 0.000
#> GSM955014 1 0.4184 0.3808 0.556 0.000 0.000 0.004 0.008 0.432
#> GSM955018 3 0.1501 0.7791 0.000 0.076 0.924 0.000 0.000 0.000
#> GSM955020 6 0.1788 0.7561 0.076 0.000 0.000 0.004 0.004 0.916
#> GSM955024 2 0.3893 0.7416 0.000 0.772 0.016 0.040 0.172 0.000
#> GSM955026 2 0.0858 0.8480 0.000 0.968 0.028 0.004 0.000 0.000
#> GSM955031 2 0.0632 0.8490 0.000 0.976 0.024 0.000 0.000 0.000
#> GSM955038 3 0.1946 0.7878 0.072 0.012 0.912 0.000 0.004 0.000
#> GSM955040 1 0.3782 0.4426 0.636 0.000 0.360 0.000 0.004 0.000
#> GSM955044 5 0.4232 0.7580 0.000 0.100 0.000 0.168 0.732 0.000
#> GSM955051 1 0.2915 0.5270 0.808 0.000 0.000 0.000 0.008 0.184
#> GSM955055 4 0.0458 0.7892 0.000 0.016 0.000 0.984 0.000 0.000
#> GSM955057 1 0.4098 0.3635 0.548 0.000 0.000 0.004 0.004 0.444
#> GSM955062 2 0.3023 0.6652 0.000 0.768 0.000 0.232 0.000 0.000
#> GSM955063 2 0.0260 0.8537 0.000 0.992 0.008 0.000 0.000 0.000
#> GSM955068 4 0.4402 0.5274 0.000 0.268 0.060 0.672 0.000 0.000
#> GSM955069 3 0.4065 0.6899 0.220 0.000 0.724 0.000 0.056 0.000
#> GSM955070 2 0.0405 0.8536 0.000 0.988 0.000 0.008 0.004 0.000
#> GSM955071 1 0.4082 -0.0455 0.560 0.004 0.432 0.000 0.004 0.000
#> GSM955077 3 0.1910 0.7348 0.108 0.000 0.892 0.000 0.000 0.000
#> GSM955080 4 0.2003 0.7169 0.000 0.000 0.000 0.884 0.116 0.000
#> GSM955081 2 0.0260 0.8531 0.000 0.992 0.008 0.000 0.000 0.000
#> GSM955082 2 0.3168 0.7636 0.000 0.804 0.024 0.000 0.172 0.000
#> GSM955085 4 0.3620 0.5379 0.000 0.352 0.000 0.648 0.000 0.000
#> GSM955090 1 0.4268 0.3852 0.556 0.000 0.000 0.004 0.012 0.428
#> GSM955094 2 0.3927 0.7235 0.000 0.756 0.072 0.000 0.172 0.000
#> GSM955096 2 0.2178 0.7772 0.000 0.868 0.132 0.000 0.000 0.000
#> GSM955102 3 0.0000 0.7980 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955105 2 0.0972 0.8490 0.000 0.964 0.008 0.000 0.028 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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> SD:pam 106 0.406 2
#> SD:pam 104 0.535 3
#> SD:pam 100 0.558 4
#> SD:pam 77 0.317 5
#> SD:pam 93 0.829 6
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 31589 rows and 108 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 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 0.995 0.998 0.3468 0.651 0.651
#> 3 3 0.556 0.746 0.812 0.6445 0.745 0.608
#> 4 4 0.604 0.768 0.845 0.1866 0.824 0.603
#> 5 5 0.603 0.744 0.822 0.0820 0.842 0.568
#> 6 6 0.577 0.582 0.771 0.0504 0.915 0.697
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
#> GSM955002 2 0.000 1.000 0.000 1.000
#> GSM955008 2 0.000 1.000 0.000 1.000
#> GSM955016 1 0.494 0.886 0.892 0.108
#> GSM955019 2 0.000 1.000 0.000 1.000
#> GSM955022 2 0.000 1.000 0.000 1.000
#> GSM955023 2 0.000 1.000 0.000 1.000
#> GSM955027 2 0.000 1.000 0.000 1.000
#> GSM955043 2 0.000 1.000 0.000 1.000
#> GSM955048 1 0.000 0.989 1.000 0.000
#> GSM955049 2 0.000 1.000 0.000 1.000
#> GSM955054 2 0.000 1.000 0.000 1.000
#> GSM955064 2 0.000 1.000 0.000 1.000
#> GSM955072 2 0.000 1.000 0.000 1.000
#> GSM955075 2 0.000 1.000 0.000 1.000
#> GSM955079 2 0.000 1.000 0.000 1.000
#> GSM955087 1 0.000 0.989 1.000 0.000
#> GSM955088 2 0.000 1.000 0.000 1.000
#> GSM955089 1 0.000 0.989 1.000 0.000
#> GSM955095 2 0.000 1.000 0.000 1.000
#> GSM955097 2 0.000 1.000 0.000 1.000
#> GSM955101 2 0.000 1.000 0.000 1.000
#> GSM954999 2 0.000 1.000 0.000 1.000
#> GSM955001 2 0.000 1.000 0.000 1.000
#> GSM955003 2 0.000 1.000 0.000 1.000
#> GSM955004 2 0.000 1.000 0.000 1.000
#> GSM955005 2 0.000 1.000 0.000 1.000
#> GSM955009 2 0.000 1.000 0.000 1.000
#> GSM955011 1 0.000 0.989 1.000 0.000
#> GSM955012 2 0.000 1.000 0.000 1.000
#> GSM955013 2 0.000 1.000 0.000 1.000
#> GSM955015 2 0.000 1.000 0.000 1.000
#> GSM955017 1 0.000 0.989 1.000 0.000
#> GSM955021 2 0.000 1.000 0.000 1.000
#> GSM955025 2 0.000 1.000 0.000 1.000
#> GSM955028 1 0.000 0.989 1.000 0.000
#> GSM955029 2 0.000 1.000 0.000 1.000
#> GSM955030 2 0.000 1.000 0.000 1.000
#> GSM955032 2 0.000 1.000 0.000 1.000
#> GSM955033 2 0.000 1.000 0.000 1.000
#> GSM955034 1 0.000 0.989 1.000 0.000
#> GSM955035 2 0.000 1.000 0.000 1.000
#> GSM955036 2 0.000 1.000 0.000 1.000
#> GSM955037 1 0.000 0.989 1.000 0.000
#> GSM955039 2 0.000 1.000 0.000 1.000
#> GSM955041 2 0.000 1.000 0.000 1.000
#> GSM955042 1 0.506 0.881 0.888 0.112
#> GSM955045 2 0.000 1.000 0.000 1.000
#> GSM955046 2 0.000 1.000 0.000 1.000
#> GSM955047 1 0.000 0.989 1.000 0.000
#> GSM955050 2 0.000 1.000 0.000 1.000
#> GSM955052 2 0.000 1.000 0.000 1.000
#> GSM955053 1 0.000 0.989 1.000 0.000
#> GSM955056 2 0.000 1.000 0.000 1.000
#> GSM955058 2 0.000 1.000 0.000 1.000
#> GSM955059 2 0.000 1.000 0.000 1.000
#> GSM955060 1 0.000 0.989 1.000 0.000
#> GSM955061 2 0.000 1.000 0.000 1.000
#> GSM955065 1 0.000 0.989 1.000 0.000
#> GSM955066 2 0.000 1.000 0.000 1.000
#> GSM955067 1 0.000 0.989 1.000 0.000
#> GSM955073 2 0.000 1.000 0.000 1.000
#> GSM955074 1 0.000 0.989 1.000 0.000
#> GSM955076 2 0.000 1.000 0.000 1.000
#> GSM955078 2 0.000 1.000 0.000 1.000
#> GSM955083 2 0.000 1.000 0.000 1.000
#> GSM955084 2 0.000 1.000 0.000 1.000
#> GSM955086 2 0.000 1.000 0.000 1.000
#> GSM955091 2 0.000 1.000 0.000 1.000
#> GSM955092 2 0.000 1.000 0.000 1.000
#> GSM955093 2 0.000 1.000 0.000 1.000
#> GSM955098 2 0.000 1.000 0.000 1.000
#> GSM955099 2 0.000 1.000 0.000 1.000
#> GSM955100 1 0.242 0.956 0.960 0.040
#> GSM955103 2 0.000 1.000 0.000 1.000
#> GSM955104 2 0.000 1.000 0.000 1.000
#> GSM955106 2 0.000 1.000 0.000 1.000
#> GSM955000 1 0.000 0.989 1.000 0.000
#> GSM955006 1 0.000 0.989 1.000 0.000
#> GSM955007 2 0.000 1.000 0.000 1.000
#> GSM955010 2 0.000 1.000 0.000 1.000
#> GSM955014 1 0.000 0.989 1.000 0.000
#> GSM955018 2 0.000 1.000 0.000 1.000
#> GSM955020 1 0.000 0.989 1.000 0.000
#> GSM955024 2 0.000 1.000 0.000 1.000
#> GSM955026 2 0.000 1.000 0.000 1.000
#> GSM955031 2 0.000 1.000 0.000 1.000
#> GSM955038 2 0.000 1.000 0.000 1.000
#> GSM955040 2 0.000 1.000 0.000 1.000
#> GSM955044 2 0.000 1.000 0.000 1.000
#> GSM955051 1 0.000 0.989 1.000 0.000
#> GSM955055 2 0.000 1.000 0.000 1.000
#> GSM955057 1 0.000 0.989 1.000 0.000
#> GSM955062 2 0.000 1.000 0.000 1.000
#> GSM955063 2 0.000 1.000 0.000 1.000
#> GSM955068 2 0.000 1.000 0.000 1.000
#> GSM955069 2 0.000 1.000 0.000 1.000
#> GSM955070 2 0.000 1.000 0.000 1.000
#> GSM955071 2 0.000 1.000 0.000 1.000
#> GSM955077 2 0.000 1.000 0.000 1.000
#> GSM955080 2 0.000 1.000 0.000 1.000
#> GSM955081 2 0.000 1.000 0.000 1.000
#> GSM955082 2 0.000 1.000 0.000 1.000
#> GSM955085 2 0.000 1.000 0.000 1.000
#> GSM955090 1 0.000 0.989 1.000 0.000
#> GSM955094 2 0.000 1.000 0.000 1.000
#> GSM955096 2 0.000 1.000 0.000 1.000
#> GSM955102 2 0.000 1.000 0.000 1.000
#> GSM955105 2 0.000 1.000 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.3686 0.720 0.000 0.860 0.140
#> GSM955008 3 0.6309 0.472 0.000 0.496 0.504
#> GSM955016 1 0.3237 0.923 0.912 0.032 0.056
#> GSM955019 2 0.1643 0.764 0.000 0.956 0.044
#> GSM955022 2 0.6307 -0.432 0.000 0.512 0.488
#> GSM955023 2 0.5178 0.547 0.000 0.744 0.256
#> GSM955027 2 0.0237 0.771 0.000 0.996 0.004
#> GSM955043 2 0.0424 0.771 0.000 0.992 0.008
#> GSM955048 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955049 2 0.3686 0.754 0.000 0.860 0.140
#> GSM955054 2 0.4931 0.593 0.000 0.768 0.232
#> GSM955064 2 0.2878 0.749 0.000 0.904 0.096
#> GSM955072 2 0.0747 0.768 0.000 0.984 0.016
#> GSM955075 2 0.4654 0.584 0.000 0.792 0.208
#> GSM955079 3 0.5706 0.891 0.000 0.320 0.680
#> GSM955087 1 0.0237 0.981 0.996 0.000 0.004
#> GSM955088 3 0.5363 0.920 0.000 0.276 0.724
#> GSM955089 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955095 2 0.3116 0.743 0.000 0.892 0.108
#> GSM955097 2 0.3038 0.747 0.000 0.896 0.104
#> GSM955101 3 0.6252 0.651 0.000 0.444 0.556
#> GSM954999 2 0.6302 -0.282 0.000 0.520 0.480
#> GSM955001 2 0.2165 0.763 0.000 0.936 0.064
#> GSM955003 2 0.5216 0.539 0.000 0.740 0.260
#> GSM955004 2 0.0747 0.768 0.000 0.984 0.016
#> GSM955005 3 0.5254 0.917 0.000 0.264 0.736
#> GSM955009 2 0.0592 0.769 0.000 0.988 0.012
#> GSM955011 1 0.1964 0.952 0.944 0.000 0.056
#> GSM955012 2 0.5016 0.606 0.000 0.760 0.240
#> GSM955013 2 0.6079 0.179 0.000 0.612 0.388
#> GSM955015 2 0.4931 0.619 0.000 0.768 0.232
#> GSM955017 1 0.0237 0.981 0.996 0.000 0.004
#> GSM955021 2 0.2261 0.763 0.000 0.932 0.068
#> GSM955025 2 0.0747 0.770 0.000 0.984 0.016
#> GSM955028 1 0.0237 0.981 0.996 0.000 0.004
#> GSM955029 2 0.4605 0.582 0.000 0.796 0.204
#> GSM955030 3 0.5216 0.916 0.000 0.260 0.740
#> GSM955032 3 0.5733 0.901 0.000 0.324 0.676
#> GSM955033 2 0.4121 0.709 0.000 0.832 0.168
#> GSM955034 1 0.0237 0.981 0.996 0.000 0.004
#> GSM955035 2 0.2796 0.765 0.000 0.908 0.092
#> GSM955036 3 0.5216 0.916 0.000 0.260 0.740
#> GSM955037 1 0.1964 0.957 0.944 0.000 0.056
#> GSM955039 2 0.6291 -0.348 0.000 0.532 0.468
#> GSM955041 2 0.4504 0.650 0.000 0.804 0.196
#> GSM955042 1 0.3356 0.919 0.908 0.036 0.056
#> GSM955045 2 0.3116 0.741 0.000 0.892 0.108
#> GSM955046 3 0.5678 0.906 0.000 0.316 0.684
#> GSM955047 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955050 2 0.4702 0.662 0.000 0.788 0.212
#> GSM955052 3 0.5706 0.904 0.000 0.320 0.680
#> GSM955053 1 0.0237 0.981 0.996 0.000 0.004
#> GSM955056 2 0.6280 -0.310 0.000 0.540 0.460
#> GSM955058 2 0.4654 0.584 0.000 0.792 0.208
#> GSM955059 3 0.5254 0.918 0.000 0.264 0.736
#> GSM955060 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955061 2 0.4654 0.584 0.000 0.792 0.208
#> GSM955065 1 0.0237 0.981 0.996 0.000 0.004
#> GSM955066 3 0.5216 0.916 0.000 0.260 0.740
#> GSM955067 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955073 3 0.5678 0.906 0.000 0.316 0.684
#> GSM955074 1 0.1964 0.952 0.944 0.000 0.056
#> GSM955076 2 0.1031 0.774 0.000 0.976 0.024
#> GSM955078 2 0.0747 0.768 0.000 0.984 0.016
#> GSM955083 2 0.5397 0.547 0.000 0.720 0.280
#> GSM955084 2 0.0747 0.768 0.000 0.984 0.016
#> GSM955086 3 0.5497 0.911 0.000 0.292 0.708
#> GSM955091 2 0.1643 0.753 0.000 0.956 0.044
#> GSM955092 2 0.4062 0.735 0.000 0.836 0.164
#> GSM955093 3 0.5678 0.906 0.000 0.316 0.684
#> GSM955098 2 0.0747 0.768 0.000 0.984 0.016
#> GSM955099 2 0.1643 0.753 0.000 0.956 0.044
#> GSM955100 1 0.3406 0.916 0.904 0.028 0.068
#> GSM955103 2 0.5327 0.511 0.000 0.728 0.272
#> GSM955104 3 0.5216 0.916 0.000 0.260 0.740
#> GSM955106 2 0.1163 0.772 0.000 0.972 0.028
#> GSM955000 1 0.0237 0.981 0.996 0.000 0.004
#> GSM955006 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955007 3 0.5810 0.888 0.000 0.336 0.664
#> GSM955010 3 0.5216 0.916 0.000 0.260 0.740
#> GSM955014 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955018 3 0.5529 0.916 0.000 0.296 0.704
#> GSM955020 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955024 2 0.5058 0.571 0.000 0.756 0.244
#> GSM955026 2 0.0592 0.769 0.000 0.988 0.012
#> GSM955031 2 0.6309 -0.362 0.000 0.504 0.496
#> GSM955038 2 0.2066 0.745 0.000 0.940 0.060
#> GSM955040 2 0.5810 0.399 0.000 0.664 0.336
#> GSM955044 2 0.0747 0.768 0.000 0.984 0.016
#> GSM955051 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955055 2 0.2066 0.762 0.000 0.940 0.060
#> GSM955057 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955062 2 0.4062 0.739 0.000 0.836 0.164
#> GSM955063 3 0.5678 0.906 0.000 0.316 0.684
#> GSM955068 2 0.0747 0.768 0.000 0.984 0.016
#> GSM955069 3 0.5216 0.916 0.000 0.260 0.740
#> GSM955070 2 0.2165 0.766 0.000 0.936 0.064
#> GSM955071 3 0.5591 0.896 0.000 0.304 0.696
#> GSM955077 2 0.3412 0.740 0.000 0.876 0.124
#> GSM955080 2 0.1529 0.770 0.000 0.960 0.040
#> GSM955081 2 0.5363 0.501 0.000 0.724 0.276
#> GSM955082 2 0.5465 0.479 0.000 0.712 0.288
#> GSM955085 2 0.1753 0.765 0.000 0.952 0.048
#> GSM955090 1 0.0000 0.982 1.000 0.000 0.000
#> GSM955094 2 0.1753 0.771 0.000 0.952 0.048
#> GSM955096 3 0.5810 0.888 0.000 0.336 0.664
#> GSM955102 3 0.5216 0.916 0.000 0.260 0.740
#> GSM955105 3 0.5291 0.917 0.000 0.268 0.732
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.6327 0.664 0.000 0.648 0.228 0.124
#> GSM955008 3 0.3390 0.818 0.000 0.132 0.852 0.016
#> GSM955016 1 0.1677 0.946 0.948 0.000 0.040 0.012
#> GSM955019 2 0.3978 0.705 0.000 0.836 0.056 0.108
#> GSM955022 3 0.2412 0.854 0.000 0.084 0.908 0.008
#> GSM955023 3 0.5990 0.508 0.000 0.284 0.644 0.072
#> GSM955027 2 0.2699 0.738 0.000 0.904 0.068 0.028
#> GSM955043 2 0.5241 0.637 0.008 0.760 0.068 0.164
#> GSM955048 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955049 2 0.6418 0.634 0.000 0.644 0.216 0.140
#> GSM955054 2 0.5823 0.514 0.000 0.608 0.348 0.044
#> GSM955064 2 0.6797 0.438 0.000 0.536 0.356 0.108
#> GSM955072 2 0.1953 0.728 0.012 0.940 0.044 0.004
#> GSM955075 4 0.4319 0.963 0.000 0.228 0.012 0.760
#> GSM955079 3 0.1557 0.859 0.000 0.056 0.944 0.000
#> GSM955087 1 0.1211 0.965 0.960 0.000 0.000 0.040
#> GSM955088 3 0.1004 0.854 0.000 0.024 0.972 0.004
#> GSM955089 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955095 2 0.6486 0.546 0.012 0.612 0.308 0.068
#> GSM955097 2 0.7348 0.379 0.036 0.600 0.112 0.252
#> GSM955101 3 0.2466 0.845 0.000 0.096 0.900 0.004
#> GSM954999 3 0.5624 0.610 0.032 0.244 0.704 0.020
#> GSM955001 2 0.4017 0.680 0.000 0.828 0.044 0.128
#> GSM955003 2 0.5487 0.388 0.000 0.580 0.400 0.020
#> GSM955004 2 0.4412 0.615 0.016 0.820 0.036 0.128
#> GSM955005 3 0.0779 0.854 0.000 0.016 0.980 0.004
#> GSM955009 2 0.1953 0.728 0.012 0.940 0.044 0.004
#> GSM955011 1 0.1256 0.958 0.964 0.000 0.028 0.008
#> GSM955012 4 0.4059 0.977 0.000 0.200 0.012 0.788
#> GSM955013 3 0.4658 0.708 0.012 0.216 0.760 0.012
#> GSM955015 2 0.7003 0.246 0.000 0.460 0.424 0.116
#> GSM955017 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955021 2 0.4022 0.735 0.000 0.836 0.096 0.068
#> GSM955025 2 0.2125 0.727 0.012 0.932 0.052 0.004
#> GSM955028 1 0.1211 0.965 0.960 0.000 0.000 0.040
#> GSM955029 4 0.4175 0.982 0.000 0.212 0.012 0.776
#> GSM955030 3 0.0592 0.844 0.000 0.000 0.984 0.016
#> GSM955032 3 0.1902 0.856 0.000 0.064 0.932 0.004
#> GSM955033 2 0.5531 0.671 0.012 0.716 0.228 0.044
#> GSM955034 1 0.1211 0.965 0.960 0.000 0.000 0.040
#> GSM955035 2 0.5483 0.684 0.000 0.736 0.128 0.136
#> GSM955036 3 0.4739 0.753 0.032 0.136 0.804 0.028
#> GSM955037 1 0.2759 0.926 0.904 0.000 0.052 0.044
#> GSM955039 3 0.3708 0.806 0.000 0.148 0.832 0.020
#> GSM955041 3 0.6637 0.305 0.000 0.368 0.540 0.092
#> GSM955042 1 0.1677 0.946 0.948 0.000 0.040 0.012
#> GSM955045 2 0.6374 0.385 0.000 0.556 0.372 0.072
#> GSM955046 3 0.1509 0.853 0.008 0.020 0.960 0.012
#> GSM955047 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955050 2 0.4001 0.719 0.036 0.840 0.116 0.008
#> GSM955052 3 0.1807 0.858 0.000 0.052 0.940 0.008
#> GSM955053 1 0.1211 0.965 0.960 0.000 0.000 0.040
#> GSM955056 3 0.3863 0.796 0.000 0.144 0.828 0.028
#> GSM955058 4 0.4137 0.983 0.000 0.208 0.012 0.780
#> GSM955059 3 0.0937 0.850 0.000 0.012 0.976 0.012
#> GSM955060 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955061 4 0.4059 0.979 0.000 0.200 0.012 0.788
#> GSM955065 1 0.1211 0.965 0.960 0.000 0.000 0.040
#> GSM955066 3 0.0592 0.844 0.000 0.000 0.984 0.016
#> GSM955067 1 0.0188 0.976 0.996 0.000 0.000 0.004
#> GSM955073 3 0.1388 0.854 0.000 0.028 0.960 0.012
#> GSM955074 1 0.1284 0.960 0.964 0.000 0.024 0.012
#> GSM955076 2 0.2271 0.730 0.012 0.928 0.052 0.008
#> GSM955078 2 0.2262 0.719 0.012 0.932 0.040 0.016
#> GSM955083 2 0.7176 0.374 0.032 0.516 0.388 0.064
#> GSM955084 2 0.3396 0.677 0.016 0.884 0.036 0.064
#> GSM955086 3 0.1890 0.859 0.000 0.056 0.936 0.008
#> GSM955091 2 0.3749 0.670 0.000 0.840 0.032 0.128
#> GSM955092 2 0.6951 0.535 0.000 0.556 0.304 0.140
#> GSM955093 3 0.1284 0.853 0.000 0.024 0.964 0.012
#> GSM955098 2 0.2075 0.727 0.016 0.936 0.044 0.004
#> GSM955099 2 0.3653 0.668 0.000 0.844 0.028 0.128
#> GSM955100 1 0.1722 0.941 0.944 0.000 0.048 0.008
#> GSM955103 3 0.5490 0.640 0.004 0.268 0.688 0.040
#> GSM955104 3 0.1262 0.845 0.008 0.008 0.968 0.016
#> GSM955106 2 0.6058 0.517 0.004 0.672 0.084 0.240
#> GSM955000 1 0.0336 0.975 0.992 0.000 0.000 0.008
#> GSM955006 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955007 3 0.1489 0.857 0.000 0.044 0.952 0.004
#> GSM955010 3 0.1394 0.843 0.012 0.008 0.964 0.016
#> GSM955014 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955018 3 0.1284 0.853 0.000 0.024 0.964 0.012
#> GSM955020 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955024 3 0.5773 0.519 0.000 0.320 0.632 0.048
#> GSM955026 2 0.1985 0.727 0.016 0.940 0.040 0.004
#> GSM955031 2 0.4957 0.688 0.040 0.764 0.188 0.008
#> GSM955038 2 0.3130 0.709 0.024 0.892 0.072 0.012
#> GSM955040 2 0.5391 0.665 0.040 0.716 0.236 0.008
#> GSM955044 2 0.3385 0.725 0.012 0.884 0.056 0.048
#> GSM955051 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955055 2 0.4259 0.690 0.000 0.816 0.056 0.128
#> GSM955057 1 0.0000 0.977 1.000 0.000 0.000 0.000
#> GSM955062 2 0.6893 0.524 0.000 0.564 0.300 0.136
#> GSM955063 3 0.1284 0.853 0.000 0.024 0.964 0.012
#> GSM955068 2 0.1985 0.727 0.016 0.940 0.040 0.004
#> GSM955069 3 0.0592 0.843 0.000 0.000 0.984 0.016
#> GSM955070 2 0.5042 0.687 0.000 0.768 0.096 0.136
#> GSM955071 3 0.4082 0.771 0.020 0.152 0.820 0.008
#> GSM955077 2 0.3315 0.731 0.016 0.872 0.104 0.008
#> GSM955080 2 0.5716 0.576 0.000 0.700 0.088 0.212
#> GSM955081 3 0.5028 0.320 0.000 0.400 0.596 0.004
#> GSM955082 3 0.4360 0.693 0.000 0.248 0.744 0.008
#> GSM955085 2 0.3842 0.679 0.000 0.836 0.036 0.128
#> GSM955090 1 0.0188 0.976 0.996 0.000 0.000 0.004
#> GSM955094 2 0.3080 0.740 0.000 0.880 0.096 0.024
#> GSM955096 3 0.2412 0.848 0.000 0.084 0.908 0.008
#> GSM955102 3 0.1724 0.828 0.032 0.000 0.948 0.020
#> GSM955105 3 0.1388 0.857 0.000 0.028 0.960 0.012
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.4676 0.3072 0.000 0.592 0.392 0.012 0.004
#> GSM955008 3 0.4455 0.7386 0.000 0.128 0.788 0.044 0.040
#> GSM955016 1 0.3671 0.8962 0.856 0.024 0.012 0.056 0.052
#> GSM955019 2 0.2535 0.7649 0.000 0.892 0.032 0.076 0.000
#> GSM955022 3 0.2915 0.7874 0.004 0.092 0.876 0.024 0.004
#> GSM955023 2 0.4928 0.4137 0.000 0.596 0.376 0.020 0.008
#> GSM955027 2 0.3452 0.7715 0.000 0.856 0.068 0.056 0.020
#> GSM955043 2 0.7397 0.2994 0.008 0.524 0.096 0.104 0.268
#> GSM955048 1 0.0579 0.9381 0.984 0.000 0.000 0.008 0.008
#> GSM955049 2 0.1478 0.7918 0.000 0.936 0.064 0.000 0.000
#> GSM955054 3 0.6356 0.3345 0.000 0.336 0.548 0.072 0.044
#> GSM955064 2 0.3569 0.7529 0.000 0.816 0.152 0.028 0.004
#> GSM955072 4 0.4568 0.7298 0.008 0.248 0.004 0.716 0.024
#> GSM955075 5 0.2850 0.9980 0.000 0.092 0.000 0.036 0.872
#> GSM955079 3 0.0727 0.8041 0.000 0.004 0.980 0.012 0.004
#> GSM955087 1 0.2506 0.9178 0.904 0.008 0.000 0.052 0.036
#> GSM955088 3 0.0833 0.8038 0.000 0.004 0.976 0.016 0.004
#> GSM955089 1 0.2067 0.9332 0.924 0.004 0.000 0.044 0.028
#> GSM955095 3 0.7395 0.4381 0.008 0.220 0.540 0.156 0.076
#> GSM955097 4 0.8195 0.3358 0.028 0.072 0.296 0.428 0.176
#> GSM955101 3 0.2897 0.7919 0.000 0.072 0.884 0.024 0.020
#> GSM954999 3 0.6652 0.5625 0.024 0.068 0.624 0.224 0.060
#> GSM955001 2 0.1469 0.7845 0.000 0.948 0.036 0.016 0.000
#> GSM955003 3 0.5944 0.6032 0.000 0.212 0.656 0.088 0.044
#> GSM955004 4 0.5204 0.7008 0.012 0.120 0.008 0.732 0.128
#> GSM955005 3 0.1187 0.8054 0.004 0.004 0.964 0.024 0.004
#> GSM955009 4 0.3561 0.7838 0.008 0.188 0.008 0.796 0.000
#> GSM955011 1 0.2803 0.9023 0.900 0.016 0.048 0.020 0.016
#> GSM955012 5 0.2850 0.9980 0.000 0.092 0.000 0.036 0.872
#> GSM955013 3 0.4834 0.7352 0.008 0.080 0.776 0.108 0.028
#> GSM955015 2 0.5064 0.6503 0.000 0.696 0.240 0.032 0.032
#> GSM955017 1 0.0960 0.9374 0.972 0.016 0.000 0.008 0.004
#> GSM955021 2 0.5913 0.6616 0.008 0.684 0.160 0.116 0.032
#> GSM955025 4 0.3825 0.7785 0.028 0.136 0.020 0.816 0.000
#> GSM955028 1 0.2506 0.9178 0.904 0.008 0.000 0.052 0.036
#> GSM955029 5 0.2850 0.9980 0.000 0.092 0.000 0.036 0.872
#> GSM955030 3 0.1202 0.8039 0.004 0.000 0.960 0.032 0.004
#> GSM955032 3 0.1173 0.8066 0.000 0.020 0.964 0.012 0.004
#> GSM955033 3 0.7401 0.3899 0.016 0.128 0.532 0.260 0.064
#> GSM955034 1 0.2283 0.9199 0.916 0.008 0.000 0.040 0.036
#> GSM955035 2 0.1792 0.7927 0.000 0.916 0.084 0.000 0.000
#> GSM955036 3 0.5679 0.6698 0.024 0.020 0.708 0.168 0.080
#> GSM955037 1 0.4040 0.8884 0.836 0.024 0.060 0.064 0.016
#> GSM955039 3 0.3344 0.7856 0.004 0.080 0.860 0.048 0.008
#> GSM955041 3 0.5766 0.5765 0.004 0.260 0.648 0.048 0.040
#> GSM955042 1 0.3634 0.8986 0.860 0.024 0.016 0.048 0.052
#> GSM955045 2 0.5208 0.6666 0.004 0.712 0.208 0.044 0.032
#> GSM955046 3 0.2027 0.8021 0.000 0.040 0.928 0.024 0.008
#> GSM955047 1 0.0000 0.9390 1.000 0.000 0.000 0.000 0.000
#> GSM955050 4 0.6838 0.5194 0.040 0.108 0.276 0.564 0.012
#> GSM955052 3 0.1949 0.8020 0.000 0.040 0.932 0.016 0.012
#> GSM955053 1 0.2506 0.9178 0.904 0.008 0.000 0.052 0.036
#> GSM955056 3 0.4554 0.7215 0.000 0.144 0.776 0.044 0.036
#> GSM955058 5 0.2850 0.9980 0.000 0.092 0.000 0.036 0.872
#> GSM955059 3 0.0671 0.8021 0.000 0.000 0.980 0.016 0.004
#> GSM955060 1 0.0162 0.9388 0.996 0.000 0.000 0.004 0.000
#> GSM955061 5 0.2871 0.9919 0.000 0.088 0.000 0.040 0.872
#> GSM955065 1 0.2506 0.9178 0.904 0.008 0.000 0.052 0.036
#> GSM955066 3 0.1329 0.8037 0.008 0.000 0.956 0.032 0.004
#> GSM955067 1 0.1708 0.9332 0.944 0.004 0.004 0.032 0.016
#> GSM955073 3 0.1442 0.8033 0.000 0.032 0.952 0.012 0.004
#> GSM955074 1 0.3046 0.9123 0.880 0.020 0.000 0.052 0.048
#> GSM955076 4 0.3966 0.7595 0.008 0.224 0.012 0.756 0.000
#> GSM955078 4 0.5104 0.7098 0.008 0.224 0.004 0.700 0.064
#> GSM955083 3 0.7381 0.3997 0.028 0.096 0.540 0.272 0.064
#> GSM955084 4 0.4630 0.7565 0.012 0.132 0.008 0.776 0.072
#> GSM955086 3 0.0960 0.8049 0.000 0.008 0.972 0.016 0.004
#> GSM955091 2 0.1597 0.7586 0.000 0.940 0.012 0.048 0.000
#> GSM955092 2 0.2787 0.7791 0.000 0.880 0.088 0.004 0.028
#> GSM955093 3 0.0833 0.8008 0.000 0.004 0.976 0.016 0.004
#> GSM955098 4 0.3403 0.7897 0.012 0.160 0.008 0.820 0.000
#> GSM955099 2 0.1774 0.7629 0.000 0.932 0.016 0.052 0.000
#> GSM955100 1 0.3554 0.8431 0.852 0.016 0.096 0.020 0.016
#> GSM955103 3 0.4516 0.7427 0.004 0.128 0.788 0.052 0.028
#> GSM955104 3 0.2235 0.8048 0.004 0.040 0.920 0.032 0.004
#> GSM955106 3 0.8319 -0.1098 0.000 0.136 0.328 0.236 0.300
#> GSM955000 1 0.1074 0.9378 0.968 0.016 0.000 0.012 0.004
#> GSM955006 1 0.1617 0.9353 0.948 0.012 0.020 0.000 0.020
#> GSM955007 3 0.2233 0.7962 0.000 0.080 0.904 0.016 0.000
#> GSM955010 3 0.1644 0.8036 0.012 0.004 0.948 0.028 0.008
#> GSM955014 1 0.0566 0.9390 0.984 0.000 0.000 0.004 0.012
#> GSM955018 3 0.0671 0.8021 0.000 0.000 0.980 0.016 0.004
#> GSM955020 1 0.2125 0.9327 0.920 0.004 0.000 0.052 0.024
#> GSM955024 3 0.5322 0.3766 0.000 0.372 0.580 0.036 0.012
#> GSM955026 4 0.3333 0.7896 0.008 0.164 0.008 0.820 0.000
#> GSM955031 4 0.6317 0.4346 0.040 0.076 0.328 0.556 0.000
#> GSM955038 4 0.3790 0.7627 0.028 0.112 0.024 0.832 0.004
#> GSM955040 3 0.7457 0.1320 0.064 0.104 0.468 0.348 0.016
#> GSM955044 2 0.6655 0.3501 0.008 0.596 0.040 0.236 0.120
#> GSM955051 1 0.0000 0.9390 1.000 0.000 0.000 0.000 0.000
#> GSM955055 2 0.1836 0.7831 0.000 0.932 0.036 0.032 0.000
#> GSM955057 1 0.0579 0.9381 0.984 0.000 0.000 0.008 0.008
#> GSM955062 2 0.2074 0.7875 0.000 0.896 0.104 0.000 0.000
#> GSM955063 3 0.1525 0.8038 0.000 0.036 0.948 0.012 0.004
#> GSM955068 4 0.3373 0.7900 0.008 0.168 0.008 0.816 0.000
#> GSM955069 3 0.1243 0.8040 0.000 0.008 0.960 0.028 0.004
#> GSM955070 2 0.1522 0.7873 0.000 0.944 0.044 0.012 0.000
#> GSM955071 3 0.3522 0.7742 0.020 0.020 0.844 0.112 0.004
#> GSM955077 4 0.5423 0.7022 0.032 0.104 0.136 0.724 0.004
#> GSM955080 3 0.8450 -0.0719 0.000 0.196 0.324 0.192 0.288
#> GSM955081 3 0.3569 0.7686 0.000 0.104 0.828 0.068 0.000
#> GSM955082 3 0.3795 0.7254 0.004 0.184 0.788 0.024 0.000
#> GSM955085 2 0.1568 0.7703 0.000 0.944 0.020 0.036 0.000
#> GSM955090 1 0.2267 0.9314 0.916 0.008 0.000 0.048 0.028
#> GSM955094 2 0.3690 0.7397 0.000 0.832 0.092 0.068 0.008
#> GSM955096 3 0.1588 0.8073 0.000 0.028 0.948 0.016 0.008
#> GSM955102 3 0.1686 0.7997 0.012 0.004 0.944 0.036 0.004
#> GSM955105 3 0.1116 0.8046 0.000 0.004 0.964 0.028 0.004
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.4413 0.16363 0.000 0.620 0.352 0.016 0.008 0.004
#> GSM955008 3 0.6360 -0.50252 0.000 0.236 0.408 0.016 0.000 0.340
#> GSM955016 1 0.4411 0.82310 0.704 0.012 0.020 0.000 0.016 0.248
#> GSM955019 2 0.2311 0.55042 0.000 0.880 0.016 0.104 0.000 0.000
#> GSM955022 3 0.4372 0.56719 0.000 0.224 0.720 0.024 0.028 0.004
#> GSM955023 2 0.5021 0.01992 0.000 0.536 0.408 0.024 0.000 0.032
#> GSM955027 2 0.4509 0.47716 0.000 0.764 0.056 0.060 0.116 0.004
#> GSM955043 5 0.6129 0.08175 0.000 0.432 0.060 0.068 0.436 0.004
#> GSM955048 1 0.0717 0.88369 0.976 0.000 0.000 0.008 0.000 0.016
#> GSM955049 2 0.0909 0.59000 0.000 0.968 0.020 0.000 0.000 0.012
#> GSM955054 6 0.5658 0.69089 0.000 0.380 0.112 0.012 0.000 0.496
#> GSM955064 2 0.3553 0.53249 0.000 0.820 0.096 0.016 0.068 0.000
#> GSM955072 4 0.4327 0.56910 0.004 0.260 0.000 0.688 0.048 0.000
#> GSM955075 5 0.1341 0.69417 0.000 0.028 0.000 0.024 0.948 0.000
#> GSM955079 3 0.0665 0.71893 0.000 0.008 0.980 0.004 0.000 0.008
#> GSM955087 1 0.2364 0.86191 0.904 0.004 0.000 0.012 0.036 0.044
#> GSM955088 3 0.0603 0.71726 0.000 0.004 0.980 0.000 0.000 0.016
#> GSM955089 1 0.1663 0.87898 0.912 0.000 0.000 0.000 0.000 0.088
#> GSM955095 3 0.7655 0.23300 0.000 0.272 0.432 0.132 0.124 0.040
#> GSM955097 3 0.7803 -0.23992 0.032 0.008 0.352 0.336 0.196 0.076
#> GSM955101 3 0.5232 0.33834 0.000 0.200 0.644 0.012 0.000 0.144
#> GSM954999 3 0.7042 0.51311 0.028 0.064 0.608 0.132 0.088 0.080
#> GSM955001 2 0.0520 0.58642 0.000 0.984 0.008 0.000 0.000 0.008
#> GSM955003 6 0.5978 0.78180 0.000 0.324 0.160 0.016 0.000 0.500
#> GSM955004 4 0.4478 0.56331 0.008 0.060 0.000 0.712 0.216 0.004
#> GSM955005 3 0.1026 0.71995 0.000 0.008 0.968 0.008 0.004 0.012
#> GSM955009 4 0.2805 0.65446 0.000 0.184 0.004 0.812 0.000 0.000
#> GSM955011 1 0.4322 0.85157 0.760 0.000 0.052 0.028 0.004 0.156
#> GSM955012 5 0.1492 0.68750 0.000 0.036 0.000 0.024 0.940 0.000
#> GSM955013 3 0.5066 0.64119 0.000 0.076 0.744 0.076 0.076 0.028
#> GSM955015 2 0.4868 -0.05116 0.000 0.632 0.060 0.012 0.000 0.296
#> GSM955017 1 0.2531 0.88984 0.860 0.000 0.000 0.004 0.008 0.128
#> GSM955021 2 0.6036 -0.38379 0.000 0.524 0.084 0.060 0.000 0.332
#> GSM955025 4 0.3079 0.64953 0.008 0.028 0.128 0.836 0.000 0.000
#> GSM955028 1 0.2364 0.86191 0.904 0.004 0.000 0.012 0.036 0.044
#> GSM955029 5 0.1341 0.69417 0.000 0.028 0.000 0.024 0.948 0.000
#> GSM955030 3 0.1225 0.72193 0.004 0.000 0.956 0.032 0.004 0.004
#> GSM955032 3 0.2384 0.67669 0.000 0.084 0.884 0.000 0.000 0.032
#> GSM955033 3 0.7651 0.33183 0.020 0.088 0.520 0.204 0.096 0.072
#> GSM955034 1 0.2430 0.86247 0.900 0.004 0.000 0.012 0.036 0.048
#> GSM955035 2 0.1088 0.58833 0.000 0.960 0.024 0.000 0.000 0.016
#> GSM955036 3 0.6479 0.48815 0.028 0.000 0.604 0.120 0.168 0.080
#> GSM955037 1 0.4628 0.85900 0.748 0.004 0.060 0.020 0.012 0.156
#> GSM955039 3 0.3572 0.69980 0.004 0.084 0.840 0.032 0.028 0.012
#> GSM955041 2 0.6103 0.12933 0.000 0.492 0.344 0.032 0.132 0.000
#> GSM955042 1 0.4094 0.83387 0.712 0.000 0.020 0.000 0.016 0.252
#> GSM955045 2 0.4890 0.41961 0.000 0.708 0.164 0.032 0.096 0.000
#> GSM955046 3 0.4225 0.66499 0.000 0.128 0.768 0.008 0.008 0.088
#> GSM955047 1 0.2257 0.89063 0.876 0.000 0.000 0.008 0.000 0.116
#> GSM955050 4 0.5978 0.49309 0.044 0.032 0.284 0.588 0.000 0.052
#> GSM955052 3 0.4166 0.57409 0.000 0.160 0.748 0.004 0.000 0.088
#> GSM955053 1 0.2364 0.86191 0.904 0.004 0.000 0.012 0.036 0.044
#> GSM955056 6 0.6282 0.68045 0.000 0.272 0.280 0.012 0.000 0.436
#> GSM955058 5 0.1341 0.69417 0.000 0.028 0.000 0.024 0.948 0.000
#> GSM955059 3 0.1327 0.71591 0.000 0.000 0.936 0.000 0.000 0.064
#> GSM955060 1 0.2278 0.88976 0.868 0.000 0.000 0.004 0.000 0.128
#> GSM955061 5 0.1341 0.69417 0.000 0.028 0.000 0.024 0.948 0.000
#> GSM955065 1 0.2364 0.86191 0.904 0.004 0.000 0.012 0.036 0.044
#> GSM955066 3 0.0951 0.71745 0.000 0.000 0.968 0.020 0.004 0.008
#> GSM955067 1 0.3098 0.88153 0.812 0.000 0.000 0.024 0.000 0.164
#> GSM955073 3 0.4741 0.54442 0.000 0.152 0.692 0.000 0.004 0.152
#> GSM955074 1 0.2994 0.87669 0.788 0.000 0.000 0.000 0.004 0.208
#> GSM955076 4 0.3348 0.62538 0.000 0.216 0.016 0.768 0.000 0.000
#> GSM955078 4 0.4672 0.58337 0.004 0.144 0.000 0.700 0.152 0.000
#> GSM955083 3 0.7758 0.27909 0.032 0.064 0.504 0.228 0.092 0.080
#> GSM955084 4 0.4589 0.58399 0.008 0.084 0.000 0.716 0.188 0.004
#> GSM955086 3 0.1078 0.71818 0.000 0.008 0.964 0.012 0.000 0.016
#> GSM955091 2 0.0653 0.58302 0.000 0.980 0.004 0.004 0.000 0.012
#> GSM955092 2 0.3139 0.47419 0.000 0.836 0.036 0.008 0.000 0.120
#> GSM955093 3 0.2001 0.70234 0.000 0.004 0.900 0.000 0.004 0.092
#> GSM955098 4 0.1700 0.65888 0.000 0.080 0.004 0.916 0.000 0.000
#> GSM955099 2 0.0870 0.58378 0.000 0.972 0.004 0.012 0.000 0.012
#> GSM955100 1 0.4775 0.81276 0.728 0.000 0.092 0.028 0.004 0.148
#> GSM955103 3 0.5955 0.48182 0.000 0.236 0.612 0.048 0.088 0.016
#> GSM955104 3 0.3672 0.70801 0.004 0.052 0.840 0.040 0.012 0.052
#> GSM955106 5 0.8120 0.00253 0.000 0.148 0.192 0.260 0.356 0.044
#> GSM955000 1 0.2573 0.88993 0.856 0.000 0.000 0.004 0.008 0.132
#> GSM955006 1 0.3555 0.88217 0.816 0.000 0.016 0.036 0.004 0.128
#> GSM955007 3 0.4357 0.58421 0.000 0.208 0.728 0.008 0.008 0.048
#> GSM955010 3 0.2263 0.71634 0.008 0.000 0.908 0.044 0.004 0.036
#> GSM955014 1 0.0806 0.88391 0.972 0.000 0.000 0.008 0.000 0.020
#> GSM955018 3 0.1075 0.71769 0.000 0.000 0.952 0.000 0.000 0.048
#> GSM955020 1 0.1913 0.87876 0.908 0.000 0.000 0.012 0.000 0.080
#> GSM955024 2 0.5120 0.21999 0.000 0.596 0.328 0.024 0.052 0.000
#> GSM955026 4 0.2149 0.66971 0.004 0.104 0.004 0.888 0.000 0.000
#> GSM955031 4 0.6299 0.47789 0.076 0.024 0.296 0.560 0.008 0.036
#> GSM955038 4 0.4303 0.64085 0.020 0.032 0.120 0.784 0.000 0.044
#> GSM955040 4 0.6598 0.08505 0.076 0.012 0.408 0.432 0.004 0.068
#> GSM955044 2 0.6376 -0.07511 0.000 0.444 0.020 0.244 0.292 0.000
#> GSM955051 1 0.2257 0.89063 0.876 0.000 0.000 0.008 0.000 0.116
#> GSM955055 2 0.0914 0.58690 0.000 0.968 0.016 0.000 0.000 0.016
#> GSM955057 1 0.0717 0.88369 0.976 0.000 0.000 0.008 0.000 0.016
#> GSM955062 2 0.1594 0.58222 0.000 0.932 0.052 0.000 0.000 0.016
#> GSM955063 3 0.4673 0.55135 0.000 0.148 0.700 0.000 0.004 0.148
#> GSM955068 4 0.2491 0.66648 0.000 0.164 0.000 0.836 0.000 0.000
#> GSM955069 3 0.1876 0.71292 0.000 0.004 0.916 0.004 0.004 0.072
#> GSM955070 2 0.1026 0.58951 0.000 0.968 0.012 0.008 0.004 0.008
#> GSM955071 3 0.3891 0.68020 0.020 0.008 0.812 0.104 0.004 0.052
#> GSM955077 4 0.4831 0.58647 0.020 0.024 0.216 0.704 0.000 0.036
#> GSM955080 5 0.7644 0.16695 0.000 0.328 0.140 0.136 0.372 0.024
#> GSM955081 3 0.3473 0.65978 0.000 0.136 0.812 0.040 0.000 0.012
#> GSM955082 2 0.4664 0.01788 0.000 0.488 0.476 0.032 0.004 0.000
#> GSM955085 2 0.1223 0.58739 0.000 0.960 0.008 0.016 0.004 0.012
#> GSM955090 1 0.1501 0.88220 0.924 0.000 0.000 0.000 0.000 0.076
#> GSM955094 2 0.3930 0.51001 0.000 0.812 0.088 0.052 0.040 0.008
#> GSM955096 3 0.3453 0.59490 0.000 0.132 0.804 0.000 0.000 0.064
#> GSM955102 3 0.2740 0.70686 0.008 0.004 0.876 0.020 0.004 0.088
#> GSM955105 3 0.0984 0.71904 0.000 0.008 0.968 0.012 0.000 0.012
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> SD:mclust 108 0.910 2
#> SD:mclust 99 0.738 3
#> SD:mclust 100 0.763 4
#> SD:mclust 94 0.883 5
#> SD:mclust 83 0.716 6
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 31589 rows and 108 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 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 0.999 0.955 0.981 0.4463 0.551 0.551
#> 3 3 0.794 0.871 0.942 0.2617 0.861 0.758
#> 4 4 0.614 0.722 0.863 0.2209 0.729 0.472
#> 5 5 0.531 0.539 0.752 0.0942 0.877 0.637
#> 6 6 0.558 0.432 0.687 0.0594 0.834 0.469
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
#> GSM955002 2 0.0000 0.988 0.000 1.000
#> GSM955008 2 0.0000 0.988 0.000 1.000
#> GSM955016 1 0.0000 0.965 1.000 0.000
#> GSM955019 2 0.0000 0.988 0.000 1.000
#> GSM955022 2 0.0000 0.988 0.000 1.000
#> GSM955023 2 0.0000 0.988 0.000 1.000
#> GSM955027 2 0.0000 0.988 0.000 1.000
#> GSM955043 2 0.0000 0.988 0.000 1.000
#> GSM955048 1 0.0000 0.965 1.000 0.000
#> GSM955049 2 0.0000 0.988 0.000 1.000
#> GSM955054 2 0.0000 0.988 0.000 1.000
#> GSM955064 2 0.0000 0.988 0.000 1.000
#> GSM955072 2 0.0000 0.988 0.000 1.000
#> GSM955075 2 0.0000 0.988 0.000 1.000
#> GSM955079 2 0.0000 0.988 0.000 1.000
#> GSM955087 1 0.0000 0.965 1.000 0.000
#> GSM955088 2 0.0000 0.988 0.000 1.000
#> GSM955089 1 0.0000 0.965 1.000 0.000
#> GSM955095 2 0.0000 0.988 0.000 1.000
#> GSM955097 2 0.0000 0.988 0.000 1.000
#> GSM955101 2 0.0000 0.988 0.000 1.000
#> GSM954999 1 0.4431 0.884 0.908 0.092
#> GSM955001 2 0.0000 0.988 0.000 1.000
#> GSM955003 2 0.0000 0.988 0.000 1.000
#> GSM955004 2 0.0000 0.988 0.000 1.000
#> GSM955005 2 0.5408 0.850 0.124 0.876
#> GSM955009 2 0.0000 0.988 0.000 1.000
#> GSM955011 1 0.0000 0.965 1.000 0.000
#> GSM955012 2 0.0000 0.988 0.000 1.000
#> GSM955013 2 0.0000 0.988 0.000 1.000
#> GSM955015 2 0.0000 0.988 0.000 1.000
#> GSM955017 1 0.0000 0.965 1.000 0.000
#> GSM955021 2 0.0000 0.988 0.000 1.000
#> GSM955025 2 0.0000 0.988 0.000 1.000
#> GSM955028 1 0.0000 0.965 1.000 0.000
#> GSM955029 2 0.0000 0.988 0.000 1.000
#> GSM955030 1 0.0376 0.963 0.996 0.004
#> GSM955032 2 0.0000 0.988 0.000 1.000
#> GSM955033 2 0.4161 0.899 0.084 0.916
#> GSM955034 1 0.0000 0.965 1.000 0.000
#> GSM955035 2 0.0000 0.988 0.000 1.000
#> GSM955036 2 0.0000 0.988 0.000 1.000
#> GSM955037 1 0.0000 0.965 1.000 0.000
#> GSM955039 2 0.0000 0.988 0.000 1.000
#> GSM955041 2 0.0000 0.988 0.000 1.000
#> GSM955042 1 0.0000 0.965 1.000 0.000
#> GSM955045 2 0.0000 0.988 0.000 1.000
#> GSM955046 2 0.0000 0.988 0.000 1.000
#> GSM955047 1 0.0000 0.965 1.000 0.000
#> GSM955050 1 0.0000 0.965 1.000 0.000
#> GSM955052 2 0.0000 0.988 0.000 1.000
#> GSM955053 1 0.0000 0.965 1.000 0.000
#> GSM955056 2 0.0000 0.988 0.000 1.000
#> GSM955058 2 0.0000 0.988 0.000 1.000
#> GSM955059 2 0.0000 0.988 0.000 1.000
#> GSM955060 1 0.0000 0.965 1.000 0.000
#> GSM955061 2 0.0000 0.988 0.000 1.000
#> GSM955065 1 0.0000 0.965 1.000 0.000
#> GSM955066 1 0.9732 0.341 0.596 0.404
#> GSM955067 1 0.0000 0.965 1.000 0.000
#> GSM955073 2 0.0000 0.988 0.000 1.000
#> GSM955074 1 0.0000 0.965 1.000 0.000
#> GSM955076 2 0.0000 0.988 0.000 1.000
#> GSM955078 2 0.0000 0.988 0.000 1.000
#> GSM955083 1 0.8608 0.617 0.716 0.284
#> GSM955084 2 0.0000 0.988 0.000 1.000
#> GSM955086 2 0.0376 0.984 0.004 0.996
#> GSM955091 2 0.0000 0.988 0.000 1.000
#> GSM955092 2 0.0000 0.988 0.000 1.000
#> GSM955093 2 0.0000 0.988 0.000 1.000
#> GSM955098 2 0.0000 0.988 0.000 1.000
#> GSM955099 2 0.0000 0.988 0.000 1.000
#> GSM955100 1 0.0000 0.965 1.000 0.000
#> GSM955103 2 0.0000 0.988 0.000 1.000
#> GSM955104 2 0.9866 0.203 0.432 0.568
#> GSM955106 2 0.0000 0.988 0.000 1.000
#> GSM955000 1 0.0000 0.965 1.000 0.000
#> GSM955006 1 0.0000 0.965 1.000 0.000
#> GSM955007 2 0.0000 0.988 0.000 1.000
#> GSM955010 1 0.0000 0.965 1.000 0.000
#> GSM955014 1 0.0000 0.965 1.000 0.000
#> GSM955018 2 0.0000 0.988 0.000 1.000
#> GSM955020 1 0.0000 0.965 1.000 0.000
#> GSM955024 2 0.0000 0.988 0.000 1.000
#> GSM955026 2 0.0000 0.988 0.000 1.000
#> GSM955031 1 0.1184 0.955 0.984 0.016
#> GSM955038 1 0.2236 0.938 0.964 0.036
#> GSM955040 1 0.0000 0.965 1.000 0.000
#> GSM955044 2 0.0000 0.988 0.000 1.000
#> GSM955051 1 0.0000 0.965 1.000 0.000
#> GSM955055 2 0.0000 0.988 0.000 1.000
#> GSM955057 1 0.0000 0.965 1.000 0.000
#> GSM955062 2 0.0000 0.988 0.000 1.000
#> GSM955063 2 0.0000 0.988 0.000 1.000
#> GSM955068 2 0.0000 0.988 0.000 1.000
#> GSM955069 2 0.0000 0.988 0.000 1.000
#> GSM955070 2 0.0000 0.988 0.000 1.000
#> GSM955071 1 0.0672 0.960 0.992 0.008
#> GSM955077 1 0.1633 0.949 0.976 0.024
#> GSM955080 2 0.0000 0.988 0.000 1.000
#> GSM955081 2 0.0000 0.988 0.000 1.000
#> GSM955082 2 0.0000 0.988 0.000 1.000
#> GSM955085 2 0.0000 0.988 0.000 1.000
#> GSM955090 1 0.0000 0.965 1.000 0.000
#> GSM955094 2 0.0000 0.988 0.000 1.000
#> GSM955096 2 0.0000 0.988 0.000 1.000
#> GSM955102 1 0.9044 0.543 0.680 0.320
#> GSM955105 2 0.6531 0.789 0.168 0.832
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.0424 0.923 0.000 0.008 0.992
#> GSM955008 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955016 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955019 3 0.1643 0.907 0.000 0.044 0.956
#> GSM955022 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955023 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955027 3 0.0747 0.920 0.000 0.016 0.984
#> GSM955043 3 0.2448 0.887 0.000 0.076 0.924
#> GSM955048 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955049 3 0.0237 0.924 0.000 0.004 0.996
#> GSM955054 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955064 3 0.0424 0.923 0.000 0.008 0.992
#> GSM955072 3 0.6168 0.357 0.000 0.412 0.588
#> GSM955075 3 0.5882 0.531 0.000 0.348 0.652
#> GSM955079 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955087 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955088 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955089 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955095 3 0.2356 0.889 0.000 0.072 0.928
#> GSM955097 2 0.0000 0.860 0.000 1.000 0.000
#> GSM955101 3 0.0000 0.924 0.000 0.000 1.000
#> GSM954999 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955001 3 0.2261 0.893 0.000 0.068 0.932
#> GSM955003 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955004 2 0.0000 0.860 0.000 1.000 0.000
#> GSM955005 3 0.0237 0.923 0.004 0.000 0.996
#> GSM955009 3 0.4931 0.731 0.000 0.232 0.768
#> GSM955011 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955012 3 0.2711 0.878 0.000 0.088 0.912
#> GSM955013 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955015 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955017 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955021 3 0.0424 0.923 0.000 0.008 0.992
#> GSM955025 2 0.0237 0.860 0.000 0.996 0.004
#> GSM955028 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955029 3 0.5016 0.720 0.000 0.240 0.760
#> GSM955030 1 0.4887 0.622 0.772 0.000 0.228
#> GSM955032 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955033 2 0.7470 0.480 0.052 0.612 0.336
#> GSM955034 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955035 3 0.0747 0.920 0.000 0.016 0.984
#> GSM955036 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955037 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955039 3 0.0237 0.924 0.000 0.004 0.996
#> GSM955041 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955042 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955045 3 0.0237 0.924 0.000 0.004 0.996
#> GSM955046 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955047 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955050 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955052 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955053 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955056 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955058 3 0.4605 0.765 0.000 0.204 0.796
#> GSM955059 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955060 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955061 3 0.6307 0.122 0.000 0.488 0.512
#> GSM955065 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955066 3 0.4974 0.618 0.236 0.000 0.764
#> GSM955067 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955073 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955074 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955076 3 0.1529 0.909 0.000 0.040 0.960
#> GSM955078 2 0.3340 0.815 0.000 0.880 0.120
#> GSM955083 1 0.5810 0.486 0.664 0.336 0.000
#> GSM955084 2 0.0000 0.860 0.000 1.000 0.000
#> GSM955086 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955091 3 0.3551 0.841 0.000 0.132 0.868
#> GSM955092 3 0.0237 0.924 0.000 0.004 0.996
#> GSM955093 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955098 2 0.2165 0.848 0.000 0.936 0.064
#> GSM955099 3 0.3482 0.845 0.000 0.128 0.872
#> GSM955100 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955103 3 0.0237 0.924 0.000 0.004 0.996
#> GSM955104 3 0.4842 0.651 0.224 0.000 0.776
#> GSM955106 3 0.4702 0.756 0.000 0.212 0.788
#> GSM955000 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955006 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955007 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955010 1 0.2796 0.853 0.908 0.000 0.092
#> GSM955014 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955018 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955020 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955024 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955026 2 0.4346 0.756 0.000 0.816 0.184
#> GSM955031 1 0.3482 0.792 0.872 0.000 0.128
#> GSM955038 2 0.5591 0.490 0.304 0.696 0.000
#> GSM955040 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955044 3 0.4062 0.812 0.000 0.164 0.836
#> GSM955051 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955055 3 0.1964 0.900 0.000 0.056 0.944
#> GSM955057 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955062 3 0.0237 0.924 0.000 0.004 0.996
#> GSM955063 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955068 2 0.0000 0.860 0.000 1.000 0.000
#> GSM955069 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955070 3 0.0424 0.923 0.000 0.008 0.992
#> GSM955071 1 0.1753 0.907 0.952 0.000 0.048
#> GSM955077 1 0.0424 0.959 0.992 0.008 0.000
#> GSM955080 3 0.5591 0.615 0.000 0.304 0.696
#> GSM955081 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955082 3 0.0237 0.924 0.000 0.004 0.996
#> GSM955085 3 0.3752 0.830 0.000 0.144 0.856
#> GSM955090 1 0.0000 0.966 1.000 0.000 0.000
#> GSM955094 3 0.1753 0.905 0.000 0.048 0.952
#> GSM955096 3 0.0000 0.924 0.000 0.000 1.000
#> GSM955102 3 0.5431 0.527 0.284 0.000 0.716
#> GSM955105 3 0.0424 0.920 0.008 0.000 0.992
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 3 0.2530 0.7586 0.000 0.112 0.888 0.000
#> GSM955008 3 0.2408 0.7680 0.000 0.104 0.896 0.000
#> GSM955016 1 0.1878 0.9214 0.944 0.008 0.008 0.040
#> GSM955019 2 0.3219 0.7703 0.000 0.836 0.164 0.000
#> GSM955022 3 0.0188 0.8047 0.000 0.000 0.996 0.004
#> GSM955023 3 0.0469 0.8067 0.000 0.012 0.988 0.000
#> GSM955027 2 0.4837 0.6768 0.000 0.648 0.348 0.004
#> GSM955043 3 0.2742 0.7788 0.000 0.024 0.900 0.076
#> GSM955048 1 0.0188 0.9470 0.996 0.004 0.000 0.000
#> GSM955049 2 0.4977 0.4413 0.000 0.540 0.460 0.000
#> GSM955054 2 0.4776 0.6315 0.000 0.624 0.376 0.000
#> GSM955064 3 0.3123 0.7039 0.000 0.156 0.844 0.000
#> GSM955072 2 0.3372 0.7321 0.000 0.868 0.096 0.036
#> GSM955075 4 0.3791 0.7364 0.000 0.004 0.200 0.796
#> GSM955079 3 0.5310 -0.0160 0.012 0.412 0.576 0.000
#> GSM955087 1 0.0336 0.9460 0.992 0.008 0.000 0.000
#> GSM955088 3 0.0817 0.8077 0.000 0.024 0.976 0.000
#> GSM955089 1 0.0336 0.9460 0.992 0.008 0.000 0.000
#> GSM955095 3 0.3390 0.7262 0.000 0.016 0.852 0.132
#> GSM955097 4 0.0188 0.7391 0.000 0.000 0.004 0.996
#> GSM955101 3 0.4888 0.0545 0.000 0.412 0.588 0.000
#> GSM954999 1 0.4339 0.6381 0.764 0.008 0.224 0.004
#> GSM955001 2 0.4331 0.7487 0.000 0.712 0.288 0.000
#> GSM955003 2 0.3942 0.7756 0.000 0.764 0.236 0.000
#> GSM955004 4 0.0469 0.7385 0.000 0.012 0.000 0.988
#> GSM955005 3 0.2466 0.7521 0.096 0.004 0.900 0.000
#> GSM955009 2 0.1637 0.7170 0.000 0.940 0.060 0.000
#> GSM955011 1 0.0188 0.9470 0.996 0.004 0.000 0.000
#> GSM955012 3 0.3024 0.7096 0.000 0.000 0.852 0.148
#> GSM955013 3 0.1229 0.7941 0.020 0.004 0.968 0.008
#> GSM955015 3 0.1940 0.7866 0.000 0.076 0.924 0.000
#> GSM955017 1 0.0188 0.9468 0.996 0.004 0.000 0.000
#> GSM955021 2 0.3400 0.7746 0.000 0.820 0.180 0.000
#> GSM955025 2 0.0712 0.6673 0.004 0.984 0.004 0.008
#> GSM955028 1 0.0336 0.9460 0.992 0.008 0.000 0.000
#> GSM955029 4 0.7020 0.4469 0.000 0.136 0.332 0.532
#> GSM955030 3 0.4123 0.5250 0.220 0.008 0.772 0.000
#> GSM955032 3 0.4543 0.3370 0.000 0.324 0.676 0.000
#> GSM955033 3 0.6114 -0.0383 0.048 0.000 0.524 0.428
#> GSM955034 1 0.0000 0.9472 1.000 0.000 0.000 0.000
#> GSM955035 2 0.4331 0.7504 0.000 0.712 0.288 0.000
#> GSM955036 3 0.3005 0.7398 0.044 0.008 0.900 0.048
#> GSM955037 1 0.1970 0.8960 0.932 0.008 0.060 0.000
#> GSM955039 3 0.0707 0.8082 0.000 0.020 0.980 0.000
#> GSM955041 3 0.0592 0.8075 0.000 0.016 0.984 0.000
#> GSM955042 1 0.0336 0.9467 0.992 0.008 0.000 0.000
#> GSM955045 3 0.1824 0.7965 0.000 0.060 0.936 0.004
#> GSM955046 3 0.0524 0.8018 0.004 0.008 0.988 0.000
#> GSM955047 1 0.0469 0.9453 0.988 0.012 0.000 0.000
#> GSM955050 1 0.2081 0.8984 0.916 0.084 0.000 0.000
#> GSM955052 3 0.1211 0.8030 0.000 0.040 0.960 0.000
#> GSM955053 1 0.0000 0.9472 1.000 0.000 0.000 0.000
#> GSM955056 3 0.4933 -0.1001 0.000 0.432 0.568 0.000
#> GSM955058 4 0.6067 0.4343 0.000 0.052 0.376 0.572
#> GSM955059 3 0.0188 0.8045 0.000 0.004 0.996 0.000
#> GSM955060 1 0.0000 0.9472 1.000 0.000 0.000 0.000
#> GSM955061 4 0.2401 0.7680 0.000 0.004 0.092 0.904
#> GSM955065 1 0.0336 0.9460 0.992 0.008 0.000 0.000
#> GSM955066 3 0.1807 0.7698 0.052 0.008 0.940 0.000
#> GSM955067 1 0.1867 0.9085 0.928 0.072 0.000 0.000
#> GSM955073 3 0.0000 0.8054 0.000 0.000 1.000 0.000
#> GSM955074 1 0.0336 0.9462 0.992 0.000 0.000 0.008
#> GSM955076 2 0.1557 0.7131 0.000 0.944 0.056 0.000
#> GSM955078 2 0.4318 0.6967 0.000 0.816 0.068 0.116
#> GSM955083 1 0.3257 0.8267 0.844 0.000 0.004 0.152
#> GSM955084 4 0.2081 0.7179 0.000 0.084 0.000 0.916
#> GSM955086 2 0.6797 0.5566 0.108 0.536 0.356 0.000
#> GSM955091 2 0.3831 0.7785 0.000 0.792 0.204 0.004
#> GSM955092 2 0.4331 0.7490 0.000 0.712 0.288 0.000
#> GSM955093 3 0.0336 0.8077 0.000 0.008 0.992 0.000
#> GSM955098 2 0.0927 0.6682 0.000 0.976 0.008 0.016
#> GSM955099 2 0.4018 0.7776 0.000 0.772 0.224 0.004
#> GSM955100 1 0.0188 0.9468 0.996 0.004 0.000 0.000
#> GSM955103 3 0.1151 0.8075 0.000 0.024 0.968 0.008
#> GSM955104 3 0.3088 0.6795 0.128 0.008 0.864 0.000
#> GSM955106 3 0.4933 0.0371 0.000 0.000 0.568 0.432
#> GSM955000 1 0.0336 0.9460 0.992 0.008 0.000 0.000
#> GSM955006 1 0.0000 0.9472 1.000 0.000 0.000 0.000
#> GSM955007 3 0.0000 0.8054 0.000 0.000 1.000 0.000
#> GSM955010 3 0.5288 0.0612 0.472 0.008 0.520 0.000
#> GSM955014 1 0.1118 0.9340 0.964 0.036 0.000 0.000
#> GSM955018 3 0.1389 0.8006 0.000 0.048 0.952 0.000
#> GSM955020 1 0.0188 0.9470 0.996 0.004 0.000 0.000
#> GSM955024 3 0.0188 0.8060 0.000 0.004 0.996 0.000
#> GSM955026 2 0.0672 0.6717 0.000 0.984 0.008 0.008
#> GSM955031 2 0.1807 0.6305 0.052 0.940 0.008 0.000
#> GSM955038 1 0.5597 0.2914 0.516 0.464 0.000 0.020
#> GSM955040 1 0.0592 0.9443 0.984 0.016 0.000 0.000
#> GSM955044 3 0.7413 0.1987 0.000 0.232 0.516 0.252
#> GSM955051 1 0.0921 0.9387 0.972 0.028 0.000 0.000
#> GSM955055 2 0.3649 0.7784 0.000 0.796 0.204 0.000
#> GSM955057 1 0.1022 0.9371 0.968 0.032 0.000 0.000
#> GSM955062 2 0.4500 0.7212 0.000 0.684 0.316 0.000
#> GSM955063 3 0.0000 0.8054 0.000 0.000 1.000 0.000
#> GSM955068 2 0.0937 0.6750 0.000 0.976 0.012 0.012
#> GSM955069 3 0.0804 0.7983 0.012 0.008 0.980 0.000
#> GSM955070 3 0.1356 0.8064 0.000 0.032 0.960 0.008
#> GSM955071 1 0.2060 0.9029 0.932 0.016 0.052 0.000
#> GSM955077 2 0.3569 0.4268 0.196 0.804 0.000 0.000
#> GSM955080 4 0.4877 0.7183 0.000 0.044 0.204 0.752
#> GSM955081 2 0.4888 0.5573 0.000 0.588 0.412 0.000
#> GSM955082 3 0.2760 0.7454 0.000 0.128 0.872 0.000
#> GSM955085 2 0.4194 0.7763 0.000 0.764 0.228 0.008
#> GSM955090 1 0.0672 0.9458 0.984 0.008 0.000 0.008
#> GSM955094 3 0.2813 0.7823 0.000 0.080 0.896 0.024
#> GSM955096 2 0.4933 0.5096 0.000 0.568 0.432 0.000
#> GSM955102 3 0.2342 0.7426 0.080 0.008 0.912 0.000
#> GSM955105 3 0.6320 0.4641 0.204 0.140 0.656 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.4986 0.41731 0.004 0.032 0.608 0.356 0.000
#> GSM955008 3 0.4252 0.56369 0.000 0.280 0.700 0.020 0.000
#> GSM955016 1 0.3432 0.84574 0.860 0.000 0.028 0.060 0.052
#> GSM955019 2 0.4252 0.19248 0.000 0.700 0.020 0.280 0.000
#> GSM955022 3 0.1484 0.70787 0.000 0.048 0.944 0.008 0.000
#> GSM955023 3 0.3438 0.68389 0.000 0.172 0.808 0.020 0.000
#> GSM955027 2 0.2393 0.56440 0.000 0.900 0.080 0.016 0.004
#> GSM955043 3 0.4253 0.66713 0.000 0.052 0.804 0.032 0.112
#> GSM955048 1 0.0609 0.88952 0.980 0.000 0.000 0.020 0.000
#> GSM955049 2 0.4620 0.43364 0.000 0.652 0.320 0.028 0.000
#> GSM955054 2 0.6793 -0.09162 0.000 0.376 0.332 0.292 0.000
#> GSM955064 3 0.4923 0.58094 0.000 0.212 0.700 0.088 0.000
#> GSM955072 2 0.5442 -0.07798 0.000 0.592 0.036 0.352 0.020
#> GSM955075 5 0.5726 0.37056 0.000 0.372 0.092 0.000 0.536
#> GSM955079 2 0.6478 0.29670 0.048 0.536 0.340 0.076 0.000
#> GSM955087 1 0.1568 0.88314 0.944 0.000 0.020 0.036 0.000
#> GSM955088 3 0.5631 0.00758 0.008 0.456 0.488 0.044 0.004
#> GSM955089 1 0.1018 0.88911 0.968 0.000 0.016 0.016 0.000
#> GSM955095 2 0.6322 0.23295 0.000 0.496 0.368 0.008 0.128
#> GSM955097 5 0.0932 0.59994 0.000 0.020 0.004 0.004 0.972
#> GSM955101 3 0.6492 0.14533 0.000 0.348 0.456 0.196 0.000
#> GSM954999 1 0.5898 0.33598 0.564 0.008 0.360 0.052 0.016
#> GSM955001 2 0.2237 0.54515 0.000 0.916 0.040 0.040 0.004
#> GSM955003 2 0.6127 -0.26440 0.000 0.484 0.132 0.384 0.000
#> GSM955004 5 0.2416 0.60811 0.000 0.100 0.000 0.012 0.888
#> GSM955005 3 0.4180 0.64882 0.132 0.024 0.800 0.044 0.000
#> GSM955009 2 0.2909 0.43191 0.000 0.848 0.000 0.140 0.012
#> GSM955011 1 0.0451 0.89139 0.988 0.000 0.000 0.008 0.004
#> GSM955012 3 0.6491 0.23193 0.000 0.228 0.488 0.000 0.284
#> GSM955013 3 0.2253 0.70759 0.012 0.036 0.924 0.020 0.008
#> GSM955015 3 0.4276 0.58129 0.000 0.032 0.724 0.244 0.000
#> GSM955017 1 0.1251 0.88747 0.956 0.000 0.008 0.036 0.000
#> GSM955021 2 0.4096 0.36222 0.000 0.760 0.040 0.200 0.000
#> GSM955025 2 0.5470 -0.16085 0.032 0.560 0.000 0.388 0.020
#> GSM955028 1 0.1399 0.88604 0.952 0.000 0.020 0.028 0.000
#> GSM955029 2 0.4624 0.45463 0.000 0.740 0.096 0.000 0.164
#> GSM955030 3 0.3317 0.66484 0.088 0.004 0.852 0.056 0.000
#> GSM955032 2 0.6066 0.05197 0.008 0.464 0.436 0.092 0.000
#> GSM955033 3 0.6816 0.28584 0.028 0.004 0.520 0.312 0.136
#> GSM955034 1 0.0451 0.89106 0.988 0.000 0.004 0.008 0.000
#> GSM955035 4 0.6771 0.30324 0.000 0.312 0.292 0.396 0.000
#> GSM955036 3 0.2927 0.67419 0.020 0.000 0.880 0.080 0.020
#> GSM955037 1 0.2504 0.85318 0.896 0.000 0.064 0.040 0.000
#> GSM955039 3 0.4755 0.55640 0.008 0.032 0.704 0.252 0.004
#> GSM955041 3 0.3239 0.69089 0.000 0.156 0.828 0.012 0.004
#> GSM955042 1 0.0960 0.89122 0.972 0.000 0.008 0.016 0.004
#> GSM955045 2 0.4879 0.45992 0.000 0.688 0.264 0.016 0.032
#> GSM955046 3 0.2026 0.68848 0.012 0.008 0.924 0.056 0.000
#> GSM955047 1 0.1331 0.88742 0.952 0.000 0.008 0.040 0.000
#> GSM955050 1 0.6044 0.24142 0.460 0.008 0.076 0.452 0.004
#> GSM955052 3 0.3906 0.54514 0.000 0.292 0.704 0.004 0.000
#> GSM955053 1 0.0932 0.88981 0.972 0.000 0.004 0.020 0.004
#> GSM955056 2 0.4138 0.50985 0.000 0.708 0.276 0.016 0.000
#> GSM955058 5 0.6066 0.19276 0.000 0.388 0.124 0.000 0.488
#> GSM955059 3 0.2624 0.70648 0.000 0.116 0.872 0.012 0.000
#> GSM955060 1 0.0880 0.88894 0.968 0.000 0.000 0.032 0.000
#> GSM955061 5 0.3835 0.62457 0.000 0.156 0.048 0.000 0.796
#> GSM955065 1 0.1485 0.88467 0.948 0.000 0.020 0.032 0.000
#> GSM955066 3 0.3424 0.68012 0.064 0.016 0.856 0.064 0.000
#> GSM955067 1 0.3741 0.70156 0.732 0.000 0.004 0.264 0.000
#> GSM955073 3 0.3318 0.67539 0.000 0.180 0.808 0.012 0.000
#> GSM955074 1 0.1310 0.88706 0.956 0.000 0.000 0.024 0.020
#> GSM955076 4 0.4689 0.49428 0.000 0.424 0.016 0.560 0.000
#> GSM955078 2 0.3184 0.47492 0.000 0.852 0.000 0.048 0.100
#> GSM955083 1 0.5119 0.72115 0.740 0.004 0.052 0.040 0.164
#> GSM955084 5 0.2234 0.58533 0.000 0.044 0.004 0.036 0.916
#> GSM955086 2 0.4707 0.55638 0.052 0.784 0.112 0.048 0.004
#> GSM955091 2 0.4430 0.27629 0.000 0.720 0.032 0.244 0.004
#> GSM955092 2 0.2754 0.56731 0.000 0.884 0.080 0.032 0.004
#> GSM955093 3 0.3236 0.69078 0.000 0.152 0.828 0.020 0.000
#> GSM955098 4 0.4394 0.67310 0.008 0.212 0.036 0.744 0.000
#> GSM955099 2 0.3336 0.44233 0.000 0.832 0.016 0.144 0.008
#> GSM955100 1 0.1485 0.88679 0.948 0.000 0.032 0.020 0.000
#> GSM955103 3 0.4500 0.48675 0.000 0.316 0.664 0.016 0.004
#> GSM955104 3 0.5737 0.55939 0.196 0.092 0.676 0.036 0.000
#> GSM955106 5 0.5781 0.13207 0.000 0.068 0.416 0.008 0.508
#> GSM955000 1 0.0807 0.89096 0.976 0.000 0.012 0.012 0.000
#> GSM955006 1 0.1117 0.88975 0.964 0.000 0.016 0.020 0.000
#> GSM955007 3 0.2574 0.70806 0.000 0.112 0.876 0.012 0.000
#> GSM955010 3 0.4569 0.56557 0.148 0.000 0.748 0.104 0.000
#> GSM955014 1 0.1864 0.87146 0.924 0.000 0.004 0.068 0.004
#> GSM955018 2 0.5496 0.24566 0.020 0.548 0.400 0.032 0.000
#> GSM955020 1 0.0451 0.89086 0.988 0.000 0.004 0.008 0.000
#> GSM955024 3 0.3246 0.66717 0.000 0.184 0.808 0.008 0.000
#> GSM955026 4 0.4724 0.66538 0.020 0.320 0.008 0.652 0.000
#> GSM955031 2 0.6819 -0.35141 0.236 0.396 0.004 0.364 0.000
#> GSM955038 4 0.4404 0.46960 0.156 0.056 0.008 0.776 0.004
#> GSM955040 1 0.5821 0.55032 0.604 0.000 0.156 0.240 0.000
#> GSM955044 3 0.7330 -0.07248 0.000 0.124 0.424 0.380 0.072
#> GSM955051 1 0.1662 0.87848 0.936 0.000 0.004 0.056 0.004
#> GSM955055 2 0.2144 0.50755 0.000 0.912 0.020 0.068 0.000
#> GSM955057 1 0.1202 0.88641 0.960 0.000 0.004 0.032 0.004
#> GSM955062 2 0.4020 0.52338 0.000 0.796 0.108 0.096 0.000
#> GSM955063 3 0.2864 0.69781 0.000 0.136 0.852 0.012 0.000
#> GSM955068 4 0.4227 0.67450 0.000 0.292 0.016 0.692 0.000
#> GSM955069 3 0.5082 0.64440 0.052 0.168 0.740 0.036 0.004
#> GSM955070 3 0.3880 0.63092 0.000 0.028 0.784 0.184 0.004
#> GSM955071 1 0.6140 0.50745 0.596 0.008 0.204 0.192 0.000
#> GSM955077 2 0.6320 0.13333 0.256 0.584 0.004 0.144 0.012
#> GSM955080 2 0.5904 -0.22983 0.000 0.468 0.068 0.012 0.452
#> GSM955081 2 0.5104 0.47328 0.000 0.692 0.192 0.116 0.000
#> GSM955082 2 0.4588 0.52725 0.000 0.756 0.180 0.040 0.024
#> GSM955085 2 0.3063 0.48923 0.000 0.864 0.012 0.104 0.020
#> GSM955090 1 0.1653 0.88282 0.944 0.000 0.004 0.028 0.024
#> GSM955094 3 0.4272 0.61164 0.000 0.020 0.752 0.212 0.016
#> GSM955096 2 0.2997 0.57048 0.000 0.840 0.148 0.012 0.000
#> GSM955102 3 0.4171 0.66143 0.112 0.052 0.808 0.028 0.000
#> GSM955105 2 0.7165 0.27504 0.236 0.476 0.256 0.032 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 4 0.3627 0.64418 0.000 0.008 0.136 0.800 0.000 0.056
#> GSM955008 3 0.3549 0.48762 0.000 0.016 0.812 0.044 0.000 0.128
#> GSM955016 1 0.2359 0.87241 0.904 0.000 0.008 0.020 0.056 0.012
#> GSM955019 6 0.5933 0.35856 0.000 0.212 0.268 0.008 0.000 0.512
#> GSM955022 3 0.3890 -0.05098 0.000 0.004 0.596 0.400 0.000 0.000
#> GSM955023 3 0.3789 0.39591 0.000 0.040 0.760 0.196 0.000 0.004
#> GSM955027 3 0.6039 -0.19644 0.000 0.344 0.436 0.000 0.004 0.216
#> GSM955043 4 0.6835 0.32813 0.000 0.028 0.352 0.400 0.204 0.016
#> GSM955048 1 0.0725 0.89439 0.976 0.000 0.000 0.012 0.000 0.012
#> GSM955049 3 0.5108 0.19326 0.000 0.096 0.620 0.008 0.000 0.276
#> GSM955054 3 0.7590 -0.13867 0.000 0.180 0.308 0.208 0.000 0.304
#> GSM955064 3 0.5874 0.30497 0.000 0.052 0.604 0.216 0.000 0.128
#> GSM955072 2 0.5510 0.12441 0.000 0.468 0.052 0.016 0.012 0.452
#> GSM955075 5 0.5379 0.37018 0.000 0.336 0.092 0.012 0.560 0.000
#> GSM955079 3 0.5661 0.25791 0.128 0.036 0.616 0.000 0.000 0.220
#> GSM955087 1 0.0405 0.89235 0.988 0.000 0.004 0.000 0.000 0.008
#> GSM955088 2 0.6044 0.15373 0.008 0.512 0.268 0.208 0.000 0.004
#> GSM955089 1 0.0665 0.89343 0.980 0.004 0.000 0.008 0.000 0.008
#> GSM955095 2 0.6947 0.14160 0.000 0.436 0.280 0.080 0.204 0.000
#> GSM955097 5 0.1554 0.62204 0.004 0.044 0.008 0.000 0.940 0.004
#> GSM955101 3 0.5208 -0.06714 0.000 0.036 0.528 0.032 0.000 0.404
#> GSM954999 1 0.4282 0.75359 0.788 0.004 0.124 0.032 0.020 0.032
#> GSM955001 2 0.5082 0.48902 0.000 0.648 0.188 0.004 0.000 0.160
#> GSM955003 6 0.6023 0.40882 0.000 0.076 0.308 0.072 0.000 0.544
#> GSM955004 5 0.3753 0.54098 0.000 0.292 0.000 0.004 0.696 0.008
#> GSM955005 3 0.5954 0.00946 0.172 0.008 0.540 0.272 0.000 0.008
#> GSM955009 2 0.2493 0.44267 0.000 0.884 0.036 0.004 0.000 0.076
#> GSM955011 1 0.0622 0.89386 0.980 0.000 0.000 0.008 0.000 0.012
#> GSM955012 3 0.4294 0.38729 0.000 0.016 0.724 0.016 0.228 0.016
#> GSM955013 3 0.3925 0.23089 0.004 0.012 0.700 0.280 0.000 0.004
#> GSM955015 4 0.5089 0.58877 0.000 0.024 0.280 0.632 0.000 0.064
#> GSM955017 1 0.3316 0.84107 0.828 0.024 0.000 0.124 0.000 0.024
#> GSM955021 2 0.5770 0.30780 0.000 0.532 0.132 0.016 0.000 0.320
#> GSM955025 2 0.6072 0.05110 0.028 0.556 0.008 0.108 0.004 0.296
#> GSM955028 1 0.0291 0.89232 0.992 0.000 0.004 0.000 0.000 0.004
#> GSM955029 2 0.6688 0.24804 0.000 0.428 0.296 0.004 0.240 0.032
#> GSM955030 3 0.5203 -0.34286 0.076 0.000 0.468 0.452 0.000 0.004
#> GSM955032 3 0.6735 -0.15203 0.016 0.272 0.468 0.028 0.000 0.216
#> GSM955033 4 0.1913 0.64813 0.000 0.000 0.080 0.908 0.000 0.012
#> GSM955034 1 0.0665 0.89367 0.980 0.004 0.000 0.008 0.000 0.008
#> GSM955035 6 0.5738 0.44807 0.000 0.020 0.244 0.156 0.000 0.580
#> GSM955036 4 0.4440 0.49488 0.004 0.004 0.380 0.596 0.012 0.004
#> GSM955037 1 0.1699 0.86869 0.928 0.004 0.060 0.004 0.000 0.004
#> GSM955039 4 0.4071 0.63441 0.000 0.000 0.248 0.712 0.004 0.036
#> GSM955041 3 0.2655 0.50095 0.000 0.004 0.876 0.060 0.000 0.060
#> GSM955042 1 0.0405 0.89359 0.988 0.000 0.000 0.004 0.000 0.008
#> GSM955045 2 0.4923 0.36613 0.000 0.564 0.388 0.012 0.028 0.008
#> GSM955046 4 0.3998 0.28405 0.000 0.004 0.492 0.504 0.000 0.000
#> GSM955047 1 0.2836 0.86421 0.872 0.052 0.000 0.060 0.000 0.016
#> GSM955050 4 0.6076 0.16718 0.104 0.096 0.000 0.600 0.000 0.200
#> GSM955052 3 0.2415 0.51446 0.000 0.040 0.900 0.024 0.000 0.036
#> GSM955053 1 0.0146 0.89230 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM955056 2 0.5774 0.33206 0.000 0.452 0.420 0.016 0.000 0.112
#> GSM955058 3 0.6325 -0.18027 0.000 0.064 0.436 0.004 0.412 0.084
#> GSM955059 3 0.4090 0.15001 0.000 0.016 0.652 0.328 0.000 0.004
#> GSM955060 1 0.2386 0.87304 0.896 0.012 0.000 0.064 0.000 0.028
#> GSM955061 5 0.3888 0.54363 0.000 0.012 0.212 0.004 0.752 0.020
#> GSM955065 1 0.1167 0.89179 0.960 0.012 0.000 0.020 0.000 0.008
#> GSM955066 4 0.5479 0.56667 0.072 0.032 0.284 0.608 0.000 0.004
#> GSM955067 1 0.4859 0.65798 0.660 0.000 0.000 0.104 0.004 0.232
#> GSM955073 3 0.1590 0.50669 0.000 0.008 0.936 0.048 0.000 0.008
#> GSM955074 1 0.1924 0.87476 0.920 0.004 0.000 0.000 0.048 0.028
#> GSM955076 6 0.3942 0.41868 0.000 0.120 0.084 0.012 0.000 0.784
#> GSM955078 2 0.6957 0.27891 0.000 0.440 0.144 0.008 0.080 0.328
#> GSM955083 1 0.5589 0.56959 0.640 0.016 0.000 0.108 0.216 0.020
#> GSM955084 5 0.3776 0.60366 0.000 0.096 0.008 0.008 0.808 0.080
#> GSM955086 2 0.6430 0.41772 0.044 0.504 0.312 0.008 0.000 0.132
#> GSM955091 6 0.5766 0.34670 0.000 0.152 0.316 0.004 0.004 0.524
#> GSM955092 2 0.5682 0.31739 0.000 0.524 0.328 0.008 0.000 0.140
#> GSM955093 3 0.1788 0.49097 0.000 0.004 0.916 0.076 0.000 0.004
#> GSM955098 6 0.3797 0.45366 0.004 0.008 0.028 0.192 0.000 0.768
#> GSM955099 6 0.6194 0.18074 0.000 0.308 0.288 0.004 0.000 0.400
#> GSM955100 1 0.3527 0.81773 0.808 0.052 0.000 0.132 0.000 0.008
#> GSM955103 3 0.3200 0.46635 0.000 0.092 0.840 0.008 0.000 0.060
#> GSM955104 3 0.4401 0.30227 0.300 0.008 0.664 0.020 0.000 0.008
#> GSM955106 5 0.4719 0.35224 0.000 0.008 0.360 0.040 0.592 0.000
#> GSM955000 1 0.0653 0.89549 0.980 0.004 0.000 0.004 0.000 0.012
#> GSM955006 1 0.3337 0.84093 0.832 0.032 0.000 0.112 0.000 0.024
#> GSM955007 3 0.4303 0.23739 0.000 0.032 0.676 0.284 0.000 0.008
#> GSM955010 4 0.3652 0.65675 0.020 0.008 0.212 0.760 0.000 0.000
#> GSM955014 1 0.3123 0.84403 0.832 0.000 0.000 0.056 0.000 0.112
#> GSM955018 3 0.4093 0.42653 0.080 0.108 0.784 0.000 0.000 0.028
#> GSM955020 1 0.0146 0.89298 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM955024 3 0.3025 0.42439 0.000 0.024 0.820 0.156 0.000 0.000
#> GSM955026 6 0.5415 0.45833 0.008 0.136 0.044 0.128 0.000 0.684
#> GSM955031 6 0.6850 0.02499 0.240 0.316 0.000 0.052 0.000 0.392
#> GSM955038 6 0.5853 0.26382 0.136 0.024 0.000 0.236 0.008 0.596
#> GSM955040 4 0.5114 0.34735 0.176 0.052 0.000 0.692 0.000 0.080
#> GSM955044 4 0.6893 0.00726 0.000 0.008 0.176 0.428 0.056 0.332
#> GSM955051 1 0.1812 0.87599 0.912 0.000 0.000 0.008 0.000 0.080
#> GSM955055 2 0.4207 0.48486 0.000 0.748 0.104 0.004 0.000 0.144
#> GSM955057 1 0.1458 0.89162 0.948 0.016 0.000 0.020 0.000 0.016
#> GSM955062 2 0.6075 0.42482 0.000 0.560 0.252 0.044 0.000 0.144
#> GSM955063 3 0.3076 0.32310 0.000 0.000 0.760 0.240 0.000 0.000
#> GSM955068 6 0.3597 0.42584 0.000 0.088 0.032 0.040 0.008 0.832
#> GSM955069 3 0.4547 0.44050 0.052 0.072 0.768 0.100 0.000 0.008
#> GSM955070 4 0.3529 0.66563 0.000 0.036 0.172 0.788 0.000 0.004
#> GSM955071 1 0.7426 -0.05609 0.376 0.028 0.120 0.368 0.000 0.108
#> GSM955077 2 0.5979 0.18383 0.192 0.636 0.020 0.060 0.000 0.092
#> GSM955080 2 0.6425 -0.13423 0.000 0.456 0.084 0.024 0.396 0.040
#> GSM955081 3 0.7222 -0.18711 0.004 0.336 0.344 0.076 0.000 0.240
#> GSM955082 3 0.4895 0.07074 0.004 0.364 0.584 0.004 0.004 0.040
#> GSM955085 2 0.4437 0.41082 0.000 0.764 0.096 0.016 0.012 0.112
#> GSM955090 1 0.1777 0.88587 0.932 0.000 0.000 0.012 0.032 0.024
#> GSM955094 4 0.3302 0.66415 0.000 0.028 0.136 0.824 0.004 0.008
#> GSM955096 3 0.5294 -0.08725 0.000 0.356 0.532 0.000 0.000 0.112
#> GSM955102 3 0.5567 0.05959 0.072 0.024 0.580 0.316 0.000 0.008
#> GSM955105 3 0.5761 0.20161 0.240 0.120 0.600 0.000 0.000 0.040
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> SD:NMF 106 0.170 2
#> SD:NMF 103 0.606 3
#> SD:NMF 94 0.907 4
#> SD:NMF 70 0.811 5
#> SD:NMF 41 0.651 6
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 31589 rows and 108 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 0.430 0.814 0.886 0.3617 0.662 0.662
#> 3 3 0.259 0.544 0.712 0.5949 0.690 0.538
#> 4 4 0.313 0.586 0.733 0.1725 0.848 0.638
#> 5 5 0.393 0.525 0.681 0.0905 0.956 0.867
#> 6 6 0.444 0.324 0.609 0.0495 0.958 0.870
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
#> GSM955002 2 0.3114 0.898 0.056 0.944
#> GSM955008 2 0.4022 0.897 0.080 0.920
#> GSM955016 1 0.8555 0.682 0.720 0.280
#> GSM955019 2 0.0938 0.891 0.012 0.988
#> GSM955022 2 0.3733 0.899 0.072 0.928
#> GSM955023 2 0.3584 0.900 0.068 0.932
#> GSM955027 2 0.0938 0.890 0.012 0.988
#> GSM955043 2 0.1184 0.892 0.016 0.984
#> GSM955048 1 0.1414 0.835 0.980 0.020
#> GSM955049 2 0.1633 0.898 0.024 0.976
#> GSM955054 2 0.2423 0.901 0.040 0.960
#> GSM955064 2 0.3114 0.900 0.056 0.944
#> GSM955072 2 0.1414 0.893 0.020 0.980
#> GSM955075 2 0.2236 0.901 0.036 0.964
#> GSM955079 2 0.5408 0.879 0.124 0.876
#> GSM955087 1 0.0672 0.833 0.992 0.008
#> GSM955088 2 0.6887 0.840 0.184 0.816
#> GSM955089 1 0.1414 0.836 0.980 0.020
#> GSM955095 2 0.2778 0.902 0.048 0.952
#> GSM955097 2 0.9933 0.129 0.452 0.548
#> GSM955101 2 0.3114 0.900 0.056 0.944
#> GSM954999 1 0.9552 0.493 0.624 0.376
#> GSM955001 2 0.2043 0.901 0.032 0.968
#> GSM955003 2 0.1414 0.898 0.020 0.980
#> GSM955004 2 0.1184 0.890 0.016 0.984
#> GSM955005 2 0.4939 0.883 0.108 0.892
#> GSM955009 2 0.0672 0.889 0.008 0.992
#> GSM955011 2 0.9754 0.421 0.408 0.592
#> GSM955012 2 0.2043 0.900 0.032 0.968
#> GSM955013 2 0.6801 0.821 0.180 0.820
#> GSM955015 2 0.2603 0.901 0.044 0.956
#> GSM955017 1 0.6531 0.780 0.832 0.168
#> GSM955021 2 0.0672 0.895 0.008 0.992
#> GSM955025 2 0.2423 0.892 0.040 0.960
#> GSM955028 1 0.0672 0.833 0.992 0.008
#> GSM955029 2 0.1633 0.899 0.024 0.976
#> GSM955030 2 0.8955 0.668 0.312 0.688
#> GSM955032 2 0.5178 0.883 0.116 0.884
#> GSM955033 2 0.6712 0.816 0.176 0.824
#> GSM955034 1 0.0672 0.833 0.992 0.008
#> GSM955035 2 0.1633 0.899 0.024 0.976
#> GSM955036 2 0.5946 0.871 0.144 0.856
#> GSM955037 1 0.9044 0.514 0.680 0.320
#> GSM955039 2 0.4431 0.897 0.092 0.908
#> GSM955041 2 0.3114 0.901 0.056 0.944
#> GSM955042 1 0.9358 0.538 0.648 0.352
#> GSM955045 2 0.3114 0.901 0.056 0.944
#> GSM955046 2 0.5946 0.871 0.144 0.856
#> GSM955047 1 0.4161 0.834 0.916 0.084
#> GSM955050 2 0.7376 0.770 0.208 0.792
#> GSM955052 2 0.4939 0.886 0.108 0.892
#> GSM955053 1 0.0672 0.833 0.992 0.008
#> GSM955056 2 0.4431 0.893 0.092 0.908
#> GSM955058 2 0.1414 0.898 0.020 0.980
#> GSM955059 2 0.6623 0.850 0.172 0.828
#> GSM955060 1 0.4022 0.832 0.920 0.080
#> GSM955061 2 0.1633 0.899 0.024 0.976
#> GSM955065 1 0.0672 0.833 0.992 0.008
#> GSM955066 2 0.7745 0.788 0.228 0.772
#> GSM955067 1 0.7056 0.783 0.808 0.192
#> GSM955073 2 0.5408 0.879 0.124 0.876
#> GSM955074 1 0.8327 0.703 0.736 0.264
#> GSM955076 2 0.0672 0.889 0.008 0.992
#> GSM955078 2 0.0672 0.889 0.008 0.992
#> GSM955083 2 0.9922 0.170 0.448 0.552
#> GSM955084 2 0.1184 0.890 0.016 0.984
#> GSM955086 2 0.5294 0.883 0.120 0.880
#> GSM955091 2 0.0938 0.890 0.012 0.988
#> GSM955092 2 0.2778 0.901 0.048 0.952
#> GSM955093 2 0.5737 0.873 0.136 0.864
#> GSM955098 2 0.0672 0.889 0.008 0.992
#> GSM955099 2 0.0672 0.889 0.008 0.992
#> GSM955100 2 0.9358 0.549 0.352 0.648
#> GSM955103 2 0.4298 0.895 0.088 0.912
#> GSM955104 2 0.6438 0.854 0.164 0.836
#> GSM955106 2 0.2236 0.900 0.036 0.964
#> GSM955000 1 0.9522 0.393 0.628 0.372
#> GSM955006 2 0.9944 0.260 0.456 0.544
#> GSM955007 2 0.5294 0.885 0.120 0.880
#> GSM955010 2 0.8661 0.702 0.288 0.712
#> GSM955014 1 0.6887 0.789 0.816 0.184
#> GSM955018 2 0.6048 0.868 0.148 0.852
#> GSM955020 1 0.1633 0.837 0.976 0.024
#> GSM955024 2 0.3733 0.898 0.072 0.928
#> GSM955026 2 0.0672 0.889 0.008 0.992
#> GSM955031 2 0.6247 0.831 0.156 0.844
#> GSM955038 1 0.9988 0.256 0.520 0.480
#> GSM955040 2 0.7528 0.762 0.216 0.784
#> GSM955044 2 0.0672 0.889 0.008 0.992
#> GSM955051 1 0.3733 0.835 0.928 0.072
#> GSM955055 2 0.0672 0.892 0.008 0.992
#> GSM955057 1 0.1184 0.836 0.984 0.016
#> GSM955062 2 0.2423 0.901 0.040 0.960
#> GSM955063 2 0.5178 0.883 0.116 0.884
#> GSM955068 2 0.0672 0.889 0.008 0.992
#> GSM955069 2 0.7376 0.816 0.208 0.792
#> GSM955070 2 0.4431 0.890 0.092 0.908
#> GSM955071 2 0.5842 0.858 0.140 0.860
#> GSM955077 2 0.2043 0.894 0.032 0.968
#> GSM955080 2 0.4022 0.898 0.080 0.920
#> GSM955081 2 0.2778 0.897 0.048 0.952
#> GSM955082 2 0.4298 0.896 0.088 0.912
#> GSM955085 2 0.2043 0.896 0.032 0.968
#> GSM955090 1 0.3431 0.834 0.936 0.064
#> GSM955094 2 0.2043 0.897 0.032 0.968
#> GSM955096 2 0.4939 0.886 0.108 0.892
#> GSM955102 2 0.9922 0.312 0.448 0.552
#> GSM955105 2 0.5946 0.870 0.144 0.856
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.6318 0.1785 0.008 0.636 0.356
#> GSM955008 3 0.6500 0.5276 0.004 0.464 0.532
#> GSM955016 1 0.9248 0.6054 0.516 0.188 0.296
#> GSM955019 2 0.0892 0.7038 0.000 0.980 0.020
#> GSM955022 3 0.6483 0.5213 0.004 0.452 0.544
#> GSM955023 3 0.6495 0.5167 0.004 0.460 0.536
#> GSM955027 2 0.2959 0.6873 0.000 0.900 0.100
#> GSM955043 2 0.2066 0.7041 0.000 0.940 0.060
#> GSM955048 1 0.2939 0.7965 0.916 0.012 0.072
#> GSM955049 2 0.4399 0.5974 0.000 0.812 0.188
#> GSM955054 2 0.4796 0.5484 0.000 0.780 0.220
#> GSM955064 2 0.6267 -0.2547 0.000 0.548 0.452
#> GSM955072 2 0.1163 0.7002 0.000 0.972 0.028
#> GSM955075 2 0.2959 0.6970 0.000 0.900 0.100
#> GSM955079 3 0.6033 0.6938 0.004 0.336 0.660
#> GSM955087 1 0.1529 0.7864 0.960 0.000 0.040
#> GSM955088 3 0.7250 0.6978 0.056 0.288 0.656
#> GSM955089 1 0.2200 0.7947 0.940 0.004 0.056
#> GSM955095 2 0.3267 0.6911 0.000 0.884 0.116
#> GSM955097 2 0.9738 0.0629 0.288 0.448 0.264
#> GSM955101 2 0.6267 -0.2547 0.000 0.548 0.452
#> GSM954999 1 0.9724 0.4543 0.448 0.252 0.300
#> GSM955001 2 0.2878 0.6967 0.000 0.904 0.096
#> GSM955003 2 0.4842 0.5296 0.000 0.776 0.224
#> GSM955004 2 0.1163 0.6958 0.000 0.972 0.028
#> GSM955005 2 0.7584 -0.4605 0.040 0.488 0.472
#> GSM955009 2 0.1163 0.7014 0.000 0.972 0.028
#> GSM955011 3 0.9519 0.4092 0.292 0.224 0.484
#> GSM955012 2 0.2796 0.6978 0.000 0.908 0.092
#> GSM955013 3 0.7624 0.4668 0.052 0.368 0.580
#> GSM955015 2 0.5058 0.4948 0.000 0.756 0.244
#> GSM955017 1 0.6699 0.7228 0.700 0.044 0.256
#> GSM955021 2 0.3619 0.6584 0.000 0.864 0.136
#> GSM955025 2 0.4291 0.6480 0.008 0.840 0.152
#> GSM955028 1 0.1529 0.7864 0.960 0.000 0.040
#> GSM955029 2 0.1753 0.7047 0.000 0.952 0.048
#> GSM955030 3 0.7988 0.6119 0.144 0.200 0.656
#> GSM955032 2 0.6274 -0.2014 0.000 0.544 0.456
#> GSM955033 2 0.6744 0.4235 0.032 0.668 0.300
#> GSM955034 1 0.1529 0.7864 0.960 0.000 0.040
#> GSM955035 2 0.2796 0.6971 0.000 0.908 0.092
#> GSM955036 3 0.6051 0.7101 0.012 0.292 0.696
#> GSM955037 1 0.6209 0.4514 0.628 0.004 0.368
#> GSM955039 3 0.6647 0.6404 0.012 0.396 0.592
#> GSM955041 2 0.6192 -0.1490 0.000 0.580 0.420
#> GSM955042 1 0.9629 0.5033 0.456 0.224 0.320
#> GSM955045 2 0.5178 0.4949 0.000 0.744 0.256
#> GSM955046 3 0.6051 0.7101 0.012 0.292 0.696
#> GSM955047 1 0.5734 0.7872 0.788 0.048 0.164
#> GSM955050 3 0.8128 0.2773 0.068 0.440 0.492
#> GSM955052 3 0.6432 0.5861 0.004 0.428 0.568
#> GSM955053 1 0.1289 0.7873 0.968 0.000 0.032
#> GSM955056 2 0.6126 0.0424 0.000 0.600 0.400
#> GSM955058 2 0.1643 0.7046 0.000 0.956 0.044
#> GSM955059 3 0.6420 0.7113 0.024 0.288 0.688
#> GSM955060 1 0.5092 0.7871 0.804 0.020 0.176
#> GSM955061 2 0.1753 0.7047 0.000 0.952 0.048
#> GSM955065 1 0.1529 0.7864 0.960 0.000 0.040
#> GSM955066 3 0.7495 0.6579 0.084 0.248 0.668
#> GSM955067 1 0.8201 0.7132 0.612 0.112 0.276
#> GSM955073 3 0.5754 0.7031 0.004 0.296 0.700
#> GSM955074 1 0.9133 0.6253 0.528 0.176 0.296
#> GSM955076 2 0.2066 0.7017 0.000 0.940 0.060
#> GSM955078 2 0.0424 0.6977 0.000 0.992 0.008
#> GSM955083 2 0.9836 -0.0275 0.280 0.424 0.296
#> GSM955084 2 0.1163 0.6958 0.000 0.972 0.028
#> GSM955086 3 0.6339 0.6843 0.008 0.360 0.632
#> GSM955091 2 0.1031 0.7027 0.000 0.976 0.024
#> GSM955092 2 0.5733 0.2788 0.000 0.676 0.324
#> GSM955093 3 0.5623 0.7038 0.004 0.280 0.716
#> GSM955098 2 0.0424 0.6983 0.000 0.992 0.008
#> GSM955099 2 0.0592 0.6974 0.000 0.988 0.012
#> GSM955100 3 0.8911 0.5008 0.204 0.224 0.572
#> GSM955103 3 0.6359 0.6312 0.004 0.404 0.592
#> GSM955104 3 0.6501 0.7047 0.020 0.316 0.664
#> GSM955106 2 0.2959 0.6954 0.000 0.900 0.100
#> GSM955000 1 0.7747 0.2831 0.544 0.052 0.404
#> GSM955006 3 0.9500 0.2361 0.344 0.196 0.460
#> GSM955007 3 0.6102 0.7037 0.008 0.320 0.672
#> GSM955010 3 0.8103 0.6305 0.120 0.248 0.632
#> GSM955014 1 0.8142 0.7169 0.620 0.112 0.268
#> GSM955018 3 0.6445 0.7101 0.020 0.308 0.672
#> GSM955020 1 0.2301 0.7956 0.936 0.004 0.060
#> GSM955024 3 0.6309 0.4086 0.000 0.500 0.500
#> GSM955026 2 0.1289 0.6953 0.000 0.968 0.032
#> GSM955031 2 0.8350 -0.1313 0.088 0.532 0.380
#> GSM955038 2 0.9963 -0.2990 0.348 0.360 0.292
#> GSM955040 3 0.8273 0.2002 0.076 0.448 0.476
#> GSM955044 2 0.1289 0.6904 0.000 0.968 0.032
#> GSM955051 1 0.5778 0.7823 0.768 0.032 0.200
#> GSM955055 2 0.2356 0.7007 0.000 0.928 0.072
#> GSM955057 1 0.3038 0.7958 0.896 0.000 0.104
#> GSM955062 2 0.5327 0.4469 0.000 0.728 0.272
#> GSM955063 3 0.5591 0.7026 0.000 0.304 0.696
#> GSM955068 2 0.0237 0.6988 0.000 0.996 0.004
#> GSM955069 3 0.6875 0.6969 0.056 0.244 0.700
#> GSM955070 2 0.4931 0.5883 0.000 0.768 0.232
#> GSM955071 2 0.7993 -0.3855 0.060 0.484 0.456
#> GSM955077 2 0.3644 0.6796 0.004 0.872 0.124
#> GSM955080 2 0.4473 0.6522 0.008 0.828 0.164
#> GSM955081 2 0.6062 0.3810 0.016 0.708 0.276
#> GSM955082 3 0.6676 0.4790 0.008 0.476 0.516
#> GSM955085 2 0.3482 0.6807 0.000 0.872 0.128
#> GSM955090 1 0.5849 0.7771 0.756 0.028 0.216
#> GSM955094 2 0.2878 0.6993 0.000 0.904 0.096
#> GSM955096 3 0.6168 0.6132 0.000 0.412 0.588
#> GSM955102 3 0.5831 0.3191 0.284 0.008 0.708
#> GSM955105 3 0.6313 0.7119 0.016 0.308 0.676
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.6801 0.00307 0.000 0.456 0.448 0.096
#> GSM955008 3 0.4775 0.61489 0.000 0.232 0.740 0.028
#> GSM955016 4 0.6625 0.63620 0.184 0.076 0.052 0.688
#> GSM955019 2 0.3128 0.76481 0.000 0.884 0.076 0.040
#> GSM955022 3 0.5361 0.62518 0.000 0.208 0.724 0.068
#> GSM955023 3 0.5397 0.61924 0.000 0.220 0.716 0.064
#> GSM955027 2 0.4323 0.74496 0.000 0.788 0.184 0.028
#> GSM955043 2 0.3856 0.76560 0.000 0.832 0.136 0.032
#> GSM955048 1 0.4737 0.51781 0.728 0.000 0.020 0.252
#> GSM955049 2 0.4908 0.63609 0.000 0.692 0.292 0.016
#> GSM955054 2 0.5807 0.46094 0.000 0.596 0.364 0.040
#> GSM955064 3 0.5289 0.42805 0.000 0.344 0.636 0.020
#> GSM955072 2 0.3323 0.76097 0.000 0.876 0.060 0.064
#> GSM955075 2 0.4500 0.73013 0.000 0.776 0.192 0.032
#> GSM955079 3 0.2631 0.70837 0.008 0.064 0.912 0.016
#> GSM955087 1 0.0188 0.71104 0.996 0.000 0.004 0.000
#> GSM955088 3 0.5164 0.70719 0.044 0.056 0.796 0.104
#> GSM955089 1 0.2329 0.70257 0.916 0.000 0.012 0.072
#> GSM955095 2 0.4831 0.71721 0.000 0.752 0.208 0.040
#> GSM955097 4 0.8678 0.39683 0.092 0.316 0.128 0.464
#> GSM955101 3 0.5306 0.42039 0.000 0.348 0.632 0.020
#> GSM954999 4 0.6589 0.64427 0.108 0.104 0.076 0.712
#> GSM955001 2 0.4919 0.73745 0.000 0.752 0.200 0.048
#> GSM955003 2 0.5812 0.52475 0.000 0.624 0.328 0.048
#> GSM955004 2 0.2565 0.74536 0.000 0.912 0.032 0.056
#> GSM955005 3 0.7029 0.50161 0.024 0.308 0.584 0.084
#> GSM955009 2 0.3088 0.74148 0.000 0.888 0.052 0.060
#> GSM955011 3 0.9142 0.30204 0.224 0.100 0.440 0.236
#> GSM955012 2 0.4245 0.73543 0.000 0.784 0.196 0.020
#> GSM955013 3 0.7308 0.52021 0.004 0.188 0.552 0.256
#> GSM955015 2 0.5912 0.27961 0.000 0.524 0.440 0.036
#> GSM955017 1 0.6757 0.40425 0.572 0.000 0.120 0.308
#> GSM955021 2 0.5184 0.70053 0.000 0.732 0.212 0.056
#> GSM955025 2 0.5650 0.69915 0.000 0.716 0.180 0.104
#> GSM955028 1 0.0188 0.71104 0.996 0.000 0.004 0.000
#> GSM955029 2 0.3495 0.75702 0.000 0.844 0.140 0.016
#> GSM955030 3 0.6396 0.60341 0.108 0.028 0.700 0.164
#> GSM955032 3 0.5393 0.46657 0.008 0.272 0.692 0.028
#> GSM955033 2 0.7290 0.32282 0.000 0.504 0.168 0.328
#> GSM955034 1 0.0188 0.71104 0.996 0.000 0.004 0.000
#> GSM955035 2 0.4549 0.73932 0.000 0.776 0.188 0.036
#> GSM955036 3 0.3574 0.71263 0.016 0.064 0.876 0.044
#> GSM955037 1 0.5453 0.35972 0.660 0.000 0.304 0.036
#> GSM955039 3 0.4685 0.68936 0.000 0.156 0.784 0.060
#> GSM955041 3 0.5313 0.35515 0.000 0.376 0.608 0.016
#> GSM955042 4 0.6161 0.64271 0.108 0.084 0.068 0.740
#> GSM955045 2 0.5693 0.27998 0.000 0.504 0.472 0.024
#> GSM955046 3 0.3574 0.71263 0.016 0.064 0.876 0.044
#> GSM955047 1 0.5395 0.45312 0.628 0.016 0.004 0.352
#> GSM955050 3 0.8239 0.30199 0.016 0.244 0.408 0.332
#> GSM955052 3 0.4199 0.65958 0.000 0.164 0.804 0.032
#> GSM955053 1 0.0657 0.71068 0.984 0.000 0.004 0.012
#> GSM955056 3 0.6098 0.34489 0.000 0.316 0.616 0.068
#> GSM955058 2 0.3390 0.75870 0.000 0.852 0.132 0.016
#> GSM955059 3 0.4255 0.71607 0.024 0.056 0.844 0.076
#> GSM955060 1 0.5331 0.50828 0.644 0.000 0.024 0.332
#> GSM955061 2 0.3597 0.75539 0.000 0.836 0.148 0.016
#> GSM955065 1 0.0188 0.71104 0.996 0.000 0.004 0.000
#> GSM955066 3 0.5910 0.66671 0.068 0.044 0.744 0.144
#> GSM955067 4 0.7144 0.44966 0.340 0.056 0.044 0.560
#> GSM955073 3 0.1624 0.70359 0.000 0.028 0.952 0.020
#> GSM955074 4 0.6546 0.63059 0.192 0.076 0.044 0.688
#> GSM955076 2 0.3833 0.74131 0.000 0.848 0.080 0.072
#> GSM955078 2 0.2408 0.75386 0.000 0.920 0.044 0.036
#> GSM955083 4 0.8058 0.52305 0.072 0.268 0.112 0.548
#> GSM955084 2 0.2565 0.74536 0.000 0.912 0.032 0.056
#> GSM955086 3 0.3313 0.71311 0.008 0.084 0.880 0.028
#> GSM955091 2 0.2660 0.76136 0.000 0.908 0.056 0.036
#> GSM955092 2 0.6213 0.14758 0.000 0.484 0.464 0.052
#> GSM955093 3 0.1962 0.70461 0.008 0.024 0.944 0.024
#> GSM955098 2 0.2816 0.74068 0.000 0.900 0.036 0.064
#> GSM955099 2 0.2773 0.75988 0.000 0.900 0.072 0.028
#> GSM955100 3 0.7712 0.36220 0.100 0.040 0.512 0.348
#> GSM955103 3 0.4277 0.68340 0.004 0.172 0.800 0.024
#> GSM955104 3 0.4014 0.71785 0.008 0.064 0.848 0.080
#> GSM955106 2 0.4485 0.72666 0.000 0.772 0.200 0.028
#> GSM955000 1 0.6635 0.22568 0.524 0.000 0.388 0.088
#> GSM955006 3 0.9311 0.15614 0.284 0.096 0.384 0.236
#> GSM955007 3 0.4149 0.71111 0.020 0.096 0.844 0.040
#> GSM955010 3 0.6672 0.58494 0.088 0.036 0.672 0.204
#> GSM955014 4 0.7083 0.43744 0.344 0.056 0.040 0.560
#> GSM955018 3 0.2780 0.71151 0.024 0.048 0.912 0.016
#> GSM955020 1 0.2342 0.70076 0.912 0.000 0.008 0.080
#> GSM955024 3 0.4857 0.54213 0.000 0.284 0.700 0.016
#> GSM955026 2 0.3156 0.72467 0.000 0.884 0.048 0.068
#> GSM955031 3 0.8602 0.16707 0.044 0.348 0.408 0.200
#> GSM955038 4 0.5964 0.62514 0.036 0.192 0.052 0.720
#> GSM955040 3 0.8414 0.18963 0.020 0.268 0.360 0.352
#> GSM955044 2 0.2222 0.71646 0.000 0.924 0.016 0.060
#> GSM955051 1 0.4888 0.35460 0.588 0.000 0.000 0.412
#> GSM955055 2 0.4337 0.75113 0.000 0.808 0.140 0.052
#> GSM955057 1 0.3569 0.63343 0.804 0.000 0.000 0.196
#> GSM955062 2 0.5510 0.43655 0.000 0.600 0.376 0.024
#> GSM955063 3 0.1796 0.70429 0.004 0.032 0.948 0.016
#> GSM955068 2 0.2840 0.75143 0.000 0.900 0.044 0.056
#> GSM955069 3 0.4277 0.70152 0.052 0.028 0.844 0.076
#> GSM955070 2 0.6790 0.54026 0.000 0.604 0.228 0.168
#> GSM955071 3 0.7879 0.43394 0.020 0.288 0.508 0.184
#> GSM955077 2 0.5277 0.71967 0.000 0.752 0.132 0.116
#> GSM955080 2 0.6513 0.65636 0.004 0.640 0.236 0.120
#> GSM955081 2 0.6626 0.34710 0.000 0.544 0.364 0.092
#> GSM955082 3 0.5366 0.60564 0.004 0.240 0.712 0.044
#> GSM955085 2 0.5454 0.73250 0.000 0.732 0.172 0.096
#> GSM955090 4 0.4843 0.13484 0.396 0.000 0.000 0.604
#> GSM955094 2 0.4720 0.74415 0.000 0.768 0.188 0.044
#> GSM955096 3 0.4050 0.67334 0.000 0.144 0.820 0.036
#> GSM955102 3 0.5857 0.41485 0.308 0.000 0.636 0.056
#> GSM955105 3 0.3232 0.71368 0.012 0.028 0.888 0.072
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.7263 0.0332 0.000 0.404 0.412 0.080 0.104
#> GSM955008 3 0.5006 0.6040 0.000 0.184 0.712 0.004 0.100
#> GSM955016 4 0.4642 0.5628 0.120 0.032 0.020 0.792 0.036
#> GSM955019 2 0.4186 0.6923 0.000 0.796 0.064 0.012 0.128
#> GSM955022 3 0.5714 0.5916 0.000 0.184 0.688 0.072 0.056
#> GSM955023 3 0.5681 0.5863 0.000 0.196 0.684 0.072 0.048
#> GSM955027 2 0.4693 0.6701 0.000 0.752 0.148 0.008 0.092
#> GSM955043 2 0.4671 0.6837 0.000 0.776 0.092 0.028 0.104
#> GSM955048 1 0.5212 0.5169 0.696 0.000 0.016 0.216 0.072
#> GSM955049 2 0.5586 0.5534 0.000 0.648 0.260 0.020 0.072
#> GSM955054 2 0.6460 0.3029 0.000 0.476 0.356 0.004 0.164
#> GSM955064 3 0.5886 0.4410 0.000 0.288 0.608 0.020 0.084
#> GSM955072 2 0.4566 0.6767 0.000 0.768 0.032 0.040 0.160
#> GSM955075 2 0.5843 0.6194 0.000 0.684 0.168 0.056 0.092
#> GSM955079 3 0.2619 0.6814 0.004 0.024 0.896 0.004 0.072
#> GSM955087 1 0.0404 0.7224 0.988 0.000 0.000 0.000 0.012
#> GSM955088 3 0.5212 0.6530 0.028 0.032 0.756 0.048 0.136
#> GSM955089 1 0.2214 0.7137 0.916 0.000 0.004 0.052 0.028
#> GSM955095 2 0.6011 0.6042 0.000 0.664 0.184 0.052 0.100
#> GSM955097 4 0.7663 0.4499 0.052 0.204 0.080 0.564 0.100
#> GSM955101 3 0.5886 0.4426 0.000 0.288 0.608 0.020 0.084
#> GSM954999 4 0.3992 0.5826 0.040 0.036 0.024 0.844 0.056
#> GSM955001 2 0.5533 0.6456 0.000 0.684 0.176 0.016 0.124
#> GSM955003 2 0.6470 0.4147 0.000 0.552 0.308 0.032 0.108
#> GSM955004 2 0.3936 0.6494 0.000 0.800 0.004 0.052 0.144
#> GSM955005 3 0.7091 0.4609 0.024 0.276 0.560 0.064 0.076
#> GSM955009 2 0.4402 0.6085 0.000 0.688 0.012 0.008 0.292
#> GSM955011 3 0.9139 0.2259 0.220 0.064 0.384 0.184 0.148
#> GSM955012 2 0.5574 0.6265 0.000 0.696 0.176 0.036 0.092
#> GSM955013 3 0.7162 0.4048 0.000 0.144 0.504 0.292 0.060
#> GSM955015 2 0.6546 0.1292 0.000 0.428 0.412 0.008 0.152
#> GSM955017 1 0.7350 0.4458 0.520 0.000 0.080 0.224 0.176
#> GSM955021 2 0.6218 0.5361 0.000 0.544 0.152 0.004 0.300
#> GSM955025 2 0.6718 0.5968 0.000 0.596 0.120 0.072 0.212
#> GSM955028 1 0.0404 0.7224 0.988 0.000 0.000 0.000 0.012
#> GSM955029 2 0.4971 0.6629 0.000 0.752 0.112 0.028 0.108
#> GSM955030 3 0.6631 0.5626 0.100 0.016 0.656 0.124 0.104
#> GSM955032 3 0.5572 0.5265 0.004 0.112 0.660 0.004 0.220
#> GSM955033 2 0.7665 0.1380 0.000 0.428 0.124 0.336 0.112
#> GSM955034 1 0.0404 0.7224 0.988 0.000 0.000 0.000 0.012
#> GSM955035 2 0.5533 0.6440 0.000 0.684 0.176 0.016 0.124
#> GSM955036 3 0.4296 0.6726 0.008 0.048 0.808 0.024 0.112
#> GSM955037 1 0.5271 0.3930 0.652 0.000 0.284 0.016 0.048
#> GSM955039 3 0.4958 0.6619 0.000 0.136 0.756 0.056 0.052
#> GSM955041 3 0.5949 0.3752 0.000 0.328 0.576 0.020 0.076
#> GSM955042 4 0.3422 0.5757 0.044 0.020 0.020 0.872 0.044
#> GSM955045 2 0.6412 0.1576 0.000 0.436 0.432 0.012 0.120
#> GSM955046 3 0.4296 0.6726 0.008 0.048 0.808 0.024 0.112
#> GSM955047 1 0.6414 0.4849 0.560 0.012 0.000 0.248 0.180
#> GSM955050 4 0.8513 -0.1377 0.012 0.176 0.324 0.344 0.144
#> GSM955052 3 0.4425 0.6385 0.000 0.112 0.772 0.004 0.112
#> GSM955053 1 0.0290 0.7222 0.992 0.000 0.000 0.008 0.000
#> GSM955056 3 0.6380 0.3791 0.000 0.176 0.524 0.004 0.296
#> GSM955058 2 0.4874 0.6659 0.000 0.760 0.104 0.028 0.108
#> GSM955059 3 0.4298 0.6834 0.016 0.040 0.824 0.064 0.056
#> GSM955060 1 0.6190 0.5197 0.584 0.000 0.008 0.236 0.172
#> GSM955061 2 0.5063 0.6598 0.000 0.744 0.120 0.028 0.108
#> GSM955065 1 0.0404 0.7224 0.988 0.000 0.000 0.000 0.012
#> GSM955066 3 0.6759 0.5923 0.048 0.040 0.644 0.100 0.168
#> GSM955067 4 0.6023 0.3433 0.272 0.020 0.008 0.620 0.080
#> GSM955073 3 0.1877 0.6744 0.000 0.012 0.924 0.000 0.064
#> GSM955074 4 0.4694 0.5543 0.128 0.036 0.012 0.784 0.040
#> GSM955076 2 0.4774 0.5936 0.000 0.644 0.016 0.012 0.328
#> GSM955078 2 0.3116 0.6679 0.000 0.852 0.012 0.012 0.124
#> GSM955083 4 0.6580 0.5230 0.028 0.188 0.056 0.648 0.080
#> GSM955084 2 0.3936 0.6494 0.000 0.800 0.004 0.052 0.144
#> GSM955086 3 0.3368 0.6883 0.004 0.040 0.856 0.008 0.092
#> GSM955091 2 0.3405 0.6880 0.000 0.848 0.036 0.012 0.104
#> GSM955092 3 0.6780 -0.0323 0.000 0.368 0.404 0.004 0.224
#> GSM955093 3 0.1798 0.6723 0.004 0.004 0.928 0.000 0.064
#> GSM955098 2 0.4323 0.6458 0.000 0.760 0.020 0.024 0.196
#> GSM955099 2 0.2929 0.6903 0.000 0.876 0.044 0.004 0.076
#> GSM955100 3 0.7990 0.2561 0.088 0.012 0.448 0.280 0.172
#> GSM955103 3 0.4495 0.6577 0.004 0.148 0.776 0.012 0.060
#> GSM955104 3 0.4228 0.6895 0.008 0.048 0.824 0.068 0.052
#> GSM955106 2 0.5814 0.6192 0.000 0.684 0.172 0.052 0.092
#> GSM955000 1 0.6411 0.2525 0.528 0.000 0.356 0.044 0.072
#> GSM955006 3 0.9151 0.0895 0.284 0.052 0.328 0.192 0.144
#> GSM955007 3 0.4593 0.6775 0.012 0.068 0.792 0.020 0.108
#> GSM955010 3 0.7038 0.5074 0.072 0.020 0.612 0.160 0.136
#> GSM955014 4 0.6094 0.3308 0.276 0.020 0.008 0.612 0.084
#> GSM955018 3 0.2797 0.6826 0.020 0.016 0.896 0.008 0.060
#> GSM955020 1 0.2104 0.7126 0.916 0.000 0.000 0.060 0.024
#> GSM955024 3 0.5060 0.5374 0.000 0.240 0.688 0.008 0.064
#> GSM955026 2 0.4765 0.6242 0.000 0.728 0.020 0.040 0.212
#> GSM955031 3 0.8821 0.0712 0.024 0.264 0.300 0.124 0.288
#> GSM955038 4 0.3750 0.5893 0.004 0.096 0.012 0.836 0.052
#> GSM955040 4 0.8529 0.0181 0.012 0.172 0.268 0.384 0.164
#> GSM955044 2 0.4285 0.6191 0.000 0.752 0.008 0.032 0.208
#> GSM955051 1 0.6170 0.3838 0.524 0.000 0.000 0.320 0.156
#> GSM955055 2 0.5516 0.6150 0.000 0.624 0.088 0.004 0.284
#> GSM955057 1 0.4020 0.6650 0.796 0.000 0.000 0.108 0.096
#> GSM955062 2 0.6092 0.3539 0.000 0.552 0.340 0.016 0.092
#> GSM955063 3 0.1682 0.6795 0.000 0.012 0.940 0.004 0.044
#> GSM955068 2 0.3943 0.6651 0.000 0.796 0.020 0.020 0.164
#> GSM955069 3 0.4216 0.6637 0.040 0.008 0.824 0.068 0.060
#> GSM955070 2 0.7345 0.4517 0.000 0.536 0.188 0.180 0.096
#> GSM955071 3 0.8255 0.3901 0.016 0.232 0.452 0.176 0.124
#> GSM955077 2 0.6715 0.5538 0.004 0.548 0.068 0.068 0.312
#> GSM955080 2 0.7484 0.5184 0.000 0.528 0.192 0.144 0.136
#> GSM955081 2 0.7096 0.2516 0.000 0.488 0.332 0.064 0.116
#> GSM955082 3 0.5935 0.5845 0.004 0.196 0.660 0.024 0.116
#> GSM955085 2 0.6885 0.5901 0.000 0.548 0.108 0.068 0.276
#> GSM955090 4 0.6024 0.1487 0.296 0.000 0.000 0.556 0.148
#> GSM955094 2 0.5475 0.6548 0.000 0.720 0.136 0.052 0.092
#> GSM955096 3 0.4049 0.6495 0.000 0.084 0.792 0.000 0.124
#> GSM955102 3 0.5913 0.4074 0.296 0.000 0.588 0.008 0.108
#> GSM955105 3 0.3587 0.6757 0.000 0.012 0.824 0.024 0.140
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.7246 -0.20933 0.000 0.388 0.376 0.076 0.028 0.132
#> GSM955008 3 0.5711 0.33874 0.000 0.176 0.628 0.004 0.032 0.160
#> GSM955016 4 0.4024 0.47882 0.032 0.016 0.012 0.796 0.136 0.008
#> GSM955019 2 0.3980 0.49057 0.000 0.780 0.056 0.012 0.004 0.148
#> GSM955022 3 0.6028 0.37730 0.000 0.184 0.644 0.068 0.036 0.068
#> GSM955023 3 0.5967 0.37074 0.000 0.192 0.644 0.064 0.032 0.068
#> GSM955027 2 0.4104 0.47978 0.000 0.772 0.132 0.000 0.016 0.080
#> GSM955043 2 0.4624 0.48916 0.000 0.764 0.056 0.020 0.040 0.120
#> GSM955048 1 0.5913 -0.04133 0.548 0.000 0.016 0.208 0.228 0.000
#> GSM955049 2 0.5110 0.37107 0.000 0.656 0.232 0.004 0.012 0.096
#> GSM955054 2 0.6515 0.03273 0.000 0.432 0.304 0.004 0.020 0.240
#> GSM955064 3 0.6305 0.24140 0.000 0.276 0.544 0.008 0.048 0.124
#> GSM955072 2 0.4330 0.47484 0.000 0.748 0.020 0.028 0.016 0.188
#> GSM955075 2 0.5928 0.46055 0.000 0.660 0.128 0.040 0.040 0.132
#> GSM955079 3 0.4006 0.48502 0.004 0.028 0.800 0.008 0.036 0.124
#> GSM955087 1 0.0000 0.68490 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955088 3 0.6296 0.35934 0.016 0.032 0.632 0.028 0.152 0.140
#> GSM955089 1 0.2380 0.62205 0.892 0.000 0.004 0.036 0.068 0.000
#> GSM955095 2 0.6149 0.44460 0.000 0.640 0.148 0.040 0.048 0.124
#> GSM955097 4 0.7275 0.34122 0.012 0.156 0.076 0.568 0.084 0.104
#> GSM955101 3 0.6305 0.24207 0.000 0.276 0.544 0.008 0.048 0.124
#> GSM954999 4 0.2450 0.49640 0.012 0.020 0.004 0.908 0.036 0.020
#> GSM955001 2 0.5427 0.44129 0.000 0.676 0.160 0.016 0.024 0.124
#> GSM955003 2 0.6188 0.13642 0.000 0.516 0.284 0.032 0.000 0.168
#> GSM955004 2 0.4509 0.47928 0.000 0.744 0.004 0.040 0.044 0.168
#> GSM955005 3 0.7586 0.07407 0.024 0.264 0.492 0.052 0.076 0.092
#> GSM955009 2 0.4249 0.28269 0.000 0.624 0.008 0.004 0.008 0.356
#> GSM955011 3 0.9286 -0.08493 0.188 0.068 0.324 0.148 0.192 0.080
#> GSM955012 2 0.5659 0.46682 0.000 0.668 0.140 0.020 0.036 0.136
#> GSM955013 3 0.7336 0.15013 0.000 0.124 0.472 0.280 0.060 0.064
#> GSM955015 2 0.6810 -0.00444 0.000 0.388 0.344 0.008 0.032 0.228
#> GSM955017 5 0.7081 0.57707 0.336 0.000 0.068 0.124 0.444 0.028
#> GSM955021 2 0.5875 0.10378 0.000 0.496 0.124 0.000 0.020 0.360
#> GSM955025 2 0.6444 0.15490 0.000 0.548 0.080 0.064 0.024 0.284
#> GSM955028 1 0.0000 0.68490 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955029 2 0.4817 0.49808 0.000 0.740 0.088 0.012 0.032 0.128
#> GSM955030 3 0.6999 0.33136 0.080 0.012 0.588 0.084 0.172 0.064
#> GSM955032 3 0.5943 0.19263 0.004 0.096 0.572 0.008 0.028 0.292
#> GSM955033 2 0.7713 -0.06278 0.000 0.396 0.076 0.332 0.084 0.112
#> GSM955034 1 0.0000 0.68490 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955035 2 0.5185 0.44659 0.000 0.676 0.156 0.012 0.008 0.148
#> GSM955036 3 0.5683 0.46863 0.004 0.036 0.684 0.028 0.136 0.112
#> GSM955037 1 0.5369 0.30599 0.660 0.000 0.212 0.004 0.084 0.040
#> GSM955039 3 0.5515 0.47092 0.000 0.128 0.704 0.060 0.036 0.072
#> GSM955041 3 0.6420 0.17514 0.000 0.316 0.508 0.008 0.052 0.116
#> GSM955042 4 0.1967 0.49272 0.016 0.012 0.004 0.928 0.036 0.004
#> GSM955045 2 0.6534 0.06477 0.000 0.416 0.380 0.004 0.036 0.164
#> GSM955046 3 0.5683 0.46863 0.004 0.036 0.684 0.028 0.136 0.112
#> GSM955047 5 0.5702 0.72117 0.304 0.004 0.000 0.148 0.540 0.004
#> GSM955050 4 0.8540 -0.29532 0.000 0.160 0.256 0.332 0.128 0.124
#> GSM955052 3 0.5279 0.39379 0.000 0.120 0.684 0.004 0.036 0.156
#> GSM955053 1 0.0692 0.67651 0.976 0.000 0.000 0.004 0.020 0.000
#> GSM955056 3 0.6541 -0.17475 0.000 0.160 0.412 0.000 0.048 0.380
#> GSM955058 2 0.4729 0.49996 0.000 0.748 0.084 0.012 0.032 0.124
#> GSM955059 3 0.4698 0.50098 0.016 0.024 0.784 0.052 0.076 0.048
#> GSM955060 5 0.5792 0.71078 0.344 0.000 0.004 0.132 0.512 0.008
#> GSM955061 2 0.4910 0.49656 0.000 0.732 0.096 0.012 0.032 0.128
#> GSM955065 1 0.0000 0.68490 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955066 3 0.7578 0.23985 0.028 0.040 0.516 0.068 0.200 0.148
#> GSM955067 4 0.5615 0.22502 0.116 0.008 0.000 0.592 0.272 0.012
#> GSM955073 3 0.3510 0.49611 0.000 0.012 0.828 0.004 0.072 0.084
#> GSM955074 4 0.4062 0.47179 0.036 0.016 0.004 0.788 0.144 0.012
#> GSM955076 2 0.4063 0.23364 0.000 0.572 0.004 0.000 0.004 0.420
#> GSM955078 2 0.2865 0.48112 0.000 0.840 0.000 0.008 0.012 0.140
#> GSM955083 4 0.5490 0.42837 0.008 0.164 0.028 0.700 0.056 0.044
#> GSM955084 2 0.4509 0.47928 0.000 0.744 0.004 0.040 0.044 0.168
#> GSM955086 3 0.4444 0.47372 0.004 0.040 0.768 0.008 0.040 0.140
#> GSM955091 2 0.3091 0.50291 0.000 0.844 0.028 0.008 0.004 0.116
#> GSM955092 2 0.6486 -0.27792 0.000 0.340 0.336 0.000 0.016 0.308
#> GSM955093 3 0.3569 0.49322 0.000 0.004 0.820 0.008 0.084 0.084
#> GSM955098 2 0.4377 0.41369 0.000 0.708 0.012 0.012 0.024 0.244
#> GSM955099 2 0.2420 0.51359 0.000 0.888 0.032 0.000 0.004 0.076
#> GSM955100 3 0.8431 -0.05782 0.060 0.016 0.352 0.232 0.244 0.096
#> GSM955103 3 0.5218 0.45953 0.000 0.160 0.704 0.012 0.048 0.076
#> GSM955104 3 0.4765 0.50143 0.004 0.056 0.776 0.060 0.064 0.040
#> GSM955106 2 0.5901 0.46053 0.000 0.660 0.132 0.036 0.040 0.132
#> GSM955000 1 0.6670 0.13991 0.508 0.000 0.280 0.016 0.148 0.048
#> GSM955006 3 0.9310 -0.14215 0.244 0.056 0.276 0.164 0.180 0.080
#> GSM955007 3 0.5765 0.47267 0.008 0.060 0.684 0.016 0.112 0.120
#> GSM955010 3 0.7545 0.23488 0.056 0.020 0.528 0.136 0.188 0.072
#> GSM955014 4 0.5716 0.18811 0.120 0.008 0.000 0.572 0.288 0.012
#> GSM955018 3 0.4297 0.48743 0.016 0.024 0.792 0.008 0.048 0.112
#> GSM955020 1 0.2376 0.61564 0.888 0.000 0.000 0.044 0.068 0.000
#> GSM955024 3 0.5380 0.34235 0.000 0.248 0.636 0.004 0.028 0.084
#> GSM955026 2 0.5075 0.38047 0.000 0.660 0.008 0.032 0.044 0.256
#> GSM955031 6 0.8553 0.00000 0.000 0.248 0.200 0.076 0.180 0.296
#> GSM955038 4 0.2958 0.50585 0.000 0.060 0.000 0.864 0.016 0.060
#> GSM955040 4 0.8470 -0.31981 0.000 0.148 0.188 0.380 0.128 0.156
#> GSM955044 2 0.4595 0.42868 0.000 0.684 0.008 0.008 0.044 0.256
#> GSM955051 5 0.6248 0.59981 0.308 0.000 0.000 0.240 0.440 0.012
#> GSM955055 2 0.5210 0.25773 0.000 0.576 0.068 0.000 0.016 0.340
#> GSM955057 1 0.4087 0.30487 0.744 0.000 0.000 0.064 0.188 0.004
#> GSM955062 2 0.6020 0.20770 0.000 0.552 0.304 0.012 0.028 0.104
#> GSM955063 3 0.3387 0.50979 0.000 0.016 0.840 0.004 0.068 0.072
#> GSM955068 2 0.3706 0.45403 0.000 0.772 0.008 0.012 0.012 0.196
#> GSM955069 3 0.4875 0.48785 0.036 0.012 0.772 0.056 0.080 0.044
#> GSM955070 2 0.7332 0.16528 0.000 0.520 0.136 0.184 0.048 0.112
#> GSM955071 3 0.8378 -0.23016 0.000 0.236 0.372 0.156 0.104 0.132
#> GSM955077 2 0.6322 0.03497 0.000 0.488 0.040 0.064 0.032 0.376
#> GSM955080 2 0.7628 0.28955 0.000 0.496 0.136 0.140 0.064 0.164
#> GSM955081 2 0.7110 -0.10143 0.000 0.468 0.300 0.064 0.032 0.136
#> GSM955082 3 0.5961 0.33036 0.000 0.220 0.600 0.012 0.028 0.140
#> GSM955085 2 0.6394 0.11507 0.000 0.496 0.064 0.064 0.020 0.356
#> GSM955090 4 0.5830 -0.01230 0.132 0.000 0.000 0.508 0.344 0.016
#> GSM955094 2 0.5521 0.45060 0.000 0.708 0.084 0.048 0.048 0.112
#> GSM955096 3 0.5223 0.40370 0.000 0.096 0.688 0.004 0.040 0.172
#> GSM955102 3 0.6778 0.19994 0.304 0.000 0.476 0.004 0.128 0.088
#> GSM955105 3 0.5258 0.37934 0.000 0.008 0.644 0.004 0.136 0.208
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> CV:hclust 100 0.940 2
#> CV:hclust 79 0.999 3
#> CV:hclust 78 0.956 4
#> CV:hclust 75 0.942 5
#> CV:hclust 17 0.499 6
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 31589 rows and 108 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 0.799 0.898 0.954 0.3898 0.641 0.641
#> 3 3 0.772 0.853 0.915 0.6550 0.693 0.526
#> 4 4 0.555 0.585 0.775 0.1358 0.855 0.624
#> 5 5 0.555 0.468 0.695 0.0726 0.893 0.645
#> 6 6 0.589 0.417 0.648 0.0468 0.884 0.532
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
#> GSM955002 2 0.0000 0.9422 0.000 1.000
#> GSM955008 2 0.0000 0.9422 0.000 1.000
#> GSM955016 1 0.0000 0.9782 1.000 0.000
#> GSM955019 2 0.0000 0.9422 0.000 1.000
#> GSM955022 2 0.0000 0.9422 0.000 1.000
#> GSM955023 2 0.0000 0.9422 0.000 1.000
#> GSM955027 2 0.0000 0.9422 0.000 1.000
#> GSM955043 2 0.0000 0.9422 0.000 1.000
#> GSM955048 1 0.0000 0.9782 1.000 0.000
#> GSM955049 2 0.0000 0.9422 0.000 1.000
#> GSM955054 2 0.0000 0.9422 0.000 1.000
#> GSM955064 2 0.0000 0.9422 0.000 1.000
#> GSM955072 2 0.0000 0.9422 0.000 1.000
#> GSM955075 2 0.0000 0.9422 0.000 1.000
#> GSM955079 2 0.3431 0.8995 0.064 0.936
#> GSM955087 1 0.0000 0.9782 1.000 0.000
#> GSM955088 2 0.7219 0.7721 0.200 0.800
#> GSM955089 1 0.0000 0.9782 1.000 0.000
#> GSM955095 2 0.0000 0.9422 0.000 1.000
#> GSM955097 2 0.6247 0.8199 0.156 0.844
#> GSM955101 2 0.0000 0.9422 0.000 1.000
#> GSM954999 2 0.9491 0.5064 0.368 0.632
#> GSM955001 2 0.0000 0.9422 0.000 1.000
#> GSM955003 2 0.0000 0.9422 0.000 1.000
#> GSM955004 2 0.0000 0.9422 0.000 1.000
#> GSM955005 2 0.0672 0.9379 0.008 0.992
#> GSM955009 2 0.0000 0.9422 0.000 1.000
#> GSM955011 1 0.0000 0.9782 1.000 0.000
#> GSM955012 2 0.0000 0.9422 0.000 1.000
#> GSM955013 2 0.0672 0.9378 0.008 0.992
#> GSM955015 2 0.0000 0.9422 0.000 1.000
#> GSM955017 1 0.0000 0.9782 1.000 0.000
#> GSM955021 2 0.0000 0.9422 0.000 1.000
#> GSM955025 2 0.0000 0.9422 0.000 1.000
#> GSM955028 1 0.0000 0.9782 1.000 0.000
#> GSM955029 2 0.0000 0.9422 0.000 1.000
#> GSM955030 2 0.9460 0.5145 0.364 0.636
#> GSM955032 2 0.1633 0.9279 0.024 0.976
#> GSM955033 2 0.0000 0.9422 0.000 1.000
#> GSM955034 1 0.0000 0.9782 1.000 0.000
#> GSM955035 2 0.0000 0.9422 0.000 1.000
#> GSM955036 2 0.9580 0.4802 0.380 0.620
#> GSM955037 1 0.0000 0.9782 1.000 0.000
#> GSM955039 2 0.0000 0.9422 0.000 1.000
#> GSM955041 2 0.0000 0.9422 0.000 1.000
#> GSM955042 1 0.0000 0.9782 1.000 0.000
#> GSM955045 2 0.0000 0.9422 0.000 1.000
#> GSM955046 2 0.7219 0.7722 0.200 0.800
#> GSM955047 1 0.0000 0.9782 1.000 0.000
#> GSM955050 2 0.0000 0.9422 0.000 1.000
#> GSM955052 2 0.0000 0.9422 0.000 1.000
#> GSM955053 1 0.0000 0.9782 1.000 0.000
#> GSM955056 2 0.0000 0.9422 0.000 1.000
#> GSM955058 2 0.0000 0.9422 0.000 1.000
#> GSM955059 2 0.7602 0.7482 0.220 0.780
#> GSM955060 1 0.0000 0.9782 1.000 0.000
#> GSM955061 2 0.0000 0.9422 0.000 1.000
#> GSM955065 1 0.0000 0.9782 1.000 0.000
#> GSM955066 2 0.9129 0.5838 0.328 0.672
#> GSM955067 1 0.0000 0.9782 1.000 0.000
#> GSM955073 2 0.0000 0.9422 0.000 1.000
#> GSM955074 1 0.0000 0.9782 1.000 0.000
#> GSM955076 2 0.0000 0.9422 0.000 1.000
#> GSM955078 2 0.0000 0.9422 0.000 1.000
#> GSM955083 2 0.5946 0.8309 0.144 0.856
#> GSM955084 2 0.0000 0.9422 0.000 1.000
#> GSM955086 2 0.5842 0.8349 0.140 0.860
#> GSM955091 2 0.0000 0.9422 0.000 1.000
#> GSM955092 2 0.0000 0.9422 0.000 1.000
#> GSM955093 2 0.7745 0.7379 0.228 0.772
#> GSM955098 2 0.0000 0.9422 0.000 1.000
#> GSM955099 2 0.0000 0.9422 0.000 1.000
#> GSM955100 1 0.0000 0.9782 1.000 0.000
#> GSM955103 2 0.0000 0.9422 0.000 1.000
#> GSM955104 2 0.9286 0.5542 0.344 0.656
#> GSM955106 2 0.0000 0.9422 0.000 1.000
#> GSM955000 1 0.0000 0.9782 1.000 0.000
#> GSM955006 1 0.0000 0.9782 1.000 0.000
#> GSM955007 2 0.0376 0.9401 0.004 0.996
#> GSM955010 2 0.9710 0.4332 0.400 0.600
#> GSM955014 1 0.0000 0.9782 1.000 0.000
#> GSM955018 2 0.7745 0.7379 0.228 0.772
#> GSM955020 1 0.0000 0.9782 1.000 0.000
#> GSM955024 2 0.0000 0.9422 0.000 1.000
#> GSM955026 2 0.0000 0.9422 0.000 1.000
#> GSM955031 2 0.0000 0.9422 0.000 1.000
#> GSM955038 2 0.0000 0.9422 0.000 1.000
#> GSM955040 2 0.2423 0.9168 0.040 0.960
#> GSM955044 2 0.0000 0.9422 0.000 1.000
#> GSM955051 1 0.0000 0.9782 1.000 0.000
#> GSM955055 2 0.0000 0.9422 0.000 1.000
#> GSM955057 1 0.0000 0.9782 1.000 0.000
#> GSM955062 2 0.0000 0.9422 0.000 1.000
#> GSM955063 2 0.0938 0.9355 0.012 0.988
#> GSM955068 2 0.0000 0.9422 0.000 1.000
#> GSM955069 2 0.9580 0.4802 0.380 0.620
#> GSM955070 2 0.0000 0.9422 0.000 1.000
#> GSM955071 2 0.4431 0.8768 0.092 0.908
#> GSM955077 2 0.0000 0.9422 0.000 1.000
#> GSM955080 2 0.0000 0.9422 0.000 1.000
#> GSM955081 2 0.0000 0.9422 0.000 1.000
#> GSM955082 2 0.0000 0.9422 0.000 1.000
#> GSM955085 2 0.0000 0.9422 0.000 1.000
#> GSM955090 1 0.0000 0.9782 1.000 0.000
#> GSM955094 2 0.0000 0.9422 0.000 1.000
#> GSM955096 2 0.0000 0.9422 0.000 1.000
#> GSM955102 1 0.9963 -0.0373 0.536 0.464
#> GSM955105 2 0.7528 0.7534 0.216 0.784
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.4346 0.767 0.000 0.816 0.184
#> GSM955008 3 0.3879 0.818 0.000 0.152 0.848
#> GSM955016 1 0.2804 0.954 0.924 0.016 0.060
#> GSM955019 2 0.1289 0.913 0.000 0.968 0.032
#> GSM955022 3 0.2165 0.880 0.000 0.064 0.936
#> GSM955023 3 0.5882 0.522 0.000 0.348 0.652
#> GSM955027 2 0.1289 0.913 0.000 0.968 0.032
#> GSM955043 2 0.0592 0.911 0.000 0.988 0.012
#> GSM955048 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955049 2 0.1860 0.907 0.000 0.948 0.052
#> GSM955054 3 0.6235 0.327 0.000 0.436 0.564
#> GSM955064 2 0.1753 0.912 0.000 0.952 0.048
#> GSM955072 2 0.0237 0.911 0.000 0.996 0.004
#> GSM955075 2 0.0592 0.911 0.000 0.988 0.012
#> GSM955079 3 0.1643 0.883 0.000 0.044 0.956
#> GSM955087 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955088 3 0.1399 0.883 0.004 0.028 0.968
#> GSM955089 1 0.0237 0.980 0.996 0.000 0.004
#> GSM955095 2 0.4291 0.771 0.000 0.820 0.180
#> GSM955097 2 0.5656 0.619 0.004 0.712 0.284
#> GSM955101 3 0.3116 0.851 0.000 0.108 0.892
#> GSM954999 3 0.2269 0.856 0.016 0.040 0.944
#> GSM955001 2 0.1163 0.914 0.000 0.972 0.028
#> GSM955003 3 0.6235 0.327 0.000 0.436 0.564
#> GSM955004 2 0.0237 0.909 0.000 0.996 0.004
#> GSM955005 3 0.1289 0.884 0.000 0.032 0.968
#> GSM955009 2 0.1289 0.913 0.000 0.968 0.032
#> GSM955011 1 0.1647 0.977 0.960 0.004 0.036
#> GSM955012 2 0.1289 0.905 0.000 0.968 0.032
#> GSM955013 3 0.2356 0.875 0.000 0.072 0.928
#> GSM955015 2 0.6280 0.038 0.000 0.540 0.460
#> GSM955017 1 0.1289 0.981 0.968 0.000 0.032
#> GSM955021 2 0.1860 0.907 0.000 0.948 0.052
#> GSM955025 2 0.1163 0.913 0.000 0.972 0.028
#> GSM955028 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955029 2 0.0592 0.911 0.000 0.988 0.012
#> GSM955030 3 0.1751 0.866 0.028 0.012 0.960
#> GSM955032 3 0.1643 0.883 0.000 0.044 0.956
#> GSM955033 2 0.4555 0.752 0.000 0.800 0.200
#> GSM955034 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955035 2 0.1643 0.910 0.000 0.956 0.044
#> GSM955036 3 0.2173 0.871 0.008 0.048 0.944
#> GSM955037 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955039 3 0.1964 0.878 0.000 0.056 0.944
#> GSM955041 2 0.2625 0.890 0.000 0.916 0.084
#> GSM955042 1 0.1647 0.978 0.960 0.004 0.036
#> GSM955045 2 0.5016 0.695 0.000 0.760 0.240
#> GSM955046 3 0.2384 0.878 0.008 0.056 0.936
#> GSM955047 1 0.1289 0.979 0.968 0.000 0.032
#> GSM955050 2 0.4931 0.710 0.000 0.768 0.232
#> GSM955052 3 0.1964 0.879 0.000 0.056 0.944
#> GSM955053 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955056 3 0.3551 0.835 0.000 0.132 0.868
#> GSM955058 2 0.0592 0.911 0.000 0.988 0.012
#> GSM955059 3 0.1585 0.883 0.008 0.028 0.964
#> GSM955060 1 0.0892 0.981 0.980 0.000 0.020
#> GSM955061 2 0.0592 0.911 0.000 0.988 0.012
#> GSM955065 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955066 3 0.1751 0.877 0.012 0.028 0.960
#> GSM955067 1 0.1950 0.974 0.952 0.008 0.040
#> GSM955073 3 0.1753 0.881 0.000 0.048 0.952
#> GSM955074 1 0.2229 0.970 0.944 0.012 0.044
#> GSM955076 2 0.1860 0.907 0.000 0.948 0.052
#> GSM955078 2 0.0237 0.911 0.000 0.996 0.004
#> GSM955083 3 0.6075 0.522 0.008 0.316 0.676
#> GSM955084 2 0.0237 0.909 0.000 0.996 0.004
#> GSM955086 3 0.1643 0.883 0.000 0.044 0.956
#> GSM955091 2 0.1163 0.914 0.000 0.972 0.028
#> GSM955092 2 0.5016 0.694 0.000 0.760 0.240
#> GSM955093 3 0.1585 0.883 0.008 0.028 0.964
#> GSM955098 2 0.1163 0.913 0.000 0.972 0.028
#> GSM955099 2 0.1163 0.914 0.000 0.972 0.028
#> GSM955100 1 0.1647 0.977 0.960 0.004 0.036
#> GSM955103 3 0.2711 0.873 0.000 0.088 0.912
#> GSM955104 3 0.1781 0.877 0.020 0.020 0.960
#> GSM955106 2 0.1411 0.903 0.000 0.964 0.036
#> GSM955000 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955006 1 0.1289 0.979 0.968 0.000 0.032
#> GSM955007 3 0.2165 0.880 0.000 0.064 0.936
#> GSM955010 3 0.2902 0.845 0.064 0.016 0.920
#> GSM955014 1 0.1529 0.978 0.960 0.000 0.040
#> GSM955018 3 0.1585 0.883 0.008 0.028 0.964
#> GSM955020 1 0.0237 0.980 0.996 0.000 0.004
#> GSM955024 3 0.2537 0.874 0.000 0.080 0.920
#> GSM955026 2 0.1163 0.913 0.000 0.972 0.028
#> GSM955031 3 0.6192 0.365 0.000 0.420 0.580
#> GSM955038 2 0.3310 0.852 0.064 0.908 0.028
#> GSM955040 2 0.5763 0.627 0.008 0.716 0.276
#> GSM955044 2 0.0424 0.911 0.000 0.992 0.008
#> GSM955051 1 0.1289 0.979 0.968 0.000 0.032
#> GSM955055 2 0.1289 0.913 0.000 0.968 0.032
#> GSM955057 1 0.0424 0.980 0.992 0.000 0.008
#> GSM955062 2 0.1964 0.905 0.000 0.944 0.056
#> GSM955063 3 0.1411 0.883 0.000 0.036 0.964
#> GSM955068 2 0.0000 0.910 0.000 1.000 0.000
#> GSM955069 3 0.2443 0.877 0.032 0.028 0.940
#> GSM955070 2 0.1031 0.914 0.000 0.976 0.024
#> GSM955071 3 0.3941 0.798 0.000 0.156 0.844
#> GSM955077 2 0.1411 0.911 0.000 0.964 0.036
#> GSM955080 2 0.5216 0.646 0.000 0.740 0.260
#> GSM955081 3 0.6291 0.222 0.000 0.468 0.532
#> GSM955082 3 0.5810 0.502 0.000 0.336 0.664
#> GSM955085 2 0.1031 0.914 0.000 0.976 0.024
#> GSM955090 1 0.1529 0.978 0.960 0.000 0.040
#> GSM955094 2 0.2165 0.885 0.000 0.936 0.064
#> GSM955096 3 0.2066 0.878 0.000 0.060 0.940
#> GSM955102 3 0.4291 0.746 0.180 0.000 0.820
#> GSM955105 3 0.1411 0.883 0.000 0.036 0.964
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.4804 0.6560 0.000 0.780 0.072 0.148
#> GSM955008 3 0.2805 0.7166 0.000 0.100 0.888 0.012
#> GSM955016 4 0.4920 -0.2613 0.368 0.000 0.004 0.628
#> GSM955019 2 0.1677 0.7182 0.000 0.948 0.012 0.040
#> GSM955022 3 0.4980 0.6125 0.000 0.016 0.680 0.304
#> GSM955023 3 0.6483 0.3231 0.000 0.312 0.592 0.096
#> GSM955027 2 0.3697 0.7212 0.000 0.852 0.048 0.100
#> GSM955043 2 0.4456 0.6194 0.000 0.716 0.004 0.280
#> GSM955048 1 0.0592 0.8115 0.984 0.000 0.000 0.016
#> GSM955049 2 0.4227 0.6953 0.000 0.820 0.120 0.060
#> GSM955054 2 0.5846 0.1814 0.000 0.516 0.452 0.032
#> GSM955064 2 0.5947 0.6339 0.000 0.688 0.112 0.200
#> GSM955072 2 0.1978 0.7172 0.000 0.928 0.004 0.068
#> GSM955075 2 0.5075 0.5790 0.000 0.644 0.012 0.344
#> GSM955079 3 0.1297 0.7758 0.000 0.016 0.964 0.020
#> GSM955087 1 0.0000 0.8078 1.000 0.000 0.000 0.000
#> GSM955088 3 0.1637 0.7774 0.000 0.000 0.940 0.060
#> GSM955089 1 0.0817 0.8131 0.976 0.000 0.000 0.024
#> GSM955095 4 0.7115 -0.2000 0.000 0.420 0.128 0.452
#> GSM955097 4 0.4798 0.3978 0.000 0.180 0.052 0.768
#> GSM955101 3 0.2796 0.7232 0.000 0.092 0.892 0.016
#> GSM954999 4 0.4295 0.3180 0.008 0.000 0.240 0.752
#> GSM955001 2 0.3587 0.7234 0.000 0.856 0.040 0.104
#> GSM955003 2 0.5688 0.1664 0.000 0.512 0.464 0.024
#> GSM955004 2 0.3837 0.6710 0.000 0.776 0.000 0.224
#> GSM955005 3 0.3356 0.7356 0.000 0.000 0.824 0.176
#> GSM955009 2 0.2101 0.7179 0.000 0.928 0.012 0.060
#> GSM955011 1 0.4972 0.5565 0.544 0.000 0.000 0.456
#> GSM955012 2 0.5291 0.5753 0.000 0.652 0.024 0.324
#> GSM955013 4 0.5500 -0.2688 0.000 0.016 0.464 0.520
#> GSM955015 3 0.7431 0.0158 0.000 0.380 0.448 0.172
#> GSM955017 1 0.3311 0.7938 0.828 0.000 0.000 0.172
#> GSM955021 2 0.3659 0.6778 0.000 0.840 0.136 0.024
#> GSM955025 2 0.2342 0.7082 0.000 0.912 0.008 0.080
#> GSM955028 1 0.0000 0.8078 1.000 0.000 0.000 0.000
#> GSM955029 2 0.5038 0.6030 0.000 0.684 0.020 0.296
#> GSM955030 3 0.3688 0.7055 0.000 0.000 0.792 0.208
#> GSM955032 3 0.1510 0.7784 0.000 0.016 0.956 0.028
#> GSM955033 4 0.4332 0.4729 0.000 0.176 0.032 0.792
#> GSM955034 1 0.0000 0.8078 1.000 0.000 0.000 0.000
#> GSM955035 2 0.2611 0.7062 0.000 0.896 0.096 0.008
#> GSM955036 4 0.5168 -0.2970 0.000 0.004 0.496 0.500
#> GSM955037 1 0.3088 0.7279 0.864 0.000 0.008 0.128
#> GSM955039 3 0.5038 0.5657 0.000 0.012 0.652 0.336
#> GSM955041 2 0.6756 0.5419 0.000 0.612 0.200 0.188
#> GSM955042 1 0.4999 0.4961 0.508 0.000 0.000 0.492
#> GSM955045 2 0.7818 0.1847 0.000 0.408 0.268 0.324
#> GSM955046 3 0.4049 0.6990 0.000 0.008 0.780 0.212
#> GSM955047 1 0.4250 0.7557 0.724 0.000 0.000 0.276
#> GSM955050 4 0.5038 0.3724 0.000 0.336 0.012 0.652
#> GSM955052 3 0.1284 0.7688 0.000 0.024 0.964 0.012
#> GSM955053 1 0.0000 0.8078 1.000 0.000 0.000 0.000
#> GSM955056 3 0.3320 0.7323 0.000 0.068 0.876 0.056
#> GSM955058 2 0.5085 0.5971 0.000 0.676 0.020 0.304
#> GSM955059 3 0.2081 0.7712 0.000 0.000 0.916 0.084
#> GSM955060 1 0.2589 0.8051 0.884 0.000 0.000 0.116
#> GSM955061 2 0.5152 0.5864 0.000 0.664 0.020 0.316
#> GSM955065 1 0.0000 0.8078 1.000 0.000 0.000 0.000
#> GSM955066 3 0.3726 0.7075 0.000 0.000 0.788 0.212
#> GSM955067 1 0.4679 0.6920 0.648 0.000 0.000 0.352
#> GSM955073 3 0.0524 0.7772 0.000 0.004 0.988 0.008
#> GSM955074 4 0.4998 -0.5166 0.488 0.000 0.000 0.512
#> GSM955076 2 0.3370 0.6937 0.000 0.872 0.080 0.048
#> GSM955078 2 0.2704 0.7132 0.000 0.876 0.000 0.124
#> GSM955083 4 0.4057 0.4268 0.000 0.032 0.152 0.816
#> GSM955084 2 0.3610 0.6825 0.000 0.800 0.000 0.200
#> GSM955086 3 0.1610 0.7780 0.000 0.016 0.952 0.032
#> GSM955091 2 0.1151 0.7285 0.000 0.968 0.008 0.024
#> GSM955092 2 0.6100 0.5277 0.000 0.644 0.272 0.084
#> GSM955093 3 0.1118 0.7782 0.000 0.000 0.964 0.036
#> GSM955098 2 0.2402 0.7080 0.000 0.912 0.012 0.076
#> GSM955099 2 0.1489 0.7312 0.000 0.952 0.004 0.044
#> GSM955100 1 0.5168 0.4901 0.504 0.000 0.004 0.492
#> GSM955103 3 0.5907 0.5223 0.000 0.080 0.668 0.252
#> GSM955104 3 0.3837 0.6886 0.000 0.000 0.776 0.224
#> GSM955106 2 0.5517 0.4777 0.000 0.568 0.020 0.412
#> GSM955000 1 0.0469 0.8060 0.988 0.000 0.000 0.012
#> GSM955006 1 0.4406 0.7392 0.700 0.000 0.000 0.300
#> GSM955007 3 0.3718 0.7273 0.000 0.012 0.820 0.168
#> GSM955010 3 0.5110 0.5161 0.012 0.000 0.636 0.352
#> GSM955014 1 0.4277 0.7527 0.720 0.000 0.000 0.280
#> GSM955018 3 0.1022 0.7784 0.000 0.000 0.968 0.032
#> GSM955020 1 0.1022 0.8134 0.968 0.000 0.000 0.032
#> GSM955024 3 0.4378 0.6729 0.000 0.040 0.796 0.164
#> GSM955026 2 0.2473 0.7071 0.000 0.908 0.012 0.080
#> GSM955031 2 0.6889 0.1914 0.000 0.496 0.396 0.108
#> GSM955038 4 0.4999 0.0643 0.000 0.492 0.000 0.508
#> GSM955040 4 0.5130 0.3776 0.000 0.332 0.016 0.652
#> GSM955044 2 0.3448 0.6985 0.000 0.828 0.004 0.168
#> GSM955051 1 0.4222 0.7561 0.728 0.000 0.000 0.272
#> GSM955055 2 0.2675 0.7288 0.000 0.908 0.044 0.048
#> GSM955057 1 0.0817 0.8131 0.976 0.000 0.000 0.024
#> GSM955062 2 0.3427 0.7017 0.000 0.860 0.112 0.028
#> GSM955063 3 0.0592 0.7786 0.000 0.000 0.984 0.016
#> GSM955068 2 0.2053 0.7129 0.000 0.924 0.004 0.072
#> GSM955069 3 0.2868 0.7470 0.000 0.000 0.864 0.136
#> GSM955070 2 0.3625 0.7066 0.000 0.828 0.012 0.160
#> GSM955071 3 0.6759 0.3614 0.000 0.108 0.548 0.344
#> GSM955077 2 0.2805 0.6937 0.000 0.888 0.012 0.100
#> GSM955080 4 0.7300 -0.0673 0.000 0.372 0.156 0.472
#> GSM955081 2 0.6007 0.3064 0.000 0.548 0.408 0.044
#> GSM955082 3 0.6341 0.4067 0.000 0.212 0.652 0.136
#> GSM955085 2 0.2197 0.7245 0.000 0.916 0.004 0.080
#> GSM955090 1 0.4406 0.7383 0.700 0.000 0.000 0.300
#> GSM955094 2 0.5582 0.4956 0.000 0.620 0.032 0.348
#> GSM955096 3 0.1520 0.7707 0.000 0.024 0.956 0.020
#> GSM955102 3 0.6286 0.5680 0.200 0.000 0.660 0.140
#> GSM955105 3 0.1510 0.7784 0.000 0.016 0.956 0.028
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.6196 0.4366 0.000 0.652 0.080 0.080 0.188
#> GSM955008 3 0.4322 0.6105 0.000 0.084 0.804 0.032 0.080
#> GSM955016 4 0.4098 0.4316 0.156 0.000 0.000 0.780 0.064
#> GSM955019 2 0.1117 0.6381 0.000 0.964 0.000 0.020 0.016
#> GSM955022 3 0.6066 0.2934 0.000 0.000 0.456 0.120 0.424
#> GSM955023 3 0.7470 0.1367 0.000 0.260 0.444 0.048 0.248
#> GSM955027 2 0.5375 0.4950 0.000 0.652 0.036 0.032 0.280
#> GSM955043 5 0.4644 0.3419 0.000 0.380 0.004 0.012 0.604
#> GSM955048 1 0.2361 0.7536 0.892 0.000 0.000 0.096 0.012
#> GSM955049 2 0.6106 0.5205 0.000 0.644 0.152 0.032 0.172
#> GSM955054 2 0.6704 0.3644 0.000 0.520 0.332 0.044 0.104
#> GSM955064 2 0.7186 0.1343 0.000 0.420 0.144 0.048 0.388
#> GSM955072 2 0.3011 0.5852 0.000 0.844 0.000 0.016 0.140
#> GSM955075 5 0.4359 0.4973 0.000 0.288 0.004 0.016 0.692
#> GSM955079 3 0.2305 0.6963 0.000 0.044 0.916 0.012 0.028
#> GSM955087 1 0.0404 0.7451 0.988 0.000 0.000 0.000 0.012
#> GSM955088 3 0.3339 0.7040 0.000 0.008 0.856 0.068 0.068
#> GSM955089 1 0.2338 0.7502 0.884 0.000 0.000 0.112 0.004
#> GSM955095 5 0.4851 0.5768 0.000 0.104 0.040 0.088 0.768
#> GSM955097 5 0.4592 0.3870 0.000 0.028 0.016 0.232 0.724
#> GSM955101 3 0.4844 0.5816 0.000 0.116 0.764 0.032 0.088
#> GSM954999 4 0.3779 0.4976 0.004 0.000 0.056 0.816 0.124
#> GSM955001 2 0.5287 0.5033 0.000 0.668 0.036 0.032 0.264
#> GSM955003 2 0.6652 0.3648 0.000 0.508 0.352 0.040 0.100
#> GSM955004 2 0.4397 0.0793 0.000 0.564 0.000 0.004 0.432
#> GSM955005 3 0.5039 0.6490 0.000 0.000 0.700 0.184 0.116
#> GSM955009 2 0.1018 0.6351 0.000 0.968 0.000 0.016 0.016
#> GSM955011 4 0.4109 0.2714 0.260 0.000 0.008 0.724 0.008
#> GSM955012 5 0.4207 0.4953 0.000 0.276 0.008 0.008 0.708
#> GSM955013 5 0.6976 -0.0714 0.000 0.012 0.228 0.348 0.412
#> GSM955015 5 0.8008 0.0883 0.000 0.272 0.268 0.088 0.372
#> GSM955017 1 0.4520 0.6331 0.680 0.000 0.008 0.296 0.016
#> GSM955021 2 0.4995 0.5900 0.000 0.752 0.120 0.032 0.096
#> GSM955025 2 0.1211 0.6308 0.000 0.960 0.000 0.024 0.016
#> GSM955028 1 0.0404 0.7451 0.988 0.000 0.000 0.000 0.012
#> GSM955029 5 0.4464 0.3837 0.000 0.356 0.004 0.008 0.632
#> GSM955030 3 0.5704 0.5797 0.000 0.000 0.620 0.232 0.148
#> GSM955032 3 0.3501 0.6953 0.000 0.056 0.856 0.028 0.060
#> GSM955033 4 0.6010 0.1641 0.000 0.060 0.024 0.512 0.404
#> GSM955034 1 0.0404 0.7451 0.988 0.000 0.000 0.000 0.012
#> GSM955035 2 0.4474 0.6216 0.000 0.796 0.076 0.040 0.088
#> GSM955036 4 0.6726 -0.0706 0.000 0.000 0.252 0.388 0.360
#> GSM955037 1 0.5059 0.4448 0.728 0.000 0.080 0.172 0.020
#> GSM955039 3 0.7114 0.1830 0.000 0.012 0.368 0.336 0.284
#> GSM955041 2 0.7020 0.0441 0.000 0.412 0.144 0.036 0.408
#> GSM955042 4 0.4026 0.3291 0.244 0.000 0.000 0.736 0.020
#> GSM955045 5 0.5346 0.4982 0.000 0.084 0.200 0.020 0.696
#> GSM955046 3 0.6061 0.5572 0.000 0.000 0.576 0.212 0.212
#> GSM955047 1 0.4597 0.4740 0.564 0.000 0.000 0.424 0.012
#> GSM955050 4 0.6608 0.3229 0.000 0.264 0.016 0.536 0.184
#> GSM955052 3 0.2887 0.6733 0.000 0.028 0.884 0.016 0.072
#> GSM955053 1 0.0404 0.7451 0.988 0.000 0.000 0.000 0.012
#> GSM955056 3 0.5789 0.5652 0.000 0.104 0.688 0.048 0.160
#> GSM955058 5 0.4387 0.4160 0.000 0.336 0.004 0.008 0.652
#> GSM955059 3 0.4450 0.6703 0.000 0.000 0.760 0.132 0.108
#> GSM955060 1 0.3967 0.6610 0.724 0.000 0.000 0.264 0.012
#> GSM955061 5 0.4181 0.4523 0.000 0.316 0.004 0.004 0.676
#> GSM955065 1 0.0404 0.7451 0.988 0.000 0.000 0.000 0.012
#> GSM955066 3 0.5917 0.5721 0.000 0.000 0.596 0.224 0.180
#> GSM955067 4 0.4744 -0.3500 0.476 0.000 0.000 0.508 0.016
#> GSM955073 3 0.1741 0.7048 0.000 0.000 0.936 0.024 0.040
#> GSM955074 4 0.4029 0.3463 0.232 0.000 0.000 0.744 0.024
#> GSM955076 2 0.1989 0.6357 0.000 0.932 0.032 0.016 0.020
#> GSM955078 2 0.3662 0.4538 0.000 0.744 0.000 0.004 0.252
#> GSM955083 4 0.4880 0.3149 0.000 0.000 0.036 0.616 0.348
#> GSM955084 2 0.4415 0.1716 0.000 0.604 0.000 0.008 0.388
#> GSM955086 3 0.3091 0.6991 0.000 0.044 0.880 0.032 0.044
#> GSM955091 2 0.3340 0.5989 0.000 0.824 0.004 0.016 0.156
#> GSM955092 2 0.7194 0.2399 0.000 0.416 0.380 0.040 0.164
#> GSM955093 3 0.2504 0.7030 0.000 0.000 0.896 0.064 0.040
#> GSM955098 2 0.1106 0.6315 0.000 0.964 0.000 0.024 0.012
#> GSM955099 2 0.3967 0.5741 0.000 0.772 0.008 0.020 0.200
#> GSM955100 4 0.4411 0.3315 0.232 0.000 0.012 0.732 0.024
#> GSM955103 5 0.6771 -0.1753 0.000 0.076 0.428 0.060 0.436
#> GSM955104 3 0.5554 0.5060 0.000 0.000 0.592 0.316 0.092
#> GSM955106 5 0.4522 0.5613 0.000 0.192 0.004 0.060 0.744
#> GSM955000 1 0.2363 0.7123 0.912 0.000 0.012 0.052 0.024
#> GSM955006 4 0.4562 -0.3812 0.492 0.000 0.000 0.500 0.008
#> GSM955007 3 0.5475 0.5648 0.000 0.000 0.604 0.088 0.308
#> GSM955010 3 0.6349 0.2907 0.000 0.000 0.424 0.416 0.160
#> GSM955014 1 0.4504 0.4665 0.564 0.000 0.000 0.428 0.008
#> GSM955018 3 0.1549 0.7074 0.000 0.000 0.944 0.040 0.016
#> GSM955020 1 0.2843 0.7392 0.848 0.000 0.000 0.144 0.008
#> GSM955024 3 0.5970 0.3994 0.000 0.040 0.572 0.048 0.340
#> GSM955026 2 0.1195 0.6310 0.000 0.960 0.000 0.028 0.012
#> GSM955031 2 0.6738 0.3814 0.000 0.560 0.280 0.088 0.072
#> GSM955038 4 0.5534 0.1751 0.000 0.424 0.000 0.508 0.068
#> GSM955040 4 0.5198 0.4644 0.000 0.196 0.004 0.692 0.108
#> GSM955044 2 0.4629 0.4135 0.000 0.688 0.012 0.020 0.280
#> GSM955051 1 0.4590 0.4738 0.568 0.000 0.000 0.420 0.012
#> GSM955055 2 0.4126 0.6159 0.000 0.800 0.028 0.032 0.140
#> GSM955057 1 0.2513 0.7500 0.876 0.000 0.000 0.116 0.008
#> GSM955062 2 0.4644 0.6081 0.000 0.780 0.084 0.032 0.104
#> GSM955063 3 0.2171 0.7067 0.000 0.000 0.912 0.024 0.064
#> GSM955068 2 0.1800 0.6197 0.000 0.932 0.000 0.020 0.048
#> GSM955069 3 0.4294 0.6677 0.000 0.000 0.768 0.152 0.080
#> GSM955070 2 0.6135 0.2515 0.000 0.544 0.036 0.060 0.360
#> GSM955071 4 0.6958 -0.0586 0.004 0.072 0.344 0.504 0.076
#> GSM955077 2 0.1978 0.6230 0.000 0.928 0.004 0.044 0.024
#> GSM955080 5 0.4581 0.5473 0.000 0.076 0.040 0.096 0.788
#> GSM955081 2 0.6646 0.4022 0.000 0.536 0.320 0.048 0.096
#> GSM955082 3 0.6554 0.3259 0.000 0.156 0.580 0.032 0.232
#> GSM955085 2 0.2522 0.6019 0.000 0.880 0.000 0.012 0.108
#> GSM955090 1 0.4637 0.4127 0.536 0.000 0.000 0.452 0.012
#> GSM955094 5 0.6112 0.4127 0.000 0.300 0.012 0.116 0.572
#> GSM955096 3 0.3452 0.6677 0.000 0.068 0.856 0.020 0.056
#> GSM955102 3 0.7350 0.4640 0.224 0.000 0.520 0.176 0.080
#> GSM955105 3 0.3448 0.6914 0.000 0.052 0.860 0.032 0.056
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.6740 0.3156 0.000 0.552 0.036 0.044 0.176 0.192
#> GSM955008 6 0.4766 0.0608 0.000 0.044 0.400 0.000 0.004 0.552
#> GSM955016 4 0.2747 0.5564 0.068 0.000 0.008 0.880 0.036 0.008
#> GSM955019 2 0.1391 0.6188 0.000 0.944 0.000 0.000 0.016 0.040
#> GSM955022 5 0.6522 0.0422 0.000 0.000 0.356 0.048 0.436 0.160
#> GSM955023 6 0.7642 0.3883 0.000 0.172 0.156 0.020 0.224 0.428
#> GSM955027 2 0.5896 0.2932 0.000 0.460 0.000 0.000 0.224 0.316
#> GSM955043 5 0.5280 0.3620 0.000 0.236 0.000 0.004 0.612 0.148
#> GSM955048 1 0.2846 0.7560 0.856 0.000 0.000 0.084 0.000 0.060
#> GSM955049 6 0.6193 -0.0630 0.000 0.392 0.024 0.000 0.156 0.428
#> GSM955054 6 0.6519 0.2177 0.000 0.368 0.076 0.024 0.056 0.476
#> GSM955064 6 0.6383 0.1427 0.000 0.256 0.016 0.004 0.260 0.464
#> GSM955072 2 0.3798 0.5636 0.000 0.748 0.000 0.004 0.216 0.032
#> GSM955075 5 0.2709 0.5895 0.000 0.132 0.000 0.000 0.848 0.020
#> GSM955079 3 0.4301 0.4996 0.000 0.004 0.660 0.024 0.004 0.308
#> GSM955087 1 0.0000 0.7933 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955088 3 0.4063 0.5623 0.000 0.012 0.752 0.028 0.008 0.200
#> GSM955089 1 0.2831 0.7377 0.840 0.000 0.000 0.136 0.000 0.024
#> GSM955095 5 0.3039 0.6002 0.000 0.032 0.040 0.028 0.876 0.024
#> GSM955097 5 0.3529 0.5363 0.000 0.008 0.028 0.148 0.808 0.008
#> GSM955101 6 0.5117 0.2220 0.000 0.076 0.336 0.008 0.000 0.580
#> GSM954999 4 0.3345 0.5349 0.000 0.000 0.068 0.844 0.052 0.036
#> GSM955001 2 0.6310 0.1357 0.000 0.376 0.000 0.008 0.288 0.328
#> GSM955003 6 0.5863 0.2279 0.000 0.368 0.072 0.012 0.028 0.520
#> GSM955004 5 0.4128 -0.0457 0.000 0.488 0.000 0.004 0.504 0.004
#> GSM955005 3 0.4209 0.6197 0.000 0.000 0.780 0.056 0.052 0.112
#> GSM955009 2 0.2144 0.6045 0.000 0.908 0.008 0.004 0.012 0.068
#> GSM955011 4 0.5764 0.4829 0.148 0.000 0.072 0.668 0.016 0.096
#> GSM955012 5 0.3655 0.5782 0.000 0.112 0.000 0.000 0.792 0.096
#> GSM955013 5 0.7514 0.1660 0.000 0.008 0.204 0.232 0.412 0.144
#> GSM955015 6 0.7714 0.2465 0.000 0.168 0.116 0.028 0.320 0.368
#> GSM955017 1 0.6505 0.3944 0.568 0.000 0.076 0.228 0.016 0.112
#> GSM955021 2 0.5295 0.1699 0.000 0.488 0.004 0.008 0.064 0.436
#> GSM955025 2 0.1942 0.5999 0.000 0.916 0.000 0.012 0.008 0.064
#> GSM955028 1 0.0000 0.7933 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955029 5 0.4154 0.5164 0.000 0.144 0.000 0.000 0.744 0.112
#> GSM955030 3 0.3842 0.6110 0.000 0.000 0.812 0.068 0.052 0.068
#> GSM955032 3 0.4626 0.4899 0.000 0.000 0.652 0.028 0.024 0.296
#> GSM955033 4 0.7130 0.0560 0.000 0.056 0.060 0.444 0.348 0.092
#> GSM955034 1 0.0000 0.7933 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955035 2 0.5385 0.2363 0.000 0.516 0.004 0.008 0.076 0.396
#> GSM955036 3 0.7206 0.1959 0.000 0.004 0.404 0.272 0.236 0.084
#> GSM955037 1 0.4329 0.4636 0.700 0.000 0.240 0.056 0.000 0.004
#> GSM955039 3 0.7784 0.2182 0.000 0.008 0.348 0.200 0.204 0.240
#> GSM955041 6 0.6927 0.1635 0.000 0.248 0.040 0.012 0.264 0.436
#> GSM955042 4 0.2852 0.5504 0.100 0.000 0.004 0.864 0.016 0.016
#> GSM955045 5 0.5792 0.4304 0.000 0.040 0.112 0.016 0.644 0.188
#> GSM955046 3 0.4972 0.5698 0.000 0.004 0.732 0.080 0.100 0.084
#> GSM955047 4 0.6008 0.1507 0.384 0.000 0.000 0.464 0.024 0.128
#> GSM955050 4 0.7896 0.2542 0.000 0.208 0.044 0.412 0.216 0.120
#> GSM955052 6 0.4128 -0.2468 0.000 0.000 0.492 0.004 0.004 0.500
#> GSM955053 1 0.0000 0.7933 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955056 6 0.6719 0.0715 0.000 0.048 0.356 0.032 0.096 0.468
#> GSM955058 5 0.3985 0.5486 0.000 0.140 0.000 0.000 0.760 0.100
#> GSM955059 3 0.1332 0.6339 0.000 0.000 0.952 0.028 0.012 0.008
#> GSM955060 1 0.5496 0.3841 0.588 0.000 0.000 0.280 0.016 0.116
#> GSM955061 5 0.3718 0.5720 0.000 0.132 0.000 0.000 0.784 0.084
#> GSM955065 1 0.0000 0.7933 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955066 3 0.4445 0.5921 0.000 0.000 0.768 0.076 0.080 0.076
#> GSM955067 4 0.4945 0.2922 0.344 0.004 0.000 0.584 0.000 0.068
#> GSM955073 3 0.3981 0.5078 0.000 0.004 0.672 0.008 0.004 0.312
#> GSM955074 4 0.2871 0.5499 0.116 0.000 0.000 0.852 0.024 0.008
#> GSM955076 2 0.3056 0.5515 0.000 0.820 0.000 0.008 0.012 0.160
#> GSM955078 2 0.3641 0.4889 0.000 0.732 0.000 0.000 0.248 0.020
#> GSM955083 4 0.5277 0.3019 0.000 0.004 0.044 0.628 0.280 0.044
#> GSM955084 2 0.4103 0.0779 0.000 0.544 0.000 0.004 0.448 0.004
#> GSM955086 3 0.4625 0.4916 0.000 0.008 0.656 0.028 0.012 0.296
#> GSM955091 2 0.4250 0.5740 0.000 0.744 0.000 0.004 0.108 0.144
#> GSM955092 6 0.6544 0.3675 0.000 0.212 0.116 0.012 0.092 0.568
#> GSM955093 3 0.3263 0.5988 0.000 0.004 0.800 0.020 0.000 0.176
#> GSM955098 2 0.0692 0.6094 0.000 0.976 0.000 0.004 0.000 0.020
#> GSM955099 2 0.5173 0.5030 0.000 0.620 0.000 0.000 0.180 0.200
#> GSM955100 4 0.5897 0.5029 0.092 0.004 0.084 0.668 0.016 0.136
#> GSM955103 5 0.6761 -0.0337 0.000 0.028 0.228 0.008 0.376 0.360
#> GSM955104 3 0.4870 0.5645 0.000 0.000 0.708 0.136 0.024 0.132
#> GSM955106 5 0.2006 0.6173 0.000 0.060 0.016 0.004 0.916 0.004
#> GSM955000 1 0.2997 0.7287 0.868 0.000 0.068 0.024 0.004 0.036
#> GSM955006 4 0.5516 0.3091 0.328 0.000 0.000 0.556 0.016 0.100
#> GSM955007 3 0.5431 0.5094 0.000 0.004 0.664 0.032 0.144 0.156
#> GSM955010 3 0.6293 0.4202 0.000 0.004 0.556 0.256 0.064 0.120
#> GSM955014 4 0.5082 0.1757 0.408 0.000 0.000 0.512 0.000 0.080
#> GSM955018 3 0.3201 0.5776 0.000 0.000 0.780 0.012 0.000 0.208
#> GSM955020 1 0.3555 0.6794 0.776 0.000 0.000 0.184 0.000 0.040
#> GSM955024 6 0.7044 0.2080 0.000 0.032 0.240 0.020 0.316 0.392
#> GSM955026 2 0.0858 0.6085 0.000 0.968 0.000 0.004 0.000 0.028
#> GSM955031 6 0.7006 0.1702 0.000 0.348 0.120 0.068 0.024 0.440
#> GSM955038 4 0.5004 0.3693 0.000 0.316 0.000 0.604 0.072 0.008
#> GSM955040 4 0.6989 0.4347 0.000 0.208 0.048 0.548 0.076 0.120
#> GSM955044 2 0.4840 0.4737 0.000 0.672 0.000 0.012 0.232 0.084
#> GSM955051 4 0.5656 0.1749 0.396 0.000 0.000 0.488 0.016 0.100
#> GSM955055 2 0.5443 0.3585 0.000 0.556 0.000 0.008 0.112 0.324
#> GSM955057 1 0.3227 0.7279 0.824 0.000 0.000 0.116 0.000 0.060
#> GSM955062 2 0.5408 0.2629 0.000 0.524 0.004 0.008 0.080 0.384
#> GSM955063 3 0.3795 0.5357 0.000 0.004 0.724 0.012 0.004 0.256
#> GSM955068 2 0.1780 0.6160 0.000 0.924 0.000 0.000 0.048 0.028
#> GSM955069 3 0.2002 0.6352 0.000 0.000 0.920 0.028 0.012 0.040
#> GSM955070 2 0.6829 0.1680 0.000 0.420 0.008 0.036 0.304 0.232
#> GSM955071 6 0.7635 -0.0329 0.000 0.104 0.180 0.344 0.024 0.348
#> GSM955077 2 0.3746 0.5114 0.000 0.804 0.008 0.036 0.016 0.136
#> GSM955080 5 0.2472 0.5992 0.000 0.016 0.052 0.024 0.900 0.008
#> GSM955081 6 0.6769 0.2209 0.000 0.352 0.124 0.016 0.056 0.452
#> GSM955082 6 0.6470 0.3638 0.000 0.064 0.212 0.004 0.172 0.548
#> GSM955085 2 0.3302 0.6136 0.000 0.836 0.008 0.004 0.104 0.048
#> GSM955090 4 0.5012 0.2712 0.352 0.000 0.000 0.580 0.012 0.056
#> GSM955094 5 0.6663 0.3221 0.000 0.276 0.040 0.040 0.532 0.112
#> GSM955096 3 0.4992 0.3553 0.000 0.016 0.548 0.032 0.004 0.400
#> GSM955102 3 0.4451 0.5185 0.212 0.000 0.716 0.060 0.004 0.008
#> GSM955105 3 0.5063 0.4530 0.000 0.012 0.612 0.032 0.020 0.324
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> CV:kmeans 104 0.887 2
#> CV:kmeans 103 0.963 3
#> CV:kmeans 82 0.870 4
#> CV:kmeans 55 0.985 5
#> CV:kmeans 50 0.596 6
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 31589 rows and 108 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 0.830 0.886 0.954 0.4960 0.502 0.502
#> 3 3 0.693 0.779 0.898 0.3335 0.748 0.538
#> 4 4 0.533 0.594 0.776 0.1297 0.853 0.599
#> 5 5 0.531 0.438 0.656 0.0595 0.955 0.828
#> 6 6 0.537 0.372 0.597 0.0398 0.898 0.612
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
#> GSM955002 2 0.0000 0.9626 0.000 1.000
#> GSM955008 2 0.0000 0.9626 0.000 1.000
#> GSM955016 1 0.0000 0.9323 1.000 0.000
#> GSM955019 2 0.0000 0.9626 0.000 1.000
#> GSM955022 2 0.0672 0.9562 0.008 0.992
#> GSM955023 2 0.0000 0.9626 0.000 1.000
#> GSM955027 2 0.0000 0.9626 0.000 1.000
#> GSM955043 2 0.0000 0.9626 0.000 1.000
#> GSM955048 1 0.0000 0.9323 1.000 0.000
#> GSM955049 2 0.0000 0.9626 0.000 1.000
#> GSM955054 2 0.0000 0.9626 0.000 1.000
#> GSM955064 2 0.0000 0.9626 0.000 1.000
#> GSM955072 2 0.0000 0.9626 0.000 1.000
#> GSM955075 2 0.0000 0.9626 0.000 1.000
#> GSM955079 1 0.5178 0.8495 0.884 0.116
#> GSM955087 1 0.0000 0.9323 1.000 0.000
#> GSM955088 1 0.8081 0.6914 0.752 0.248
#> GSM955089 1 0.0000 0.9323 1.000 0.000
#> GSM955095 2 0.0000 0.9626 0.000 1.000
#> GSM955097 1 0.8955 0.5744 0.688 0.312
#> GSM955101 2 0.0000 0.9626 0.000 1.000
#> GSM954999 1 0.0000 0.9323 1.000 0.000
#> GSM955001 2 0.0000 0.9626 0.000 1.000
#> GSM955003 2 0.0000 0.9626 0.000 1.000
#> GSM955004 2 0.0000 0.9626 0.000 1.000
#> GSM955005 1 0.0376 0.9304 0.996 0.004
#> GSM955009 2 0.0000 0.9626 0.000 1.000
#> GSM955011 1 0.0000 0.9323 1.000 0.000
#> GSM955012 2 0.0000 0.9626 0.000 1.000
#> GSM955013 2 1.0000 -0.1036 0.500 0.500
#> GSM955015 2 0.0000 0.9626 0.000 1.000
#> GSM955017 1 0.0000 0.9323 1.000 0.000
#> GSM955021 2 0.0000 0.9626 0.000 1.000
#> GSM955025 2 0.0000 0.9626 0.000 1.000
#> GSM955028 1 0.0000 0.9323 1.000 0.000
#> GSM955029 2 0.0000 0.9626 0.000 1.000
#> GSM955030 1 0.0000 0.9323 1.000 0.000
#> GSM955032 1 0.9775 0.3535 0.588 0.412
#> GSM955033 2 0.5946 0.8093 0.144 0.856
#> GSM955034 1 0.0000 0.9323 1.000 0.000
#> GSM955035 2 0.0000 0.9626 0.000 1.000
#> GSM955036 1 0.4939 0.8531 0.892 0.108
#> GSM955037 1 0.0000 0.9323 1.000 0.000
#> GSM955039 2 0.3879 0.8892 0.076 0.924
#> GSM955041 2 0.0000 0.9626 0.000 1.000
#> GSM955042 1 0.0000 0.9323 1.000 0.000
#> GSM955045 2 0.0000 0.9626 0.000 1.000
#> GSM955046 1 0.9635 0.4158 0.612 0.388
#> GSM955047 1 0.0000 0.9323 1.000 0.000
#> GSM955050 1 0.8661 0.5954 0.712 0.288
#> GSM955052 2 0.0000 0.9626 0.000 1.000
#> GSM955053 1 0.0000 0.9323 1.000 0.000
#> GSM955056 2 0.0000 0.9626 0.000 1.000
#> GSM955058 2 0.0000 0.9626 0.000 1.000
#> GSM955059 1 0.7602 0.7307 0.780 0.220
#> GSM955060 1 0.0000 0.9323 1.000 0.000
#> GSM955061 2 0.0000 0.9626 0.000 1.000
#> GSM955065 1 0.0000 0.9323 1.000 0.000
#> GSM955066 1 0.0000 0.9323 1.000 0.000
#> GSM955067 1 0.0000 0.9323 1.000 0.000
#> GSM955073 2 0.3274 0.9059 0.060 0.940
#> GSM955074 1 0.0000 0.9323 1.000 0.000
#> GSM955076 2 0.0000 0.9626 0.000 1.000
#> GSM955078 2 0.0000 0.9626 0.000 1.000
#> GSM955083 1 0.1633 0.9188 0.976 0.024
#> GSM955084 2 0.0000 0.9626 0.000 1.000
#> GSM955086 1 0.4161 0.8771 0.916 0.084
#> GSM955091 2 0.0000 0.9626 0.000 1.000
#> GSM955092 2 0.0000 0.9626 0.000 1.000
#> GSM955093 1 0.7056 0.7665 0.808 0.192
#> GSM955098 2 0.0000 0.9626 0.000 1.000
#> GSM955099 2 0.0000 0.9626 0.000 1.000
#> GSM955100 1 0.0000 0.9323 1.000 0.000
#> GSM955103 2 0.0000 0.9626 0.000 1.000
#> GSM955104 1 0.0000 0.9323 1.000 0.000
#> GSM955106 2 0.0000 0.9626 0.000 1.000
#> GSM955000 1 0.0000 0.9323 1.000 0.000
#> GSM955006 1 0.0000 0.9323 1.000 0.000
#> GSM955007 2 0.2423 0.9266 0.040 0.960
#> GSM955010 1 0.0000 0.9323 1.000 0.000
#> GSM955014 1 0.0000 0.9323 1.000 0.000
#> GSM955018 1 0.4161 0.8767 0.916 0.084
#> GSM955020 1 0.0000 0.9323 1.000 0.000
#> GSM955024 2 0.0000 0.9626 0.000 1.000
#> GSM955026 2 0.0000 0.9626 0.000 1.000
#> GSM955031 1 0.9866 0.2460 0.568 0.432
#> GSM955038 2 0.9988 0.0458 0.480 0.520
#> GSM955040 1 0.1843 0.9163 0.972 0.028
#> GSM955044 2 0.0000 0.9626 0.000 1.000
#> GSM955051 1 0.0000 0.9323 1.000 0.000
#> GSM955055 2 0.0000 0.9626 0.000 1.000
#> GSM955057 1 0.0000 0.9323 1.000 0.000
#> GSM955062 2 0.0000 0.9626 0.000 1.000
#> GSM955063 2 0.9170 0.4525 0.332 0.668
#> GSM955068 2 0.0000 0.9626 0.000 1.000
#> GSM955069 1 0.2043 0.9146 0.968 0.032
#> GSM955070 2 0.0000 0.9626 0.000 1.000
#> GSM955071 1 0.0376 0.9304 0.996 0.004
#> GSM955077 2 0.9460 0.4048 0.364 0.636
#> GSM955080 2 0.0376 0.9594 0.004 0.996
#> GSM955081 2 0.0000 0.9626 0.000 1.000
#> GSM955082 2 0.0000 0.9626 0.000 1.000
#> GSM955085 2 0.0000 0.9626 0.000 1.000
#> GSM955090 1 0.0000 0.9323 1.000 0.000
#> GSM955094 2 0.0000 0.9626 0.000 1.000
#> GSM955096 2 0.0672 0.9561 0.008 0.992
#> GSM955102 1 0.0000 0.9323 1.000 0.000
#> GSM955105 1 0.0376 0.9305 0.996 0.004
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.1411 0.8846 0.000 0.964 0.036
#> GSM955008 3 0.3116 0.7982 0.000 0.108 0.892
#> GSM955016 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955019 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955022 3 0.3340 0.7842 0.000 0.120 0.880
#> GSM955023 2 0.6274 0.1897 0.000 0.544 0.456
#> GSM955027 2 0.0592 0.8955 0.000 0.988 0.012
#> GSM955043 2 0.0237 0.8956 0.000 0.996 0.004
#> GSM955048 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955049 2 0.2066 0.8767 0.000 0.940 0.060
#> GSM955054 2 0.6302 0.0758 0.000 0.520 0.480
#> GSM955064 2 0.2356 0.8695 0.000 0.928 0.072
#> GSM955072 2 0.0424 0.8948 0.000 0.992 0.008
#> GSM955075 2 0.0747 0.8946 0.000 0.984 0.016
#> GSM955079 3 0.1411 0.8399 0.036 0.000 0.964
#> GSM955087 1 0.0237 0.9126 0.996 0.000 0.004
#> GSM955088 3 0.2356 0.8290 0.072 0.000 0.928
#> GSM955089 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955095 2 0.2878 0.8461 0.000 0.904 0.096
#> GSM955097 1 0.7309 0.2361 0.552 0.416 0.032
#> GSM955101 3 0.2625 0.8151 0.000 0.084 0.916
#> GSM954999 1 0.0424 0.9102 0.992 0.000 0.008
#> GSM955001 2 0.0892 0.8953 0.000 0.980 0.020
#> GSM955003 3 0.6302 0.0276 0.000 0.480 0.520
#> GSM955004 2 0.0237 0.8954 0.000 0.996 0.004
#> GSM955005 3 0.3267 0.8063 0.116 0.000 0.884
#> GSM955009 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955011 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955012 2 0.1289 0.8906 0.000 0.968 0.032
#> GSM955013 3 0.9333 0.4571 0.216 0.268 0.516
#> GSM955015 2 0.6204 0.2949 0.000 0.576 0.424
#> GSM955017 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955021 2 0.3482 0.8155 0.000 0.872 0.128
#> GSM955025 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955028 1 0.0237 0.9126 0.996 0.000 0.004
#> GSM955029 2 0.0424 0.8956 0.000 0.992 0.008
#> GSM955030 3 0.6026 0.4693 0.376 0.000 0.624
#> GSM955032 3 0.0424 0.8395 0.008 0.000 0.992
#> GSM955033 2 0.5881 0.6144 0.256 0.728 0.016
#> GSM955034 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955035 2 0.1031 0.8927 0.000 0.976 0.024
#> GSM955036 3 0.7671 0.4007 0.380 0.052 0.568
#> GSM955037 1 0.2261 0.8570 0.932 0.000 0.068
#> GSM955039 3 0.4121 0.8031 0.024 0.108 0.868
#> GSM955041 2 0.2878 0.8542 0.000 0.904 0.096
#> GSM955042 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955045 2 0.4702 0.7308 0.000 0.788 0.212
#> GSM955046 3 0.0892 0.8414 0.020 0.000 0.980
#> GSM955047 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955050 1 0.5536 0.6474 0.752 0.236 0.012
#> GSM955052 3 0.1163 0.8376 0.000 0.028 0.972
#> GSM955053 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955056 3 0.4887 0.6569 0.000 0.228 0.772
#> GSM955058 2 0.0592 0.8953 0.000 0.988 0.012
#> GSM955059 3 0.0747 0.8405 0.016 0.000 0.984
#> GSM955060 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955061 2 0.0747 0.8951 0.000 0.984 0.016
#> GSM955065 1 0.0237 0.9126 0.996 0.000 0.004
#> GSM955066 3 0.5138 0.6748 0.252 0.000 0.748
#> GSM955067 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955073 3 0.0237 0.8388 0.000 0.004 0.996
#> GSM955074 1 0.0237 0.9120 0.996 0.000 0.004
#> GSM955076 2 0.1964 0.8723 0.000 0.944 0.056
#> GSM955078 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955083 1 0.1585 0.8941 0.964 0.008 0.028
#> GSM955084 2 0.0237 0.8954 0.000 0.996 0.004
#> GSM955086 3 0.1860 0.8368 0.052 0.000 0.948
#> GSM955091 2 0.0237 0.8957 0.000 0.996 0.004
#> GSM955092 2 0.5138 0.6722 0.000 0.748 0.252
#> GSM955093 3 0.0592 0.8397 0.012 0.000 0.988
#> GSM955098 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955099 2 0.0237 0.8957 0.000 0.996 0.004
#> GSM955100 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955103 3 0.5678 0.4988 0.000 0.316 0.684
#> GSM955104 3 0.5905 0.5083 0.352 0.000 0.648
#> GSM955106 2 0.0592 0.8941 0.000 0.988 0.012
#> GSM955000 1 0.0892 0.9020 0.980 0.000 0.020
#> GSM955006 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955007 3 0.0892 0.8382 0.000 0.020 0.980
#> GSM955010 1 0.5882 0.3664 0.652 0.000 0.348
#> GSM955014 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955018 3 0.1031 0.8408 0.024 0.000 0.976
#> GSM955020 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955024 3 0.5733 0.4795 0.000 0.324 0.676
#> GSM955026 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955031 1 0.9322 0.2621 0.504 0.304 0.192
#> GSM955038 1 0.6267 0.1860 0.548 0.452 0.000
#> GSM955040 1 0.2945 0.8336 0.908 0.088 0.004
#> GSM955044 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955051 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955055 2 0.0747 0.8944 0.000 0.984 0.016
#> GSM955057 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955062 2 0.1753 0.8839 0.000 0.952 0.048
#> GSM955063 3 0.0237 0.8389 0.004 0.000 0.996
#> GSM955068 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955069 3 0.2448 0.8260 0.076 0.000 0.924
#> GSM955070 2 0.0592 0.8954 0.000 0.988 0.012
#> GSM955071 1 0.2173 0.8769 0.944 0.008 0.048
#> GSM955077 2 0.5178 0.6211 0.256 0.744 0.000
#> GSM955080 2 0.4062 0.7832 0.000 0.836 0.164
#> GSM955081 2 0.5760 0.4973 0.000 0.672 0.328
#> GSM955082 2 0.6307 0.0777 0.000 0.512 0.488
#> GSM955085 2 0.0000 0.8956 0.000 1.000 0.000
#> GSM955090 1 0.0000 0.9145 1.000 0.000 0.000
#> GSM955094 2 0.1289 0.8889 0.000 0.968 0.032
#> GSM955096 3 0.0592 0.8391 0.000 0.012 0.988
#> GSM955102 3 0.4796 0.7157 0.220 0.000 0.780
#> GSM955105 3 0.3038 0.8136 0.104 0.000 0.896
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.5430 0.4641 0.000 0.664 0.036 0.300
#> GSM955008 3 0.4761 0.6267 0.000 0.192 0.764 0.044
#> GSM955016 1 0.1474 0.8734 0.948 0.000 0.000 0.052
#> GSM955019 2 0.1902 0.6749 0.000 0.932 0.004 0.064
#> GSM955022 4 0.4631 0.3904 0.004 0.008 0.260 0.728
#> GSM955023 2 0.7771 0.1075 0.000 0.408 0.348 0.244
#> GSM955027 2 0.4406 0.6154 0.000 0.780 0.028 0.192
#> GSM955043 4 0.5296 0.0901 0.000 0.492 0.008 0.500
#> GSM955048 1 0.0188 0.8907 0.996 0.000 0.004 0.000
#> GSM955049 2 0.6397 0.5060 0.000 0.648 0.144 0.208
#> GSM955054 2 0.5673 0.4467 0.000 0.660 0.288 0.052
#> GSM955064 4 0.7226 0.1806 0.000 0.388 0.144 0.468
#> GSM955072 2 0.3311 0.6369 0.000 0.828 0.000 0.172
#> GSM955075 4 0.4313 0.5197 0.000 0.260 0.004 0.736
#> GSM955079 3 0.3304 0.7514 0.052 0.048 0.888 0.012
#> GSM955087 1 0.0779 0.8861 0.980 0.000 0.016 0.004
#> GSM955088 3 0.4371 0.7530 0.080 0.020 0.836 0.064
#> GSM955089 1 0.0188 0.8907 0.996 0.000 0.004 0.000
#> GSM955095 4 0.3384 0.5897 0.000 0.116 0.024 0.860
#> GSM955097 4 0.5230 0.5333 0.152 0.084 0.004 0.760
#> GSM955101 3 0.5254 0.5915 0.000 0.220 0.724 0.056
#> GSM954999 1 0.3894 0.7957 0.844 0.000 0.068 0.088
#> GSM955001 2 0.5733 0.4322 0.000 0.640 0.048 0.312
#> GSM955003 2 0.5213 0.4134 0.000 0.652 0.328 0.020
#> GSM955004 2 0.4916 0.2129 0.000 0.576 0.000 0.424
#> GSM955005 3 0.6327 0.6911 0.140 0.048 0.720 0.092
#> GSM955009 2 0.1716 0.6732 0.000 0.936 0.000 0.064
#> GSM955011 1 0.0188 0.8907 0.996 0.000 0.004 0.000
#> GSM955012 4 0.4718 0.5217 0.000 0.280 0.012 0.708
#> GSM955013 4 0.5263 0.5040 0.060 0.020 0.148 0.772
#> GSM955015 2 0.7886 -0.0164 0.000 0.380 0.324 0.296
#> GSM955017 1 0.0657 0.8878 0.984 0.000 0.012 0.004
#> GSM955021 2 0.3612 0.6401 0.000 0.856 0.100 0.044
#> GSM955025 2 0.2593 0.6695 0.000 0.892 0.004 0.104
#> GSM955028 1 0.0779 0.8861 0.980 0.000 0.016 0.004
#> GSM955029 4 0.5112 0.3591 0.000 0.384 0.008 0.608
#> GSM955030 3 0.6562 0.3245 0.404 0.000 0.516 0.080
#> GSM955032 3 0.2877 0.7507 0.008 0.060 0.904 0.028
#> GSM955033 4 0.4603 0.5334 0.032 0.160 0.012 0.796
#> GSM955034 1 0.0376 0.8902 0.992 0.000 0.004 0.004
#> GSM955035 2 0.3521 0.6664 0.000 0.864 0.052 0.084
#> GSM955036 4 0.6074 0.3146 0.104 0.000 0.228 0.668
#> GSM955037 1 0.3441 0.7788 0.856 0.000 0.120 0.024
#> GSM955039 4 0.7213 -0.0457 0.012 0.100 0.400 0.488
#> GSM955041 4 0.7338 0.2451 0.000 0.376 0.160 0.464
#> GSM955042 1 0.0592 0.8891 0.984 0.000 0.000 0.016
#> GSM955045 4 0.6792 0.4710 0.000 0.272 0.140 0.588
#> GSM955046 3 0.4677 0.5822 0.004 0.000 0.680 0.316
#> GSM955047 1 0.0469 0.8890 0.988 0.000 0.000 0.012
#> GSM955050 1 0.8077 0.0154 0.408 0.360 0.012 0.220
#> GSM955052 3 0.3525 0.7232 0.000 0.100 0.860 0.040
#> GSM955053 1 0.0376 0.8902 0.992 0.000 0.004 0.004
#> GSM955056 3 0.6640 0.4459 0.000 0.268 0.604 0.128
#> GSM955058 4 0.5167 0.4370 0.000 0.340 0.016 0.644
#> GSM955059 3 0.2861 0.7434 0.016 0.000 0.888 0.096
#> GSM955060 1 0.0188 0.8907 0.996 0.000 0.000 0.004
#> GSM955061 4 0.4814 0.4671 0.000 0.316 0.008 0.676
#> GSM955065 1 0.0657 0.8878 0.984 0.000 0.012 0.004
#> GSM955066 3 0.6991 0.5780 0.232 0.004 0.596 0.168
#> GSM955067 1 0.1022 0.8824 0.968 0.000 0.000 0.032
#> GSM955073 3 0.1109 0.7515 0.000 0.004 0.968 0.028
#> GSM955074 1 0.1118 0.8804 0.964 0.000 0.000 0.036
#> GSM955076 2 0.2300 0.6641 0.000 0.924 0.048 0.028
#> GSM955078 2 0.3486 0.6242 0.000 0.812 0.000 0.188
#> GSM955083 1 0.6001 0.5397 0.648 0.028 0.024 0.300
#> GSM955084 2 0.4585 0.4291 0.000 0.668 0.000 0.332
#> GSM955086 3 0.3768 0.7602 0.044 0.048 0.872 0.036
#> GSM955091 2 0.3355 0.6437 0.000 0.836 0.004 0.160
#> GSM955092 2 0.6921 0.3917 0.000 0.580 0.260 0.160
#> GSM955093 3 0.1389 0.7520 0.000 0.000 0.952 0.048
#> GSM955098 2 0.1211 0.6692 0.000 0.960 0.000 0.040
#> GSM955099 2 0.3444 0.6286 0.000 0.816 0.000 0.184
#> GSM955100 1 0.0188 0.8908 0.996 0.000 0.000 0.004
#> GSM955103 4 0.5599 0.5423 0.000 0.072 0.228 0.700
#> GSM955104 3 0.7540 0.3876 0.304 0.000 0.480 0.216
#> GSM955106 4 0.3791 0.5618 0.000 0.200 0.004 0.796
#> GSM955000 1 0.1576 0.8659 0.948 0.000 0.048 0.004
#> GSM955006 1 0.0188 0.8907 0.996 0.000 0.004 0.000
#> GSM955007 3 0.4978 0.5235 0.000 0.012 0.664 0.324
#> GSM955010 1 0.6457 0.3409 0.604 0.000 0.296 0.100
#> GSM955014 1 0.0592 0.8875 0.984 0.000 0.000 0.016
#> GSM955018 3 0.1174 0.7567 0.012 0.000 0.968 0.020
#> GSM955020 1 0.0000 0.8904 1.000 0.000 0.000 0.000
#> GSM955024 4 0.6993 0.3475 0.000 0.124 0.364 0.512
#> GSM955026 2 0.1389 0.6691 0.000 0.952 0.000 0.048
#> GSM955031 2 0.7744 0.3361 0.148 0.572 0.240 0.040
#> GSM955038 1 0.7343 -0.0714 0.428 0.416 0.000 0.156
#> GSM955040 1 0.5950 0.6284 0.704 0.176 0.004 0.116
#> GSM955044 2 0.4746 0.3238 0.000 0.632 0.000 0.368
#> GSM955051 1 0.0336 0.8894 0.992 0.000 0.000 0.008
#> GSM955055 2 0.4046 0.6631 0.000 0.828 0.048 0.124
#> GSM955057 1 0.0188 0.8907 0.996 0.000 0.004 0.000
#> GSM955062 2 0.4428 0.6562 0.000 0.808 0.068 0.124
#> GSM955063 3 0.1004 0.7516 0.000 0.004 0.972 0.024
#> GSM955068 2 0.2281 0.6642 0.000 0.904 0.000 0.096
#> GSM955069 3 0.5171 0.7094 0.128 0.000 0.760 0.112
#> GSM955070 2 0.5295 0.0513 0.000 0.504 0.008 0.488
#> GSM955071 1 0.6112 0.6852 0.744 0.092 0.096 0.068
#> GSM955077 2 0.4444 0.5890 0.112 0.816 0.004 0.068
#> GSM955080 4 0.3749 0.5908 0.000 0.128 0.032 0.840
#> GSM955081 2 0.6068 0.4955 0.000 0.676 0.208 0.116
#> GSM955082 4 0.7775 0.2373 0.000 0.240 0.376 0.384
#> GSM955085 2 0.3688 0.6058 0.000 0.792 0.000 0.208
#> GSM955090 1 0.0592 0.8875 0.984 0.000 0.000 0.016
#> GSM955094 4 0.5130 0.3637 0.004 0.344 0.008 0.644
#> GSM955096 3 0.3757 0.6911 0.000 0.152 0.828 0.020
#> GSM955102 3 0.6025 0.6272 0.236 0.000 0.668 0.096
#> GSM955105 3 0.4723 0.7403 0.108 0.036 0.816 0.040
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.6612 0.3368 0.000 0.568 0.028 0.228 0.176
#> GSM955008 3 0.5020 0.4666 0.000 0.140 0.748 0.076 0.036
#> GSM955016 1 0.2903 0.8019 0.872 0.000 0.000 0.080 0.048
#> GSM955019 2 0.3809 0.5329 0.000 0.824 0.016 0.044 0.116
#> GSM955022 5 0.6675 -0.0228 0.000 0.020 0.136 0.384 0.460
#> GSM955023 2 0.8454 0.1356 0.000 0.348 0.220 0.196 0.236
#> GSM955027 2 0.6197 0.3110 0.000 0.560 0.044 0.060 0.336
#> GSM955043 5 0.5579 0.2301 0.000 0.368 0.000 0.080 0.552
#> GSM955048 1 0.0609 0.8533 0.980 0.000 0.000 0.020 0.000
#> GSM955049 2 0.7393 0.2760 0.000 0.488 0.152 0.076 0.284
#> GSM955054 2 0.6958 0.2716 0.000 0.484 0.356 0.096 0.064
#> GSM955064 5 0.7932 0.0844 0.000 0.316 0.116 0.164 0.404
#> GSM955072 2 0.5195 0.4561 0.000 0.692 0.008 0.088 0.212
#> GSM955075 5 0.4203 0.4798 0.000 0.188 0.000 0.052 0.760
#> GSM955079 3 0.5025 0.5112 0.060 0.040 0.772 0.112 0.016
#> GSM955087 1 0.1300 0.8467 0.956 0.000 0.016 0.028 0.000
#> GSM955088 3 0.6264 0.3230 0.060 0.032 0.604 0.288 0.016
#> GSM955089 1 0.0404 0.8527 0.988 0.000 0.000 0.012 0.000
#> GSM955095 5 0.4431 0.5343 0.000 0.068 0.004 0.168 0.760
#> GSM955097 5 0.5108 0.4807 0.108 0.028 0.000 0.124 0.740
#> GSM955101 3 0.6210 0.3735 0.000 0.136 0.656 0.148 0.060
#> GSM954999 1 0.5711 0.5625 0.668 0.000 0.048 0.224 0.060
#> GSM955001 2 0.6792 0.2124 0.000 0.476 0.072 0.068 0.384
#> GSM955003 2 0.6555 0.2840 0.000 0.496 0.380 0.080 0.044
#> GSM955004 2 0.5352 0.1053 0.000 0.480 0.000 0.052 0.468
#> GSM955005 4 0.7970 0.1404 0.132 0.056 0.376 0.400 0.036
#> GSM955009 2 0.3445 0.5313 0.000 0.856 0.020 0.052 0.072
#> GSM955011 1 0.0912 0.8548 0.972 0.000 0.000 0.016 0.012
#> GSM955012 5 0.4435 0.4968 0.000 0.164 0.012 0.056 0.768
#> GSM955013 5 0.6791 0.1966 0.028 0.016 0.092 0.344 0.520
#> GSM955015 2 0.8549 0.0295 0.000 0.296 0.272 0.228 0.204
#> GSM955017 1 0.2102 0.8329 0.916 0.000 0.012 0.068 0.004
#> GSM955021 2 0.6139 0.4636 0.000 0.648 0.204 0.060 0.088
#> GSM955025 2 0.4277 0.5071 0.000 0.784 0.004 0.112 0.100
#> GSM955028 1 0.1386 0.8450 0.952 0.000 0.016 0.032 0.000
#> GSM955029 5 0.4243 0.4009 0.000 0.264 0.000 0.024 0.712
#> GSM955030 4 0.7253 0.3311 0.300 0.000 0.296 0.384 0.020
#> GSM955032 3 0.4612 0.5427 0.004 0.056 0.768 0.156 0.016
#> GSM955033 5 0.6729 0.2732 0.016 0.132 0.004 0.416 0.432
#> GSM955034 1 0.0771 0.8505 0.976 0.000 0.004 0.020 0.000
#> GSM955035 2 0.6254 0.4957 0.000 0.664 0.116 0.100 0.120
#> GSM955036 4 0.6976 0.3379 0.048 0.000 0.140 0.516 0.296
#> GSM955037 1 0.4309 0.6367 0.768 0.000 0.084 0.148 0.000
#> GSM955039 4 0.7398 0.1966 0.012 0.040 0.300 0.484 0.164
#> GSM955041 5 0.8042 0.1820 0.000 0.292 0.148 0.152 0.408
#> GSM955042 1 0.1978 0.8412 0.928 0.000 0.004 0.044 0.024
#> GSM955045 5 0.7399 0.3688 0.000 0.192 0.156 0.116 0.536
#> GSM955046 4 0.6120 0.1974 0.012 0.000 0.392 0.504 0.092
#> GSM955047 1 0.1484 0.8488 0.944 0.000 0.000 0.048 0.008
#> GSM955050 2 0.8691 0.1211 0.216 0.356 0.012 0.244 0.172
#> GSM955052 3 0.4062 0.5359 0.000 0.068 0.820 0.084 0.028
#> GSM955053 1 0.0912 0.8510 0.972 0.000 0.012 0.016 0.000
#> GSM955056 3 0.6889 0.3243 0.000 0.232 0.572 0.120 0.076
#> GSM955058 5 0.4026 0.4213 0.000 0.244 0.000 0.020 0.736
#> GSM955059 3 0.5115 0.2099 0.012 0.000 0.608 0.352 0.028
#> GSM955060 1 0.0794 0.8543 0.972 0.000 0.000 0.028 0.000
#> GSM955061 5 0.4229 0.4643 0.000 0.208 0.012 0.024 0.756
#> GSM955065 1 0.1195 0.8469 0.960 0.000 0.012 0.028 0.000
#> GSM955066 4 0.7571 0.2898 0.148 0.008 0.344 0.440 0.060
#> GSM955067 1 0.2291 0.8287 0.908 0.008 0.000 0.072 0.012
#> GSM955073 3 0.3127 0.5324 0.000 0.004 0.848 0.128 0.020
#> GSM955074 1 0.2074 0.8341 0.920 0.000 0.000 0.044 0.036
#> GSM955076 2 0.3870 0.5303 0.000 0.832 0.088 0.048 0.032
#> GSM955078 2 0.4546 0.3976 0.000 0.668 0.000 0.028 0.304
#> GSM955083 1 0.7637 0.0203 0.436 0.020 0.024 0.244 0.276
#> GSM955084 2 0.5215 0.2799 0.000 0.576 0.000 0.052 0.372
#> GSM955086 3 0.4611 0.5392 0.024 0.044 0.784 0.136 0.012
#> GSM955091 2 0.5292 0.4493 0.000 0.668 0.020 0.052 0.260
#> GSM955092 2 0.7944 0.1505 0.000 0.360 0.328 0.084 0.228
#> GSM955093 3 0.3905 0.4471 0.000 0.004 0.752 0.232 0.012
#> GSM955098 2 0.2393 0.5246 0.000 0.900 0.004 0.080 0.016
#> GSM955099 2 0.5053 0.3993 0.000 0.644 0.004 0.048 0.304
#> GSM955100 1 0.2115 0.8363 0.916 0.000 0.008 0.068 0.008
#> GSM955103 5 0.6779 0.3085 0.000 0.028 0.220 0.208 0.544
#> GSM955104 4 0.8174 0.3679 0.248 0.008 0.300 0.364 0.080
#> GSM955106 5 0.4010 0.5186 0.000 0.116 0.000 0.088 0.796
#> GSM955000 1 0.2554 0.8019 0.892 0.000 0.036 0.072 0.000
#> GSM955006 1 0.0510 0.8535 0.984 0.000 0.000 0.016 0.000
#> GSM955007 3 0.6891 -0.0886 0.000 0.012 0.456 0.308 0.224
#> GSM955010 1 0.6917 -0.3359 0.412 0.000 0.172 0.396 0.020
#> GSM955014 1 0.1597 0.8434 0.940 0.000 0.000 0.048 0.012
#> GSM955018 3 0.3560 0.5191 0.008 0.004 0.816 0.160 0.012
#> GSM955020 1 0.0566 0.8529 0.984 0.000 0.000 0.012 0.004
#> GSM955024 5 0.8097 0.2569 0.000 0.124 0.264 0.208 0.404
#> GSM955026 2 0.3289 0.5273 0.000 0.860 0.016 0.088 0.036
#> GSM955031 2 0.8348 0.2299 0.112 0.456 0.252 0.148 0.032
#> GSM955038 2 0.7691 0.1351 0.356 0.408 0.000 0.120 0.116
#> GSM955040 1 0.7732 0.1853 0.468 0.216 0.000 0.220 0.096
#> GSM955044 2 0.5979 0.2363 0.000 0.520 0.000 0.120 0.360
#> GSM955051 1 0.1043 0.8536 0.960 0.000 0.000 0.040 0.000
#> GSM955055 2 0.5836 0.4678 0.000 0.668 0.072 0.052 0.208
#> GSM955057 1 0.0609 0.8533 0.980 0.000 0.000 0.020 0.000
#> GSM955062 2 0.6866 0.4357 0.000 0.584 0.108 0.092 0.216
#> GSM955063 3 0.3320 0.5277 0.000 0.008 0.828 0.152 0.012
#> GSM955068 2 0.3748 0.5197 0.000 0.832 0.016 0.052 0.100
#> GSM955069 3 0.6631 -0.0428 0.112 0.000 0.528 0.324 0.036
#> GSM955070 2 0.7086 0.1606 0.000 0.448 0.028 0.188 0.336
#> GSM955071 1 0.7681 0.2348 0.532 0.112 0.096 0.236 0.024
#> GSM955077 2 0.6097 0.4642 0.056 0.704 0.028 0.124 0.088
#> GSM955080 5 0.4398 0.5342 0.000 0.060 0.016 0.144 0.780
#> GSM955081 2 0.7560 0.3483 0.000 0.512 0.212 0.152 0.124
#> GSM955082 5 0.8065 0.1748 0.000 0.180 0.348 0.120 0.352
#> GSM955085 2 0.5110 0.4274 0.000 0.668 0.012 0.048 0.272
#> GSM955090 1 0.1549 0.8456 0.944 0.000 0.000 0.040 0.016
#> GSM955094 5 0.6887 0.1608 0.000 0.308 0.004 0.284 0.404
#> GSM955096 3 0.4456 0.5383 0.000 0.088 0.796 0.080 0.036
#> GSM955102 3 0.6480 -0.2753 0.184 0.000 0.416 0.400 0.000
#> GSM955105 3 0.5423 0.4831 0.064 0.052 0.740 0.132 0.012
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.7236 0.30637 0.000 0.532 0.076 0.168 0.164 0.060
#> GSM955008 6 0.5037 0.42584 0.000 0.096 0.060 0.048 0.048 0.748
#> GSM955016 1 0.4881 0.56025 0.616 0.004 0.032 0.328 0.020 0.000
#> GSM955019 2 0.5186 0.52434 0.000 0.716 0.012 0.068 0.136 0.068
#> GSM955022 3 0.7466 -0.03576 0.000 0.024 0.384 0.124 0.348 0.120
#> GSM955023 6 0.8551 0.05756 0.000 0.260 0.144 0.104 0.172 0.320
#> GSM955027 2 0.7007 0.21052 0.000 0.408 0.020 0.072 0.380 0.120
#> GSM955043 5 0.6354 0.34722 0.000 0.232 0.044 0.100 0.588 0.036
#> GSM955048 1 0.1082 0.81121 0.956 0.000 0.004 0.040 0.000 0.000
#> GSM955049 2 0.7341 0.23082 0.000 0.380 0.036 0.036 0.292 0.256
#> GSM955054 6 0.6962 -0.03737 0.000 0.396 0.048 0.108 0.040 0.408
#> GSM955064 5 0.8205 0.10417 0.000 0.196 0.068 0.128 0.380 0.228
#> GSM955072 2 0.5571 0.43403 0.000 0.632 0.020 0.056 0.256 0.036
#> GSM955075 5 0.3126 0.56519 0.000 0.080 0.024 0.028 0.860 0.008
#> GSM955079 6 0.6986 0.28282 0.052 0.036 0.232 0.112 0.016 0.552
#> GSM955087 1 0.1049 0.80328 0.960 0.000 0.032 0.008 0.000 0.000
#> GSM955088 6 0.7589 0.01435 0.084 0.044 0.320 0.128 0.004 0.420
#> GSM955089 1 0.1643 0.81078 0.924 0.000 0.008 0.068 0.000 0.000
#> GSM955095 5 0.5298 0.44572 0.000 0.036 0.144 0.112 0.696 0.012
#> GSM955097 5 0.5332 0.28469 0.080 0.004 0.044 0.204 0.668 0.000
#> GSM955101 6 0.7157 0.33596 0.000 0.112 0.204 0.096 0.052 0.536
#> GSM954999 1 0.6823 0.26047 0.468 0.000 0.148 0.320 0.036 0.028
#> GSM955001 5 0.7045 -0.12602 0.000 0.356 0.024 0.080 0.432 0.108
#> GSM955003 6 0.6190 -0.02464 0.000 0.416 0.024 0.060 0.040 0.460
#> GSM955004 5 0.4916 0.01221 0.000 0.436 0.008 0.044 0.512 0.000
#> GSM955005 3 0.8361 0.23552 0.116 0.052 0.416 0.140 0.032 0.244
#> GSM955009 2 0.4552 0.52677 0.000 0.772 0.012 0.072 0.092 0.052
#> GSM955011 1 0.1926 0.80840 0.912 0.000 0.020 0.068 0.000 0.000
#> GSM955012 5 0.2806 0.57188 0.000 0.056 0.016 0.028 0.884 0.016
#> GSM955013 4 0.8154 0.04090 0.016 0.024 0.252 0.316 0.288 0.104
#> GSM955015 2 0.8726 -0.03481 0.000 0.284 0.160 0.156 0.136 0.264
#> GSM955017 1 0.2619 0.78313 0.880 0.000 0.072 0.040 0.000 0.008
#> GSM955021 2 0.6617 0.34889 0.000 0.528 0.032 0.064 0.080 0.296
#> GSM955025 2 0.5093 0.49031 0.008 0.720 0.008 0.144 0.092 0.028
#> GSM955028 1 0.1196 0.80135 0.952 0.000 0.040 0.008 0.000 0.000
#> GSM955029 5 0.3475 0.51511 0.000 0.132 0.004 0.040 0.816 0.008
#> GSM955030 3 0.6598 0.30773 0.340 0.000 0.472 0.092 0.004 0.092
#> GSM955032 6 0.6416 0.30724 0.024 0.044 0.252 0.084 0.012 0.584
#> GSM955033 4 0.7800 0.25480 0.012 0.168 0.176 0.412 0.224 0.008
#> GSM955034 1 0.0603 0.80627 0.980 0.000 0.016 0.004 0.000 0.000
#> GSM955035 2 0.6736 0.44703 0.000 0.576 0.036 0.072 0.136 0.180
#> GSM955036 3 0.6555 0.15325 0.040 0.000 0.532 0.244 0.168 0.016
#> GSM955037 1 0.4029 0.56340 0.736 0.000 0.220 0.012 0.000 0.032
#> GSM955039 3 0.8460 0.05244 0.008 0.068 0.348 0.256 0.124 0.196
#> GSM955041 5 0.8268 0.12333 0.000 0.196 0.100 0.108 0.392 0.204
#> GSM955042 1 0.3709 0.71467 0.748 0.000 0.016 0.228 0.004 0.004
#> GSM955045 5 0.7709 0.37032 0.000 0.128 0.120 0.092 0.496 0.164
#> GSM955046 3 0.4659 0.37425 0.008 0.000 0.752 0.060 0.048 0.132
#> GSM955047 1 0.2566 0.79688 0.868 0.000 0.012 0.112 0.000 0.008
#> GSM955050 4 0.8614 0.35439 0.172 0.296 0.060 0.340 0.096 0.036
#> GSM955052 6 0.4810 0.39444 0.000 0.028 0.124 0.060 0.036 0.752
#> GSM955053 1 0.0603 0.80728 0.980 0.000 0.016 0.004 0.000 0.000
#> GSM955056 6 0.7503 0.38480 0.000 0.192 0.144 0.108 0.056 0.500
#> GSM955058 5 0.3145 0.55117 0.000 0.104 0.004 0.028 0.848 0.016
#> GSM955059 3 0.4941 0.23299 0.032 0.000 0.624 0.020 0.008 0.316
#> GSM955060 1 0.1807 0.81184 0.920 0.000 0.020 0.060 0.000 0.000
#> GSM955061 5 0.3314 0.56029 0.000 0.100 0.004 0.040 0.840 0.016
#> GSM955065 1 0.1010 0.80145 0.960 0.000 0.036 0.004 0.000 0.000
#> GSM955066 3 0.6935 0.39761 0.152 0.004 0.556 0.148 0.016 0.124
#> GSM955067 1 0.3460 0.72673 0.760 0.020 0.000 0.220 0.000 0.000
#> GSM955073 6 0.4397 0.24878 0.000 0.000 0.284 0.032 0.012 0.672
#> GSM955074 1 0.3672 0.69511 0.712 0.000 0.008 0.276 0.004 0.000
#> GSM955076 2 0.4639 0.51857 0.000 0.748 0.012 0.048 0.040 0.152
#> GSM955078 2 0.4975 0.38491 0.000 0.616 0.004 0.052 0.316 0.012
#> GSM955083 1 0.7817 -0.15935 0.372 0.028 0.112 0.332 0.148 0.008
#> GSM955084 2 0.4770 0.07183 0.000 0.508 0.004 0.040 0.448 0.000
#> GSM955086 6 0.7089 0.21859 0.080 0.036 0.216 0.096 0.016 0.556
#> GSM955091 2 0.6376 0.41438 0.000 0.544 0.008 0.084 0.280 0.084
#> GSM955092 6 0.8034 -0.00336 0.000 0.240 0.060 0.092 0.236 0.372
#> GSM955093 3 0.5224 -0.00479 0.016 0.000 0.480 0.044 0.004 0.456
#> GSM955098 2 0.1965 0.51960 0.000 0.924 0.004 0.040 0.024 0.008
#> GSM955099 2 0.5979 0.33105 0.000 0.532 0.012 0.056 0.348 0.052
#> GSM955100 1 0.3165 0.76199 0.844 0.000 0.072 0.076 0.000 0.008
#> GSM955103 5 0.7358 0.17255 0.000 0.012 0.208 0.148 0.464 0.168
#> GSM955104 3 0.7996 0.28740 0.244 0.000 0.416 0.120 0.068 0.152
#> GSM955106 5 0.3889 0.54918 0.000 0.072 0.048 0.072 0.808 0.000
#> GSM955000 1 0.2803 0.74309 0.856 0.000 0.116 0.016 0.000 0.012
#> GSM955006 1 0.1075 0.81434 0.952 0.000 0.000 0.048 0.000 0.000
#> GSM955007 3 0.6672 0.16472 0.000 0.012 0.532 0.060 0.172 0.224
#> GSM955010 3 0.6610 0.21819 0.368 0.012 0.456 0.120 0.004 0.040
#> GSM955014 1 0.2773 0.77346 0.828 0.004 0.004 0.164 0.000 0.000
#> GSM955018 6 0.5537 0.10567 0.040 0.000 0.328 0.040 0.012 0.580
#> GSM955020 1 0.1806 0.80586 0.908 0.000 0.004 0.088 0.000 0.000
#> GSM955024 6 0.8549 0.06414 0.000 0.100 0.180 0.140 0.280 0.300
#> GSM955026 2 0.2961 0.52393 0.000 0.872 0.004 0.048 0.052 0.024
#> GSM955031 2 0.8531 -0.06952 0.144 0.332 0.040 0.180 0.024 0.280
#> GSM955038 2 0.7193 -0.31083 0.232 0.372 0.004 0.316 0.076 0.000
#> GSM955040 4 0.8092 0.31102 0.300 0.252 0.060 0.328 0.040 0.020
#> GSM955044 2 0.6457 0.17313 0.000 0.472 0.040 0.060 0.384 0.044
#> GSM955051 1 0.2006 0.80002 0.892 0.000 0.004 0.104 0.000 0.000
#> GSM955055 2 0.7303 0.41383 0.000 0.516 0.052 0.092 0.208 0.132
#> GSM955057 1 0.0858 0.81291 0.968 0.000 0.004 0.028 0.000 0.000
#> GSM955062 2 0.7401 0.38329 0.000 0.484 0.040 0.084 0.208 0.184
#> GSM955063 6 0.4752 0.20842 0.004 0.000 0.360 0.028 0.012 0.596
#> GSM955068 2 0.3838 0.51224 0.000 0.800 0.004 0.048 0.128 0.020
#> GSM955069 3 0.6132 0.33377 0.116 0.000 0.584 0.044 0.012 0.244
#> GSM955070 2 0.7827 0.16861 0.000 0.396 0.088 0.204 0.264 0.048
#> GSM955071 1 0.8435 -0.03814 0.428 0.100 0.128 0.208 0.020 0.116
#> GSM955077 2 0.6636 0.31468 0.056 0.612 0.024 0.196 0.072 0.040
#> GSM955080 5 0.4862 0.47606 0.000 0.040 0.156 0.068 0.728 0.008
#> GSM955081 2 0.7868 0.19916 0.000 0.416 0.048 0.144 0.136 0.256
#> GSM955082 6 0.8129 0.02771 0.000 0.080 0.124 0.128 0.328 0.340
#> GSM955085 2 0.5706 0.38075 0.000 0.588 0.012 0.084 0.292 0.024
#> GSM955090 1 0.2964 0.75104 0.792 0.000 0.004 0.204 0.000 0.000
#> GSM955094 5 0.8076 0.04266 0.000 0.276 0.172 0.204 0.320 0.028
#> GSM955096 6 0.4873 0.41585 0.000 0.072 0.088 0.060 0.024 0.756
#> GSM955102 3 0.6294 0.39066 0.208 0.000 0.560 0.048 0.004 0.180
#> GSM955105 6 0.6701 0.26905 0.072 0.024 0.180 0.108 0.016 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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> CV:skmeans 101 0.482 2
#> CV:skmeans 93 0.910 3
#> CV:skmeans 76 0.831 4
#> CV:skmeans 43 0.981 5
#> CV:skmeans 36 0.623 6
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 31589 rows and 108 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 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 0.506 0.880 0.853 0.3175 0.732 0.732
#> 3 3 0.484 0.727 0.873 0.8581 0.669 0.548
#> 4 4 0.488 0.635 0.797 0.2016 0.734 0.442
#> 5 5 0.480 0.520 0.716 0.0597 0.962 0.872
#> 6 6 0.510 0.520 0.721 0.0443 0.906 0.669
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
#> GSM955002 2 0.7674 0.8468 0.224 0.776
#> GSM955008 2 0.4562 0.9061 0.096 0.904
#> GSM955016 2 0.8713 0.7731 0.292 0.708
#> GSM955019 2 0.0000 0.8919 0.000 1.000
#> GSM955022 2 0.4690 0.9057 0.100 0.900
#> GSM955023 2 0.4022 0.9069 0.080 0.920
#> GSM955027 2 0.0000 0.8919 0.000 1.000
#> GSM955043 2 0.3274 0.9058 0.060 0.940
#> GSM955048 1 0.0000 0.9579 1.000 0.000
#> GSM955049 2 0.5178 0.9028 0.116 0.884
#> GSM955054 2 0.2043 0.9019 0.032 0.968
#> GSM955064 2 0.1843 0.9010 0.028 0.972
#> GSM955072 2 0.0000 0.8919 0.000 1.000
#> GSM955075 2 0.0000 0.8919 0.000 1.000
#> GSM955079 2 0.6048 0.8935 0.148 0.852
#> GSM955087 1 0.0000 0.9579 1.000 0.000
#> GSM955088 2 0.6531 0.8860 0.168 0.832
#> GSM955089 1 0.0000 0.9579 1.000 0.000
#> GSM955095 2 0.0376 0.8920 0.004 0.996
#> GSM955097 2 0.0376 0.8920 0.004 0.996
#> GSM955101 2 0.0938 0.8958 0.012 0.988
#> GSM954999 2 0.8661 0.7783 0.288 0.712
#> GSM955001 2 0.0000 0.8919 0.000 1.000
#> GSM955003 2 0.0000 0.8919 0.000 1.000
#> GSM955004 2 0.0000 0.8919 0.000 1.000
#> GSM955005 2 0.6343 0.8897 0.160 0.840
#> GSM955009 2 0.0000 0.8919 0.000 1.000
#> GSM955011 2 0.8713 0.7731 0.292 0.708
#> GSM955012 2 0.5842 0.8959 0.140 0.860
#> GSM955013 2 0.5408 0.9028 0.124 0.876
#> GSM955015 2 0.0000 0.8919 0.000 1.000
#> GSM955017 2 0.8955 0.7452 0.312 0.688
#> GSM955021 2 0.0000 0.8919 0.000 1.000
#> GSM955025 2 0.5842 0.8962 0.140 0.860
#> GSM955028 1 0.0000 0.9579 1.000 0.000
#> GSM955029 2 0.0000 0.8919 0.000 1.000
#> GSM955030 2 0.8661 0.7783 0.288 0.712
#> GSM955032 2 0.6531 0.8854 0.168 0.832
#> GSM955033 2 0.7219 0.8661 0.200 0.800
#> GSM955034 1 0.0000 0.9579 1.000 0.000
#> GSM955035 2 0.0000 0.8919 0.000 1.000
#> GSM955036 2 0.7745 0.8434 0.228 0.772
#> GSM955037 2 0.9710 0.5828 0.400 0.600
#> GSM955039 2 0.5946 0.8946 0.144 0.856
#> GSM955041 2 0.2948 0.9051 0.052 0.948
#> GSM955042 2 0.8016 0.8285 0.244 0.756
#> GSM955045 2 0.0000 0.8919 0.000 1.000
#> GSM955046 2 0.5946 0.8946 0.144 0.856
#> GSM955047 1 0.0376 0.9545 0.996 0.004
#> GSM955050 2 0.1843 0.8932 0.028 0.972
#> GSM955052 2 0.5946 0.8946 0.144 0.856
#> GSM955053 1 0.0000 0.9579 1.000 0.000
#> GSM955056 2 0.5946 0.8946 0.144 0.856
#> GSM955058 2 0.0000 0.8919 0.000 1.000
#> GSM955059 2 0.6048 0.8935 0.148 0.852
#> GSM955060 1 0.0000 0.9579 1.000 0.000
#> GSM955061 2 0.4562 0.9055 0.096 0.904
#> GSM955065 1 0.0000 0.9579 1.000 0.000
#> GSM955066 2 0.7950 0.8324 0.240 0.760
#> GSM955067 1 0.0672 0.9506 0.992 0.008
#> GSM955073 2 0.3431 0.9060 0.064 0.936
#> GSM955074 2 0.8443 0.7982 0.272 0.728
#> GSM955076 2 0.0000 0.8919 0.000 1.000
#> GSM955078 2 0.0376 0.8936 0.004 0.996
#> GSM955083 2 0.7602 0.8509 0.220 0.780
#> GSM955084 2 0.0000 0.8919 0.000 1.000
#> GSM955086 2 0.6712 0.8818 0.176 0.824
#> GSM955091 2 0.4939 0.9048 0.108 0.892
#> GSM955092 2 0.2778 0.9046 0.048 0.952
#> GSM955093 2 0.5842 0.8964 0.140 0.860
#> GSM955098 2 0.1184 0.8974 0.016 0.984
#> GSM955099 2 0.1633 0.9001 0.024 0.976
#> GSM955100 2 0.8608 0.7834 0.284 0.716
#> GSM955103 2 0.1843 0.9006 0.028 0.972
#> GSM955104 2 0.7139 0.8689 0.196 0.804
#> GSM955106 2 0.2778 0.9045 0.048 0.952
#> GSM955000 1 0.9732 0.0277 0.596 0.404
#> GSM955006 1 0.5842 0.8176 0.860 0.140
#> GSM955007 2 0.0376 0.8935 0.004 0.996
#> GSM955010 2 0.5629 0.8987 0.132 0.868
#> GSM955014 1 0.0000 0.9579 1.000 0.000
#> GSM955018 2 0.6801 0.8794 0.180 0.820
#> GSM955020 1 0.0000 0.9579 1.000 0.000
#> GSM955024 2 0.0376 0.8936 0.004 0.996
#> GSM955026 2 0.4939 0.9045 0.108 0.892
#> GSM955031 2 0.0376 0.8935 0.004 0.996
#> GSM955038 2 0.4939 0.9049 0.108 0.892
#> GSM955040 2 0.3584 0.8835 0.068 0.932
#> GSM955044 2 0.0000 0.8919 0.000 1.000
#> GSM955051 1 0.0000 0.9579 1.000 0.000
#> GSM955055 2 0.0000 0.8919 0.000 1.000
#> GSM955057 1 0.0000 0.9579 1.000 0.000
#> GSM955062 2 0.0000 0.8919 0.000 1.000
#> GSM955063 2 0.6148 0.8923 0.152 0.848
#> GSM955068 2 0.5842 0.8963 0.140 0.860
#> GSM955069 2 0.6343 0.8902 0.160 0.840
#> GSM955070 2 0.1414 0.8989 0.020 0.980
#> GSM955071 2 0.7674 0.8471 0.224 0.776
#> GSM955077 2 0.7376 0.8593 0.208 0.792
#> GSM955080 2 0.0000 0.8919 0.000 1.000
#> GSM955081 2 0.4161 0.9061 0.084 0.916
#> GSM955082 2 0.5519 0.8997 0.128 0.872
#> GSM955085 2 0.0000 0.8919 0.000 1.000
#> GSM955090 1 0.0000 0.9579 1.000 0.000
#> GSM955094 2 0.5519 0.8994 0.128 0.872
#> GSM955096 2 0.5946 0.8946 0.144 0.856
#> GSM955102 2 0.8144 0.8201 0.252 0.748
#> GSM955105 2 0.6712 0.8825 0.176 0.824
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.0592 0.8323 0.000 0.012 0.988
#> GSM955008 3 0.2625 0.8109 0.000 0.084 0.916
#> GSM955016 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955019 2 0.3941 0.8088 0.000 0.844 0.156
#> GSM955022 3 0.2878 0.8015 0.000 0.096 0.904
#> GSM955023 3 0.4235 0.7418 0.000 0.176 0.824
#> GSM955027 2 0.0592 0.7858 0.000 0.988 0.012
#> GSM955043 3 0.6308 0.1182 0.000 0.492 0.508
#> GSM955048 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955049 3 0.6305 -0.0952 0.000 0.484 0.516
#> GSM955054 3 0.5327 0.6127 0.000 0.272 0.728
#> GSM955064 2 0.1411 0.7825 0.000 0.964 0.036
#> GSM955072 2 0.4121 0.8069 0.000 0.832 0.168
#> GSM955075 2 0.0000 0.7835 0.000 1.000 0.000
#> GSM955079 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955087 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955088 3 0.2537 0.8147 0.000 0.080 0.920
#> GSM955089 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955095 2 0.0000 0.7835 0.000 1.000 0.000
#> GSM955097 2 0.0592 0.7811 0.000 0.988 0.012
#> GSM955101 3 0.6280 0.0805 0.000 0.460 0.540
#> GSM954999 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955001 2 0.4062 0.8071 0.000 0.836 0.164
#> GSM955003 2 0.3879 0.8091 0.000 0.848 0.152
#> GSM955004 2 0.0000 0.7835 0.000 1.000 0.000
#> GSM955005 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955009 2 0.4062 0.8071 0.000 0.836 0.164
#> GSM955011 3 0.0237 0.8331 0.004 0.000 0.996
#> GSM955012 3 0.6308 0.0375 0.000 0.492 0.508
#> GSM955013 3 0.5650 0.5070 0.000 0.312 0.688
#> GSM955015 2 0.6235 0.3006 0.000 0.564 0.436
#> GSM955017 3 0.1289 0.8242 0.032 0.000 0.968
#> GSM955021 2 0.4062 0.8071 0.000 0.836 0.164
#> GSM955025 3 0.0237 0.8337 0.000 0.004 0.996
#> GSM955028 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955029 2 0.0424 0.7824 0.000 0.992 0.008
#> GSM955030 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955032 3 0.0592 0.8338 0.000 0.012 0.988
#> GSM955033 3 0.1031 0.8326 0.000 0.024 0.976
#> GSM955034 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955035 2 0.4121 0.8060 0.000 0.832 0.168
#> GSM955036 3 0.0592 0.8301 0.000 0.012 0.988
#> GSM955037 3 0.5988 0.4575 0.368 0.000 0.632
#> GSM955039 3 0.1163 0.8325 0.000 0.028 0.972
#> GSM955041 3 0.6307 0.1127 0.000 0.488 0.512
#> GSM955042 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955045 2 0.4178 0.8048 0.000 0.828 0.172
#> GSM955046 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955047 1 0.3192 0.8455 0.888 0.000 0.112
#> GSM955050 3 0.6062 0.3471 0.000 0.384 0.616
#> GSM955052 3 0.0592 0.8323 0.000 0.012 0.988
#> GSM955053 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955056 3 0.1163 0.8315 0.000 0.028 0.972
#> GSM955058 2 0.0000 0.7835 0.000 1.000 0.000
#> GSM955059 3 0.0237 0.8338 0.000 0.004 0.996
#> GSM955060 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955061 2 0.4654 0.6528 0.000 0.792 0.208
#> GSM955065 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955066 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955067 1 0.4178 0.7786 0.828 0.000 0.172
#> GSM955073 3 0.5138 0.6501 0.000 0.252 0.748
#> GSM955074 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955076 2 0.5882 0.5390 0.000 0.652 0.348
#> GSM955078 2 0.0237 0.7842 0.000 0.996 0.004
#> GSM955083 3 0.0237 0.8338 0.000 0.004 0.996
#> GSM955084 2 0.0000 0.7835 0.000 1.000 0.000
#> GSM955086 3 0.5138 0.6148 0.000 0.252 0.748
#> GSM955091 3 0.5948 0.4222 0.000 0.360 0.640
#> GSM955092 2 0.4931 0.7560 0.000 0.768 0.232
#> GSM955093 3 0.1860 0.8266 0.000 0.052 0.948
#> GSM955098 3 0.4842 0.6767 0.000 0.224 0.776
#> GSM955099 2 0.4399 0.7947 0.000 0.812 0.188
#> GSM955100 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955103 2 0.6095 0.4729 0.000 0.608 0.392
#> GSM955104 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955106 2 0.5835 0.4380 0.000 0.660 0.340
#> GSM955000 1 0.6154 0.1772 0.592 0.000 0.408
#> GSM955006 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955007 2 0.6295 0.1898 0.000 0.528 0.472
#> GSM955010 3 0.4233 0.7536 0.004 0.160 0.836
#> GSM955014 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955018 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955020 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955024 2 0.5926 0.5361 0.000 0.644 0.356
#> GSM955026 3 0.4887 0.6771 0.000 0.228 0.772
#> GSM955031 3 0.6244 0.1813 0.000 0.440 0.560
#> GSM955038 3 0.2537 0.8115 0.000 0.080 0.920
#> GSM955040 3 0.5397 0.5856 0.000 0.280 0.720
#> GSM955044 2 0.2711 0.7751 0.000 0.912 0.088
#> GSM955051 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955055 2 0.4178 0.8058 0.000 0.828 0.172
#> GSM955057 1 0.0000 0.9454 1.000 0.000 0.000
#> GSM955062 2 0.4062 0.8071 0.000 0.836 0.164
#> GSM955063 3 0.0592 0.8323 0.000 0.012 0.988
#> GSM955068 3 0.5678 0.4317 0.000 0.316 0.684
#> GSM955069 3 0.1643 0.8279 0.000 0.044 0.956
#> GSM955070 2 0.5497 0.6739 0.000 0.708 0.292
#> GSM955071 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955077 3 0.0424 0.8343 0.000 0.008 0.992
#> GSM955080 2 0.0000 0.7835 0.000 1.000 0.000
#> GSM955081 3 0.3816 0.7644 0.000 0.148 0.852
#> GSM955082 3 0.5291 0.5912 0.000 0.268 0.732
#> GSM955085 2 0.4452 0.7883 0.000 0.808 0.192
#> GSM955090 1 0.0424 0.9395 0.992 0.000 0.008
#> GSM955094 3 0.3267 0.7884 0.000 0.116 0.884
#> GSM955096 3 0.0000 0.8331 0.000 0.000 1.000
#> GSM955102 3 0.1753 0.8172 0.048 0.000 0.952
#> GSM955105 3 0.3038 0.7968 0.000 0.104 0.896
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 3 0.5693 -0.1119 0.000 0.472 0.504 0.024
#> GSM955008 2 0.4422 0.6200 0.000 0.736 0.256 0.008
#> GSM955016 3 0.0000 0.7964 0.000 0.000 1.000 0.000
#> GSM955019 2 0.2081 0.6446 0.000 0.916 0.000 0.084
#> GSM955022 3 0.3653 0.7306 0.000 0.028 0.844 0.128
#> GSM955023 2 0.4175 0.6682 0.000 0.784 0.200 0.016
#> GSM955027 2 0.5345 0.0413 0.000 0.560 0.012 0.428
#> GSM955043 4 0.6521 0.5841 0.000 0.124 0.256 0.620
#> GSM955048 1 0.0000 0.9243 1.000 0.000 0.000 0.000
#> GSM955049 2 0.5188 0.6527 0.000 0.756 0.148 0.096
#> GSM955054 2 0.3032 0.6758 0.000 0.868 0.124 0.008
#> GSM955064 2 0.4980 0.4567 0.000 0.680 0.016 0.304
#> GSM955072 2 0.6616 0.4721 0.000 0.624 0.156 0.220
#> GSM955075 4 0.3801 0.7517 0.000 0.220 0.000 0.780
#> GSM955079 3 0.0000 0.7964 0.000 0.000 1.000 0.000
#> GSM955087 1 0.2011 0.9016 0.920 0.000 0.000 0.080
#> GSM955088 3 0.5517 0.0998 0.000 0.412 0.568 0.020
#> GSM955089 1 0.0000 0.9243 1.000 0.000 0.000 0.000
#> GSM955095 4 0.3837 0.7478 0.000 0.224 0.000 0.776
#> GSM955097 4 0.3764 0.7544 0.000 0.216 0.000 0.784
#> GSM955101 2 0.4547 0.6820 0.000 0.804 0.104 0.092
#> GSM954999 3 0.1389 0.7856 0.000 0.000 0.952 0.048
#> GSM955001 2 0.6010 0.5341 0.000 0.676 0.104 0.220
#> GSM955003 2 0.0188 0.6503 0.000 0.996 0.000 0.004
#> GSM955004 4 0.3688 0.7559 0.000 0.208 0.000 0.792
#> GSM955005 3 0.0000 0.7964 0.000 0.000 1.000 0.000
#> GSM955009 2 0.5530 0.5560 0.000 0.712 0.076 0.212
#> GSM955011 3 0.0469 0.7967 0.012 0.000 0.988 0.000
#> GSM955012 4 0.4927 0.5575 0.000 0.024 0.264 0.712
#> GSM955013 3 0.5878 0.4490 0.000 0.312 0.632 0.056
#> GSM955015 2 0.4706 0.6362 0.000 0.788 0.072 0.140
#> GSM955017 3 0.1022 0.7908 0.032 0.000 0.968 0.000
#> GSM955021 2 0.1902 0.6512 0.000 0.932 0.004 0.064
#> GSM955025 3 0.0188 0.7970 0.000 0.000 0.996 0.004
#> GSM955028 1 0.2011 0.9016 0.920 0.000 0.000 0.080
#> GSM955029 4 0.2345 0.7705 0.000 0.100 0.000 0.900
#> GSM955030 3 0.0000 0.7964 0.000 0.000 1.000 0.000
#> GSM955032 3 0.4356 0.5257 0.000 0.292 0.708 0.000
#> GSM955033 3 0.2124 0.7833 0.000 0.040 0.932 0.028
#> GSM955034 1 0.0336 0.9233 0.992 0.000 0.000 0.008
#> GSM955035 2 0.3751 0.5849 0.000 0.800 0.004 0.196
#> GSM955036 3 0.3569 0.6671 0.000 0.000 0.804 0.196
#> GSM955037 3 0.6222 0.3949 0.304 0.000 0.616 0.080
#> GSM955039 3 0.4730 0.3702 0.000 0.364 0.636 0.000
#> GSM955041 4 0.6871 0.5873 0.000 0.240 0.168 0.592
#> GSM955042 3 0.1356 0.7916 0.008 0.032 0.960 0.000
#> GSM955045 3 0.7416 0.1845 0.000 0.240 0.516 0.244
#> GSM955046 3 0.0000 0.7964 0.000 0.000 1.000 0.000
#> GSM955047 1 0.2530 0.8266 0.888 0.000 0.112 0.000
#> GSM955050 3 0.6646 0.4086 0.000 0.204 0.624 0.172
#> GSM955052 2 0.5047 0.5655 0.000 0.668 0.316 0.016
#> GSM955053 1 0.2011 0.9016 0.920 0.000 0.000 0.080
#> GSM955056 2 0.4898 0.4314 0.000 0.584 0.416 0.000
#> GSM955058 4 0.2345 0.7705 0.000 0.100 0.000 0.900
#> GSM955059 3 0.0188 0.7970 0.000 0.000 0.996 0.004
#> GSM955060 1 0.0000 0.9243 1.000 0.000 0.000 0.000
#> GSM955061 4 0.4415 0.6964 0.000 0.056 0.140 0.804
#> GSM955065 1 0.2011 0.9016 0.920 0.000 0.000 0.080
#> GSM955066 3 0.0000 0.7964 0.000 0.000 1.000 0.000
#> GSM955067 1 0.3219 0.7582 0.836 0.000 0.164 0.000
#> GSM955073 2 0.4093 0.6821 0.000 0.832 0.096 0.072
#> GSM955074 3 0.0000 0.7964 0.000 0.000 1.000 0.000
#> GSM955076 2 0.0707 0.6516 0.000 0.980 0.000 0.020
#> GSM955078 4 0.4277 0.6629 0.000 0.280 0.000 0.720
#> GSM955083 3 0.0524 0.7975 0.004 0.000 0.988 0.008
#> GSM955084 4 0.3486 0.7658 0.000 0.188 0.000 0.812
#> GSM955086 2 0.5957 0.4118 0.000 0.540 0.420 0.040
#> GSM955091 3 0.7795 -0.0291 0.000 0.312 0.420 0.268
#> GSM955092 2 0.4022 0.6620 0.000 0.836 0.068 0.096
#> GSM955093 2 0.4936 0.5808 0.000 0.672 0.316 0.012
#> GSM955098 2 0.3708 0.6534 0.000 0.832 0.148 0.020
#> GSM955099 2 0.4057 0.6339 0.000 0.816 0.032 0.152
#> GSM955100 3 0.0336 0.7965 0.008 0.000 0.992 0.000
#> GSM955103 4 0.7530 0.2676 0.000 0.212 0.308 0.480
#> GSM955104 3 0.0000 0.7964 0.000 0.000 1.000 0.000
#> GSM955106 4 0.3796 0.7476 0.000 0.096 0.056 0.848
#> GSM955000 1 0.4898 0.2168 0.584 0.000 0.416 0.000
#> GSM955006 1 0.0000 0.9243 1.000 0.000 0.000 0.000
#> GSM955007 3 0.7006 0.3183 0.000 0.216 0.580 0.204
#> GSM955010 3 0.6379 0.4068 0.012 0.288 0.632 0.068
#> GSM955014 1 0.0336 0.9215 0.992 0.000 0.008 0.000
#> GSM955018 3 0.0817 0.7937 0.000 0.024 0.976 0.000
#> GSM955020 1 0.0188 0.9234 0.996 0.000 0.004 0.000
#> GSM955024 2 0.7262 0.3854 0.000 0.540 0.252 0.208
#> GSM955026 2 0.4507 0.6291 0.000 0.756 0.224 0.020
#> GSM955031 2 0.4465 0.6428 0.000 0.800 0.056 0.144
#> GSM955038 3 0.2751 0.7677 0.000 0.056 0.904 0.040
#> GSM955040 3 0.5998 0.5712 0.004 0.192 0.696 0.108
#> GSM955044 2 0.4999 -0.2383 0.000 0.508 0.000 0.492
#> GSM955051 1 0.0000 0.9243 1.000 0.000 0.000 0.000
#> GSM955055 2 0.6167 0.5152 0.000 0.664 0.116 0.220
#> GSM955057 1 0.0000 0.9243 1.000 0.000 0.000 0.000
#> GSM955062 2 0.4307 0.5943 0.000 0.784 0.024 0.192
#> GSM955063 2 0.4382 0.5831 0.000 0.704 0.296 0.000
#> GSM955068 3 0.3505 0.7300 0.000 0.088 0.864 0.048
#> GSM955069 3 0.1520 0.7896 0.000 0.024 0.956 0.020
#> GSM955070 2 0.1820 0.6675 0.000 0.944 0.036 0.020
#> GSM955071 3 0.0592 0.7969 0.000 0.016 0.984 0.000
#> GSM955077 3 0.1443 0.7941 0.008 0.028 0.960 0.004
#> GSM955080 4 0.2973 0.7744 0.000 0.144 0.000 0.856
#> GSM955081 2 0.4567 0.5861 0.000 0.716 0.276 0.008
#> GSM955082 2 0.5650 0.3586 0.000 0.544 0.432 0.024
#> GSM955085 2 0.6844 0.0665 0.000 0.500 0.396 0.104
#> GSM955090 1 0.0188 0.9234 0.996 0.000 0.004 0.000
#> GSM955094 3 0.5488 -0.0592 0.000 0.452 0.532 0.016
#> GSM955096 3 0.3569 0.6579 0.000 0.196 0.804 0.000
#> GSM955102 3 0.2586 0.7674 0.040 0.000 0.912 0.048
#> GSM955105 2 0.4585 0.5704 0.000 0.668 0.332 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.5806 0.1191 0.000 0.012 0.464 0.464 0.060
#> GSM955008 3 0.3826 0.5874 0.000 0.004 0.752 0.236 0.008
#> GSM955016 4 0.5513 0.5663 0.188 0.144 0.000 0.664 0.004
#> GSM955019 3 0.2580 0.6048 0.000 0.044 0.892 0.000 0.064
#> GSM955022 4 0.3441 0.6789 0.000 0.004 0.028 0.828 0.140
#> GSM955023 3 0.3938 0.6322 0.000 0.016 0.796 0.164 0.024
#> GSM955027 3 0.5797 0.0779 0.000 0.064 0.528 0.012 0.396
#> GSM955043 5 0.6048 0.5362 0.000 0.032 0.108 0.224 0.636
#> GSM955048 1 0.2970 0.4155 0.828 0.168 0.000 0.004 0.000
#> GSM955049 3 0.4593 0.5993 0.000 0.000 0.748 0.128 0.124
#> GSM955054 3 0.2392 0.6352 0.000 0.004 0.888 0.104 0.004
#> GSM955064 3 0.6172 0.3907 0.000 0.172 0.600 0.012 0.216
#> GSM955072 3 0.6940 0.2876 0.000 0.324 0.496 0.040 0.140
#> GSM955075 5 0.4581 0.6223 0.000 0.072 0.196 0.000 0.732
#> GSM955079 4 0.0000 0.7256 0.000 0.000 0.000 1.000 0.000
#> GSM955087 2 0.4305 0.6542 0.488 0.512 0.000 0.000 0.000
#> GSM955088 4 0.5103 0.0742 0.008 0.004 0.428 0.544 0.016
#> GSM955089 1 0.2280 0.6564 0.880 0.120 0.000 0.000 0.000
#> GSM955095 5 0.6433 0.5004 0.000 0.312 0.200 0.000 0.488
#> GSM955097 5 0.6243 0.5379 0.000 0.284 0.184 0.000 0.532
#> GSM955101 3 0.4128 0.6405 0.000 0.032 0.816 0.092 0.060
#> GSM954999 4 0.2069 0.7173 0.012 0.000 0.000 0.912 0.076
#> GSM955001 3 0.6809 0.2964 0.000 0.324 0.504 0.032 0.140
#> GSM955003 3 0.0671 0.6135 0.000 0.016 0.980 0.000 0.004
#> GSM955004 5 0.6358 0.5051 0.000 0.328 0.180 0.000 0.492
#> GSM955005 4 0.0000 0.7256 0.000 0.000 0.000 1.000 0.000
#> GSM955009 3 0.6864 0.3020 0.000 0.320 0.508 0.040 0.132
#> GSM955011 4 0.3481 0.7010 0.100 0.056 0.000 0.840 0.004
#> GSM955012 5 0.2886 0.5548 0.000 0.000 0.008 0.148 0.844
#> GSM955013 4 0.5922 0.4136 0.000 0.064 0.272 0.624 0.040
#> GSM955015 3 0.5519 0.5734 0.000 0.108 0.720 0.056 0.116
#> GSM955017 4 0.2484 0.7186 0.068 0.028 0.000 0.900 0.004
#> GSM955021 3 0.2149 0.6118 0.000 0.036 0.916 0.000 0.048
#> GSM955025 4 0.0162 0.7263 0.000 0.000 0.000 0.996 0.004
#> GSM955028 2 0.4305 0.6542 0.488 0.512 0.000 0.000 0.000
#> GSM955029 5 0.0963 0.6621 0.000 0.000 0.036 0.000 0.964
#> GSM955030 4 0.0324 0.7263 0.000 0.004 0.000 0.992 0.004
#> GSM955032 4 0.3796 0.4943 0.000 0.000 0.300 0.700 0.000
#> GSM955033 4 0.4591 0.7017 0.084 0.040 0.032 0.808 0.036
#> GSM955034 1 0.3424 0.2198 0.760 0.240 0.000 0.000 0.000
#> GSM955035 3 0.5451 0.4732 0.000 0.212 0.664 0.004 0.120
#> GSM955036 4 0.4134 0.5660 0.008 0.008 0.000 0.720 0.264
#> GSM955037 2 0.5685 0.0901 0.084 0.520 0.000 0.396 0.000
#> GSM955039 4 0.4088 0.3467 0.000 0.000 0.368 0.632 0.000
#> GSM955041 5 0.4845 0.5774 0.000 0.000 0.148 0.128 0.724
#> GSM955042 4 0.6272 0.5386 0.216 0.132 0.020 0.624 0.008
#> GSM955045 4 0.8339 -0.2198 0.000 0.316 0.208 0.324 0.152
#> GSM955046 4 0.0000 0.7256 0.000 0.000 0.000 1.000 0.000
#> GSM955047 1 0.3620 0.6019 0.824 0.068 0.000 0.108 0.000
#> GSM955050 4 0.6728 0.4021 0.000 0.092 0.168 0.612 0.128
#> GSM955052 3 0.4750 0.5610 0.000 0.004 0.692 0.260 0.044
#> GSM955053 2 0.4304 0.6508 0.484 0.516 0.000 0.000 0.000
#> GSM955056 3 0.4341 0.3891 0.000 0.004 0.592 0.404 0.000
#> GSM955058 5 0.0880 0.6599 0.000 0.000 0.032 0.000 0.968
#> GSM955059 4 0.0162 0.7263 0.000 0.000 0.000 0.996 0.004
#> GSM955060 1 0.1851 0.6730 0.912 0.088 0.000 0.000 0.000
#> GSM955061 5 0.1952 0.6208 0.000 0.000 0.004 0.084 0.912
#> GSM955065 2 0.4306 0.6480 0.492 0.508 0.000 0.000 0.000
#> GSM955066 4 0.0000 0.7256 0.000 0.000 0.000 1.000 0.000
#> GSM955067 1 0.2561 0.5541 0.856 0.000 0.000 0.144 0.000
#> GSM955073 3 0.4091 0.6358 0.000 0.012 0.808 0.084 0.096
#> GSM955074 4 0.5135 0.6082 0.172 0.120 0.000 0.704 0.004
#> GSM955076 3 0.0807 0.6155 0.000 0.012 0.976 0.000 0.012
#> GSM955078 5 0.4270 0.6073 0.000 0.048 0.204 0.000 0.748
#> GSM955083 4 0.4911 0.6133 0.160 0.100 0.000 0.732 0.008
#> GSM955084 5 0.6162 0.5414 0.000 0.308 0.160 0.000 0.532
#> GSM955086 3 0.6350 0.3799 0.016 0.060 0.516 0.388 0.020
#> GSM955091 4 0.7666 -0.0870 0.000 0.048 0.276 0.352 0.324
#> GSM955092 3 0.5742 0.4440 0.000 0.284 0.628 0.040 0.048
#> GSM955093 3 0.4152 0.5473 0.000 0.000 0.692 0.296 0.012
#> GSM955098 3 0.3554 0.6130 0.000 0.020 0.836 0.120 0.024
#> GSM955099 3 0.5190 0.5675 0.000 0.112 0.736 0.032 0.120
#> GSM955100 4 0.5743 0.5353 0.220 0.144 0.000 0.632 0.004
#> GSM955103 5 0.7992 0.2729 0.000 0.144 0.164 0.256 0.436
#> GSM955104 4 0.0162 0.7263 0.000 0.000 0.000 0.996 0.004
#> GSM955106 5 0.1739 0.6413 0.000 0.004 0.024 0.032 0.940
#> GSM955000 1 0.4287 0.0528 0.540 0.000 0.000 0.460 0.000
#> GSM955006 1 0.2719 0.6327 0.852 0.144 0.000 0.000 0.004
#> GSM955007 4 0.7765 0.1307 0.000 0.184 0.192 0.488 0.136
#> GSM955010 4 0.6063 0.4207 0.032 0.024 0.276 0.628 0.040
#> GSM955014 1 0.0963 0.6775 0.964 0.000 0.000 0.036 0.000
#> GSM955018 4 0.0703 0.7245 0.000 0.000 0.024 0.976 0.000
#> GSM955020 1 0.3002 0.5280 0.856 0.116 0.000 0.028 0.000
#> GSM955024 3 0.7803 0.3275 0.000 0.192 0.480 0.196 0.132
#> GSM955026 3 0.4474 0.5900 0.000 0.016 0.740 0.216 0.028
#> GSM955031 3 0.4407 0.6029 0.000 0.040 0.796 0.052 0.112
#> GSM955038 4 0.2673 0.7122 0.000 0.024 0.048 0.900 0.028
#> GSM955040 4 0.9086 0.3239 0.196 0.160 0.148 0.416 0.080
#> GSM955044 5 0.4088 0.3421 0.000 0.000 0.368 0.000 0.632
#> GSM955051 1 0.1153 0.6877 0.964 0.024 0.000 0.008 0.004
#> GSM955055 3 0.6876 0.2920 0.000 0.324 0.500 0.036 0.140
#> GSM955057 1 0.0000 0.6820 1.000 0.000 0.000 0.000 0.000
#> GSM955062 3 0.5512 0.5088 0.000 0.168 0.692 0.020 0.120
#> GSM955063 3 0.3684 0.5461 0.000 0.000 0.720 0.280 0.000
#> GSM955068 4 0.5105 0.5557 0.000 0.188 0.080 0.716 0.016
#> GSM955069 4 0.2653 0.7257 0.016 0.040 0.016 0.908 0.020
#> GSM955070 3 0.2444 0.6303 0.000 0.028 0.912 0.036 0.024
#> GSM955071 4 0.3920 0.6939 0.096 0.056 0.016 0.828 0.004
#> GSM955077 4 0.1834 0.7297 0.032 0.004 0.016 0.940 0.008
#> GSM955080 5 0.4852 0.6474 0.000 0.184 0.100 0.000 0.716
#> GSM955081 3 0.4153 0.5734 0.000 0.016 0.740 0.236 0.008
#> GSM955082 3 0.5456 0.3105 0.000 0.032 0.524 0.428 0.016
#> GSM955085 3 0.7830 0.0458 0.000 0.260 0.380 0.292 0.068
#> GSM955090 1 0.0324 0.6868 0.992 0.004 0.000 0.004 0.000
#> GSM955094 4 0.5399 -0.0169 0.000 0.020 0.432 0.524 0.024
#> GSM955096 4 0.3109 0.6251 0.000 0.000 0.200 0.800 0.000
#> GSM955102 4 0.3419 0.6270 0.016 0.180 0.000 0.804 0.000
#> GSM955105 3 0.4832 0.5322 0.000 0.032 0.668 0.292 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.5312 0.3349 0.000 0.524 0.364 0.000 0.112 0.000
#> GSM955008 2 0.3023 0.6719 0.000 0.784 0.212 0.004 0.000 0.000
#> GSM955016 3 0.7612 0.3583 0.152 0.020 0.484 0.180 0.012 0.152
#> GSM955019 2 0.3314 0.5340 0.000 0.740 0.000 0.256 0.004 0.000
#> GSM955022 3 0.3693 0.6426 0.000 0.016 0.800 0.048 0.136 0.000
#> GSM955023 2 0.3501 0.6857 0.000 0.816 0.128 0.044 0.004 0.008
#> GSM955027 2 0.6153 -0.0412 0.000 0.420 0.004 0.304 0.272 0.000
#> GSM955043 5 0.6027 0.4166 0.000 0.036 0.220 0.176 0.568 0.000
#> GSM955048 1 0.2462 0.5855 0.860 0.000 0.004 0.000 0.004 0.132
#> GSM955049 2 0.5320 0.6421 0.000 0.692 0.112 0.084 0.112 0.000
#> GSM955054 2 0.2856 0.6775 0.000 0.856 0.076 0.068 0.000 0.000
#> GSM955064 4 0.5913 0.3017 0.000 0.356 0.012 0.480 0.152 0.000
#> GSM955072 4 0.3314 0.5413 0.000 0.256 0.004 0.740 0.000 0.000
#> GSM955075 5 0.4219 0.2541 0.000 0.020 0.000 0.388 0.592 0.000
#> GSM955079 3 0.0000 0.7222 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955087 6 0.2378 0.9197 0.152 0.000 0.000 0.000 0.000 0.848
#> GSM955088 3 0.5098 -0.0784 0.012 0.424 0.512 0.052 0.000 0.000
#> GSM955089 1 0.4624 0.6272 0.712 0.012 0.000 0.180 0.000 0.096
#> GSM955095 4 0.3424 0.4331 0.000 0.024 0.000 0.772 0.204 0.000
#> GSM955097 4 0.3853 0.3135 0.000 0.016 0.000 0.680 0.304 0.000
#> GSM955101 2 0.4373 0.6251 0.000 0.720 0.084 0.192 0.004 0.000
#> GSM954999 3 0.2214 0.7006 0.016 0.000 0.888 0.000 0.096 0.000
#> GSM955001 4 0.3078 0.5937 0.000 0.192 0.012 0.796 0.000 0.000
#> GSM955003 2 0.1204 0.6405 0.000 0.944 0.000 0.056 0.000 0.000
#> GSM955004 4 0.3168 0.4307 0.000 0.016 0.000 0.792 0.192 0.000
#> GSM955005 3 0.0000 0.7222 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955009 4 0.3315 0.5934 0.000 0.200 0.020 0.780 0.000 0.000
#> GSM955011 3 0.5717 0.6164 0.132 0.020 0.688 0.032 0.016 0.112
#> GSM955012 5 0.1155 0.6522 0.000 0.004 0.036 0.004 0.956 0.000
#> GSM955013 3 0.5111 0.4004 0.000 0.152 0.624 0.224 0.000 0.000
#> GSM955015 2 0.4706 0.3639 0.000 0.624 0.048 0.320 0.008 0.000
#> GSM955017 3 0.3396 0.7055 0.056 0.020 0.848 0.012 0.000 0.064
#> GSM955021 2 0.3240 0.5493 0.000 0.752 0.000 0.244 0.004 0.000
#> GSM955025 3 0.0146 0.7227 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM955028 6 0.2378 0.9197 0.152 0.000 0.000 0.000 0.000 0.848
#> GSM955029 5 0.1075 0.6691 0.000 0.000 0.000 0.048 0.952 0.000
#> GSM955030 3 0.0405 0.7236 0.000 0.008 0.988 0.000 0.000 0.004
#> GSM955032 3 0.3772 0.4540 0.004 0.320 0.672 0.000 0.004 0.000
#> GSM955033 3 0.6039 0.6277 0.088 0.080 0.688 0.088 0.016 0.040
#> GSM955034 1 0.3996 -0.1863 0.512 0.000 0.000 0.000 0.004 0.484
#> GSM955035 4 0.4088 0.1754 0.000 0.436 0.004 0.556 0.004 0.000
#> GSM955036 3 0.3971 0.4363 0.004 0.004 0.652 0.000 0.336 0.004
#> GSM955037 6 0.2302 0.6988 0.008 0.000 0.120 0.000 0.000 0.872
#> GSM955039 3 0.3717 0.2742 0.000 0.384 0.616 0.000 0.000 0.000
#> GSM955041 5 0.4298 0.6101 0.000 0.096 0.116 0.024 0.764 0.000
#> GSM955042 3 0.8161 0.2949 0.192 0.036 0.432 0.176 0.020 0.144
#> GSM955045 4 0.3558 0.4857 0.000 0.032 0.184 0.780 0.004 0.000
#> GSM955046 3 0.0000 0.7222 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955047 1 0.4743 0.6548 0.740 0.000 0.104 0.116 0.004 0.036
#> GSM955050 3 0.5547 0.3085 0.000 0.044 0.580 0.320 0.004 0.052
#> GSM955052 2 0.4331 0.6598 0.000 0.704 0.220 0.000 0.076 0.000
#> GSM955053 6 0.2378 0.9197 0.152 0.000 0.000 0.000 0.000 0.848
#> GSM955056 2 0.3872 0.5050 0.000 0.604 0.392 0.004 0.000 0.000
#> GSM955058 5 0.1007 0.6667 0.000 0.000 0.000 0.044 0.956 0.000
#> GSM955059 3 0.0146 0.7227 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM955060 1 0.3683 0.6679 0.784 0.000 0.000 0.160 0.004 0.052
#> GSM955061 5 0.1074 0.6659 0.000 0.000 0.012 0.028 0.960 0.000
#> GSM955065 6 0.2454 0.9124 0.160 0.000 0.000 0.000 0.000 0.840
#> GSM955066 3 0.0000 0.7222 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955067 1 0.2278 0.6592 0.868 0.000 0.128 0.000 0.004 0.000
#> GSM955073 2 0.4838 0.6509 0.000 0.732 0.064 0.120 0.084 0.000
#> GSM955074 3 0.7454 0.4157 0.168 0.020 0.516 0.132 0.016 0.148
#> GSM955076 2 0.1957 0.6342 0.000 0.888 0.000 0.112 0.000 0.000
#> GSM955078 5 0.4877 0.5177 0.000 0.148 0.000 0.192 0.660 0.000
#> GSM955083 3 0.6070 0.4898 0.124 0.000 0.620 0.164 0.004 0.088
#> GSM955084 4 0.3558 0.3666 0.000 0.016 0.000 0.736 0.248 0.000
#> GSM955086 2 0.6183 0.4391 0.032 0.476 0.368 0.120 0.000 0.004
#> GSM955091 5 0.7288 0.2089 0.000 0.184 0.312 0.128 0.376 0.000
#> GSM955092 4 0.4264 0.4540 0.000 0.332 0.032 0.636 0.000 0.000
#> GSM955093 2 0.3717 0.6496 0.000 0.708 0.276 0.016 0.000 0.000
#> GSM955098 2 0.2001 0.6547 0.000 0.920 0.044 0.020 0.016 0.000
#> GSM955099 2 0.4578 0.2921 0.000 0.568 0.032 0.396 0.004 0.000
#> GSM955100 3 0.7929 0.2921 0.196 0.020 0.436 0.180 0.016 0.152
#> GSM955103 5 0.7284 0.1694 0.000 0.112 0.228 0.276 0.384 0.000
#> GSM955104 3 0.0146 0.7228 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM955106 5 0.0858 0.6638 0.000 0.000 0.004 0.028 0.968 0.000
#> GSM955000 1 0.4124 0.1214 0.516 0.000 0.476 0.000 0.004 0.004
#> GSM955006 1 0.5745 0.5699 0.632 0.020 0.000 0.180 0.016 0.152
#> GSM955007 4 0.4399 0.1241 0.000 0.024 0.460 0.516 0.000 0.000
#> GSM955010 3 0.6082 0.4311 0.044 0.204 0.616 0.120 0.004 0.012
#> GSM955014 1 0.1226 0.7077 0.952 0.000 0.040 0.000 0.004 0.004
#> GSM955018 3 0.0858 0.7200 0.000 0.028 0.968 0.000 0.004 0.000
#> GSM955020 1 0.2065 0.6781 0.912 0.000 0.032 0.000 0.004 0.052
#> GSM955024 4 0.5583 0.3385 0.000 0.284 0.180 0.536 0.000 0.000
#> GSM955026 2 0.4327 0.5980 0.000 0.748 0.156 0.080 0.016 0.000
#> GSM955031 2 0.4476 0.4669 0.000 0.640 0.052 0.308 0.000 0.000
#> GSM955038 3 0.2492 0.7057 0.000 0.036 0.888 0.068 0.008 0.000
#> GSM955040 4 0.8496 -0.1995 0.164 0.132 0.280 0.332 0.004 0.088
#> GSM955044 5 0.3314 0.5112 0.000 0.256 0.000 0.004 0.740 0.000
#> GSM955051 1 0.2195 0.7063 0.916 0.020 0.012 0.004 0.004 0.044
#> GSM955055 4 0.2933 0.5880 0.000 0.200 0.004 0.796 0.000 0.000
#> GSM955057 1 0.0260 0.7113 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM955062 4 0.4486 0.0891 0.000 0.464 0.016 0.512 0.008 0.000
#> GSM955063 2 0.3151 0.6568 0.000 0.748 0.252 0.000 0.000 0.000
#> GSM955068 3 0.4979 0.4003 0.000 0.056 0.612 0.316 0.016 0.000
#> GSM955069 3 0.3541 0.7073 0.020 0.020 0.852 0.036 0.012 0.060
#> GSM955070 2 0.2163 0.6389 0.000 0.892 0.008 0.096 0.004 0.000
#> GSM955071 3 0.4878 0.6670 0.048 0.012 0.764 0.088 0.016 0.072
#> GSM955077 3 0.2678 0.7173 0.048 0.048 0.888 0.008 0.004 0.004
#> GSM955080 5 0.4264 0.1592 0.000 0.016 0.000 0.484 0.500 0.000
#> GSM955081 2 0.2980 0.6466 0.000 0.808 0.180 0.012 0.000 0.000
#> GSM955082 2 0.5375 0.4062 0.000 0.484 0.416 0.096 0.004 0.000
#> GSM955085 4 0.5643 0.4083 0.000 0.248 0.192 0.556 0.004 0.000
#> GSM955090 1 0.0551 0.7141 0.984 0.000 0.004 0.000 0.008 0.004
#> GSM955094 3 0.5137 -0.0866 0.000 0.416 0.508 0.072 0.004 0.000
#> GSM955096 3 0.2883 0.6044 0.000 0.212 0.788 0.000 0.000 0.000
#> GSM955102 3 0.3023 0.6197 0.004 0.000 0.784 0.000 0.000 0.212
#> GSM955105 2 0.4512 0.6325 0.000 0.696 0.248 0.020 0.004 0.032
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> CV:pam 107 0.707 2
#> CV:pam 93 0.852 3
#> CV:pam 86 0.458 4
#> CV:pam 77 0.140 5
#> CV:pam 67 0.200 6
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 31589 rows and 108 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 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 0.980 0.962 0.983 0.315 0.695 0.695
#> 3 3 0.414 0.716 0.818 0.877 0.648 0.503
#> 4 4 0.304 0.586 0.752 0.128 0.858 0.647
#> 5 5 0.452 0.524 0.688 0.104 0.909 0.720
#> 6 6 0.473 0.432 0.624 0.057 0.820 0.438
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
#> GSM955002 2 0.0000 0.984 0.000 1.000
#> GSM955008 2 0.0000 0.984 0.000 1.000
#> GSM955016 2 0.6887 0.771 0.184 0.816
#> GSM955019 2 0.0000 0.984 0.000 1.000
#> GSM955022 2 0.0000 0.984 0.000 1.000
#> GSM955023 2 0.0000 0.984 0.000 1.000
#> GSM955027 2 0.0000 0.984 0.000 1.000
#> GSM955043 2 0.0000 0.984 0.000 1.000
#> GSM955048 1 0.0000 0.975 1.000 0.000
#> GSM955049 2 0.0000 0.984 0.000 1.000
#> GSM955054 2 0.0000 0.984 0.000 1.000
#> GSM955064 2 0.0000 0.984 0.000 1.000
#> GSM955072 2 0.0000 0.984 0.000 1.000
#> GSM955075 2 0.0000 0.984 0.000 1.000
#> GSM955079 2 0.0000 0.984 0.000 1.000
#> GSM955087 1 0.0000 0.975 1.000 0.000
#> GSM955088 2 0.0000 0.984 0.000 1.000
#> GSM955089 1 0.0000 0.975 1.000 0.000
#> GSM955095 2 0.0000 0.984 0.000 1.000
#> GSM955097 2 0.0000 0.984 0.000 1.000
#> GSM955101 2 0.0000 0.984 0.000 1.000
#> GSM954999 2 0.0000 0.984 0.000 1.000
#> GSM955001 2 0.0000 0.984 0.000 1.000
#> GSM955003 2 0.0000 0.984 0.000 1.000
#> GSM955004 2 0.0000 0.984 0.000 1.000
#> GSM955005 2 0.0000 0.984 0.000 1.000
#> GSM955009 2 0.0000 0.984 0.000 1.000
#> GSM955011 2 0.8207 0.662 0.256 0.744
#> GSM955012 2 0.0000 0.984 0.000 1.000
#> GSM955013 2 0.0000 0.984 0.000 1.000
#> GSM955015 2 0.0000 0.984 0.000 1.000
#> GSM955017 1 0.0000 0.975 1.000 0.000
#> GSM955021 2 0.0000 0.984 0.000 1.000
#> GSM955025 2 0.0000 0.984 0.000 1.000
#> GSM955028 1 0.0000 0.975 1.000 0.000
#> GSM955029 2 0.0000 0.984 0.000 1.000
#> GSM955030 2 0.0000 0.984 0.000 1.000
#> GSM955032 2 0.0000 0.984 0.000 1.000
#> GSM955033 2 0.0000 0.984 0.000 1.000
#> GSM955034 1 0.0000 0.975 1.000 0.000
#> GSM955035 2 0.0000 0.984 0.000 1.000
#> GSM955036 2 0.0000 0.984 0.000 1.000
#> GSM955037 1 0.0000 0.975 1.000 0.000
#> GSM955039 2 0.0000 0.984 0.000 1.000
#> GSM955041 2 0.0000 0.984 0.000 1.000
#> GSM955042 2 0.9087 0.518 0.324 0.676
#> GSM955045 2 0.0000 0.984 0.000 1.000
#> GSM955046 2 0.0000 0.984 0.000 1.000
#> GSM955047 1 0.3879 0.911 0.924 0.076
#> GSM955050 2 0.0000 0.984 0.000 1.000
#> GSM955052 2 0.0000 0.984 0.000 1.000
#> GSM955053 1 0.0000 0.975 1.000 0.000
#> GSM955056 2 0.0000 0.984 0.000 1.000
#> GSM955058 2 0.0000 0.984 0.000 1.000
#> GSM955059 2 0.0000 0.984 0.000 1.000
#> GSM955060 1 0.0000 0.975 1.000 0.000
#> GSM955061 2 0.0000 0.984 0.000 1.000
#> GSM955065 1 0.0000 0.975 1.000 0.000
#> GSM955066 2 0.0000 0.984 0.000 1.000
#> GSM955067 1 0.8081 0.682 0.752 0.248
#> GSM955073 2 0.0000 0.984 0.000 1.000
#> GSM955074 1 0.5842 0.839 0.860 0.140
#> GSM955076 2 0.0000 0.984 0.000 1.000
#> GSM955078 2 0.0000 0.984 0.000 1.000
#> GSM955083 2 0.0000 0.984 0.000 1.000
#> GSM955084 2 0.0000 0.984 0.000 1.000
#> GSM955086 2 0.0000 0.984 0.000 1.000
#> GSM955091 2 0.0000 0.984 0.000 1.000
#> GSM955092 2 0.0000 0.984 0.000 1.000
#> GSM955093 2 0.0000 0.984 0.000 1.000
#> GSM955098 2 0.0000 0.984 0.000 1.000
#> GSM955099 2 0.0000 0.984 0.000 1.000
#> GSM955100 2 0.8608 0.612 0.284 0.716
#> GSM955103 2 0.0000 0.984 0.000 1.000
#> GSM955104 2 0.0000 0.984 0.000 1.000
#> GSM955106 2 0.0000 0.984 0.000 1.000
#> GSM955000 1 0.0000 0.975 1.000 0.000
#> GSM955006 1 0.0376 0.972 0.996 0.004
#> GSM955007 2 0.0000 0.984 0.000 1.000
#> GSM955010 2 0.2236 0.950 0.036 0.964
#> GSM955014 1 0.0000 0.975 1.000 0.000
#> GSM955018 2 0.0000 0.984 0.000 1.000
#> GSM955020 1 0.0000 0.975 1.000 0.000
#> GSM955024 2 0.0000 0.984 0.000 1.000
#> GSM955026 2 0.0000 0.984 0.000 1.000
#> GSM955031 2 0.0000 0.984 0.000 1.000
#> GSM955038 2 0.0000 0.984 0.000 1.000
#> GSM955040 2 0.0376 0.981 0.004 0.996
#> GSM955044 2 0.0000 0.984 0.000 1.000
#> GSM955051 1 0.0000 0.975 1.000 0.000
#> GSM955055 2 0.0000 0.984 0.000 1.000
#> GSM955057 1 0.0000 0.975 1.000 0.000
#> GSM955062 2 0.0000 0.984 0.000 1.000
#> GSM955063 2 0.0000 0.984 0.000 1.000
#> GSM955068 2 0.0000 0.984 0.000 1.000
#> GSM955069 2 0.0000 0.984 0.000 1.000
#> GSM955070 2 0.0000 0.984 0.000 1.000
#> GSM955071 2 0.0376 0.981 0.004 0.996
#> GSM955077 2 0.0000 0.984 0.000 1.000
#> GSM955080 2 0.0000 0.984 0.000 1.000
#> GSM955081 2 0.0000 0.984 0.000 1.000
#> GSM955082 2 0.0000 0.984 0.000 1.000
#> GSM955085 2 0.0000 0.984 0.000 1.000
#> GSM955090 1 0.0000 0.975 1.000 0.000
#> GSM955094 2 0.0000 0.984 0.000 1.000
#> GSM955096 2 0.0000 0.984 0.000 1.000
#> GSM955102 2 0.8016 0.680 0.244 0.756
#> GSM955105 2 0.0000 0.984 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.5058 0.7114 0.000 0.756 0.244
#> GSM955008 3 0.5016 0.7447 0.000 0.240 0.760
#> GSM955016 1 0.7319 0.6215 0.708 0.164 0.128
#> GSM955019 2 0.3412 0.7542 0.000 0.876 0.124
#> GSM955022 3 0.6180 0.3134 0.000 0.416 0.584
#> GSM955023 2 0.6154 0.5131 0.000 0.592 0.408
#> GSM955027 2 0.2878 0.7568 0.000 0.904 0.096
#> GSM955043 2 0.2711 0.7593 0.000 0.912 0.088
#> GSM955048 1 0.0000 0.9232 1.000 0.000 0.000
#> GSM955049 2 0.5529 0.6728 0.000 0.704 0.296
#> GSM955054 2 0.6168 0.4528 0.000 0.588 0.412
#> GSM955064 2 0.5098 0.7230 0.000 0.752 0.248
#> GSM955072 2 0.1753 0.7432 0.000 0.952 0.048
#> GSM955075 2 0.3816 0.6918 0.000 0.852 0.148
#> GSM955079 3 0.3816 0.8419 0.000 0.148 0.852
#> GSM955087 1 0.0424 0.9223 0.992 0.000 0.008
#> GSM955088 3 0.3116 0.8517 0.000 0.108 0.892
#> GSM955089 1 0.0424 0.9226 0.992 0.000 0.008
#> GSM955095 2 0.5016 0.6952 0.000 0.760 0.240
#> GSM955097 2 0.5681 0.6569 0.016 0.748 0.236
#> GSM955101 3 0.4121 0.8299 0.000 0.168 0.832
#> GSM954999 2 0.7074 0.1889 0.020 0.500 0.480
#> GSM955001 2 0.5098 0.7253 0.000 0.752 0.248
#> GSM955003 2 0.6295 0.2504 0.000 0.528 0.472
#> GSM955004 2 0.1636 0.7171 0.016 0.964 0.020
#> GSM955005 3 0.5016 0.7235 0.000 0.240 0.760
#> GSM955009 2 0.2261 0.7483 0.000 0.932 0.068
#> GSM955011 1 0.6621 0.4918 0.684 0.032 0.284
#> GSM955012 2 0.5138 0.6699 0.000 0.748 0.252
#> GSM955013 2 0.6291 0.2460 0.000 0.532 0.468
#> GSM955015 2 0.6062 0.5088 0.000 0.616 0.384
#> GSM955017 1 0.0237 0.9233 0.996 0.000 0.004
#> GSM955021 2 0.5254 0.6912 0.000 0.736 0.264
#> GSM955025 2 0.2356 0.7466 0.000 0.928 0.072
#> GSM955028 1 0.0424 0.9223 0.992 0.000 0.008
#> GSM955029 2 0.3619 0.6835 0.000 0.864 0.136
#> GSM955030 3 0.3267 0.8415 0.000 0.116 0.884
#> GSM955032 3 0.3192 0.8525 0.000 0.112 0.888
#> GSM955033 2 0.4002 0.7545 0.000 0.840 0.160
#> GSM955034 1 0.0424 0.9223 0.992 0.000 0.008
#> GSM955035 2 0.4750 0.7294 0.000 0.784 0.216
#> GSM955036 3 0.4349 0.8081 0.020 0.128 0.852
#> GSM955037 1 0.2165 0.8895 0.936 0.000 0.064
#> GSM955039 3 0.5882 0.5566 0.000 0.348 0.652
#> GSM955041 2 0.5810 0.6200 0.000 0.664 0.336
#> GSM955042 1 0.6546 0.6977 0.756 0.096 0.148
#> GSM955045 2 0.5905 0.6078 0.000 0.648 0.352
#> GSM955046 3 0.4195 0.8192 0.012 0.136 0.852
#> GSM955047 1 0.0475 0.9223 0.992 0.004 0.004
#> GSM955050 2 0.5327 0.6972 0.000 0.728 0.272
#> GSM955052 3 0.3879 0.8402 0.000 0.152 0.848
#> GSM955053 1 0.0592 0.9228 0.988 0.000 0.012
#> GSM955056 3 0.6079 0.3457 0.000 0.388 0.612
#> GSM955058 2 0.4121 0.6948 0.000 0.832 0.168
#> GSM955059 3 0.2959 0.8497 0.000 0.100 0.900
#> GSM955060 1 0.0000 0.9232 1.000 0.000 0.000
#> GSM955061 2 0.4291 0.6930 0.000 0.820 0.180
#> GSM955065 1 0.0424 0.9223 0.992 0.000 0.008
#> GSM955066 3 0.3551 0.8307 0.000 0.132 0.868
#> GSM955067 1 0.5060 0.7569 0.816 0.156 0.028
#> GSM955073 3 0.3412 0.8475 0.000 0.124 0.876
#> GSM955074 1 0.1015 0.9157 0.980 0.012 0.008
#> GSM955076 2 0.4452 0.7291 0.000 0.808 0.192
#> GSM955078 2 0.0424 0.7319 0.000 0.992 0.008
#> GSM955083 2 0.6753 0.4991 0.016 0.596 0.388
#> GSM955084 2 0.1636 0.7171 0.016 0.964 0.020
#> GSM955086 3 0.3116 0.8524 0.000 0.108 0.892
#> GSM955091 2 0.2356 0.7498 0.000 0.928 0.072
#> GSM955092 2 0.6111 0.5113 0.000 0.604 0.396
#> GSM955093 3 0.3412 0.8475 0.000 0.124 0.876
#> GSM955098 2 0.2804 0.7394 0.016 0.924 0.060
#> GSM955099 2 0.2165 0.7472 0.000 0.936 0.064
#> GSM955100 1 0.7299 0.1871 0.556 0.032 0.412
#> GSM955103 3 0.6062 0.4615 0.000 0.384 0.616
#> GSM955104 3 0.3116 0.8519 0.000 0.108 0.892
#> GSM955106 2 0.3192 0.7476 0.000 0.888 0.112
#> GSM955000 1 0.0237 0.9233 0.996 0.000 0.004
#> GSM955006 1 0.0237 0.9233 0.996 0.000 0.004
#> GSM955007 3 0.4002 0.8288 0.000 0.160 0.840
#> GSM955010 3 0.3918 0.8346 0.012 0.120 0.868
#> GSM955014 1 0.0000 0.9232 1.000 0.000 0.000
#> GSM955018 3 0.3340 0.8476 0.000 0.120 0.880
#> GSM955020 1 0.0000 0.9232 1.000 0.000 0.000
#> GSM955024 2 0.6235 0.4229 0.000 0.564 0.436
#> GSM955026 2 0.2261 0.7480 0.000 0.932 0.068
#> GSM955031 2 0.6952 0.1941 0.016 0.504 0.480
#> GSM955038 2 0.3359 0.7493 0.016 0.900 0.084
#> GSM955040 2 0.6501 0.6421 0.020 0.664 0.316
#> GSM955044 2 0.0592 0.7362 0.000 0.988 0.012
#> GSM955051 1 0.0424 0.9226 0.992 0.000 0.008
#> GSM955055 2 0.4750 0.7347 0.000 0.784 0.216
#> GSM955057 1 0.0000 0.9232 1.000 0.000 0.000
#> GSM955062 2 0.5497 0.6720 0.000 0.708 0.292
#> GSM955063 3 0.3267 0.8502 0.000 0.116 0.884
#> GSM955068 2 0.0747 0.7378 0.000 0.984 0.016
#> GSM955069 3 0.3207 0.8416 0.012 0.084 0.904
#> GSM955070 2 0.3192 0.7621 0.000 0.888 0.112
#> GSM955071 3 0.5650 0.5971 0.000 0.312 0.688
#> GSM955077 2 0.4002 0.7485 0.000 0.840 0.160
#> GSM955080 2 0.5178 0.6730 0.000 0.744 0.256
#> GSM955081 2 0.6111 0.5040 0.000 0.604 0.396
#> GSM955082 3 0.6302 -0.0992 0.000 0.480 0.520
#> GSM955085 2 0.2625 0.7534 0.000 0.916 0.084
#> GSM955090 1 0.0424 0.9226 0.992 0.000 0.008
#> GSM955094 2 0.3879 0.7541 0.000 0.848 0.152
#> GSM955096 3 0.4062 0.8330 0.000 0.164 0.836
#> GSM955102 3 0.6266 0.6842 0.156 0.076 0.768
#> GSM955105 3 0.3192 0.8527 0.000 0.112 0.888
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.5775 0.5319 0.000 0.696 0.212 0.092
#> GSM955008 3 0.3356 0.6030 0.000 0.176 0.824 0.000
#> GSM955016 1 0.5319 0.7252 0.764 0.024 0.048 0.164
#> GSM955019 2 0.2846 0.5488 0.028 0.908 0.052 0.012
#> GSM955022 3 0.7591 0.5082 0.072 0.088 0.600 0.240
#> GSM955023 2 0.5815 0.2756 0.000 0.540 0.428 0.032
#> GSM955027 2 0.4548 0.5819 0.008 0.804 0.144 0.044
#> GSM955043 2 0.7374 0.4799 0.052 0.628 0.120 0.200
#> GSM955048 1 0.0188 0.9195 0.996 0.000 0.000 0.004
#> GSM955049 2 0.5339 0.5280 0.000 0.688 0.272 0.040
#> GSM955054 2 0.5155 0.3716 0.000 0.528 0.468 0.004
#> GSM955064 2 0.7926 0.4689 0.056 0.540 0.292 0.112
#> GSM955072 2 0.4952 0.5212 0.080 0.804 0.024 0.092
#> GSM955075 4 0.4054 0.6420 0.000 0.188 0.016 0.796
#> GSM955079 3 0.3648 0.7328 0.076 0.056 0.864 0.004
#> GSM955087 1 0.2530 0.8892 0.888 0.000 0.000 0.112
#> GSM955088 3 0.1209 0.6854 0.000 0.032 0.964 0.004
#> GSM955089 1 0.1821 0.9150 0.948 0.012 0.008 0.032
#> GSM955095 4 0.9043 0.0819 0.060 0.288 0.288 0.364
#> GSM955097 4 0.9340 0.2598 0.308 0.104 0.212 0.376
#> GSM955101 3 0.2593 0.7003 0.016 0.080 0.904 0.000
#> GSM954999 3 0.9149 0.2073 0.264 0.104 0.436 0.196
#> GSM955001 2 0.5522 0.5424 0.000 0.716 0.204 0.080
#> GSM955003 3 0.5137 -0.1804 0.000 0.452 0.544 0.004
#> GSM955004 2 0.7175 0.3357 0.116 0.612 0.028 0.244
#> GSM955005 3 0.4640 0.7254 0.092 0.068 0.820 0.020
#> GSM955009 2 0.5027 0.5506 0.116 0.796 0.064 0.024
#> GSM955011 1 0.2989 0.8579 0.884 0.012 0.100 0.004
#> GSM955012 4 0.4370 0.6377 0.000 0.156 0.044 0.800
#> GSM955013 3 0.8696 0.3036 0.080 0.180 0.492 0.248
#> GSM955015 2 0.7075 0.2444 0.000 0.488 0.384 0.128
#> GSM955017 1 0.0000 0.9196 1.000 0.000 0.000 0.000
#> GSM955021 2 0.5594 0.5798 0.040 0.672 0.284 0.004
#> GSM955025 2 0.4740 0.5377 0.116 0.808 0.060 0.016
#> GSM955028 1 0.2530 0.8892 0.888 0.000 0.000 0.112
#> GSM955029 4 0.4776 0.6045 0.000 0.244 0.024 0.732
#> GSM955030 3 0.3551 0.7194 0.096 0.020 0.868 0.016
#> GSM955032 3 0.1489 0.6913 0.000 0.044 0.952 0.004
#> GSM955033 2 0.9166 0.0508 0.096 0.396 0.188 0.320
#> GSM955034 1 0.2469 0.8902 0.892 0.000 0.000 0.108
#> GSM955035 2 0.4212 0.5772 0.000 0.772 0.216 0.012
#> GSM955036 3 0.8264 0.1946 0.252 0.024 0.460 0.264
#> GSM955037 1 0.5024 0.8205 0.780 0.004 0.112 0.104
#> GSM955039 3 0.7345 0.6007 0.076 0.100 0.644 0.180
#> GSM955041 2 0.8482 0.2308 0.072 0.416 0.392 0.120
#> GSM955042 1 0.3641 0.8676 0.868 0.008 0.072 0.052
#> GSM955045 2 0.7351 0.3385 0.012 0.520 0.344 0.124
#> GSM955046 3 0.5695 0.6733 0.104 0.032 0.760 0.104
#> GSM955047 1 0.0657 0.9198 0.984 0.012 0.004 0.000
#> GSM955050 2 0.8523 0.4243 0.120 0.516 0.260 0.104
#> GSM955052 3 0.1940 0.6852 0.000 0.076 0.924 0.000
#> GSM955053 1 0.2530 0.8892 0.888 0.000 0.000 0.112
#> GSM955056 3 0.4483 0.4395 0.000 0.284 0.712 0.004
#> GSM955058 4 0.4472 0.6331 0.000 0.220 0.020 0.760
#> GSM955059 3 0.3215 0.7316 0.092 0.032 0.876 0.000
#> GSM955060 1 0.0000 0.9196 1.000 0.000 0.000 0.000
#> GSM955061 4 0.4307 0.6454 0.000 0.192 0.024 0.784
#> GSM955065 1 0.2530 0.8892 0.888 0.000 0.000 0.112
#> GSM955066 3 0.4457 0.7102 0.092 0.016 0.828 0.064
#> GSM955067 1 0.3504 0.8707 0.876 0.020 0.024 0.080
#> GSM955073 3 0.3366 0.7316 0.096 0.028 0.872 0.004
#> GSM955074 1 0.2667 0.8959 0.912 0.008 0.020 0.060
#> GSM955076 2 0.5154 0.5580 0.120 0.788 0.068 0.024
#> GSM955078 2 0.5302 0.5310 0.100 0.784 0.028 0.088
#> GSM955083 3 0.9728 -0.0291 0.232 0.160 0.352 0.256
#> GSM955084 2 0.6816 0.3918 0.116 0.652 0.024 0.208
#> GSM955086 3 0.1209 0.6919 0.000 0.032 0.964 0.004
#> GSM955091 2 0.2716 0.5280 0.008 0.912 0.052 0.028
#> GSM955092 3 0.5250 -0.1290 0.000 0.440 0.552 0.008
#> GSM955093 3 0.3182 0.7309 0.096 0.028 0.876 0.000
#> GSM955098 2 0.5208 0.5286 0.132 0.784 0.052 0.032
#> GSM955099 2 0.2111 0.5165 0.000 0.932 0.044 0.024
#> GSM955100 1 0.3946 0.7630 0.812 0.012 0.172 0.004
#> GSM955103 3 0.7502 0.5892 0.076 0.128 0.636 0.160
#> GSM955104 3 0.4174 0.7107 0.116 0.024 0.836 0.024
#> GSM955106 4 0.7321 0.4161 0.012 0.312 0.132 0.544
#> GSM955000 1 0.0817 0.9199 0.976 0.000 0.024 0.000
#> GSM955006 1 0.1516 0.9155 0.960 0.008 0.016 0.016
#> GSM955007 3 0.6515 0.6381 0.084 0.048 0.700 0.168
#> GSM955010 3 0.4673 0.6785 0.156 0.016 0.796 0.032
#> GSM955014 1 0.0524 0.9201 0.988 0.008 0.000 0.004
#> GSM955018 3 0.3051 0.7317 0.088 0.028 0.884 0.000
#> GSM955020 1 0.0592 0.9201 0.984 0.000 0.000 0.016
#> GSM955024 3 0.7675 0.1287 0.024 0.376 0.480 0.120
#> GSM955026 2 0.5147 0.5265 0.116 0.792 0.060 0.032
#> GSM955031 2 0.7854 0.4196 0.216 0.512 0.256 0.016
#> GSM955038 2 0.7390 0.4574 0.124 0.652 0.132 0.092
#> GSM955040 2 0.8541 0.3938 0.136 0.460 0.332 0.072
#> GSM955044 2 0.7158 0.5092 0.092 0.660 0.076 0.172
#> GSM955051 1 0.0469 0.9200 0.988 0.012 0.000 0.000
#> GSM955055 2 0.3852 0.5854 0.000 0.800 0.192 0.008
#> GSM955057 1 0.0188 0.9195 0.996 0.000 0.000 0.004
#> GSM955062 2 0.4927 0.5443 0.000 0.712 0.264 0.024
#> GSM955063 3 0.3107 0.7322 0.080 0.036 0.884 0.000
#> GSM955068 2 0.5254 0.5486 0.100 0.792 0.044 0.064
#> GSM955069 3 0.2926 0.7247 0.096 0.012 0.888 0.004
#> GSM955070 2 0.5280 0.5517 0.000 0.748 0.156 0.096
#> GSM955071 3 0.6139 0.6321 0.120 0.164 0.704 0.012
#> GSM955077 2 0.5990 0.5247 0.132 0.724 0.128 0.016
#> GSM955080 4 0.7608 0.2522 0.000 0.328 0.216 0.456
#> GSM955081 2 0.7034 0.3371 0.076 0.496 0.412 0.016
#> GSM955082 3 0.5479 0.4996 0.024 0.264 0.696 0.016
#> GSM955085 2 0.3463 0.5628 0.004 0.868 0.096 0.032
#> GSM955090 1 0.1786 0.9124 0.948 0.008 0.008 0.036
#> GSM955094 2 0.6869 0.4326 0.016 0.636 0.132 0.216
#> GSM955096 3 0.2281 0.6806 0.000 0.096 0.904 0.000
#> GSM955102 3 0.6001 0.5487 0.248 0.008 0.676 0.068
#> GSM955105 3 0.1697 0.7045 0.016 0.028 0.952 0.004
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.4797 0.5172 0.000 0.724 0.172 NA 0.104
#> GSM955008 3 0.3878 0.5824 0.000 0.236 0.748 NA 0.000
#> GSM955016 1 0.5221 0.6888 0.720 0.012 0.004 NA 0.160
#> GSM955019 2 0.2721 0.5786 0.000 0.896 0.052 NA 0.016
#> GSM955022 3 0.6958 0.0139 0.012 0.188 0.432 NA 0.364
#> GSM955023 2 0.4286 0.4778 0.000 0.716 0.260 NA 0.020
#> GSM955027 2 0.3800 0.5622 0.000 0.812 0.108 NA 0.080
#> GSM955043 2 0.5956 0.0324 0.020 0.496 0.060 NA 0.424
#> GSM955048 1 0.1732 0.8189 0.920 0.000 0.000 NA 0.000
#> GSM955049 2 0.4267 0.5421 0.000 0.772 0.180 NA 0.020
#> GSM955054 3 0.4973 -0.0277 0.000 0.480 0.496 NA 0.004
#> GSM955064 2 0.5800 0.4643 0.008 0.640 0.196 NA 0.156
#> GSM955072 2 0.5956 0.4682 0.020 0.672 0.012 NA 0.120
#> GSM955075 5 0.2389 0.6088 0.000 0.116 0.000 NA 0.880
#> GSM955079 3 0.2338 0.7042 0.024 0.048 0.916 NA 0.004
#> GSM955087 1 0.4278 0.6390 0.548 0.000 0.000 NA 0.000
#> GSM955088 3 0.1106 0.7020 0.000 0.024 0.964 NA 0.000
#> GSM955089 1 0.2445 0.8089 0.884 0.000 0.004 NA 0.004
#> GSM955095 5 0.6351 0.5607 0.024 0.216 0.144 NA 0.612
#> GSM955097 5 0.6460 0.5845 0.144 0.056 0.124 NA 0.660
#> GSM955101 3 0.3106 0.6776 0.000 0.140 0.840 NA 0.000
#> GSM954999 5 0.8660 0.3329 0.152 0.084 0.312 NA 0.392
#> GSM955001 2 0.4596 0.5496 0.000 0.780 0.116 NA 0.076
#> GSM955003 3 0.4738 0.0549 0.000 0.464 0.520 NA 0.000
#> GSM955004 5 0.7112 -0.1051 0.048 0.368 0.000 NA 0.448
#> GSM955005 3 0.3351 0.6883 0.028 0.084 0.864 NA 0.016
#> GSM955009 2 0.6837 0.4626 0.040 0.604 0.056 NA 0.056
#> GSM955011 1 0.3483 0.7678 0.848 0.000 0.088 NA 0.012
#> GSM955012 5 0.2497 0.6099 0.000 0.112 0.004 NA 0.880
#> GSM955013 5 0.6850 0.1596 0.024 0.148 0.408 NA 0.420
#> GSM955015 2 0.6130 0.3447 0.000 0.556 0.264 NA 0.180
#> GSM955017 1 0.0609 0.8262 0.980 0.000 0.000 NA 0.000
#> GSM955021 2 0.5189 0.3173 0.012 0.584 0.380 NA 0.004
#> GSM955025 2 0.6612 0.4554 0.044 0.616 0.040 NA 0.052
#> GSM955028 1 0.4278 0.6390 0.548 0.000 0.000 NA 0.000
#> GSM955029 5 0.3167 0.5661 0.000 0.172 0.004 NA 0.820
#> GSM955030 3 0.2363 0.6854 0.024 0.000 0.912 NA 0.012
#> GSM955032 3 0.1525 0.7033 0.000 0.036 0.948 NA 0.004
#> GSM955033 5 0.6978 0.5608 0.032 0.176 0.216 NA 0.564
#> GSM955034 1 0.4273 0.6405 0.552 0.000 0.000 NA 0.000
#> GSM955035 2 0.3519 0.5669 0.000 0.828 0.136 NA 0.008
#> GSM955036 5 0.6444 0.4233 0.096 0.008 0.328 NA 0.548
#> GSM955037 1 0.6000 0.5336 0.452 0.000 0.096 NA 0.004
#> GSM955039 3 0.6507 0.3657 0.012 0.156 0.588 NA 0.232
#> GSM955041 2 0.6904 0.1188 0.012 0.464 0.256 NA 0.268
#> GSM955042 1 0.3883 0.7878 0.820 0.000 0.012 NA 0.060
#> GSM955045 2 0.6365 0.2069 0.000 0.520 0.228 NA 0.252
#> GSM955046 3 0.5936 0.5062 0.008 0.028 0.680 NA 0.144
#> GSM955047 1 0.0609 0.8262 0.980 0.000 0.000 NA 0.000
#> GSM955050 2 0.8781 0.2495 0.072 0.384 0.316 NA 0.096
#> GSM955052 3 0.2563 0.6881 0.000 0.120 0.872 NA 0.000
#> GSM955053 1 0.4278 0.6390 0.548 0.000 0.000 NA 0.000
#> GSM955056 3 0.5120 0.4219 0.000 0.328 0.628 NA 0.016
#> GSM955058 5 0.2964 0.5882 0.000 0.152 0.004 NA 0.840
#> GSM955059 3 0.2084 0.6859 0.004 0.008 0.920 NA 0.004
#> GSM955060 1 0.0609 0.8262 0.980 0.000 0.000 NA 0.000
#> GSM955061 5 0.2597 0.6089 0.000 0.120 0.004 NA 0.872
#> GSM955065 1 0.4278 0.6390 0.548 0.000 0.000 NA 0.000
#> GSM955066 3 0.2721 0.6881 0.020 0.008 0.904 NA 0.032
#> GSM955067 1 0.2166 0.8155 0.912 0.000 0.004 NA 0.012
#> GSM955073 3 0.4102 0.6616 0.004 0.080 0.796 NA 0.000
#> GSM955074 1 0.3299 0.7992 0.848 0.004 0.000 NA 0.040
#> GSM955076 2 0.6790 0.4727 0.040 0.612 0.056 NA 0.056
#> GSM955078 2 0.6721 0.3918 0.044 0.580 0.000 NA 0.192
#> GSM955083 5 0.7601 0.5378 0.104 0.112 0.236 NA 0.532
#> GSM955084 2 0.7137 0.1230 0.048 0.412 0.000 NA 0.404
#> GSM955086 3 0.1356 0.7025 0.000 0.028 0.956 NA 0.004
#> GSM955091 2 0.2521 0.5796 0.000 0.900 0.068 NA 0.008
#> GSM955092 2 0.5092 0.1349 0.000 0.524 0.440 NA 0.000
#> GSM955093 3 0.3449 0.6332 0.004 0.016 0.832 NA 0.008
#> GSM955098 2 0.6559 0.4493 0.044 0.612 0.028 NA 0.060
#> GSM955099 2 0.2381 0.5668 0.000 0.908 0.036 NA 0.004
#> GSM955100 1 0.3944 0.7282 0.812 0.000 0.124 NA 0.012
#> GSM955103 3 0.6755 0.2116 0.012 0.208 0.492 NA 0.288
#> GSM955104 3 0.2863 0.6926 0.032 0.024 0.900 NA 0.016
#> GSM955106 5 0.5955 0.5931 0.016 0.196 0.084 NA 0.676
#> GSM955000 1 0.2300 0.8133 0.908 0.000 0.052 NA 0.000
#> GSM955006 1 0.1872 0.8164 0.928 0.000 0.020 NA 0.000
#> GSM955007 3 0.6602 0.3164 0.000 0.144 0.552 NA 0.276
#> GSM955010 3 0.3708 0.6431 0.056 0.000 0.836 NA 0.016
#> GSM955014 1 0.1478 0.8234 0.936 0.000 0.000 NA 0.000
#> GSM955018 3 0.2464 0.6705 0.004 0.012 0.892 NA 0.000
#> GSM955020 1 0.2230 0.8260 0.884 0.000 0.000 NA 0.000
#> GSM955024 3 0.6740 0.0465 0.000 0.380 0.404 NA 0.212
#> GSM955026 2 0.6514 0.4498 0.040 0.612 0.028 NA 0.060
#> GSM955031 2 0.7723 0.1818 0.172 0.408 0.356 NA 0.012
#> GSM955038 2 0.8626 0.3124 0.124 0.480 0.096 NA 0.100
#> GSM955040 3 0.8464 -0.0156 0.172 0.288 0.420 NA 0.052
#> GSM955044 2 0.6051 0.0895 0.020 0.500 0.016 NA 0.428
#> GSM955051 1 0.0324 0.8266 0.992 0.000 0.004 NA 0.000
#> GSM955055 2 0.3160 0.5715 0.000 0.852 0.116 NA 0.004
#> GSM955057 1 0.1732 0.8189 0.920 0.000 0.000 NA 0.000
#> GSM955062 2 0.3965 0.5461 0.000 0.784 0.180 NA 0.008
#> GSM955063 3 0.3110 0.6916 0.000 0.080 0.860 NA 0.000
#> GSM955068 2 0.6540 0.4637 0.044 0.624 0.016 NA 0.092
#> GSM955069 3 0.3067 0.6256 0.004 0.000 0.844 NA 0.012
#> GSM955070 2 0.4401 0.5269 0.000 0.764 0.104 NA 0.132
#> GSM955071 3 0.4911 0.6383 0.072 0.152 0.752 NA 0.004
#> GSM955077 2 0.7348 0.3830 0.052 0.544 0.140 NA 0.020
#> GSM955080 5 0.5585 0.5607 0.004 0.232 0.120 NA 0.644
#> GSM955081 3 0.5153 0.0793 0.012 0.452 0.520 NA 0.008
#> GSM955082 3 0.4240 0.5239 0.004 0.304 0.684 NA 0.000
#> GSM955085 2 0.2396 0.5787 0.000 0.904 0.068 NA 0.024
#> GSM955090 1 0.2573 0.8074 0.880 0.000 0.000 NA 0.016
#> GSM955094 2 0.5426 0.3255 0.004 0.636 0.084 NA 0.276
#> GSM955096 3 0.2464 0.6973 0.000 0.096 0.888 NA 0.000
#> GSM955102 3 0.4991 0.5000 0.032 0.000 0.668 NA 0.016
#> GSM955105 3 0.1461 0.7027 0.000 0.028 0.952 NA 0.004
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.2834 0.5272 0.000 0.852 0.020 0.008 0.120 0.000
#> GSM955008 2 0.4779 -0.0661 0.040 0.488 0.468 0.004 0.000 0.000
#> GSM955016 1 0.5756 0.6008 0.580 0.000 0.000 0.036 0.108 0.276
#> GSM955019 2 0.3489 0.3064 0.000 0.708 0.004 0.288 0.000 0.000
#> GSM955022 2 0.5960 -0.1717 0.008 0.424 0.144 0.004 0.420 0.000
#> GSM955023 2 0.1616 0.5869 0.000 0.932 0.048 0.000 0.020 0.000
#> GSM955027 2 0.1719 0.5694 0.000 0.928 0.008 0.008 0.056 0.000
#> GSM955043 2 0.4151 -0.0618 0.000 0.576 0.008 0.004 0.412 0.000
#> GSM955048 6 0.4120 -0.5295 0.468 0.000 0.004 0.004 0.000 0.524
#> GSM955049 2 0.0405 0.5806 0.000 0.988 0.004 0.000 0.008 0.000
#> GSM955054 2 0.4998 0.1680 0.056 0.552 0.384 0.008 0.000 0.000
#> GSM955064 2 0.2487 0.5582 0.000 0.876 0.032 0.000 0.092 0.000
#> GSM955072 4 0.5168 0.5310 0.008 0.324 0.000 0.584 0.084 0.000
#> GSM955075 5 0.1972 0.5819 0.024 0.056 0.000 0.004 0.916 0.000
#> GSM955079 3 0.3101 0.5807 0.000 0.244 0.756 0.000 0.000 0.000
#> GSM955087 6 0.0000 0.5407 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955088 3 0.3370 0.6024 0.012 0.212 0.772 0.004 0.000 0.000
#> GSM955089 1 0.4742 0.7141 0.636 0.000 0.004 0.032 0.016 0.312
#> GSM955095 5 0.5073 0.5411 0.028 0.284 0.056 0.000 0.632 0.000
#> GSM955097 5 0.5727 0.5358 0.044 0.028 0.088 0.016 0.700 0.124
#> GSM955101 3 0.4226 0.3032 0.012 0.404 0.580 0.004 0.000 0.000
#> GSM954999 5 0.8798 0.3754 0.156 0.224 0.128 0.016 0.356 0.120
#> GSM955001 2 0.1219 0.5692 0.000 0.948 0.004 0.000 0.048 0.000
#> GSM955003 2 0.5064 0.1320 0.060 0.540 0.392 0.008 0.000 0.000
#> GSM955004 4 0.6609 0.5260 0.036 0.060 0.004 0.532 0.304 0.064
#> GSM955005 3 0.3938 0.4785 0.012 0.312 0.672 0.000 0.004 0.000
#> GSM955009 4 0.3352 0.7323 0.016 0.144 0.024 0.816 0.000 0.000
#> GSM955011 1 0.6316 0.6247 0.544 0.028 0.036 0.092 0.000 0.300
#> GSM955012 5 0.2271 0.5801 0.032 0.056 0.004 0.004 0.904 0.000
#> GSM955013 5 0.6117 0.2733 0.016 0.372 0.148 0.000 0.460 0.004
#> GSM955015 2 0.4805 0.4749 0.012 0.696 0.116 0.000 0.176 0.000
#> GSM955017 1 0.3995 0.5664 0.516 0.000 0.000 0.004 0.000 0.480
#> GSM955021 2 0.5530 0.2541 0.032 0.580 0.308 0.080 0.000 0.000
#> GSM955025 4 0.3338 0.7415 0.012 0.152 0.024 0.812 0.000 0.000
#> GSM955028 6 0.0000 0.5407 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955029 5 0.3531 0.5356 0.032 0.152 0.004 0.008 0.804 0.000
#> GSM955030 3 0.4497 0.6577 0.104 0.124 0.752 0.004 0.004 0.012
#> GSM955032 3 0.3648 0.5739 0.016 0.240 0.740 0.004 0.000 0.000
#> GSM955033 5 0.6282 0.5209 0.036 0.272 0.100 0.020 0.568 0.004
#> GSM955034 6 0.0508 0.5370 0.012 0.000 0.000 0.004 0.000 0.984
#> GSM955035 2 0.0291 0.5809 0.000 0.992 0.004 0.000 0.004 0.000
#> GSM955036 5 0.6133 0.4638 0.044 0.004 0.240 0.012 0.596 0.104
#> GSM955037 6 0.5321 0.2646 0.092 0.000 0.248 0.020 0.004 0.636
#> GSM955039 2 0.6165 0.0580 0.008 0.452 0.272 0.000 0.268 0.000
#> GSM955041 2 0.3867 0.4325 0.000 0.748 0.052 0.000 0.200 0.000
#> GSM955042 1 0.4914 0.7062 0.648 0.000 0.004 0.036 0.028 0.284
#> GSM955045 2 0.3440 0.4702 0.000 0.776 0.028 0.000 0.196 0.000
#> GSM955046 3 0.6646 0.3205 0.188 0.124 0.560 0.008 0.120 0.000
#> GSM955047 1 0.4310 0.5714 0.512 0.000 0.004 0.012 0.000 0.472
#> GSM955050 2 0.8940 -0.0996 0.072 0.324 0.096 0.296 0.144 0.068
#> GSM955052 3 0.4310 0.3061 0.016 0.404 0.576 0.004 0.000 0.000
#> GSM955053 6 0.0508 0.5349 0.012 0.000 0.000 0.004 0.000 0.984
#> GSM955056 2 0.4957 0.0762 0.048 0.520 0.424 0.008 0.000 0.000
#> GSM955058 5 0.2981 0.5739 0.032 0.100 0.004 0.008 0.856 0.000
#> GSM955059 3 0.4102 0.6535 0.164 0.080 0.752 0.000 0.004 0.000
#> GSM955060 1 0.3993 0.5723 0.520 0.000 0.000 0.004 0.000 0.476
#> GSM955061 5 0.2781 0.5786 0.032 0.084 0.004 0.008 0.872 0.000
#> GSM955065 6 0.0000 0.5407 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955066 3 0.5064 0.6340 0.076 0.168 0.708 0.008 0.040 0.000
#> GSM955067 1 0.5108 0.7180 0.596 0.000 0.004 0.040 0.024 0.336
#> GSM955073 3 0.4321 0.5973 0.192 0.064 0.732 0.000 0.012 0.000
#> GSM955074 1 0.4979 0.6947 0.636 0.000 0.000 0.048 0.028 0.288
#> GSM955076 4 0.4795 0.7276 0.024 0.156 0.016 0.740 0.004 0.060
#> GSM955078 4 0.4819 0.6757 0.008 0.180 0.000 0.688 0.124 0.000
#> GSM955083 5 0.7831 0.4484 0.048 0.240 0.100 0.016 0.468 0.128
#> GSM955084 4 0.6315 0.5675 0.032 0.060 0.000 0.568 0.276 0.064
#> GSM955086 3 0.3329 0.5980 0.008 0.220 0.768 0.004 0.000 0.000
#> GSM955091 2 0.3306 0.4467 0.008 0.796 0.008 0.184 0.004 0.000
#> GSM955092 2 0.4302 0.3208 0.036 0.668 0.292 0.004 0.000 0.000
#> GSM955093 3 0.3473 0.5911 0.192 0.004 0.780 0.000 0.024 0.000
#> GSM955098 4 0.3454 0.7166 0.024 0.064 0.016 0.852 0.004 0.040
#> GSM955099 2 0.3830 0.2419 0.008 0.704 0.004 0.280 0.004 0.000
#> GSM955100 1 0.6594 0.5582 0.536 0.032 0.076 0.068 0.000 0.288
#> GSM955103 2 0.6007 -0.1078 0.004 0.444 0.208 0.000 0.344 0.000
#> GSM955104 3 0.6893 0.5344 0.092 0.200 0.580 0.012 0.040 0.076
#> GSM955106 5 0.4886 0.6091 0.032 0.144 0.016 0.008 0.744 0.056
#> GSM955000 6 0.5258 -0.4281 0.412 0.000 0.084 0.004 0.000 0.500
#> GSM955006 1 0.5411 0.6694 0.540 0.000 0.004 0.096 0.004 0.356
#> GSM955007 5 0.7609 0.1471 0.136 0.284 0.252 0.004 0.324 0.000
#> GSM955010 3 0.5630 0.6109 0.096 0.072 0.708 0.004 0.036 0.084
#> GSM955014 6 0.4468 -0.5794 0.484 0.000 0.004 0.020 0.000 0.492
#> GSM955018 3 0.3529 0.6402 0.172 0.036 0.788 0.000 0.004 0.000
#> GSM955020 1 0.5125 0.6603 0.540 0.000 0.004 0.076 0.000 0.380
#> GSM955024 2 0.3717 0.4994 0.000 0.776 0.064 0.000 0.160 0.000
#> GSM955026 4 0.2757 0.7347 0.016 0.104 0.016 0.864 0.000 0.000
#> GSM955031 2 0.7699 0.1488 0.044 0.436 0.176 0.080 0.004 0.260
#> GSM955038 4 0.7965 0.5659 0.172 0.104 0.052 0.516 0.060 0.096
#> GSM955040 2 0.9258 -0.0155 0.228 0.296 0.124 0.164 0.036 0.152
#> GSM955044 5 0.6035 0.2592 0.000 0.308 0.008 0.208 0.476 0.000
#> GSM955051 1 0.4315 0.5927 0.524 0.000 0.008 0.008 0.000 0.460
#> GSM955055 2 0.0363 0.5831 0.000 0.988 0.012 0.000 0.000 0.000
#> GSM955057 6 0.4120 -0.5295 0.468 0.000 0.004 0.004 0.000 0.524
#> GSM955062 2 0.0622 0.5811 0.000 0.980 0.008 0.000 0.012 0.000
#> GSM955063 3 0.4745 0.6248 0.188 0.136 0.676 0.000 0.000 0.000
#> GSM955068 4 0.4197 0.6934 0.012 0.196 0.004 0.744 0.044 0.000
#> GSM955069 3 0.3689 0.5841 0.192 0.004 0.772 0.004 0.028 0.000
#> GSM955070 2 0.2313 0.5435 0.000 0.884 0.012 0.004 0.100 0.000
#> GSM955071 2 0.6167 -0.1500 0.048 0.452 0.432 0.020 0.004 0.044
#> GSM955077 4 0.6628 0.5685 0.048 0.244 0.076 0.580 0.016 0.036
#> GSM955080 5 0.4516 0.5907 0.016 0.240 0.040 0.004 0.700 0.000
#> GSM955081 2 0.4267 0.1189 0.008 0.564 0.420 0.008 0.000 0.000
#> GSM955082 2 0.3923 0.0908 0.004 0.580 0.416 0.000 0.000 0.000
#> GSM955085 2 0.2730 0.5085 0.004 0.856 0.004 0.124 0.012 0.000
#> GSM955090 1 0.4973 0.7052 0.620 0.000 0.000 0.052 0.020 0.308
#> GSM955094 2 0.3926 0.3121 0.000 0.708 0.012 0.012 0.268 0.000
#> GSM955096 3 0.4562 0.3146 0.032 0.388 0.576 0.004 0.000 0.000
#> GSM955102 3 0.5572 0.4924 0.200 0.000 0.644 0.008 0.028 0.120
#> GSM955105 3 0.3329 0.5980 0.008 0.220 0.768 0.004 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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> CV:mclust 108 0.782 2
#> CV:mclust 95 0.929 3
#> CV:mclust 79 0.797 4
#> CV:mclust 70 0.616 5
#> CV:mclust 67 0.296 6
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 31589 rows and 108 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 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 0.813 0.883 0.952 0.4590 0.551 0.551
#> 3 3 0.592 0.737 0.876 0.2960 0.797 0.655
#> 4 4 0.591 0.699 0.858 0.1790 0.778 0.529
#> 5 5 0.536 0.553 0.747 0.0962 0.866 0.588
#> 6 6 0.551 0.457 0.676 0.0550 0.925 0.692
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
#> GSM955002 2 0.0000 0.9457 0.000 1.000
#> GSM955008 2 0.0000 0.9457 0.000 1.000
#> GSM955016 1 0.0000 0.9513 1.000 0.000
#> GSM955019 2 0.0000 0.9457 0.000 1.000
#> GSM955022 2 0.0672 0.9395 0.008 0.992
#> GSM955023 2 0.0000 0.9457 0.000 1.000
#> GSM955027 2 0.0000 0.9457 0.000 1.000
#> GSM955043 2 0.0000 0.9457 0.000 1.000
#> GSM955048 1 0.0000 0.9513 1.000 0.000
#> GSM955049 2 0.0000 0.9457 0.000 1.000
#> GSM955054 2 0.0000 0.9457 0.000 1.000
#> GSM955064 2 0.0000 0.9457 0.000 1.000
#> GSM955072 2 0.0000 0.9457 0.000 1.000
#> GSM955075 2 0.0000 0.9457 0.000 1.000
#> GSM955079 2 0.0000 0.9457 0.000 1.000
#> GSM955087 1 0.0000 0.9513 1.000 0.000
#> GSM955088 2 0.9635 0.4082 0.388 0.612
#> GSM955089 1 0.0000 0.9513 1.000 0.000
#> GSM955095 2 0.0000 0.9457 0.000 1.000
#> GSM955097 2 0.9661 0.3981 0.392 0.608
#> GSM955101 2 0.0000 0.9457 0.000 1.000
#> GSM954999 1 0.2043 0.9280 0.968 0.032
#> GSM955001 2 0.0000 0.9457 0.000 1.000
#> GSM955003 2 0.0000 0.9457 0.000 1.000
#> GSM955004 2 0.0000 0.9457 0.000 1.000
#> GSM955005 2 0.4431 0.8667 0.092 0.908
#> GSM955009 2 0.0000 0.9457 0.000 1.000
#> GSM955011 1 0.0000 0.9513 1.000 0.000
#> GSM955012 2 0.0000 0.9457 0.000 1.000
#> GSM955013 2 0.7056 0.7538 0.192 0.808
#> GSM955015 2 0.0000 0.9457 0.000 1.000
#> GSM955017 1 0.0000 0.9513 1.000 0.000
#> GSM955021 2 0.0000 0.9457 0.000 1.000
#> GSM955025 2 0.0000 0.9457 0.000 1.000
#> GSM955028 1 0.0000 0.9513 1.000 0.000
#> GSM955029 2 0.0000 0.9457 0.000 1.000
#> GSM955030 1 0.0000 0.9513 1.000 0.000
#> GSM955032 2 0.6247 0.7974 0.156 0.844
#> GSM955033 2 0.8081 0.6762 0.248 0.752
#> GSM955034 1 0.0000 0.9513 1.000 0.000
#> GSM955035 2 0.0000 0.9457 0.000 1.000
#> GSM955036 2 0.9209 0.5216 0.336 0.664
#> GSM955037 1 0.0000 0.9513 1.000 0.000
#> GSM955039 2 0.0000 0.9457 0.000 1.000
#> GSM955041 2 0.0000 0.9457 0.000 1.000
#> GSM955042 1 0.0000 0.9513 1.000 0.000
#> GSM955045 2 0.0000 0.9457 0.000 1.000
#> GSM955046 2 0.0000 0.9457 0.000 1.000
#> GSM955047 1 0.0000 0.9513 1.000 0.000
#> GSM955050 1 0.0672 0.9463 0.992 0.008
#> GSM955052 2 0.0000 0.9457 0.000 1.000
#> GSM955053 1 0.0000 0.9513 1.000 0.000
#> GSM955056 2 0.0000 0.9457 0.000 1.000
#> GSM955058 2 0.0000 0.9457 0.000 1.000
#> GSM955059 2 0.8207 0.6644 0.256 0.744
#> GSM955060 1 0.0000 0.9513 1.000 0.000
#> GSM955061 2 0.0000 0.9457 0.000 1.000
#> GSM955065 1 0.0000 0.9513 1.000 0.000
#> GSM955066 1 0.3584 0.8947 0.932 0.068
#> GSM955067 1 0.0000 0.9513 1.000 0.000
#> GSM955073 2 0.0000 0.9457 0.000 1.000
#> GSM955074 1 0.0000 0.9513 1.000 0.000
#> GSM955076 2 0.0000 0.9457 0.000 1.000
#> GSM955078 2 0.0000 0.9457 0.000 1.000
#> GSM955083 1 0.7674 0.7121 0.776 0.224
#> GSM955084 2 0.0000 0.9457 0.000 1.000
#> GSM955086 2 0.9732 0.3690 0.404 0.596
#> GSM955091 2 0.0000 0.9457 0.000 1.000
#> GSM955092 2 0.0000 0.9457 0.000 1.000
#> GSM955093 2 0.0000 0.9457 0.000 1.000
#> GSM955098 2 0.0000 0.9457 0.000 1.000
#> GSM955099 2 0.0000 0.9457 0.000 1.000
#> GSM955100 1 0.0000 0.9513 1.000 0.000
#> GSM955103 2 0.0000 0.9457 0.000 1.000
#> GSM955104 2 0.7883 0.6949 0.236 0.764
#> GSM955106 2 0.0000 0.9457 0.000 1.000
#> GSM955000 1 0.0000 0.9513 1.000 0.000
#> GSM955006 1 0.0000 0.9513 1.000 0.000
#> GSM955007 2 0.0000 0.9457 0.000 1.000
#> GSM955010 1 0.0000 0.9513 1.000 0.000
#> GSM955014 1 0.0000 0.9513 1.000 0.000
#> GSM955018 2 0.0000 0.9457 0.000 1.000
#> GSM955020 1 0.0000 0.9513 1.000 0.000
#> GSM955024 2 0.0000 0.9457 0.000 1.000
#> GSM955026 2 0.0000 0.9457 0.000 1.000
#> GSM955031 1 0.9954 0.1798 0.540 0.460
#> GSM955038 1 0.9896 0.2438 0.560 0.440
#> GSM955040 1 0.0000 0.9513 1.000 0.000
#> GSM955044 2 0.0000 0.9457 0.000 1.000
#> GSM955051 1 0.0000 0.9513 1.000 0.000
#> GSM955055 2 0.0000 0.9457 0.000 1.000
#> GSM955057 1 0.0000 0.9513 1.000 0.000
#> GSM955062 2 0.0000 0.9457 0.000 1.000
#> GSM955063 2 0.0000 0.9457 0.000 1.000
#> GSM955068 2 0.0000 0.9457 0.000 1.000
#> GSM955069 2 0.9732 0.3688 0.404 0.596
#> GSM955070 2 0.0000 0.9457 0.000 1.000
#> GSM955071 1 0.8016 0.6798 0.756 0.244
#> GSM955077 2 0.9988 0.0229 0.480 0.520
#> GSM955080 2 0.0000 0.9457 0.000 1.000
#> GSM955081 2 0.0000 0.9457 0.000 1.000
#> GSM955082 2 0.0000 0.9457 0.000 1.000
#> GSM955085 2 0.0000 0.9457 0.000 1.000
#> GSM955090 1 0.0000 0.9513 1.000 0.000
#> GSM955094 2 0.0376 0.9426 0.004 0.996
#> GSM955096 2 0.0000 0.9457 0.000 1.000
#> GSM955102 1 0.0938 0.9432 0.988 0.012
#> GSM955105 1 0.5059 0.8478 0.888 0.112
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.2796 0.8124 0.000 0.092 0.908
#> GSM955008 3 0.0892 0.8304 0.000 0.020 0.980
#> GSM955016 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955019 3 0.5397 0.6212 0.000 0.280 0.720
#> GSM955022 3 0.1163 0.8263 0.000 0.028 0.972
#> GSM955023 3 0.0892 0.8283 0.000 0.020 0.980
#> GSM955027 3 0.1860 0.8289 0.000 0.052 0.948
#> GSM955043 3 0.4842 0.6858 0.000 0.224 0.776
#> GSM955048 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955049 3 0.1860 0.8280 0.000 0.052 0.948
#> GSM955054 3 0.0000 0.8310 0.000 0.000 1.000
#> GSM955064 3 0.0424 0.8316 0.000 0.008 0.992
#> GSM955072 3 0.6062 0.2927 0.000 0.384 0.616
#> GSM955075 2 0.6252 0.3481 0.000 0.556 0.444
#> GSM955079 3 0.2031 0.8250 0.032 0.016 0.952
#> GSM955087 1 0.0475 0.9266 0.992 0.004 0.004
#> GSM955088 3 0.1878 0.8201 0.044 0.004 0.952
#> GSM955089 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955095 3 0.2878 0.7969 0.000 0.096 0.904
#> GSM955097 2 0.7983 0.5449 0.228 0.648 0.124
#> GSM955101 3 0.3192 0.7877 0.000 0.112 0.888
#> GSM954999 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955001 3 0.1964 0.8240 0.000 0.056 0.944
#> GSM955003 3 0.3482 0.7770 0.000 0.128 0.872
#> GSM955004 2 0.3412 0.7125 0.000 0.876 0.124
#> GSM955005 3 0.4228 0.7228 0.148 0.008 0.844
#> GSM955009 3 0.6045 0.4225 0.000 0.380 0.620
#> GSM955011 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955012 3 0.5465 0.5368 0.000 0.288 0.712
#> GSM955013 3 0.2550 0.8142 0.040 0.024 0.936
#> GSM955015 3 0.0892 0.8283 0.000 0.020 0.980
#> GSM955017 1 0.0475 0.9266 0.992 0.004 0.004
#> GSM955021 3 0.3686 0.7740 0.000 0.140 0.860
#> GSM955025 2 0.1529 0.7189 0.000 0.960 0.040
#> GSM955028 1 0.0237 0.9282 0.996 0.004 0.000
#> GSM955029 3 0.6307 -0.1824 0.000 0.488 0.512
#> GSM955030 1 0.5845 0.4817 0.688 0.004 0.308
#> GSM955032 3 0.1267 0.8260 0.024 0.004 0.972
#> GSM955033 2 0.7692 0.6655 0.108 0.668 0.224
#> GSM955034 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955035 3 0.4555 0.7240 0.000 0.200 0.800
#> GSM955036 3 0.4744 0.6985 0.136 0.028 0.836
#> GSM955037 1 0.0475 0.9266 0.992 0.004 0.004
#> GSM955039 3 0.2301 0.8266 0.004 0.060 0.936
#> GSM955041 3 0.1529 0.8312 0.000 0.040 0.960
#> GSM955042 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955045 3 0.0892 0.8283 0.000 0.020 0.980
#> GSM955046 3 0.1031 0.8279 0.000 0.024 0.976
#> GSM955047 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955050 1 0.1170 0.9101 0.976 0.008 0.016
#> GSM955052 3 0.1289 0.8294 0.000 0.032 0.968
#> GSM955053 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955056 3 0.0424 0.8305 0.000 0.008 0.992
#> GSM955058 3 0.6192 0.1435 0.000 0.420 0.580
#> GSM955059 3 0.1453 0.8253 0.024 0.008 0.968
#> GSM955060 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955061 2 0.6095 0.4550 0.000 0.608 0.392
#> GSM955065 1 0.0475 0.9266 0.992 0.004 0.004
#> GSM955066 3 0.6398 0.2832 0.372 0.008 0.620
#> GSM955067 1 0.0424 0.9248 0.992 0.008 0.000
#> GSM955073 3 0.0237 0.8310 0.000 0.004 0.996
#> GSM955074 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955076 3 0.5810 0.5189 0.000 0.336 0.664
#> GSM955078 2 0.1163 0.7256 0.000 0.972 0.028
#> GSM955083 1 0.4209 0.8010 0.860 0.120 0.020
#> GSM955084 2 0.2066 0.7260 0.000 0.940 0.060
#> GSM955086 3 0.1878 0.8156 0.044 0.004 0.952
#> GSM955091 3 0.5968 0.4637 0.000 0.364 0.636
#> GSM955092 3 0.2796 0.8048 0.000 0.092 0.908
#> GSM955093 3 0.1129 0.8309 0.004 0.020 0.976
#> GSM955098 2 0.4504 0.6623 0.000 0.804 0.196
#> GSM955099 3 0.5363 0.6050 0.000 0.276 0.724
#> GSM955100 1 0.0475 0.9266 0.992 0.004 0.004
#> GSM955103 3 0.0592 0.8322 0.000 0.012 0.988
#> GSM955104 3 0.5201 0.5942 0.236 0.004 0.760
#> GSM955106 2 0.6215 0.4015 0.000 0.572 0.428
#> GSM955000 1 0.0475 0.9266 0.992 0.004 0.004
#> GSM955006 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955007 3 0.0892 0.8283 0.000 0.020 0.980
#> GSM955010 1 0.3715 0.7833 0.868 0.004 0.128
#> GSM955014 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955018 3 0.1620 0.8300 0.012 0.024 0.964
#> GSM955020 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955024 3 0.0892 0.8283 0.000 0.020 0.980
#> GSM955026 2 0.5016 0.6181 0.000 0.760 0.240
#> GSM955031 3 0.8987 0.1375 0.340 0.144 0.516
#> GSM955038 2 0.5201 0.5093 0.236 0.760 0.004
#> GSM955040 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955044 2 0.6291 0.0896 0.000 0.532 0.468
#> GSM955051 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955055 3 0.2261 0.8218 0.000 0.068 0.932
#> GSM955057 1 0.0000 0.9295 1.000 0.000 0.000
#> GSM955062 3 0.3619 0.7836 0.000 0.136 0.864
#> GSM955063 3 0.0424 0.8309 0.000 0.008 0.992
#> GSM955068 2 0.0892 0.7144 0.000 0.980 0.020
#> GSM955069 3 0.2301 0.8035 0.060 0.004 0.936
#> GSM955070 3 0.1289 0.8277 0.000 0.032 0.968
#> GSM955071 1 0.6276 0.5724 0.736 0.040 0.224
#> GSM955077 1 0.6890 0.4297 0.632 0.340 0.028
#> GSM955080 3 0.5254 0.5801 0.000 0.264 0.736
#> GSM955081 3 0.3551 0.7868 0.000 0.132 0.868
#> GSM955082 3 0.0747 0.8308 0.000 0.016 0.984
#> GSM955085 3 0.5926 0.4805 0.000 0.356 0.644
#> GSM955090 1 0.0237 0.9275 0.996 0.004 0.000
#> GSM955094 3 0.2878 0.7983 0.000 0.096 0.904
#> GSM955096 3 0.1753 0.8245 0.000 0.048 0.952
#> GSM955102 1 0.6500 0.0872 0.532 0.004 0.464
#> GSM955105 3 0.3644 0.7359 0.124 0.004 0.872
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 3 0.5188 0.6583 0.000 0.148 0.756 0.096
#> GSM955008 3 0.2647 0.7318 0.000 0.120 0.880 0.000
#> GSM955016 1 0.2760 0.8615 0.872 0.000 0.000 0.128
#> GSM955019 2 0.1211 0.7699 0.000 0.960 0.040 0.000
#> GSM955022 3 0.0592 0.7505 0.000 0.000 0.984 0.016
#> GSM955023 3 0.1807 0.7547 0.000 0.052 0.940 0.008
#> GSM955027 2 0.4948 0.2336 0.000 0.560 0.440 0.000
#> GSM955043 3 0.6504 0.4233 0.000 0.148 0.636 0.216
#> GSM955048 1 0.0188 0.9627 0.996 0.000 0.004 0.000
#> GSM955049 3 0.4632 0.5444 0.000 0.308 0.688 0.004
#> GSM955054 3 0.5257 0.1967 0.000 0.444 0.548 0.008
#> GSM955064 3 0.1716 0.7552 0.000 0.064 0.936 0.000
#> GSM955072 2 0.6966 0.3154 0.000 0.532 0.128 0.340
#> GSM955075 4 0.3569 0.7487 0.000 0.000 0.196 0.804
#> GSM955079 3 0.6570 0.3695 0.100 0.320 0.580 0.000
#> GSM955087 1 0.0469 0.9605 0.988 0.000 0.012 0.000
#> GSM955088 3 0.0469 0.7569 0.000 0.012 0.988 0.000
#> GSM955089 1 0.0188 0.9621 0.996 0.000 0.004 0.000
#> GSM955095 3 0.4643 0.3102 0.000 0.000 0.656 0.344
#> GSM955097 4 0.0000 0.6784 0.000 0.000 0.000 1.000
#> GSM955101 3 0.4790 0.3978 0.000 0.380 0.620 0.000
#> GSM954999 1 0.0927 0.9523 0.976 0.000 0.016 0.008
#> GSM955001 3 0.5466 0.2156 0.000 0.436 0.548 0.016
#> GSM955003 2 0.3801 0.7021 0.000 0.780 0.220 0.000
#> GSM955004 4 0.0188 0.6769 0.000 0.004 0.000 0.996
#> GSM955005 3 0.5933 0.2496 0.408 0.040 0.552 0.000
#> GSM955009 2 0.0592 0.7643 0.000 0.984 0.016 0.000
#> GSM955011 1 0.0000 0.9622 1.000 0.000 0.000 0.000
#> GSM955012 3 0.4989 -0.1496 0.000 0.000 0.528 0.472
#> GSM955013 3 0.1488 0.7387 0.012 0.000 0.956 0.032
#> GSM955015 3 0.3479 0.7108 0.000 0.148 0.840 0.012
#> GSM955017 1 0.0188 0.9627 0.996 0.000 0.004 0.000
#> GSM955021 2 0.2530 0.7578 0.000 0.888 0.112 0.000
#> GSM955025 2 0.0336 0.7557 0.008 0.992 0.000 0.000
#> GSM955028 1 0.0469 0.9605 0.988 0.000 0.012 0.000
#> GSM955029 4 0.6130 0.4172 0.000 0.052 0.400 0.548
#> GSM955030 3 0.2868 0.6390 0.136 0.000 0.864 0.000
#> GSM955032 3 0.3975 0.6334 0.000 0.240 0.760 0.000
#> GSM955033 4 0.4328 0.6421 0.008 0.000 0.244 0.748
#> GSM955034 1 0.0188 0.9627 0.996 0.000 0.004 0.000
#> GSM955035 2 0.3688 0.7056 0.000 0.792 0.208 0.000
#> GSM955036 3 0.1798 0.7256 0.016 0.000 0.944 0.040
#> GSM955037 1 0.3400 0.7646 0.820 0.000 0.180 0.000
#> GSM955039 3 0.2528 0.7308 0.008 0.080 0.908 0.004
#> GSM955041 3 0.1302 0.7582 0.000 0.044 0.956 0.000
#> GSM955042 1 0.0188 0.9627 0.996 0.000 0.004 0.000
#> GSM955045 3 0.1767 0.7561 0.000 0.044 0.944 0.012
#> GSM955046 3 0.0188 0.7521 0.000 0.000 0.996 0.004
#> GSM955047 1 0.0524 0.9617 0.988 0.008 0.004 0.000
#> GSM955050 1 0.3570 0.8601 0.860 0.048 0.000 0.092
#> GSM955052 3 0.1474 0.7572 0.000 0.052 0.948 0.000
#> GSM955053 1 0.0188 0.9627 0.996 0.000 0.004 0.000
#> GSM955056 3 0.4746 0.5363 0.000 0.304 0.688 0.008
#> GSM955058 4 0.4804 0.5137 0.000 0.000 0.384 0.616
#> GSM955059 3 0.0000 0.7533 0.000 0.000 1.000 0.000
#> GSM955060 1 0.0188 0.9627 0.996 0.000 0.004 0.000
#> GSM955061 4 0.4008 0.7207 0.000 0.000 0.244 0.756
#> GSM955065 1 0.0469 0.9605 0.988 0.000 0.012 0.000
#> GSM955066 3 0.2530 0.6876 0.100 0.004 0.896 0.000
#> GSM955067 1 0.0921 0.9508 0.972 0.028 0.000 0.000
#> GSM955073 3 0.0469 0.7567 0.000 0.012 0.988 0.000
#> GSM955074 1 0.0188 0.9620 0.996 0.000 0.000 0.004
#> GSM955076 2 0.0469 0.7628 0.000 0.988 0.012 0.000
#> GSM955078 2 0.4011 0.6365 0.000 0.784 0.008 0.208
#> GSM955083 1 0.4103 0.7014 0.744 0.000 0.000 0.256
#> GSM955084 4 0.0336 0.6761 0.000 0.008 0.000 0.992
#> GSM955086 3 0.5130 0.4754 0.016 0.332 0.652 0.000
#> GSM955091 2 0.1211 0.7699 0.000 0.960 0.040 0.000
#> GSM955092 2 0.4164 0.6488 0.000 0.736 0.264 0.000
#> GSM955093 3 0.0188 0.7547 0.000 0.004 0.996 0.000
#> GSM955098 2 0.0000 0.7571 0.000 1.000 0.000 0.000
#> GSM955099 2 0.3569 0.7166 0.000 0.804 0.196 0.000
#> GSM955100 1 0.0336 0.9618 0.992 0.000 0.008 0.000
#> GSM955103 3 0.0524 0.7537 0.000 0.004 0.988 0.008
#> GSM955104 3 0.4304 0.4277 0.284 0.000 0.716 0.000
#> GSM955106 4 0.3311 0.7548 0.000 0.000 0.172 0.828
#> GSM955000 1 0.0469 0.9597 0.988 0.000 0.012 0.000
#> GSM955006 1 0.0000 0.9622 1.000 0.000 0.000 0.000
#> GSM955007 3 0.0657 0.7534 0.000 0.004 0.984 0.012
#> GSM955010 3 0.4830 0.2387 0.392 0.000 0.608 0.000
#> GSM955014 1 0.0469 0.9596 0.988 0.012 0.000 0.000
#> GSM955018 3 0.0469 0.7575 0.000 0.012 0.988 0.000
#> GSM955020 1 0.0188 0.9619 0.996 0.004 0.000 0.000
#> GSM955024 3 0.0927 0.7569 0.000 0.016 0.976 0.008
#> GSM955026 2 0.0000 0.7571 0.000 1.000 0.000 0.000
#> GSM955031 2 0.1256 0.7504 0.028 0.964 0.008 0.000
#> GSM955038 2 0.7627 -0.0102 0.388 0.408 0.000 0.204
#> GSM955040 1 0.0469 0.9600 0.988 0.012 0.000 0.000
#> GSM955044 4 0.7031 0.4378 0.000 0.224 0.200 0.576
#> GSM955051 1 0.0469 0.9596 0.988 0.012 0.000 0.000
#> GSM955055 2 0.4250 0.6248 0.000 0.724 0.276 0.000
#> GSM955057 1 0.0592 0.9579 0.984 0.016 0.000 0.000
#> GSM955062 2 0.4761 0.4956 0.000 0.664 0.332 0.004
#> GSM955063 3 0.0336 0.7557 0.000 0.008 0.992 0.000
#> GSM955068 2 0.0707 0.7513 0.000 0.980 0.000 0.020
#> GSM955069 3 0.0336 0.7500 0.008 0.000 0.992 0.000
#> GSM955070 3 0.1706 0.7506 0.000 0.016 0.948 0.036
#> GSM955071 1 0.3286 0.8587 0.876 0.080 0.044 0.000
#> GSM955077 2 0.2973 0.6328 0.144 0.856 0.000 0.000
#> GSM955080 4 0.4748 0.6973 0.000 0.016 0.268 0.716
#> GSM955081 2 0.4222 0.6277 0.000 0.728 0.272 0.000
#> GSM955082 3 0.2814 0.7244 0.000 0.132 0.868 0.000
#> GSM955085 2 0.1637 0.7689 0.000 0.940 0.060 0.000
#> GSM955090 1 0.0524 0.9602 0.988 0.008 0.000 0.004
#> GSM955094 3 0.4706 0.6644 0.000 0.072 0.788 0.140
#> GSM955096 3 0.4981 0.1198 0.000 0.464 0.536 0.000
#> GSM955102 3 0.2760 0.6531 0.128 0.000 0.872 0.000
#> GSM955105 3 0.5528 0.5290 0.236 0.064 0.700 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.7448 0.36943 0.000 0.176 0.532 0.172 0.120
#> GSM955008 3 0.4577 0.64211 0.000 0.144 0.748 0.108 0.000
#> GSM955016 1 0.4102 0.62492 0.692 0.004 0.004 0.000 0.300
#> GSM955019 4 0.3636 0.49374 0.000 0.272 0.000 0.728 0.000
#> GSM955022 3 0.2753 0.69979 0.000 0.104 0.876 0.008 0.012
#> GSM955023 3 0.4235 0.49285 0.000 0.336 0.656 0.008 0.000
#> GSM955027 2 0.5493 0.41844 0.000 0.628 0.108 0.264 0.000
#> GSM955043 3 0.7833 -0.00896 0.000 0.088 0.412 0.196 0.304
#> GSM955048 1 0.0404 0.89418 0.988 0.000 0.000 0.012 0.000
#> GSM955049 3 0.6411 -0.08651 0.000 0.408 0.440 0.148 0.004
#> GSM955054 2 0.6424 0.28613 0.000 0.508 0.240 0.252 0.000
#> GSM955064 3 0.4573 0.62681 0.000 0.092 0.744 0.164 0.000
#> GSM955072 2 0.6597 0.29907 0.000 0.576 0.088 0.272 0.064
#> GSM955075 5 0.4465 0.59055 0.000 0.204 0.060 0.000 0.736
#> GSM955079 3 0.8002 -0.03286 0.104 0.264 0.408 0.224 0.000
#> GSM955087 1 0.1869 0.88406 0.936 0.012 0.036 0.016 0.000
#> GSM955088 2 0.4798 0.15313 0.000 0.580 0.396 0.024 0.000
#> GSM955089 1 0.1503 0.89069 0.952 0.008 0.020 0.020 0.000
#> GSM955095 5 0.6949 0.09843 0.000 0.304 0.340 0.004 0.352
#> GSM955097 5 0.0404 0.62330 0.000 0.012 0.000 0.000 0.988
#> GSM955101 4 0.5834 0.27668 0.000 0.108 0.348 0.544 0.000
#> GSM954999 1 0.3583 0.84033 0.860 0.020 0.068 0.036 0.016
#> GSM955001 2 0.4088 0.57293 0.000 0.780 0.176 0.036 0.008
#> GSM955003 4 0.5392 0.46361 0.000 0.192 0.144 0.664 0.000
#> GSM955004 5 0.2424 0.62806 0.000 0.132 0.000 0.000 0.868
#> GSM955005 3 0.6940 0.19866 0.372 0.036 0.456 0.136 0.000
#> GSM955009 2 0.2732 0.43824 0.000 0.840 0.000 0.160 0.000
#> GSM955011 1 0.1186 0.89632 0.964 0.020 0.008 0.008 0.000
#> GSM955012 5 0.5465 0.38074 0.000 0.056 0.348 0.008 0.588
#> GSM955013 3 0.2522 0.70957 0.004 0.040 0.908 0.008 0.040
#> GSM955015 3 0.5543 0.53987 0.000 0.160 0.672 0.160 0.008
#> GSM955017 1 0.1413 0.89494 0.956 0.012 0.012 0.020 0.000
#> GSM955021 2 0.4571 0.49879 0.000 0.736 0.076 0.188 0.000
#> GSM955025 4 0.5726 0.38079 0.080 0.368 0.000 0.548 0.004
#> GSM955028 1 0.2277 0.87415 0.916 0.016 0.052 0.016 0.000
#> GSM955029 2 0.6829 0.16712 0.000 0.512 0.088 0.064 0.336
#> GSM955030 3 0.2141 0.69206 0.064 0.016 0.916 0.004 0.000
#> GSM955032 2 0.5671 0.37040 0.004 0.568 0.348 0.080 0.000
#> GSM955033 5 0.6419 0.40103 0.004 0.024 0.268 0.120 0.584
#> GSM955034 1 0.0854 0.89460 0.976 0.008 0.004 0.012 0.000
#> GSM955035 4 0.4450 0.55188 0.000 0.108 0.132 0.760 0.000
#> GSM955036 3 0.2422 0.68807 0.004 0.024 0.916 0.020 0.036
#> GSM955037 1 0.3955 0.77668 0.804 0.028 0.148 0.020 0.000
#> GSM955039 3 0.4533 0.62690 0.020 0.020 0.780 0.156 0.024
#> GSM955041 3 0.4696 0.64425 0.000 0.068 0.748 0.172 0.012
#> GSM955042 1 0.1565 0.89165 0.952 0.020 0.016 0.008 0.004
#> GSM955045 2 0.3816 0.48498 0.000 0.696 0.304 0.000 0.000
#> GSM955046 3 0.1074 0.70285 0.000 0.012 0.968 0.004 0.016
#> GSM955047 1 0.1106 0.89375 0.964 0.012 0.000 0.024 0.000
#> GSM955050 1 0.8269 0.13166 0.416 0.244 0.064 0.248 0.028
#> GSM955052 3 0.4010 0.63869 0.000 0.208 0.760 0.032 0.000
#> GSM955053 1 0.0854 0.89403 0.976 0.012 0.004 0.008 0.000
#> GSM955056 2 0.4237 0.56656 0.000 0.752 0.200 0.048 0.000
#> GSM955058 5 0.6926 0.46851 0.000 0.116 0.128 0.160 0.596
#> GSM955059 3 0.2513 0.70057 0.000 0.116 0.876 0.008 0.000
#> GSM955060 1 0.0771 0.89386 0.976 0.004 0.000 0.020 0.000
#> GSM955061 5 0.4891 0.60901 0.000 0.080 0.076 0.072 0.772
#> GSM955065 1 0.1893 0.88645 0.936 0.012 0.028 0.024 0.000
#> GSM955066 3 0.2897 0.69429 0.052 0.040 0.888 0.020 0.000
#> GSM955067 1 0.2439 0.84439 0.876 0.004 0.000 0.120 0.000
#> GSM955073 3 0.2249 0.70469 0.000 0.096 0.896 0.008 0.000
#> GSM955074 1 0.1492 0.88837 0.948 0.008 0.000 0.004 0.040
#> GSM955076 4 0.3462 0.55596 0.000 0.196 0.012 0.792 0.000
#> GSM955078 2 0.5740 0.31683 0.000 0.620 0.000 0.164 0.216
#> GSM955083 1 0.4654 0.52315 0.632 0.012 0.008 0.000 0.348
#> GSM955084 5 0.0992 0.62164 0.000 0.024 0.000 0.008 0.968
#> GSM955086 2 0.3860 0.56410 0.016 0.808 0.148 0.028 0.000
#> GSM955091 4 0.3752 0.46989 0.000 0.292 0.000 0.708 0.000
#> GSM955092 2 0.5331 0.17485 0.000 0.568 0.060 0.372 0.000
#> GSM955093 3 0.1928 0.70558 0.004 0.072 0.920 0.004 0.000
#> GSM955098 4 0.2392 0.57737 0.004 0.104 0.004 0.888 0.000
#> GSM955099 2 0.4817 0.16315 0.000 0.572 0.024 0.404 0.000
#> GSM955100 1 0.1815 0.89122 0.940 0.020 0.016 0.024 0.000
#> GSM955103 3 0.3712 0.67333 0.000 0.132 0.820 0.040 0.008
#> GSM955104 3 0.4923 0.57247 0.176 0.068 0.736 0.020 0.000
#> GSM955106 5 0.1956 0.65568 0.000 0.008 0.076 0.000 0.916
#> GSM955000 1 0.1299 0.89335 0.960 0.012 0.020 0.008 0.000
#> GSM955006 1 0.0854 0.89612 0.976 0.004 0.008 0.012 0.000
#> GSM955007 3 0.2570 0.70393 0.000 0.108 0.880 0.004 0.008
#> GSM955010 3 0.4345 0.56502 0.156 0.020 0.780 0.044 0.000
#> GSM955014 1 0.1282 0.88861 0.952 0.004 0.000 0.044 0.000
#> GSM955018 3 0.4207 0.53546 0.008 0.276 0.708 0.008 0.000
#> GSM955020 1 0.0324 0.89451 0.992 0.004 0.000 0.004 0.000
#> GSM955024 3 0.3205 0.67082 0.000 0.176 0.816 0.004 0.004
#> GSM955026 4 0.3496 0.57497 0.012 0.200 0.000 0.788 0.000
#> GSM955031 4 0.6759 0.18613 0.276 0.328 0.000 0.396 0.000
#> GSM955038 4 0.6264 0.22533 0.176 0.008 0.000 0.572 0.244
#> GSM955040 1 0.5537 0.71499 0.736 0.072 0.080 0.104 0.008
#> GSM955044 4 0.6799 0.20591 0.000 0.016 0.200 0.496 0.288
#> GSM955051 1 0.1106 0.89265 0.964 0.012 0.000 0.024 0.000
#> GSM955055 2 0.3239 0.54364 0.000 0.852 0.068 0.080 0.000
#> GSM955057 1 0.1211 0.89389 0.960 0.016 0.000 0.024 0.000
#> GSM955062 2 0.5843 0.35340 0.000 0.572 0.124 0.304 0.000
#> GSM955063 3 0.2763 0.68727 0.000 0.148 0.848 0.004 0.000
#> GSM955068 4 0.3482 0.58473 0.000 0.096 0.008 0.844 0.052
#> GSM955069 3 0.3166 0.70116 0.012 0.112 0.856 0.020 0.000
#> GSM955070 3 0.5282 0.58067 0.000 0.212 0.700 0.056 0.032
#> GSM955071 1 0.6436 0.45674 0.592 0.028 0.120 0.256 0.004
#> GSM955077 2 0.5967 0.03021 0.308 0.556 0.000 0.136 0.000
#> GSM955080 5 0.6011 0.27146 0.000 0.344 0.128 0.000 0.528
#> GSM955081 4 0.6309 0.19667 0.000 0.340 0.168 0.492 0.000
#> GSM955082 2 0.5499 0.26463 0.000 0.532 0.400 0.068 0.000
#> GSM955085 2 0.4491 0.16520 0.000 0.624 0.008 0.364 0.004
#> GSM955090 1 0.1306 0.89211 0.960 0.016 0.000 0.016 0.008
#> GSM955094 3 0.7001 0.08191 0.000 0.400 0.440 0.100 0.060
#> GSM955096 2 0.5304 0.50779 0.000 0.640 0.272 0.088 0.000
#> GSM955102 3 0.3925 0.64980 0.124 0.040 0.816 0.020 0.000
#> GSM955105 2 0.6373 0.33183 0.184 0.532 0.280 0.004 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 4 0.5924 0.5941 0.000 0.044 0.224 0.632 0.056 0.044
#> GSM955008 3 0.5319 0.5146 0.000 0.084 0.656 0.044 0.000 0.216
#> GSM955016 1 0.4460 0.6773 0.700 0.000 0.000 0.040 0.240 0.020
#> GSM955019 6 0.3554 0.5382 0.000 0.112 0.040 0.028 0.000 0.820
#> GSM955022 3 0.4891 0.4838 0.000 0.128 0.688 0.172 0.012 0.000
#> GSM955023 3 0.5489 0.3765 0.000 0.316 0.556 0.120 0.000 0.008
#> GSM955027 2 0.5784 0.0358 0.000 0.432 0.152 0.000 0.004 0.412
#> GSM955043 5 0.8401 0.0236 0.000 0.060 0.200 0.176 0.320 0.244
#> GSM955048 1 0.1320 0.8402 0.948 0.000 0.000 0.036 0.000 0.016
#> GSM955049 3 0.6062 0.0228 0.000 0.276 0.404 0.000 0.000 0.320
#> GSM955054 2 0.7053 -0.0465 0.000 0.388 0.144 0.352 0.000 0.116
#> GSM955064 3 0.5678 0.2667 0.000 0.028 0.516 0.084 0.000 0.372
#> GSM955072 2 0.5632 0.3795 0.000 0.668 0.012 0.120 0.048 0.152
#> GSM955075 5 0.4541 0.5564 0.000 0.236 0.012 0.036 0.704 0.012
#> GSM955079 3 0.7029 0.1058 0.100 0.116 0.444 0.012 0.000 0.328
#> GSM955087 1 0.1321 0.8385 0.952 0.000 0.020 0.024 0.000 0.004
#> GSM955088 2 0.7601 0.0907 0.020 0.368 0.260 0.264 0.000 0.088
#> GSM955089 1 0.1149 0.8426 0.960 0.000 0.008 0.024 0.000 0.008
#> GSM955095 5 0.6505 0.2917 0.000 0.308 0.168 0.040 0.480 0.004
#> GSM955097 5 0.0520 0.6469 0.000 0.008 0.000 0.008 0.984 0.000
#> GSM955101 6 0.4636 0.4292 0.000 0.020 0.272 0.040 0.000 0.668
#> GSM954999 1 0.3805 0.7956 0.832 0.000 0.056 0.044 0.032 0.036
#> GSM955001 2 0.3767 0.5115 0.000 0.792 0.152 0.012 0.004 0.040
#> GSM955003 6 0.6336 0.4677 0.000 0.096 0.156 0.172 0.000 0.576
#> GSM955004 5 0.3129 0.6205 0.000 0.152 0.000 0.024 0.820 0.004
#> GSM955005 3 0.7015 0.1174 0.312 0.020 0.464 0.076 0.000 0.128
#> GSM955009 2 0.4107 0.3701 0.000 0.756 0.004 0.092 0.000 0.148
#> GSM955011 1 0.1682 0.8425 0.928 0.000 0.000 0.052 0.000 0.020
#> GSM955012 5 0.4934 0.4147 0.000 0.020 0.344 0.004 0.600 0.032
#> GSM955013 3 0.5392 0.4055 0.000 0.044 0.672 0.208 0.060 0.016
#> GSM955015 4 0.7074 0.1737 0.000 0.160 0.368 0.396 0.020 0.056
#> GSM955017 1 0.3851 0.7170 0.740 0.012 0.012 0.232 0.000 0.004
#> GSM955021 2 0.4753 0.4527 0.000 0.732 0.068 0.056 0.000 0.144
#> GSM955025 6 0.6652 0.3377 0.064 0.180 0.004 0.240 0.000 0.512
#> GSM955028 1 0.1672 0.8298 0.932 0.000 0.048 0.016 0.000 0.004
#> GSM955029 2 0.6890 0.1215 0.000 0.456 0.116 0.004 0.316 0.108
#> GSM955030 3 0.4382 0.3966 0.076 0.008 0.724 0.192 0.000 0.000
#> GSM955032 2 0.5705 0.3539 0.000 0.560 0.316 0.036 0.000 0.088
#> GSM955033 4 0.5642 0.5460 0.004 0.004 0.152 0.616 0.212 0.012
#> GSM955034 1 0.0547 0.8403 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM955035 6 0.5553 0.5315 0.000 0.076 0.088 0.180 0.000 0.656
#> GSM955036 3 0.4990 0.2335 0.008 0.000 0.648 0.260 0.080 0.004
#> GSM955037 1 0.3850 0.6199 0.716 0.000 0.260 0.020 0.000 0.004
#> GSM955039 3 0.5768 -0.0371 0.012 0.000 0.540 0.348 0.020 0.080
#> GSM955041 3 0.4569 0.4675 0.000 0.016 0.652 0.024 0.004 0.304
#> GSM955042 1 0.1793 0.8414 0.932 0.000 0.004 0.040 0.008 0.016
#> GSM955045 2 0.5384 0.4529 0.000 0.632 0.268 0.048 0.008 0.044
#> GSM955046 3 0.3719 0.3443 0.000 0.000 0.728 0.248 0.024 0.000
#> GSM955047 1 0.3771 0.7750 0.780 0.024 0.000 0.172 0.000 0.024
#> GSM955050 4 0.4582 0.4080 0.108 0.080 0.004 0.764 0.004 0.040
#> GSM955052 3 0.4185 0.5482 0.000 0.168 0.744 0.004 0.000 0.084
#> GSM955053 1 0.0603 0.8398 0.980 0.000 0.000 0.016 0.000 0.004
#> GSM955056 2 0.3910 0.5117 0.000 0.784 0.148 0.044 0.000 0.024
#> GSM955058 5 0.5595 0.4432 0.000 0.024 0.116 0.004 0.616 0.240
#> GSM955059 3 0.3520 0.5598 0.000 0.100 0.804 0.096 0.000 0.000
#> GSM955060 1 0.1555 0.8389 0.932 0.004 0.000 0.060 0.000 0.004
#> GSM955061 5 0.3571 0.6212 0.000 0.020 0.048 0.000 0.816 0.116
#> GSM955065 1 0.1514 0.8387 0.944 0.004 0.012 0.036 0.000 0.004
#> GSM955066 3 0.5808 -0.0804 0.080 0.032 0.524 0.360 0.000 0.004
#> GSM955067 1 0.4008 0.7646 0.768 0.000 0.000 0.128 0.004 0.100
#> GSM955073 3 0.1863 0.5946 0.000 0.044 0.920 0.000 0.000 0.036
#> GSM955074 1 0.2917 0.8245 0.872 0.008 0.000 0.040 0.068 0.012
#> GSM955076 6 0.4443 0.3485 0.000 0.300 0.000 0.052 0.000 0.648
#> GSM955078 2 0.5358 0.3351 0.000 0.616 0.000 0.008 0.220 0.156
#> GSM955083 1 0.5386 0.4316 0.568 0.004 0.012 0.080 0.336 0.000
#> GSM955084 5 0.0665 0.6464 0.000 0.008 0.000 0.004 0.980 0.008
#> GSM955086 2 0.4281 0.5084 0.004 0.760 0.160 0.052 0.000 0.024
#> GSM955091 6 0.3238 0.5332 0.000 0.120 0.036 0.012 0.000 0.832
#> GSM955092 6 0.5960 -0.0455 0.000 0.396 0.140 0.016 0.000 0.448
#> GSM955093 3 0.1679 0.5775 0.000 0.016 0.936 0.036 0.000 0.012
#> GSM955098 6 0.4700 0.4477 0.000 0.060 0.000 0.340 0.000 0.600
#> GSM955099 6 0.5315 0.2018 0.000 0.360 0.076 0.008 0.004 0.552
#> GSM955100 1 0.4494 0.7222 0.748 0.048 0.012 0.168 0.000 0.024
#> GSM955103 3 0.2933 0.5792 0.000 0.032 0.852 0.008 0.000 0.108
#> GSM955104 3 0.4629 0.4348 0.196 0.008 0.724 0.028 0.000 0.044
#> GSM955106 5 0.1036 0.6466 0.000 0.004 0.024 0.008 0.964 0.000
#> GSM955000 1 0.1636 0.8439 0.936 0.000 0.004 0.036 0.000 0.024
#> GSM955006 1 0.2569 0.8187 0.880 0.004 0.012 0.092 0.000 0.012
#> GSM955007 3 0.4468 0.5457 0.000 0.180 0.724 0.088 0.004 0.004
#> GSM955010 4 0.5554 0.3458 0.088 0.000 0.404 0.492 0.000 0.016
#> GSM955014 1 0.2586 0.8284 0.868 0.000 0.000 0.100 0.000 0.032
#> GSM955018 3 0.5230 0.4752 0.052 0.156 0.708 0.016 0.000 0.068
#> GSM955020 1 0.0146 0.8399 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM955024 3 0.4136 0.5511 0.000 0.168 0.748 0.080 0.004 0.000
#> GSM955026 6 0.5108 0.4824 0.004 0.088 0.000 0.324 0.000 0.584
#> GSM955031 2 0.7537 -0.0838 0.208 0.320 0.000 0.164 0.000 0.308
#> GSM955038 1 0.8308 -0.1196 0.280 0.028 0.004 0.252 0.200 0.236
#> GSM955040 4 0.4615 0.3891 0.240 0.020 0.020 0.700 0.000 0.020
#> GSM955044 6 0.7552 -0.0457 0.000 0.012 0.100 0.316 0.232 0.340
#> GSM955051 1 0.2344 0.8352 0.892 0.004 0.000 0.076 0.000 0.028
#> GSM955055 2 0.3094 0.4891 0.000 0.860 0.060 0.032 0.000 0.048
#> GSM955057 1 0.1989 0.8410 0.916 0.028 0.000 0.052 0.000 0.004
#> GSM955062 2 0.5808 0.0422 0.000 0.464 0.108 0.020 0.000 0.408
#> GSM955063 3 0.2833 0.5887 0.000 0.088 0.864 0.040 0.000 0.008
#> GSM955068 6 0.5141 0.4504 0.000 0.148 0.000 0.108 0.048 0.696
#> GSM955069 3 0.3054 0.5880 0.020 0.068 0.868 0.032 0.000 0.012
#> GSM955070 4 0.5963 0.5508 0.000 0.072 0.280 0.588 0.032 0.028
#> GSM955071 1 0.7485 -0.1861 0.340 0.008 0.104 0.324 0.000 0.224
#> GSM955077 2 0.7291 0.0910 0.212 0.440 0.004 0.216 0.000 0.128
#> GSM955080 5 0.5791 0.1387 0.000 0.400 0.092 0.020 0.484 0.004
#> GSM955081 6 0.5530 0.4528 0.000 0.160 0.132 0.052 0.000 0.656
#> GSM955082 3 0.6642 -0.0826 0.000 0.356 0.428 0.044 0.004 0.168
#> GSM955085 2 0.6132 0.0223 0.000 0.476 0.012 0.136 0.012 0.364
#> GSM955090 1 0.2919 0.8322 0.876 0.008 0.000 0.060 0.032 0.024
#> GSM955094 4 0.5698 0.5844 0.000 0.164 0.148 0.644 0.036 0.008
#> GSM955096 2 0.6049 0.3064 0.000 0.468 0.340 0.012 0.000 0.180
#> GSM955102 3 0.3850 0.5230 0.080 0.036 0.808 0.076 0.000 0.000
#> GSM955105 2 0.6463 0.2458 0.128 0.488 0.336 0.028 0.000 0.020
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> CV:NMF 101 0.299 2
#> CV:NMF 93 0.581 3
#> CV:NMF 90 0.653 4
#> CV:NMF 68 0.696 5
#> CV:NMF 52 0.439 6
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 31589 rows and 108 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 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 0.719 0.849 0.934 0.3346 0.707 0.707
#> 3 3 0.302 0.638 0.791 0.8344 0.641 0.497
#> 4 4 0.348 0.533 0.712 0.1398 0.918 0.783
#> 5 5 0.419 0.486 0.668 0.0875 0.890 0.668
#> 6 6 0.490 0.435 0.645 0.0531 0.927 0.718
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
#> GSM955002 2 0.3431 0.8919 0.064 0.936
#> GSM955008 2 0.0000 0.9290 0.000 1.000
#> GSM955016 1 0.9732 0.2980 0.596 0.404
#> GSM955019 2 0.0000 0.9290 0.000 1.000
#> GSM955022 2 0.0000 0.9290 0.000 1.000
#> GSM955023 2 0.0000 0.9290 0.000 1.000
#> GSM955027 2 0.0000 0.9290 0.000 1.000
#> GSM955043 2 0.0000 0.9290 0.000 1.000
#> GSM955048 1 0.0000 0.9129 1.000 0.000
#> GSM955049 2 0.0000 0.9290 0.000 1.000
#> GSM955054 2 0.0000 0.9290 0.000 1.000
#> GSM955064 2 0.0000 0.9290 0.000 1.000
#> GSM955072 2 0.0000 0.9290 0.000 1.000
#> GSM955075 2 0.0376 0.9279 0.004 0.996
#> GSM955079 2 0.1184 0.9238 0.016 0.984
#> GSM955087 1 0.0000 0.9129 1.000 0.000
#> GSM955088 2 0.2043 0.9159 0.032 0.968
#> GSM955089 1 0.0000 0.9129 1.000 0.000
#> GSM955095 2 0.0672 0.9272 0.008 0.992
#> GSM955097 2 0.1184 0.9242 0.016 0.984
#> GSM955101 2 0.0000 0.9290 0.000 1.000
#> GSM954999 2 0.9977 0.1343 0.472 0.528
#> GSM955001 2 0.0376 0.9279 0.004 0.996
#> GSM955003 2 0.0000 0.9290 0.000 1.000
#> GSM955004 2 0.0376 0.9282 0.004 0.996
#> GSM955005 2 0.7453 0.7366 0.212 0.788
#> GSM955009 2 0.0000 0.9290 0.000 1.000
#> GSM955011 2 0.9815 0.3151 0.420 0.580
#> GSM955012 2 0.0000 0.9290 0.000 1.000
#> GSM955013 2 0.3431 0.8944 0.064 0.936
#> GSM955015 2 0.0000 0.9290 0.000 1.000
#> GSM955017 1 0.6048 0.8038 0.852 0.148
#> GSM955021 2 0.0000 0.9290 0.000 1.000
#> GSM955025 2 0.1184 0.9244 0.016 0.984
#> GSM955028 1 0.0000 0.9129 1.000 0.000
#> GSM955029 2 0.0000 0.9290 0.000 1.000
#> GSM955030 2 0.8327 0.6594 0.264 0.736
#> GSM955032 2 0.0938 0.9254 0.012 0.988
#> GSM955033 2 0.5629 0.8297 0.132 0.868
#> GSM955034 1 0.0000 0.9129 1.000 0.000
#> GSM955035 2 0.0000 0.9290 0.000 1.000
#> GSM955036 2 0.1184 0.9239 0.016 0.984
#> GSM955037 2 0.9000 0.5579 0.316 0.684
#> GSM955039 2 0.3274 0.8957 0.060 0.940
#> GSM955041 2 0.0000 0.9290 0.000 1.000
#> GSM955042 2 0.9996 0.0702 0.488 0.512
#> GSM955045 2 0.0000 0.9290 0.000 1.000
#> GSM955046 2 0.1184 0.9239 0.016 0.984
#> GSM955047 1 0.1414 0.9080 0.980 0.020
#> GSM955050 2 0.8608 0.6289 0.284 0.716
#> GSM955052 2 0.0000 0.9290 0.000 1.000
#> GSM955053 1 0.0000 0.9129 1.000 0.000
#> GSM955056 2 0.0000 0.9290 0.000 1.000
#> GSM955058 2 0.0000 0.9290 0.000 1.000
#> GSM955059 2 0.0000 0.9290 0.000 1.000
#> GSM955060 1 0.5408 0.8287 0.876 0.124
#> GSM955061 2 0.0000 0.9290 0.000 1.000
#> GSM955065 1 0.0000 0.9129 1.000 0.000
#> GSM955066 2 0.4431 0.8724 0.092 0.908
#> GSM955067 1 0.0938 0.9116 0.988 0.012
#> GSM955073 2 0.0000 0.9290 0.000 1.000
#> GSM955074 1 0.7883 0.6826 0.764 0.236
#> GSM955076 2 0.0000 0.9290 0.000 1.000
#> GSM955078 2 0.0000 0.9290 0.000 1.000
#> GSM955083 2 0.8555 0.6349 0.280 0.720
#> GSM955084 2 0.0000 0.9290 0.000 1.000
#> GSM955086 2 0.3584 0.8910 0.068 0.932
#> GSM955091 2 0.0000 0.9290 0.000 1.000
#> GSM955092 2 0.0000 0.9290 0.000 1.000
#> GSM955093 2 0.0000 0.9290 0.000 1.000
#> GSM955098 2 0.0000 0.9290 0.000 1.000
#> GSM955099 2 0.0000 0.9290 0.000 1.000
#> GSM955100 2 0.9170 0.5400 0.332 0.668
#> GSM955103 2 0.0376 0.9282 0.004 0.996
#> GSM955104 2 0.2948 0.9042 0.052 0.948
#> GSM955106 2 0.0938 0.9261 0.012 0.988
#> GSM955000 2 0.9686 0.3637 0.396 0.604
#> GSM955006 1 0.9775 0.2658 0.588 0.412
#> GSM955007 2 0.0376 0.9280 0.004 0.996
#> GSM955010 2 0.7528 0.7349 0.216 0.784
#> GSM955014 1 0.0672 0.9126 0.992 0.008
#> GSM955018 2 0.1184 0.9238 0.016 0.984
#> GSM955020 1 0.1414 0.9081 0.980 0.020
#> GSM955024 2 0.0000 0.9290 0.000 1.000
#> GSM955026 2 0.0000 0.9290 0.000 1.000
#> GSM955031 2 0.8555 0.6375 0.280 0.720
#> GSM955038 2 0.9209 0.5206 0.336 0.664
#> GSM955040 2 0.8661 0.6222 0.288 0.712
#> GSM955044 2 0.0000 0.9290 0.000 1.000
#> GSM955051 1 0.0672 0.9125 0.992 0.008
#> GSM955055 2 0.0000 0.9290 0.000 1.000
#> GSM955057 1 0.0000 0.9129 1.000 0.000
#> GSM955062 2 0.0000 0.9290 0.000 1.000
#> GSM955063 2 0.0000 0.9290 0.000 1.000
#> GSM955068 2 0.0000 0.9290 0.000 1.000
#> GSM955069 2 0.2236 0.9135 0.036 0.964
#> GSM955070 2 0.1184 0.9238 0.016 0.984
#> GSM955071 2 0.8081 0.6858 0.248 0.752
#> GSM955077 2 0.4431 0.8660 0.092 0.908
#> GSM955080 2 0.0938 0.9257 0.012 0.988
#> GSM955081 2 0.0376 0.9281 0.004 0.996
#> GSM955082 2 0.0000 0.9290 0.000 1.000
#> GSM955085 2 0.0000 0.9290 0.000 1.000
#> GSM955090 1 0.0376 0.9130 0.996 0.004
#> GSM955094 2 0.1184 0.9242 0.016 0.984
#> GSM955096 2 0.0000 0.9290 0.000 1.000
#> GSM955102 2 0.2423 0.9108 0.040 0.960
#> GSM955105 2 0.1184 0.9238 0.016 0.984
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.7945 0.0785 0.064 0.548 0.388
#> GSM955008 3 0.4178 0.7074 0.000 0.172 0.828
#> GSM955016 1 0.8915 0.3953 0.572 0.216 0.212
#> GSM955019 2 0.3412 0.7742 0.000 0.876 0.124
#> GSM955022 3 0.5058 0.6812 0.000 0.244 0.756
#> GSM955023 3 0.5058 0.6812 0.000 0.244 0.756
#> GSM955027 2 0.2261 0.8106 0.000 0.932 0.068
#> GSM955043 2 0.1964 0.8113 0.000 0.944 0.056
#> GSM955048 1 0.0237 0.8565 0.996 0.000 0.004
#> GSM955049 3 0.6126 0.4769 0.000 0.400 0.600
#> GSM955054 3 0.6260 0.3452 0.000 0.448 0.552
#> GSM955064 3 0.6154 0.4294 0.000 0.408 0.592
#> GSM955072 2 0.1529 0.8075 0.000 0.960 0.040
#> GSM955075 2 0.2356 0.8079 0.000 0.928 0.072
#> GSM955079 3 0.3771 0.7157 0.012 0.112 0.876
#> GSM955087 1 0.0237 0.8569 0.996 0.000 0.004
#> GSM955088 3 0.5455 0.7031 0.020 0.204 0.776
#> GSM955089 1 0.0237 0.8569 0.996 0.000 0.004
#> GSM955095 2 0.5588 0.5541 0.004 0.720 0.276
#> GSM955097 2 0.2229 0.8074 0.012 0.944 0.044
#> GSM955101 3 0.6095 0.4575 0.000 0.392 0.608
#> GSM954999 1 0.9734 0.1100 0.448 0.292 0.260
#> GSM955001 2 0.5016 0.6363 0.000 0.760 0.240
#> GSM955003 3 0.6126 0.4749 0.000 0.400 0.600
#> GSM955004 2 0.0237 0.7988 0.000 0.996 0.004
#> GSM955005 3 0.7495 0.6355 0.188 0.120 0.692
#> GSM955009 2 0.0424 0.8022 0.000 0.992 0.008
#> GSM955011 3 0.9433 0.1717 0.404 0.176 0.420
#> GSM955012 2 0.1163 0.8123 0.000 0.972 0.028
#> GSM955013 3 0.7794 0.5126 0.060 0.368 0.572
#> GSM955015 3 0.5882 0.5465 0.000 0.348 0.652
#> GSM955017 1 0.4663 0.7489 0.828 0.016 0.156
#> GSM955021 2 0.5497 0.5378 0.000 0.708 0.292
#> GSM955025 2 0.4059 0.7657 0.012 0.860 0.128
#> GSM955028 1 0.0237 0.8569 0.996 0.000 0.004
#> GSM955029 2 0.1163 0.8123 0.000 0.972 0.028
#> GSM955030 3 0.7421 0.5596 0.240 0.084 0.676
#> GSM955032 3 0.4963 0.7087 0.008 0.200 0.792
#> GSM955033 3 0.8915 0.3303 0.124 0.404 0.472
#> GSM955034 1 0.0237 0.8569 0.996 0.000 0.004
#> GSM955035 2 0.6299 -0.0739 0.000 0.524 0.476
#> GSM955036 3 0.2537 0.7090 0.000 0.080 0.920
#> GSM955037 3 0.6229 0.4489 0.280 0.020 0.700
#> GSM955039 3 0.6836 0.6657 0.056 0.240 0.704
#> GSM955041 3 0.6008 0.5055 0.000 0.372 0.628
#> GSM955042 1 0.9663 0.1536 0.464 0.280 0.256
#> GSM955045 2 0.6244 0.0126 0.000 0.560 0.440
#> GSM955046 3 0.2537 0.7090 0.000 0.080 0.920
#> GSM955047 1 0.1482 0.8509 0.968 0.012 0.020
#> GSM955050 3 0.9775 0.3795 0.272 0.288 0.440
#> GSM955052 3 0.4178 0.7074 0.000 0.172 0.828
#> GSM955053 1 0.0237 0.8569 0.996 0.000 0.004
#> GSM955056 3 0.4887 0.6916 0.000 0.228 0.772
#> GSM955058 2 0.1163 0.8123 0.000 0.972 0.028
#> GSM955059 3 0.4887 0.6914 0.000 0.228 0.772
#> GSM955060 1 0.4277 0.7707 0.852 0.016 0.132
#> GSM955061 2 0.1163 0.8123 0.000 0.972 0.028
#> GSM955065 1 0.0237 0.8569 0.996 0.000 0.004
#> GSM955066 3 0.4887 0.7069 0.060 0.096 0.844
#> GSM955067 1 0.1015 0.8557 0.980 0.012 0.008
#> GSM955073 3 0.1753 0.6977 0.000 0.048 0.952
#> GSM955074 1 0.6719 0.6652 0.744 0.160 0.096
#> GSM955076 2 0.1411 0.8050 0.000 0.964 0.036
#> GSM955078 2 0.1163 0.8119 0.000 0.972 0.028
#> GSM955083 2 0.9647 0.0391 0.264 0.468 0.268
#> GSM955084 2 0.0000 0.8008 0.000 1.000 0.000
#> GSM955086 3 0.6062 0.7140 0.064 0.160 0.776
#> GSM955091 2 0.3340 0.7777 0.000 0.880 0.120
#> GSM955092 3 0.5905 0.5685 0.000 0.352 0.648
#> GSM955093 3 0.2066 0.7010 0.000 0.060 0.940
#> GSM955098 2 0.1163 0.8014 0.000 0.972 0.028
#> GSM955099 2 0.1860 0.8113 0.000 0.948 0.052
#> GSM955100 3 0.9502 0.3831 0.308 0.212 0.480
#> GSM955103 3 0.5070 0.7024 0.004 0.224 0.772
#> GSM955104 3 0.4489 0.7179 0.036 0.108 0.856
#> GSM955106 2 0.4963 0.6914 0.008 0.792 0.200
#> GSM955000 3 0.7209 0.2899 0.360 0.036 0.604
#> GSM955006 1 0.8674 0.3113 0.568 0.136 0.296
#> GSM955007 3 0.3551 0.7148 0.000 0.132 0.868
#> GSM955010 3 0.8907 0.5442 0.200 0.228 0.572
#> GSM955014 1 0.0848 0.8564 0.984 0.008 0.008
#> GSM955018 3 0.3989 0.7182 0.012 0.124 0.864
#> GSM955020 1 0.1337 0.8541 0.972 0.012 0.016
#> GSM955024 3 0.6154 0.4610 0.000 0.408 0.592
#> GSM955026 2 0.1163 0.8014 0.000 0.972 0.028
#> GSM955031 3 0.9796 0.3712 0.264 0.304 0.432
#> GSM955038 2 0.8134 0.3399 0.328 0.584 0.088
#> GSM955040 3 0.9772 0.3650 0.268 0.292 0.440
#> GSM955044 2 0.1860 0.8136 0.000 0.948 0.052
#> GSM955051 1 0.0747 0.8550 0.984 0.000 0.016
#> GSM955055 2 0.2448 0.8051 0.000 0.924 0.076
#> GSM955057 1 0.0000 0.8564 1.000 0.000 0.000
#> GSM955062 2 0.5254 0.5947 0.000 0.736 0.264
#> GSM955063 3 0.2066 0.7035 0.000 0.060 0.940
#> GSM955068 2 0.1031 0.8008 0.000 0.976 0.024
#> GSM955069 3 0.3207 0.7134 0.012 0.084 0.904
#> GSM955070 2 0.5956 0.5518 0.016 0.720 0.264
#> GSM955071 3 0.9474 0.4604 0.232 0.272 0.496
#> GSM955077 2 0.4725 0.7460 0.088 0.852 0.060
#> GSM955080 2 0.3213 0.7994 0.008 0.900 0.092
#> GSM955081 3 0.6209 0.5496 0.004 0.368 0.628
#> GSM955082 3 0.5733 0.6085 0.000 0.324 0.676
#> GSM955085 2 0.2625 0.8028 0.000 0.916 0.084
#> GSM955090 1 0.0661 0.8556 0.988 0.004 0.008
#> GSM955094 2 0.5884 0.5381 0.012 0.716 0.272
#> GSM955096 3 0.4750 0.6976 0.000 0.216 0.784
#> GSM955102 3 0.1399 0.6865 0.004 0.028 0.968
#> GSM955105 3 0.3918 0.7175 0.012 0.120 0.868
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.8678 -0.1298 0.032 0.352 0.304 0.312
#> GSM955008 3 0.3278 0.6491 0.000 0.116 0.864 0.020
#> GSM955016 4 0.8128 0.2128 0.400 0.060 0.100 0.440
#> GSM955019 2 0.4773 0.7054 0.000 0.788 0.120 0.092
#> GSM955022 3 0.4937 0.6370 0.000 0.172 0.764 0.064
#> GSM955023 3 0.4937 0.6370 0.000 0.172 0.764 0.064
#> GSM955027 2 0.3621 0.7298 0.000 0.860 0.068 0.072
#> GSM955043 2 0.3706 0.7237 0.000 0.848 0.040 0.112
#> GSM955048 1 0.1902 0.8032 0.932 0.000 0.004 0.064
#> GSM955049 3 0.5614 0.4690 0.000 0.336 0.628 0.036
#> GSM955054 3 0.6663 0.3876 0.000 0.344 0.556 0.100
#> GSM955064 3 0.6351 0.4237 0.000 0.332 0.588 0.080
#> GSM955072 2 0.5713 0.6082 0.000 0.620 0.040 0.340
#> GSM955075 2 0.4144 0.7068 0.000 0.828 0.068 0.104
#> GSM955079 3 0.3266 0.6176 0.004 0.032 0.880 0.084
#> GSM955087 1 0.0188 0.8077 0.996 0.000 0.000 0.004
#> GSM955088 3 0.5707 0.6056 0.004 0.144 0.728 0.124
#> GSM955089 1 0.0469 0.8080 0.988 0.000 0.000 0.012
#> GSM955095 2 0.6269 0.5085 0.000 0.632 0.272 0.096
#> GSM955097 2 0.3962 0.6740 0.000 0.820 0.028 0.152
#> GSM955101 3 0.6179 0.4526 0.000 0.320 0.608 0.072
#> GSM954999 4 0.8517 0.5193 0.260 0.100 0.124 0.516
#> GSM955001 2 0.5998 0.5834 0.000 0.668 0.240 0.092
#> GSM955003 3 0.6194 0.5150 0.000 0.288 0.628 0.084
#> GSM955004 2 0.2868 0.6891 0.000 0.864 0.000 0.136
#> GSM955005 3 0.7842 0.2952 0.148 0.056 0.584 0.212
#> GSM955009 2 0.3443 0.7026 0.000 0.848 0.016 0.136
#> GSM955011 1 0.8927 -0.5262 0.336 0.048 0.304 0.312
#> GSM955012 2 0.3037 0.7068 0.000 0.880 0.020 0.100
#> GSM955013 3 0.7606 0.3999 0.012 0.260 0.536 0.192
#> GSM955015 3 0.5859 0.5336 0.000 0.284 0.652 0.064
#> GSM955017 1 0.5186 0.6104 0.752 0.000 0.084 0.164
#> GSM955021 2 0.6319 0.4532 0.000 0.604 0.312 0.084
#> GSM955025 2 0.5964 0.6485 0.000 0.676 0.096 0.228
#> GSM955028 1 0.0188 0.8077 0.996 0.000 0.000 0.004
#> GSM955029 2 0.3037 0.7068 0.000 0.880 0.020 0.100
#> GSM955030 3 0.7575 0.1663 0.192 0.016 0.556 0.236
#> GSM955032 3 0.4790 0.6355 0.004 0.104 0.796 0.096
#> GSM955033 4 0.8694 0.2405 0.052 0.196 0.340 0.412
#> GSM955034 1 0.0188 0.8077 0.996 0.000 0.000 0.004
#> GSM955035 3 0.6653 0.0966 0.000 0.436 0.480 0.084
#> GSM955036 3 0.4098 0.5685 0.000 0.012 0.784 0.204
#> GSM955037 3 0.6833 0.1576 0.272 0.000 0.584 0.144
#> GSM955039 3 0.6654 0.4680 0.032 0.088 0.668 0.212
#> GSM955041 3 0.6121 0.4853 0.000 0.308 0.620 0.072
#> GSM955042 4 0.8478 0.4973 0.272 0.092 0.124 0.512
#> GSM955045 2 0.6393 -0.0555 0.000 0.480 0.456 0.064
#> GSM955046 3 0.4059 0.5702 0.000 0.012 0.788 0.200
#> GSM955047 1 0.2593 0.7830 0.892 0.000 0.004 0.104
#> GSM955050 4 0.9239 0.5071 0.180 0.112 0.300 0.408
#> GSM955052 3 0.3278 0.6491 0.000 0.116 0.864 0.020
#> GSM955053 1 0.0188 0.8077 0.996 0.000 0.000 0.004
#> GSM955056 3 0.4322 0.6471 0.000 0.152 0.804 0.044
#> GSM955058 2 0.3037 0.7068 0.000 0.880 0.020 0.100
#> GSM955059 3 0.5011 0.6411 0.000 0.160 0.764 0.076
#> GSM955060 1 0.4731 0.6552 0.780 0.000 0.060 0.160
#> GSM955061 2 0.3037 0.7068 0.000 0.880 0.020 0.100
#> GSM955065 1 0.0188 0.8077 0.996 0.000 0.000 0.004
#> GSM955066 3 0.5750 0.4651 0.024 0.028 0.688 0.260
#> GSM955067 1 0.3257 0.7662 0.844 0.000 0.004 0.152
#> GSM955073 3 0.1706 0.6237 0.000 0.016 0.948 0.036
#> GSM955074 1 0.6662 0.3813 0.608 0.060 0.024 0.308
#> GSM955076 2 0.5882 0.5934 0.000 0.608 0.048 0.344
#> GSM955078 2 0.3307 0.7241 0.000 0.868 0.028 0.104
#> GSM955083 4 0.8987 0.4010 0.100 0.300 0.160 0.440
#> GSM955084 2 0.2647 0.7073 0.000 0.880 0.000 0.120
#> GSM955086 3 0.5439 0.5832 0.028 0.064 0.768 0.140
#> GSM955091 2 0.4780 0.7077 0.000 0.788 0.116 0.096
#> GSM955092 3 0.5498 0.5739 0.000 0.272 0.680 0.048
#> GSM955093 3 0.1888 0.6228 0.000 0.016 0.940 0.044
#> GSM955098 2 0.5839 0.5778 0.000 0.604 0.044 0.352
#> GSM955099 2 0.3463 0.7255 0.000 0.864 0.040 0.096
#> GSM955100 4 0.8951 0.4769 0.216 0.064 0.336 0.384
#> GSM955103 3 0.4624 0.6436 0.000 0.164 0.784 0.052
#> GSM955104 3 0.4569 0.5961 0.016 0.036 0.808 0.140
#> GSM955106 2 0.5889 0.6330 0.000 0.696 0.188 0.116
#> GSM955000 3 0.7449 -0.0977 0.332 0.000 0.480 0.188
#> GSM955006 1 0.8117 -0.2032 0.512 0.036 0.180 0.272
#> GSM955007 3 0.4168 0.6381 0.000 0.080 0.828 0.092
#> GSM955010 3 0.8355 -0.2807 0.112 0.068 0.428 0.392
#> GSM955014 1 0.3157 0.7699 0.852 0.000 0.004 0.144
#> GSM955018 3 0.3382 0.6243 0.004 0.040 0.876 0.080
#> GSM955020 1 0.2589 0.7874 0.884 0.000 0.000 0.116
#> GSM955024 3 0.6156 0.4392 0.000 0.344 0.592 0.064
#> GSM955026 2 0.5790 0.5884 0.000 0.616 0.044 0.340
#> GSM955031 3 0.9504 -0.2877 0.188 0.140 0.376 0.296
#> GSM955038 4 0.7858 0.3730 0.152 0.240 0.044 0.564
#> GSM955040 4 0.9227 0.5175 0.172 0.116 0.300 0.412
#> GSM955044 2 0.4152 0.7160 0.000 0.808 0.032 0.160
#> GSM955051 1 0.2401 0.7969 0.904 0.000 0.004 0.092
#> GSM955055 2 0.4359 0.7199 0.000 0.816 0.084 0.100
#> GSM955057 1 0.0592 0.8076 0.984 0.000 0.000 0.016
#> GSM955062 2 0.6138 0.5463 0.000 0.648 0.260 0.092
#> GSM955063 3 0.2197 0.6277 0.000 0.024 0.928 0.048
#> GSM955068 2 0.5677 0.5983 0.000 0.628 0.040 0.332
#> GSM955069 3 0.4233 0.6256 0.008 0.044 0.828 0.120
#> GSM955070 2 0.7170 0.4238 0.000 0.548 0.184 0.268
#> GSM955071 3 0.9224 -0.3954 0.160 0.116 0.368 0.356
#> GSM955077 2 0.6772 0.6059 0.076 0.676 0.056 0.192
#> GSM955080 2 0.4656 0.6865 0.000 0.784 0.056 0.160
#> GSM955081 3 0.5791 0.5585 0.000 0.284 0.656 0.060
#> GSM955082 3 0.5143 0.5920 0.000 0.256 0.708 0.036
#> GSM955085 2 0.5110 0.7059 0.000 0.764 0.104 0.132
#> GSM955090 1 0.2469 0.7819 0.892 0.000 0.000 0.108
#> GSM955094 2 0.7001 0.4468 0.000 0.576 0.180 0.244
#> GSM955096 3 0.3913 0.6450 0.000 0.148 0.824 0.028
#> GSM955102 3 0.3610 0.5382 0.000 0.000 0.800 0.200
#> GSM955105 3 0.3556 0.6152 0.004 0.036 0.864 0.096
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 4 0.8441 0.1360 0.004 0.184 0.184 0.380 0.248
#> GSM955008 3 0.3201 0.6344 0.000 0.060 0.872 0.024 0.044
#> GSM955016 4 0.6163 0.2995 0.268 0.072 0.012 0.620 0.028
#> GSM955019 5 0.6231 0.3739 0.000 0.292 0.132 0.012 0.564
#> GSM955022 3 0.5702 0.6267 0.000 0.072 0.708 0.096 0.124
#> GSM955023 3 0.5702 0.6267 0.000 0.072 0.708 0.096 0.124
#> GSM955027 5 0.5074 0.4255 0.000 0.268 0.072 0.000 0.660
#> GSM955043 5 0.4915 0.5092 0.000 0.192 0.048 0.028 0.732
#> GSM955048 1 0.2848 0.8498 0.868 0.028 0.000 0.104 0.000
#> GSM955049 3 0.6248 0.5146 0.000 0.120 0.620 0.036 0.224
#> GSM955054 3 0.6968 0.4038 0.000 0.188 0.540 0.044 0.228
#> GSM955064 3 0.6279 0.4213 0.000 0.108 0.596 0.032 0.264
#> GSM955072 2 0.5287 0.5506 0.000 0.648 0.028 0.032 0.292
#> GSM955075 5 0.3165 0.5544 0.000 0.044 0.048 0.032 0.876
#> GSM955079 3 0.3873 0.5733 0.004 0.024 0.808 0.152 0.012
#> GSM955087 1 0.0290 0.8592 0.992 0.000 0.000 0.008 0.000
#> GSM955088 3 0.6793 0.5119 0.004 0.104 0.588 0.236 0.068
#> GSM955089 1 0.0451 0.8593 0.988 0.008 0.000 0.004 0.000
#> GSM955095 5 0.6180 0.3963 0.000 0.052 0.228 0.088 0.632
#> GSM955097 5 0.2459 0.4940 0.000 0.040 0.004 0.052 0.904
#> GSM955101 3 0.6221 0.4427 0.000 0.100 0.608 0.036 0.256
#> GSM954999 4 0.6287 0.4916 0.124 0.124 0.020 0.680 0.052
#> GSM955001 5 0.7098 0.2815 0.000 0.236 0.240 0.032 0.492
#> GSM955003 3 0.6020 0.5394 0.000 0.160 0.644 0.024 0.172
#> GSM955004 5 0.2388 0.5069 0.000 0.072 0.000 0.028 0.900
#> GSM955005 3 0.7774 -0.1206 0.136 0.048 0.396 0.392 0.028
#> GSM955009 2 0.4746 0.1474 0.000 0.504 0.016 0.000 0.480
#> GSM955011 4 0.7369 0.5545 0.236 0.064 0.128 0.552 0.020
#> GSM955012 5 0.0613 0.5507 0.000 0.004 0.008 0.004 0.984
#> GSM955013 3 0.7872 0.3018 0.008 0.068 0.444 0.240 0.240
#> GSM955015 3 0.6279 0.5204 0.000 0.120 0.628 0.044 0.208
#> GSM955017 1 0.4887 0.6474 0.692 0.048 0.008 0.252 0.000
#> GSM955021 5 0.7027 0.1024 0.000 0.300 0.312 0.008 0.380
#> GSM955025 2 0.7165 0.2527 0.000 0.432 0.060 0.120 0.388
#> GSM955028 1 0.0290 0.8592 0.992 0.000 0.000 0.008 0.000
#> GSM955029 5 0.0613 0.5507 0.000 0.004 0.008 0.004 0.984
#> GSM955030 4 0.7303 0.1714 0.176 0.044 0.360 0.420 0.000
#> GSM955032 3 0.5330 0.6066 0.004 0.088 0.744 0.108 0.056
#> GSM955033 4 0.7155 0.4449 0.004 0.116 0.152 0.584 0.144
#> GSM955034 1 0.0290 0.8592 0.992 0.000 0.000 0.008 0.000
#> GSM955035 3 0.7017 0.0962 0.000 0.144 0.472 0.040 0.344
#> GSM955036 3 0.5579 0.3604 0.000 0.064 0.580 0.348 0.008
#> GSM955037 3 0.7363 -0.1316 0.272 0.028 0.388 0.312 0.000
#> GSM955039 3 0.6757 0.2550 0.004 0.060 0.520 0.344 0.072
#> GSM955041 3 0.5987 0.4684 0.000 0.088 0.628 0.032 0.252
#> GSM955042 4 0.6260 0.4766 0.136 0.116 0.020 0.680 0.048
#> GSM955045 3 0.6475 0.0792 0.000 0.092 0.444 0.028 0.436
#> GSM955046 3 0.5566 0.3627 0.000 0.064 0.584 0.344 0.008
#> GSM955047 1 0.3438 0.7973 0.808 0.020 0.000 0.172 0.000
#> GSM955050 4 0.6936 0.5968 0.076 0.100 0.116 0.652 0.056
#> GSM955052 3 0.3201 0.6344 0.000 0.060 0.872 0.024 0.044
#> GSM955053 1 0.0000 0.8580 1.000 0.000 0.000 0.000 0.000
#> GSM955056 3 0.4420 0.6378 0.000 0.080 0.800 0.040 0.080
#> GSM955058 5 0.0613 0.5507 0.000 0.004 0.008 0.004 0.984
#> GSM955059 3 0.5758 0.6269 0.000 0.072 0.704 0.116 0.108
#> GSM955060 1 0.4441 0.6913 0.720 0.044 0.000 0.236 0.000
#> GSM955061 5 0.0613 0.5507 0.000 0.004 0.008 0.004 0.984
#> GSM955065 1 0.0290 0.8592 0.992 0.000 0.000 0.008 0.000
#> GSM955066 3 0.6347 0.1207 0.024 0.064 0.464 0.440 0.008
#> GSM955067 1 0.4294 0.8041 0.768 0.080 0.000 0.152 0.000
#> GSM955073 3 0.1954 0.6072 0.000 0.032 0.932 0.028 0.008
#> GSM955074 1 0.6152 0.4008 0.548 0.068 0.000 0.352 0.032
#> GSM955076 2 0.4411 0.6275 0.000 0.756 0.024 0.024 0.196
#> GSM955078 5 0.4890 0.3678 0.000 0.332 0.040 0.000 0.628
#> GSM955083 4 0.8525 0.2921 0.056 0.144 0.092 0.444 0.264
#> GSM955084 5 0.3300 0.4244 0.000 0.204 0.000 0.004 0.792
#> GSM955086 3 0.5827 0.5120 0.020 0.068 0.688 0.196 0.028
#> GSM955091 5 0.6194 0.3803 0.000 0.292 0.128 0.012 0.568
#> GSM955092 3 0.5957 0.5927 0.000 0.132 0.668 0.040 0.160
#> GSM955093 3 0.2694 0.6060 0.000 0.032 0.888 0.076 0.004
#> GSM955098 2 0.4235 0.6341 0.000 0.776 0.024 0.024 0.176
#> GSM955099 5 0.5228 0.4512 0.000 0.260 0.048 0.020 0.672
#> GSM955100 4 0.6355 0.6020 0.104 0.052 0.136 0.680 0.028
#> GSM955103 3 0.5143 0.6306 0.000 0.036 0.740 0.088 0.136
#> GSM955104 3 0.5077 0.5012 0.012 0.020 0.688 0.260 0.020
#> GSM955106 5 0.5514 0.4705 0.000 0.052 0.156 0.080 0.712
#> GSM955000 4 0.7629 0.2799 0.332 0.044 0.284 0.340 0.000
#> GSM955006 4 0.7043 0.2558 0.424 0.048 0.076 0.436 0.016
#> GSM955007 3 0.4871 0.6049 0.000 0.052 0.764 0.128 0.056
#> GSM955010 4 0.6308 0.4980 0.048 0.048 0.192 0.668 0.044
#> GSM955014 1 0.4197 0.8092 0.776 0.076 0.000 0.148 0.000
#> GSM955018 3 0.3912 0.5794 0.004 0.032 0.812 0.140 0.012
#> GSM955020 1 0.2853 0.8412 0.876 0.072 0.000 0.052 0.000
#> GSM955024 3 0.6073 0.4646 0.000 0.068 0.588 0.036 0.308
#> GSM955026 2 0.4684 0.6291 0.000 0.740 0.024 0.036 0.200
#> GSM955031 4 0.8653 0.3141 0.096 0.240 0.284 0.352 0.028
#> GSM955038 2 0.6761 -0.2092 0.032 0.444 0.016 0.436 0.072
#> GSM955040 4 0.6833 0.5974 0.068 0.092 0.120 0.660 0.060
#> GSM955044 5 0.5062 0.4425 0.000 0.244 0.044 0.020 0.692
#> GSM955051 1 0.3037 0.8496 0.860 0.040 0.000 0.100 0.000
#> GSM955055 5 0.5737 0.1341 0.000 0.396 0.076 0.004 0.524
#> GSM955057 1 0.1341 0.8568 0.944 0.000 0.000 0.056 0.000
#> GSM955062 5 0.7080 0.2654 0.000 0.236 0.252 0.028 0.484
#> GSM955063 3 0.2788 0.6115 0.000 0.040 0.888 0.064 0.008
#> GSM955068 2 0.4208 0.6325 0.000 0.760 0.016 0.020 0.204
#> GSM955069 3 0.4844 0.5543 0.004 0.036 0.720 0.224 0.016
#> GSM955070 5 0.8025 0.1245 0.000 0.220 0.116 0.244 0.420
#> GSM955071 4 0.7916 0.5241 0.068 0.092 0.208 0.544 0.088
#> GSM955077 2 0.7424 0.3818 0.024 0.452 0.036 0.124 0.364
#> GSM955080 5 0.4143 0.5432 0.000 0.060 0.048 0.072 0.820
#> GSM955081 3 0.6295 0.5753 0.000 0.104 0.644 0.068 0.184
#> GSM955082 3 0.5542 0.6035 0.000 0.104 0.704 0.036 0.156
#> GSM955085 5 0.6347 -0.0403 0.000 0.408 0.088 0.024 0.480
#> GSM955090 1 0.2974 0.8301 0.868 0.052 0.000 0.080 0.000
#> GSM955094 5 0.7560 0.2592 0.000 0.192 0.088 0.228 0.492
#> GSM955096 3 0.4498 0.6281 0.000 0.092 0.796 0.056 0.056
#> GSM955102 3 0.5314 0.3066 0.004 0.044 0.548 0.404 0.000
#> GSM955105 3 0.4009 0.5700 0.004 0.028 0.792 0.168 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 4 0.8792 0.1803 0.000 0.196 0.116 0.268 0.188 0.232
#> GSM955008 3 0.2959 0.5741 0.000 0.060 0.872 0.004 0.036 0.028
#> GSM955016 4 0.4804 0.3726 0.184 0.008 0.004 0.712 0.008 0.084
#> GSM955019 5 0.6370 0.1856 0.000 0.372 0.116 0.008 0.464 0.040
#> GSM955022 3 0.5600 0.5495 0.000 0.056 0.676 0.012 0.112 0.144
#> GSM955023 3 0.5600 0.5495 0.000 0.056 0.676 0.012 0.112 0.144
#> GSM955027 5 0.5607 0.3351 0.000 0.300 0.060 0.016 0.596 0.028
#> GSM955043 5 0.5055 0.4897 0.000 0.212 0.032 0.016 0.692 0.048
#> GSM955048 1 0.3457 0.7843 0.808 0.004 0.000 0.136 0.000 0.052
#> GSM955049 3 0.5865 0.5035 0.000 0.132 0.620 0.004 0.196 0.048
#> GSM955054 3 0.7186 0.4185 0.000 0.188 0.492 0.020 0.208 0.092
#> GSM955064 3 0.6576 0.4548 0.000 0.144 0.548 0.008 0.224 0.076
#> GSM955072 2 0.4832 0.5157 0.000 0.696 0.028 0.032 0.228 0.016
#> GSM955075 5 0.3172 0.5660 0.000 0.032 0.044 0.020 0.868 0.036
#> GSM955079 3 0.4042 0.4260 0.004 0.004 0.760 0.060 0.000 0.172
#> GSM955087 1 0.0508 0.8037 0.984 0.000 0.000 0.012 0.000 0.004
#> GSM955088 3 0.6557 0.2477 0.000 0.064 0.492 0.040 0.052 0.352
#> GSM955089 1 0.0622 0.8031 0.980 0.000 0.000 0.012 0.000 0.008
#> GSM955095 5 0.6298 0.3789 0.000 0.064 0.204 0.036 0.612 0.084
#> GSM955097 5 0.2547 0.5294 0.000 0.020 0.004 0.064 0.892 0.020
#> GSM955101 3 0.6548 0.4731 0.000 0.140 0.556 0.008 0.216 0.080
#> GSM954999 4 0.3887 0.4342 0.040 0.012 0.004 0.812 0.020 0.112
#> GSM955001 5 0.7123 0.1312 0.000 0.280 0.208 0.020 0.440 0.052
#> GSM955003 3 0.5846 0.5362 0.000 0.176 0.628 0.012 0.152 0.032
#> GSM955004 5 0.3150 0.5174 0.000 0.088 0.000 0.060 0.844 0.008
#> GSM955005 6 0.7547 0.4306 0.116 0.024 0.280 0.112 0.012 0.456
#> GSM955009 2 0.4984 0.4250 0.000 0.624 0.020 0.020 0.316 0.020
#> GSM955011 4 0.7505 0.2255 0.180 0.020 0.080 0.384 0.004 0.332
#> GSM955012 5 0.0870 0.5705 0.000 0.012 0.004 0.012 0.972 0.000
#> GSM955013 3 0.8169 0.1387 0.000 0.056 0.388 0.168 0.208 0.180
#> GSM955015 3 0.6804 0.4876 0.000 0.116 0.556 0.020 0.196 0.112
#> GSM955017 1 0.5223 0.6234 0.648 0.008 0.004 0.132 0.000 0.208
#> GSM955021 2 0.7034 0.1189 0.000 0.384 0.296 0.020 0.272 0.028
#> GSM955025 2 0.7215 0.3834 0.000 0.488 0.036 0.096 0.268 0.112
#> GSM955028 1 0.0508 0.8037 0.984 0.000 0.000 0.012 0.000 0.004
#> GSM955029 5 0.0870 0.5705 0.000 0.012 0.004 0.012 0.972 0.000
#> GSM955030 6 0.6999 0.4177 0.156 0.000 0.240 0.132 0.000 0.472
#> GSM955032 3 0.5541 0.4980 0.004 0.056 0.704 0.044 0.048 0.144
#> GSM955033 4 0.7472 0.2692 0.000 0.088 0.048 0.400 0.112 0.352
#> GSM955034 1 0.0508 0.8037 0.984 0.000 0.000 0.012 0.000 0.004
#> GSM955035 3 0.7111 0.1761 0.000 0.160 0.424 0.008 0.320 0.088
#> GSM955036 6 0.5043 0.3725 0.000 0.008 0.332 0.052 0.008 0.600
#> GSM955037 6 0.6931 0.4080 0.268 0.008 0.204 0.060 0.000 0.460
#> GSM955039 3 0.7456 -0.1453 0.000 0.048 0.412 0.216 0.044 0.280
#> GSM955041 3 0.6499 0.4852 0.000 0.104 0.568 0.012 0.224 0.092
#> GSM955042 4 0.3989 0.4332 0.052 0.012 0.004 0.808 0.020 0.104
#> GSM955045 3 0.6320 0.1491 0.000 0.088 0.428 0.004 0.420 0.060
#> GSM955046 6 0.5056 0.3726 0.000 0.008 0.336 0.052 0.008 0.596
#> GSM955047 1 0.4519 0.7270 0.736 0.020 0.000 0.152 0.000 0.092
#> GSM955050 4 0.6893 0.3989 0.016 0.088 0.052 0.468 0.020 0.356
#> GSM955052 3 0.2959 0.5741 0.000 0.060 0.872 0.004 0.036 0.028
#> GSM955053 1 0.0291 0.8029 0.992 0.000 0.000 0.004 0.000 0.004
#> GSM955056 3 0.4072 0.5728 0.000 0.080 0.800 0.004 0.044 0.072
#> GSM955058 5 0.0870 0.5705 0.000 0.012 0.004 0.012 0.972 0.000
#> GSM955059 3 0.5566 0.5344 0.000 0.056 0.668 0.008 0.096 0.172
#> GSM955060 1 0.4915 0.6585 0.676 0.008 0.000 0.128 0.000 0.188
#> GSM955061 5 0.0870 0.5705 0.000 0.012 0.004 0.012 0.972 0.000
#> GSM955065 1 0.0508 0.8037 0.984 0.000 0.000 0.012 0.000 0.004
#> GSM955066 6 0.5479 0.4509 0.016 0.008 0.296 0.084 0.000 0.596
#> GSM955067 1 0.4400 0.7400 0.708 0.012 0.000 0.228 0.000 0.052
#> GSM955073 3 0.2845 0.4929 0.000 0.000 0.836 0.008 0.008 0.148
#> GSM955074 1 0.5433 0.2548 0.464 0.012 0.000 0.460 0.012 0.052
#> GSM955076 2 0.3184 0.6014 0.000 0.856 0.016 0.032 0.084 0.012
#> GSM955078 5 0.5286 0.2946 0.000 0.372 0.020 0.016 0.560 0.032
#> GSM955083 4 0.7083 0.2820 0.020 0.032 0.032 0.520 0.244 0.152
#> GSM955084 5 0.4106 0.2834 0.000 0.312 0.000 0.020 0.664 0.004
#> GSM955086 3 0.5818 0.3149 0.012 0.048 0.644 0.120 0.000 0.176
#> GSM955091 5 0.6306 0.2075 0.000 0.372 0.108 0.008 0.472 0.040
#> GSM955092 3 0.5695 0.5457 0.000 0.132 0.660 0.004 0.132 0.072
#> GSM955093 3 0.3073 0.4828 0.000 0.000 0.816 0.016 0.004 0.164
#> GSM955098 2 0.2635 0.5982 0.000 0.892 0.016 0.036 0.048 0.008
#> GSM955099 5 0.5523 0.4074 0.000 0.292 0.028 0.016 0.608 0.056
#> GSM955100 4 0.6343 0.3367 0.036 0.024 0.068 0.464 0.004 0.404
#> GSM955103 3 0.5616 0.5367 0.000 0.028 0.684 0.040 0.120 0.128
#> GSM955104 3 0.5535 0.0880 0.004 0.000 0.580 0.108 0.012 0.296
#> GSM955106 5 0.5473 0.4787 0.000 0.048 0.152 0.044 0.700 0.056
#> GSM955000 6 0.6729 0.3370 0.320 0.000 0.152 0.076 0.000 0.452
#> GSM955006 1 0.7272 -0.2568 0.380 0.020 0.044 0.336 0.004 0.216
#> GSM955007 3 0.5613 0.4176 0.000 0.024 0.632 0.032 0.060 0.252
#> GSM955010 6 0.6554 -0.2792 0.020 0.016 0.088 0.412 0.024 0.440
#> GSM955014 1 0.4348 0.7448 0.716 0.012 0.000 0.220 0.000 0.052
#> GSM955018 3 0.4034 0.4354 0.004 0.008 0.764 0.052 0.000 0.172
#> GSM955020 1 0.2699 0.7787 0.856 0.008 0.000 0.124 0.000 0.012
#> GSM955024 3 0.6158 0.4934 0.000 0.072 0.564 0.008 0.280 0.076
#> GSM955026 2 0.3262 0.5939 0.000 0.852 0.016 0.052 0.072 0.008
#> GSM955031 6 0.7957 -0.0448 0.016 0.168 0.248 0.268 0.000 0.300
#> GSM955038 4 0.4694 0.3089 0.000 0.352 0.008 0.608 0.016 0.016
#> GSM955040 4 0.6607 0.3910 0.008 0.064 0.060 0.472 0.020 0.376
#> GSM955044 5 0.5210 0.4307 0.000 0.256 0.016 0.020 0.652 0.056
#> GSM955051 1 0.3416 0.7921 0.820 0.012 0.000 0.124 0.000 0.044
#> GSM955055 2 0.6215 0.1446 0.000 0.468 0.068 0.024 0.404 0.036
#> GSM955057 1 0.1924 0.7996 0.920 0.004 0.000 0.048 0.000 0.028
#> GSM955062 5 0.7078 0.1104 0.000 0.284 0.212 0.016 0.436 0.052
#> GSM955063 3 0.3448 0.4854 0.000 0.008 0.788 0.008 0.008 0.188
#> GSM955068 2 0.3003 0.6053 0.000 0.868 0.016 0.028 0.076 0.012
#> GSM955069 3 0.5301 0.2207 0.000 0.024 0.620 0.044 0.016 0.296
#> GSM955070 5 0.8263 0.0724 0.000 0.256 0.052 0.168 0.340 0.184
#> GSM955071 4 0.7675 0.3004 0.016 0.060 0.136 0.412 0.044 0.332
#> GSM955077 2 0.6856 0.4770 0.000 0.556 0.032 0.108 0.208 0.096
#> GSM955080 5 0.4070 0.5612 0.000 0.052 0.032 0.052 0.816 0.048
#> GSM955081 3 0.6209 0.5282 0.000 0.120 0.632 0.024 0.148 0.076
#> GSM955082 3 0.5172 0.5538 0.000 0.108 0.704 0.004 0.136 0.048
#> GSM955085 2 0.6561 0.1516 0.000 0.436 0.080 0.028 0.408 0.048
#> GSM955090 1 0.3209 0.7553 0.816 0.012 0.000 0.156 0.000 0.016
#> GSM955094 5 0.7409 0.2591 0.000 0.184 0.032 0.076 0.448 0.260
#> GSM955096 3 0.4166 0.5578 0.000 0.072 0.796 0.008 0.040 0.084
#> GSM955102 6 0.4952 0.4581 0.004 0.008 0.320 0.056 0.000 0.612
#> GSM955105 3 0.3943 0.4383 0.004 0.000 0.756 0.056 0.000 0.184
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> MAD:hclust 102 0.973 2
#> MAD:hclust 84 0.965 3
#> MAD:hclust 77 0.978 4
#> MAD:hclust 60 0.939 5
#> MAD:hclust 42 0.920 6
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 31589 rows and 108 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 0.923 0.936 0.970 0.3780 0.651 0.651
#> 3 3 0.783 0.915 0.938 0.7202 0.695 0.531
#> 4 4 0.586 0.615 0.795 0.1375 0.892 0.702
#> 5 5 0.599 0.529 0.711 0.0699 0.889 0.619
#> 6 6 0.614 0.480 0.676 0.0443 0.907 0.602
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
#> GSM955002 2 0.0000 0.961 0.000 1.000
#> GSM955008 2 0.0000 0.961 0.000 1.000
#> GSM955016 1 0.0000 1.000 1.000 0.000
#> GSM955019 2 0.0000 0.961 0.000 1.000
#> GSM955022 2 0.0000 0.961 0.000 1.000
#> GSM955023 2 0.0000 0.961 0.000 1.000
#> GSM955027 2 0.0000 0.961 0.000 1.000
#> GSM955043 2 0.0000 0.961 0.000 1.000
#> GSM955048 1 0.0000 1.000 1.000 0.000
#> GSM955049 2 0.0000 0.961 0.000 1.000
#> GSM955054 2 0.0000 0.961 0.000 1.000
#> GSM955064 2 0.0000 0.961 0.000 1.000
#> GSM955072 2 0.0000 0.961 0.000 1.000
#> GSM955075 2 0.0000 0.961 0.000 1.000
#> GSM955079 2 0.0000 0.961 0.000 1.000
#> GSM955087 1 0.0000 1.000 1.000 0.000
#> GSM955088 2 0.0376 0.958 0.004 0.996
#> GSM955089 1 0.0000 1.000 1.000 0.000
#> GSM955095 2 0.0000 0.961 0.000 1.000
#> GSM955097 2 0.0000 0.961 0.000 1.000
#> GSM955101 2 0.0000 0.961 0.000 1.000
#> GSM954999 2 0.7674 0.736 0.224 0.776
#> GSM955001 2 0.0000 0.961 0.000 1.000
#> GSM955003 2 0.0000 0.961 0.000 1.000
#> GSM955004 2 0.0000 0.961 0.000 1.000
#> GSM955005 2 0.0000 0.961 0.000 1.000
#> GSM955009 2 0.0000 0.961 0.000 1.000
#> GSM955011 1 0.0000 1.000 1.000 0.000
#> GSM955012 2 0.0000 0.961 0.000 1.000
#> GSM955013 2 0.0000 0.961 0.000 1.000
#> GSM955015 2 0.0000 0.961 0.000 1.000
#> GSM955017 1 0.0000 1.000 1.000 0.000
#> GSM955021 2 0.0000 0.961 0.000 1.000
#> GSM955025 2 0.0000 0.961 0.000 1.000
#> GSM955028 1 0.0000 1.000 1.000 0.000
#> GSM955029 2 0.0000 0.961 0.000 1.000
#> GSM955030 2 0.9209 0.555 0.336 0.664
#> GSM955032 2 0.0000 0.961 0.000 1.000
#> GSM955033 2 0.3879 0.900 0.076 0.924
#> GSM955034 1 0.0000 1.000 1.000 0.000
#> GSM955035 2 0.0000 0.961 0.000 1.000
#> GSM955036 2 0.7299 0.761 0.204 0.796
#> GSM955037 1 0.0000 1.000 1.000 0.000
#> GSM955039 2 0.0000 0.961 0.000 1.000
#> GSM955041 2 0.0000 0.961 0.000 1.000
#> GSM955042 1 0.0000 1.000 1.000 0.000
#> GSM955045 2 0.0000 0.961 0.000 1.000
#> GSM955046 2 0.0000 0.961 0.000 1.000
#> GSM955047 1 0.0000 1.000 1.000 0.000
#> GSM955050 2 0.8608 0.648 0.284 0.716
#> GSM955052 2 0.0000 0.961 0.000 1.000
#> GSM955053 1 0.0000 1.000 1.000 0.000
#> GSM955056 2 0.0000 0.961 0.000 1.000
#> GSM955058 2 0.0000 0.961 0.000 1.000
#> GSM955059 2 0.0672 0.955 0.008 0.992
#> GSM955060 1 0.0000 1.000 1.000 0.000
#> GSM955061 2 0.0000 0.961 0.000 1.000
#> GSM955065 1 0.0000 1.000 1.000 0.000
#> GSM955066 2 0.8861 0.614 0.304 0.696
#> GSM955067 1 0.0000 1.000 1.000 0.000
#> GSM955073 2 0.0000 0.961 0.000 1.000
#> GSM955074 1 0.0000 1.000 1.000 0.000
#> GSM955076 2 0.0000 0.961 0.000 1.000
#> GSM955078 2 0.0000 0.961 0.000 1.000
#> GSM955083 2 0.3879 0.900 0.076 0.924
#> GSM955084 2 0.0000 0.961 0.000 1.000
#> GSM955086 2 0.0376 0.958 0.004 0.996
#> GSM955091 2 0.0000 0.961 0.000 1.000
#> GSM955092 2 0.0000 0.961 0.000 1.000
#> GSM955093 2 0.0000 0.961 0.000 1.000
#> GSM955098 2 0.0000 0.961 0.000 1.000
#> GSM955099 2 0.0000 0.961 0.000 1.000
#> GSM955100 1 0.0000 1.000 1.000 0.000
#> GSM955103 2 0.0000 0.961 0.000 1.000
#> GSM955104 2 0.3274 0.915 0.060 0.940
#> GSM955106 2 0.0000 0.961 0.000 1.000
#> GSM955000 1 0.0000 1.000 1.000 0.000
#> GSM955006 1 0.0000 1.000 1.000 0.000
#> GSM955007 2 0.0000 0.961 0.000 1.000
#> GSM955010 2 0.9209 0.555 0.336 0.664
#> GSM955014 1 0.0000 1.000 1.000 0.000
#> GSM955018 2 0.0000 0.961 0.000 1.000
#> GSM955020 1 0.0000 1.000 1.000 0.000
#> GSM955024 2 0.0000 0.961 0.000 1.000
#> GSM955026 2 0.0000 0.961 0.000 1.000
#> GSM955031 2 0.2423 0.931 0.040 0.960
#> GSM955038 2 0.8327 0.658 0.264 0.736
#> GSM955040 2 0.8763 0.628 0.296 0.704
#> GSM955044 2 0.0000 0.961 0.000 1.000
#> GSM955051 1 0.0000 1.000 1.000 0.000
#> GSM955055 2 0.0000 0.961 0.000 1.000
#> GSM955057 1 0.0000 1.000 1.000 0.000
#> GSM955062 2 0.0000 0.961 0.000 1.000
#> GSM955063 2 0.0000 0.961 0.000 1.000
#> GSM955068 2 0.0000 0.961 0.000 1.000
#> GSM955069 2 0.1843 0.941 0.028 0.972
#> GSM955070 2 0.0000 0.961 0.000 1.000
#> GSM955071 2 0.8267 0.685 0.260 0.740
#> GSM955077 2 0.0000 0.961 0.000 1.000
#> GSM955080 2 0.0000 0.961 0.000 1.000
#> GSM955081 2 0.0000 0.961 0.000 1.000
#> GSM955082 2 0.0000 0.961 0.000 1.000
#> GSM955085 2 0.0000 0.961 0.000 1.000
#> GSM955090 1 0.0000 1.000 1.000 0.000
#> GSM955094 2 0.0000 0.961 0.000 1.000
#> GSM955096 2 0.0000 0.961 0.000 1.000
#> GSM955102 2 0.9795 0.371 0.416 0.584
#> GSM955105 2 0.0672 0.955 0.008 0.992
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.5327 0.748 0.000 0.272 0.728
#> GSM955008 3 0.4062 0.871 0.000 0.164 0.836
#> GSM955016 1 0.2866 0.939 0.916 0.008 0.076
#> GSM955019 2 0.0747 0.945 0.000 0.984 0.016
#> GSM955022 3 0.2261 0.920 0.000 0.068 0.932
#> GSM955023 3 0.3038 0.907 0.000 0.104 0.896
#> GSM955027 2 0.0892 0.945 0.000 0.980 0.020
#> GSM955043 2 0.1163 0.945 0.000 0.972 0.028
#> GSM955048 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955049 2 0.1289 0.944 0.000 0.968 0.032
#> GSM955054 3 0.3941 0.884 0.000 0.156 0.844
#> GSM955064 2 0.1964 0.940 0.000 0.944 0.056
#> GSM955072 2 0.0237 0.943 0.000 0.996 0.004
#> GSM955075 2 0.1411 0.942 0.000 0.964 0.036
#> GSM955079 3 0.1529 0.922 0.000 0.040 0.960
#> GSM955087 1 0.0237 0.978 0.996 0.000 0.004
#> GSM955088 3 0.1163 0.922 0.000 0.028 0.972
#> GSM955089 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955095 2 0.3879 0.845 0.000 0.848 0.152
#> GSM955097 2 0.2959 0.903 0.000 0.900 0.100
#> GSM955101 3 0.4178 0.866 0.000 0.172 0.828
#> GSM954999 3 0.1774 0.906 0.024 0.016 0.960
#> GSM955001 2 0.0747 0.945 0.000 0.984 0.016
#> GSM955003 3 0.4504 0.850 0.000 0.196 0.804
#> GSM955004 2 0.0592 0.941 0.000 0.988 0.012
#> GSM955005 3 0.0424 0.917 0.000 0.008 0.992
#> GSM955009 2 0.0747 0.945 0.000 0.984 0.016
#> GSM955011 1 0.2625 0.937 0.916 0.000 0.084
#> GSM955012 2 0.1753 0.939 0.000 0.952 0.048
#> GSM955013 3 0.0892 0.914 0.000 0.020 0.980
#> GSM955015 3 0.4291 0.868 0.000 0.180 0.820
#> GSM955017 1 0.1163 0.970 0.972 0.000 0.028
#> GSM955021 2 0.0747 0.945 0.000 0.984 0.016
#> GSM955025 2 0.0983 0.941 0.004 0.980 0.016
#> GSM955028 1 0.0237 0.978 0.996 0.000 0.004
#> GSM955029 2 0.1289 0.944 0.000 0.968 0.032
#> GSM955030 3 0.1170 0.908 0.016 0.008 0.976
#> GSM955032 3 0.2356 0.920 0.000 0.072 0.928
#> GSM955033 3 0.4629 0.808 0.004 0.188 0.808
#> GSM955034 1 0.0237 0.978 0.996 0.000 0.004
#> GSM955035 2 0.1289 0.943 0.000 0.968 0.032
#> GSM955036 3 0.0747 0.912 0.000 0.016 0.984
#> GSM955037 1 0.2878 0.930 0.904 0.000 0.096
#> GSM955039 3 0.1964 0.914 0.000 0.056 0.944
#> GSM955041 2 0.4750 0.738 0.000 0.784 0.216
#> GSM955042 1 0.2866 0.939 0.916 0.008 0.076
#> GSM955045 2 0.2356 0.923 0.000 0.928 0.072
#> GSM955046 3 0.0747 0.917 0.000 0.016 0.984
#> GSM955047 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955050 3 0.4925 0.853 0.076 0.080 0.844
#> GSM955052 3 0.2711 0.911 0.000 0.088 0.912
#> GSM955053 1 0.0237 0.978 0.996 0.000 0.004
#> GSM955056 3 0.3116 0.906 0.000 0.108 0.892
#> GSM955058 2 0.1529 0.942 0.000 0.960 0.040
#> GSM955059 3 0.0592 0.917 0.000 0.012 0.988
#> GSM955060 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955061 2 0.1529 0.942 0.000 0.960 0.040
#> GSM955065 1 0.0237 0.978 0.996 0.000 0.004
#> GSM955066 3 0.0983 0.912 0.016 0.004 0.980
#> GSM955067 1 0.0237 0.977 0.996 0.000 0.004
#> GSM955073 3 0.2537 0.915 0.000 0.080 0.920
#> GSM955074 1 0.1989 0.958 0.948 0.004 0.048
#> GSM955076 2 0.2711 0.895 0.000 0.912 0.088
#> GSM955078 2 0.0424 0.946 0.000 0.992 0.008
#> GSM955083 3 0.4473 0.826 0.008 0.164 0.828
#> GSM955084 2 0.0592 0.941 0.000 0.988 0.012
#> GSM955086 3 0.1411 0.921 0.000 0.036 0.964
#> GSM955091 2 0.0747 0.945 0.000 0.984 0.016
#> GSM955092 2 0.1753 0.937 0.000 0.952 0.048
#> GSM955093 3 0.0747 0.919 0.000 0.016 0.984
#> GSM955098 2 0.0747 0.943 0.000 0.984 0.016
#> GSM955099 2 0.0424 0.946 0.000 0.992 0.008
#> GSM955100 1 0.2625 0.937 0.916 0.000 0.084
#> GSM955103 3 0.4504 0.836 0.000 0.196 0.804
#> GSM955104 3 0.0592 0.914 0.000 0.012 0.988
#> GSM955106 2 0.2165 0.925 0.000 0.936 0.064
#> GSM955000 1 0.1411 0.967 0.964 0.000 0.036
#> GSM955006 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955007 3 0.2711 0.913 0.000 0.088 0.912
#> GSM955010 3 0.1950 0.899 0.040 0.008 0.952
#> GSM955014 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955018 3 0.0747 0.919 0.000 0.016 0.984
#> GSM955020 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955024 3 0.3192 0.902 0.000 0.112 0.888
#> GSM955026 2 0.0747 0.943 0.000 0.984 0.016
#> GSM955031 3 0.3112 0.904 0.004 0.096 0.900
#> GSM955038 2 0.8261 0.314 0.340 0.568 0.092
#> GSM955040 3 0.5085 0.841 0.092 0.072 0.836
#> GSM955044 2 0.0424 0.944 0.000 0.992 0.008
#> GSM955051 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955055 2 0.0747 0.945 0.000 0.984 0.016
#> GSM955057 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955062 2 0.0892 0.945 0.000 0.980 0.020
#> GSM955063 3 0.2537 0.915 0.000 0.080 0.920
#> GSM955068 2 0.0424 0.942 0.000 0.992 0.008
#> GSM955069 3 0.0424 0.917 0.000 0.008 0.992
#> GSM955070 2 0.1529 0.936 0.000 0.960 0.040
#> GSM955071 3 0.2383 0.899 0.044 0.016 0.940
#> GSM955077 2 0.2200 0.912 0.004 0.940 0.056
#> GSM955080 2 0.1964 0.932 0.000 0.944 0.056
#> GSM955081 3 0.4452 0.849 0.000 0.192 0.808
#> GSM955082 2 0.5621 0.586 0.000 0.692 0.308
#> GSM955085 2 0.0424 0.946 0.000 0.992 0.008
#> GSM955090 1 0.0000 0.978 1.000 0.000 0.000
#> GSM955094 2 0.3116 0.886 0.000 0.892 0.108
#> GSM955096 3 0.3038 0.908 0.000 0.104 0.896
#> GSM955102 3 0.0983 0.913 0.016 0.004 0.980
#> GSM955105 3 0.1289 0.921 0.000 0.032 0.968
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 4 0.6834 0.31993 0.000 0.164 0.240 0.596
#> GSM955008 3 0.2335 0.72900 0.000 0.060 0.920 0.020
#> GSM955016 4 0.5016 0.15513 0.396 0.000 0.004 0.600
#> GSM955019 2 0.5184 0.70239 0.000 0.732 0.056 0.212
#> GSM955022 3 0.3377 0.68308 0.000 0.012 0.848 0.140
#> GSM955023 3 0.2224 0.74201 0.000 0.032 0.928 0.040
#> GSM955027 2 0.2021 0.76582 0.000 0.936 0.040 0.024
#> GSM955043 2 0.1510 0.75896 0.000 0.956 0.016 0.028
#> GSM955048 1 0.0336 0.89899 0.992 0.000 0.000 0.008
#> GSM955049 2 0.6400 0.62687 0.000 0.632 0.252 0.116
#> GSM955054 3 0.5494 0.56385 0.000 0.076 0.716 0.208
#> GSM955064 2 0.6366 0.63665 0.000 0.640 0.240 0.120
#> GSM955072 2 0.4507 0.70969 0.000 0.756 0.020 0.224
#> GSM955075 2 0.2227 0.75529 0.000 0.928 0.036 0.036
#> GSM955079 3 0.1488 0.74087 0.000 0.012 0.956 0.032
#> GSM955087 1 0.0000 0.89910 1.000 0.000 0.000 0.000
#> GSM955088 3 0.1576 0.73325 0.000 0.004 0.948 0.048
#> GSM955089 1 0.0000 0.89910 1.000 0.000 0.000 0.000
#> GSM955095 2 0.4782 0.67062 0.000 0.780 0.068 0.152
#> GSM955097 2 0.4914 0.50520 0.000 0.676 0.012 0.312
#> GSM955101 3 0.3621 0.69968 0.000 0.068 0.860 0.072
#> GSM954999 4 0.4634 0.49949 0.004 0.004 0.280 0.712
#> GSM955001 2 0.2385 0.76802 0.000 0.920 0.028 0.052
#> GSM955003 3 0.5750 0.54261 0.000 0.088 0.696 0.216
#> GSM955004 2 0.1940 0.74399 0.000 0.924 0.000 0.076
#> GSM955005 3 0.4643 0.34966 0.000 0.000 0.656 0.344
#> GSM955009 2 0.3450 0.74522 0.000 0.836 0.008 0.156
#> GSM955011 1 0.5408 0.34069 0.576 0.000 0.016 0.408
#> GSM955012 2 0.2032 0.75684 0.000 0.936 0.036 0.028
#> GSM955013 4 0.5097 0.27369 0.000 0.004 0.428 0.568
#> GSM955015 3 0.5167 0.63385 0.000 0.108 0.760 0.132
#> GSM955017 1 0.2255 0.87568 0.920 0.000 0.012 0.068
#> GSM955021 2 0.7399 0.50341 0.000 0.512 0.280 0.208
#> GSM955025 2 0.5097 0.50794 0.000 0.568 0.004 0.428
#> GSM955028 1 0.0000 0.89910 1.000 0.000 0.000 0.000
#> GSM955029 2 0.2032 0.75684 0.000 0.936 0.036 0.028
#> GSM955030 3 0.4948 0.07190 0.000 0.000 0.560 0.440
#> GSM955032 3 0.1584 0.73884 0.000 0.012 0.952 0.036
#> GSM955033 4 0.2813 0.60530 0.000 0.024 0.080 0.896
#> GSM955034 1 0.0000 0.89910 1.000 0.000 0.000 0.000
#> GSM955035 2 0.7122 0.56949 0.000 0.560 0.248 0.192
#> GSM955036 4 0.5112 0.35829 0.000 0.008 0.384 0.608
#> GSM955037 1 0.5182 0.50357 0.684 0.000 0.028 0.288
#> GSM955039 4 0.5127 0.39715 0.000 0.012 0.356 0.632
#> GSM955041 2 0.6211 0.15003 0.000 0.488 0.460 0.052
#> GSM955042 4 0.4955 0.00723 0.444 0.000 0.000 0.556
#> GSM955045 2 0.3581 0.72690 0.000 0.852 0.116 0.032
#> GSM955046 3 0.4500 0.42797 0.000 0.000 0.684 0.316
#> GSM955047 1 0.1557 0.89250 0.944 0.000 0.000 0.056
#> GSM955050 4 0.2111 0.59355 0.000 0.024 0.044 0.932
#> GSM955052 3 0.1151 0.74272 0.000 0.024 0.968 0.008
#> GSM955053 1 0.0000 0.89910 1.000 0.000 0.000 0.000
#> GSM955056 3 0.2300 0.73186 0.000 0.028 0.924 0.048
#> GSM955058 2 0.2032 0.75684 0.000 0.936 0.036 0.028
#> GSM955059 3 0.1867 0.72382 0.000 0.000 0.928 0.072
#> GSM955060 1 0.0592 0.89902 0.984 0.000 0.000 0.016
#> GSM955061 2 0.2032 0.75684 0.000 0.936 0.036 0.028
#> GSM955065 1 0.0000 0.89910 1.000 0.000 0.000 0.000
#> GSM955066 3 0.4477 0.42622 0.000 0.000 0.688 0.312
#> GSM955067 1 0.2408 0.86275 0.896 0.000 0.000 0.104
#> GSM955073 3 0.1297 0.74317 0.000 0.020 0.964 0.016
#> GSM955074 4 0.5080 0.08857 0.420 0.000 0.004 0.576
#> GSM955076 2 0.7551 0.47844 0.000 0.488 0.240 0.272
#> GSM955078 2 0.1109 0.76399 0.000 0.968 0.004 0.028
#> GSM955083 4 0.4139 0.57652 0.000 0.024 0.176 0.800
#> GSM955084 2 0.2530 0.74129 0.000 0.896 0.004 0.100
#> GSM955086 3 0.1635 0.73900 0.000 0.008 0.948 0.044
#> GSM955091 2 0.2611 0.76468 0.000 0.896 0.008 0.096
#> GSM955092 2 0.5636 0.61748 0.000 0.680 0.260 0.060
#> GSM955093 3 0.1398 0.73697 0.000 0.004 0.956 0.040
#> GSM955098 2 0.6276 0.54698 0.000 0.556 0.064 0.380
#> GSM955099 2 0.2676 0.76708 0.000 0.896 0.012 0.092
#> GSM955100 1 0.5511 0.12699 0.500 0.000 0.016 0.484
#> GSM955103 3 0.6350 0.41063 0.000 0.296 0.612 0.092
#> GSM955104 3 0.4972 -0.02298 0.000 0.000 0.544 0.456
#> GSM955106 2 0.3877 0.71696 0.000 0.840 0.048 0.112
#> GSM955000 1 0.2089 0.87165 0.932 0.000 0.020 0.048
#> GSM955006 1 0.1637 0.89127 0.940 0.000 0.000 0.060
#> GSM955007 3 0.2871 0.72667 0.000 0.032 0.896 0.072
#> GSM955010 4 0.5039 0.33472 0.004 0.000 0.404 0.592
#> GSM955014 1 0.1867 0.88691 0.928 0.000 0.000 0.072
#> GSM955018 3 0.1209 0.73800 0.000 0.004 0.964 0.032
#> GSM955020 1 0.0707 0.89760 0.980 0.000 0.000 0.020
#> GSM955024 3 0.4307 0.66122 0.000 0.144 0.808 0.048
#> GSM955026 2 0.6315 0.52559 0.000 0.540 0.064 0.396
#> GSM955031 3 0.6163 0.26308 0.000 0.052 0.532 0.416
#> GSM955038 4 0.3415 0.48155 0.008 0.128 0.008 0.856
#> GSM955040 4 0.2521 0.60352 0.000 0.024 0.064 0.912
#> GSM955044 2 0.3342 0.76638 0.000 0.868 0.032 0.100
#> GSM955051 1 0.1716 0.89033 0.936 0.000 0.000 0.064
#> GSM955055 2 0.2730 0.76679 0.000 0.896 0.016 0.088
#> GSM955057 1 0.0469 0.89851 0.988 0.000 0.000 0.012
#> GSM955062 2 0.6296 0.62785 0.000 0.644 0.244 0.112
#> GSM955063 3 0.1411 0.74339 0.000 0.020 0.960 0.020
#> GSM955068 2 0.5213 0.62987 0.000 0.652 0.020 0.328
#> GSM955069 3 0.3801 0.55738 0.000 0.000 0.780 0.220
#> GSM955070 2 0.6347 0.50154 0.000 0.524 0.064 0.412
#> GSM955071 4 0.4034 0.57961 0.004 0.012 0.180 0.804
#> GSM955077 4 0.5937 -0.41951 0.000 0.472 0.036 0.492
#> GSM955080 2 0.3308 0.73729 0.000 0.872 0.036 0.092
#> GSM955081 3 0.5923 0.53661 0.000 0.100 0.684 0.216
#> GSM955082 3 0.5607 -0.10464 0.000 0.488 0.492 0.020
#> GSM955085 2 0.1302 0.76630 0.000 0.956 0.000 0.044
#> GSM955090 1 0.1637 0.88837 0.940 0.000 0.000 0.060
#> GSM955094 2 0.6064 0.44107 0.000 0.512 0.044 0.444
#> GSM955096 3 0.2224 0.73793 0.000 0.032 0.928 0.040
#> GSM955102 3 0.4820 0.44360 0.012 0.000 0.692 0.296
#> GSM955105 3 0.1635 0.73900 0.000 0.008 0.948 0.044
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.6483 0.2312 0.000 0.548 0.128 0.300 0.024
#> GSM955008 3 0.3730 0.6694 0.000 0.120 0.828 0.028 0.024
#> GSM955016 4 0.5405 0.5404 0.204 0.136 0.000 0.660 0.000
#> GSM955019 2 0.5251 0.4070 0.000 0.576 0.044 0.004 0.376
#> GSM955022 3 0.5704 0.4887 0.000 0.012 0.616 0.288 0.084
#> GSM955023 3 0.4473 0.6783 0.000 0.096 0.796 0.064 0.044
#> GSM955027 5 0.3769 0.5296 0.000 0.180 0.032 0.000 0.788
#> GSM955043 5 0.0955 0.6349 0.000 0.028 0.000 0.004 0.968
#> GSM955048 1 0.0404 0.8749 0.988 0.012 0.000 0.000 0.000
#> GSM955049 2 0.7016 0.2812 0.000 0.388 0.304 0.008 0.300
#> GSM955054 3 0.5080 0.2935 0.000 0.396 0.572 0.020 0.012
#> GSM955064 5 0.7355 -0.1107 0.000 0.224 0.320 0.036 0.420
#> GSM955072 2 0.4830 0.3216 0.000 0.560 0.016 0.004 0.420
#> GSM955075 5 0.1299 0.6277 0.000 0.012 0.008 0.020 0.960
#> GSM955079 3 0.2912 0.7071 0.000 0.088 0.876 0.028 0.008
#> GSM955087 1 0.0963 0.8707 0.964 0.036 0.000 0.000 0.000
#> GSM955088 3 0.4113 0.6451 0.000 0.076 0.784 0.140 0.000
#> GSM955089 1 0.1399 0.8751 0.952 0.028 0.000 0.020 0.000
#> GSM955095 5 0.3507 0.5509 0.000 0.024 0.032 0.096 0.848
#> GSM955097 5 0.3946 0.4973 0.000 0.048 0.008 0.140 0.804
#> GSM955101 3 0.4552 0.6203 0.000 0.176 0.760 0.040 0.024
#> GSM954999 4 0.2990 0.6942 0.000 0.100 0.024 0.868 0.008
#> GSM955001 5 0.4323 0.4639 0.000 0.240 0.028 0.004 0.728
#> GSM955003 3 0.5094 0.2712 0.000 0.412 0.556 0.008 0.024
#> GSM955004 5 0.2929 0.5548 0.000 0.180 0.000 0.000 0.820
#> GSM955005 4 0.5234 -0.0460 0.000 0.044 0.460 0.496 0.000
#> GSM955009 2 0.5161 0.1186 0.000 0.484 0.024 0.008 0.484
#> GSM955011 4 0.5695 0.3147 0.356 0.080 0.004 0.560 0.000
#> GSM955012 5 0.0451 0.6363 0.000 0.008 0.004 0.000 0.988
#> GSM955013 4 0.5045 0.5807 0.000 0.044 0.180 0.732 0.044
#> GSM955015 3 0.6812 0.3457 0.000 0.288 0.544 0.112 0.056
#> GSM955017 1 0.4028 0.7837 0.808 0.080 0.008 0.104 0.000
#> GSM955021 2 0.6578 0.4218 0.000 0.500 0.268 0.004 0.228
#> GSM955025 2 0.5438 0.4990 0.000 0.660 0.012 0.080 0.248
#> GSM955028 1 0.0963 0.8707 0.964 0.036 0.000 0.000 0.000
#> GSM955029 5 0.0671 0.6362 0.000 0.016 0.004 0.000 0.980
#> GSM955030 4 0.4594 0.4321 0.000 0.036 0.284 0.680 0.000
#> GSM955032 3 0.2813 0.7060 0.000 0.108 0.868 0.024 0.000
#> GSM955033 4 0.3873 0.6743 0.000 0.140 0.024 0.812 0.024
#> GSM955034 1 0.0963 0.8707 0.964 0.036 0.000 0.000 0.000
#> GSM955035 2 0.7218 0.3945 0.000 0.448 0.260 0.028 0.264
#> GSM955036 4 0.3450 0.6390 0.000 0.012 0.096 0.848 0.044
#> GSM955037 1 0.6585 -0.1107 0.452 0.060 0.060 0.428 0.000
#> GSM955039 4 0.5080 0.6071 0.000 0.080 0.156 0.736 0.028
#> GSM955041 5 0.6966 -0.0755 0.000 0.136 0.408 0.036 0.420
#> GSM955042 4 0.5607 0.5041 0.228 0.140 0.000 0.632 0.000
#> GSM955045 5 0.3155 0.5720 0.000 0.020 0.096 0.020 0.864
#> GSM955046 3 0.5754 0.1736 0.000 0.044 0.480 0.456 0.020
#> GSM955047 1 0.2928 0.8545 0.872 0.064 0.000 0.064 0.000
#> GSM955050 4 0.4101 0.5728 0.000 0.332 0.004 0.664 0.000
#> GSM955052 3 0.2243 0.7083 0.000 0.056 0.916 0.016 0.012
#> GSM955053 1 0.0963 0.8707 0.964 0.036 0.000 0.000 0.000
#> GSM955056 3 0.2295 0.6996 0.000 0.088 0.900 0.008 0.004
#> GSM955058 5 0.0566 0.6369 0.000 0.012 0.004 0.000 0.984
#> GSM955059 3 0.4054 0.5879 0.000 0.036 0.760 0.204 0.000
#> GSM955060 1 0.1205 0.8736 0.956 0.040 0.000 0.004 0.000
#> GSM955061 5 0.0451 0.6370 0.000 0.008 0.004 0.000 0.988
#> GSM955065 1 0.0963 0.8707 0.964 0.036 0.000 0.000 0.000
#> GSM955066 3 0.5296 0.0664 0.000 0.048 0.484 0.468 0.000
#> GSM955067 1 0.4123 0.8011 0.788 0.108 0.000 0.104 0.000
#> GSM955073 3 0.2774 0.7081 0.000 0.048 0.892 0.048 0.012
#> GSM955074 4 0.5740 0.4639 0.244 0.144 0.000 0.612 0.000
#> GSM955076 2 0.5268 0.5257 0.000 0.668 0.112 0.000 0.220
#> GSM955078 5 0.3766 0.4448 0.000 0.268 0.004 0.000 0.728
#> GSM955083 4 0.3745 0.6848 0.000 0.132 0.012 0.820 0.036
#> GSM955084 5 0.3661 0.4374 0.000 0.276 0.000 0.000 0.724
#> GSM955086 3 0.3075 0.7015 0.000 0.092 0.860 0.048 0.000
#> GSM955091 5 0.4686 0.1280 0.000 0.384 0.020 0.000 0.596
#> GSM955092 5 0.6783 -0.0456 0.000 0.232 0.340 0.004 0.424
#> GSM955093 3 0.2536 0.7075 0.000 0.044 0.900 0.052 0.004
#> GSM955098 2 0.4747 0.5419 0.000 0.716 0.016 0.036 0.232
#> GSM955099 5 0.4599 0.2092 0.000 0.356 0.020 0.000 0.624
#> GSM955100 4 0.5301 0.4998 0.272 0.076 0.004 0.648 0.000
#> GSM955103 3 0.6659 0.3380 0.000 0.076 0.520 0.060 0.344
#> GSM955104 4 0.4907 0.4330 0.000 0.052 0.292 0.656 0.000
#> GSM955106 5 0.2347 0.6022 0.000 0.016 0.016 0.056 0.912
#> GSM955000 1 0.4103 0.7641 0.812 0.068 0.020 0.100 0.000
#> GSM955006 1 0.3110 0.8485 0.860 0.060 0.000 0.080 0.000
#> GSM955007 3 0.4942 0.6383 0.000 0.032 0.744 0.164 0.060
#> GSM955010 4 0.2824 0.6569 0.000 0.032 0.096 0.872 0.000
#> GSM955014 1 0.3476 0.8357 0.836 0.076 0.000 0.088 0.000
#> GSM955018 3 0.2813 0.7004 0.000 0.064 0.884 0.048 0.004
#> GSM955020 1 0.2659 0.8576 0.888 0.052 0.000 0.060 0.000
#> GSM955024 3 0.5315 0.5963 0.000 0.052 0.716 0.052 0.180
#> GSM955026 2 0.4753 0.5471 0.000 0.736 0.016 0.052 0.196
#> GSM955031 2 0.5282 0.3509 0.004 0.676 0.220 0.100 0.000
#> GSM955038 4 0.5267 0.3676 0.004 0.472 0.004 0.492 0.028
#> GSM955040 4 0.3741 0.6331 0.000 0.264 0.004 0.732 0.000
#> GSM955044 5 0.4870 0.3479 0.000 0.276 0.016 0.028 0.680
#> GSM955051 1 0.3535 0.8350 0.832 0.080 0.000 0.088 0.000
#> GSM955055 5 0.4972 0.2447 0.000 0.352 0.032 0.004 0.612
#> GSM955057 1 0.0404 0.8735 0.988 0.012 0.000 0.000 0.000
#> GSM955062 2 0.7018 0.3304 0.000 0.408 0.244 0.012 0.336
#> GSM955063 3 0.2569 0.7048 0.000 0.032 0.896 0.068 0.004
#> GSM955068 2 0.4483 0.4810 0.000 0.672 0.012 0.008 0.308
#> GSM955069 3 0.4731 0.3984 0.000 0.032 0.640 0.328 0.000
#> GSM955070 2 0.7095 0.4298 0.000 0.520 0.056 0.152 0.272
#> GSM955071 4 0.4457 0.6680 0.004 0.208 0.048 0.740 0.000
#> GSM955077 2 0.5802 0.4778 0.000 0.684 0.040 0.124 0.152
#> GSM955080 5 0.1731 0.6186 0.000 0.012 0.008 0.040 0.940
#> GSM955081 3 0.5809 0.2903 0.000 0.380 0.548 0.044 0.028
#> GSM955082 3 0.6071 0.2120 0.000 0.088 0.512 0.012 0.388
#> GSM955085 5 0.4219 0.4541 0.000 0.264 0.016 0.004 0.716
#> GSM955090 1 0.3648 0.8282 0.824 0.084 0.000 0.092 0.000
#> GSM955094 2 0.7165 0.2582 0.000 0.380 0.016 0.268 0.336
#> GSM955096 3 0.2967 0.6922 0.000 0.104 0.868 0.016 0.012
#> GSM955102 3 0.5314 0.1880 0.000 0.052 0.528 0.420 0.000
#> GSM955105 3 0.2889 0.7014 0.000 0.084 0.872 0.044 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.8016 0.09141 0.000 0.404 0.128 0.208 0.052 0.208
#> GSM955008 3 0.1982 0.54889 0.000 0.068 0.912 0.000 0.004 0.016
#> GSM955016 4 0.1802 0.58328 0.072 0.000 0.000 0.916 0.000 0.012
#> GSM955019 2 0.3877 0.53825 0.000 0.792 0.056 0.008 0.136 0.008
#> GSM955022 6 0.6340 0.31518 0.000 0.012 0.336 0.028 0.132 0.492
#> GSM955023 3 0.5238 0.49325 0.000 0.100 0.704 0.004 0.064 0.128
#> GSM955027 5 0.5946 0.22774 0.000 0.312 0.096 0.000 0.544 0.048
#> GSM955043 5 0.3352 0.67717 0.000 0.108 0.020 0.004 0.836 0.032
#> GSM955048 1 0.1644 0.79757 0.932 0.004 0.000 0.052 0.000 0.012
#> GSM955049 3 0.6865 -0.03309 0.000 0.300 0.416 0.000 0.224 0.060
#> GSM955054 3 0.4819 0.36157 0.000 0.300 0.636 0.004 0.008 0.052
#> GSM955064 3 0.6641 0.09053 0.000 0.192 0.456 0.000 0.300 0.052
#> GSM955072 2 0.4560 0.47276 0.000 0.708 0.012 0.008 0.224 0.048
#> GSM955075 5 0.1129 0.73002 0.000 0.012 0.004 0.008 0.964 0.012
#> GSM955079 3 0.3455 0.49550 0.000 0.020 0.776 0.004 0.000 0.200
#> GSM955087 1 0.2224 0.78763 0.912 0.036 0.004 0.000 0.012 0.036
#> GSM955088 3 0.4931 -0.00281 0.000 0.044 0.484 0.008 0.000 0.464
#> GSM955089 1 0.2918 0.79700 0.868 0.028 0.000 0.084 0.012 0.008
#> GSM955095 5 0.3515 0.66570 0.000 0.024 0.016 0.036 0.840 0.084
#> GSM955097 5 0.2765 0.64609 0.000 0.004 0.000 0.132 0.848 0.016
#> GSM955101 3 0.2476 0.54561 0.000 0.092 0.880 0.000 0.004 0.024
#> GSM954999 4 0.2482 0.58814 0.000 0.000 0.000 0.848 0.004 0.148
#> GSM955001 5 0.5711 0.05703 0.000 0.408 0.052 0.000 0.488 0.052
#> GSM955003 3 0.3886 0.42185 0.000 0.264 0.708 0.000 0.000 0.028
#> GSM955004 5 0.4193 0.46504 0.000 0.276 0.000 0.008 0.688 0.028
#> GSM955005 6 0.4841 0.66488 0.000 0.004 0.156 0.160 0.000 0.680
#> GSM955009 2 0.4309 0.47587 0.000 0.752 0.036 0.004 0.176 0.032
#> GSM955011 4 0.5616 0.42600 0.268 0.016 0.000 0.580 0.000 0.136
#> GSM955012 5 0.1699 0.73284 0.000 0.040 0.012 0.004 0.936 0.008
#> GSM955013 4 0.6943 0.14709 0.000 0.016 0.092 0.400 0.096 0.396
#> GSM955015 3 0.6088 0.31692 0.000 0.252 0.568 0.004 0.040 0.136
#> GSM955017 1 0.4500 0.67964 0.740 0.016 0.004 0.080 0.000 0.160
#> GSM955021 2 0.5847 0.35173 0.000 0.532 0.344 0.000 0.064 0.060
#> GSM955025 2 0.4746 0.52223 0.000 0.764 0.024 0.096 0.060 0.056
#> GSM955028 1 0.2224 0.78763 0.912 0.036 0.004 0.000 0.012 0.036
#> GSM955029 5 0.1820 0.72260 0.000 0.056 0.012 0.000 0.924 0.008
#> GSM955030 6 0.4742 0.41404 0.000 0.004 0.076 0.268 0.000 0.652
#> GSM955032 3 0.3727 0.49244 0.000 0.040 0.768 0.004 0.000 0.188
#> GSM955033 4 0.5134 0.56775 0.000 0.056 0.004 0.644 0.028 0.268
#> GSM955034 1 0.2224 0.78763 0.912 0.036 0.004 0.000 0.012 0.036
#> GSM955035 2 0.6444 0.24650 0.000 0.432 0.384 0.000 0.128 0.056
#> GSM955036 4 0.5144 0.29321 0.000 0.004 0.012 0.488 0.044 0.452
#> GSM955037 1 0.7048 -0.06203 0.392 0.032 0.012 0.184 0.012 0.368
#> GSM955039 4 0.6917 0.34464 0.000 0.048 0.116 0.460 0.036 0.340
#> GSM955041 3 0.6335 0.21363 0.000 0.128 0.500 0.000 0.316 0.056
#> GSM955042 4 0.1858 0.57564 0.092 0.000 0.000 0.904 0.000 0.004
#> GSM955045 5 0.3924 0.63970 0.000 0.032 0.072 0.008 0.812 0.076
#> GSM955046 6 0.5408 0.65050 0.000 0.004 0.236 0.124 0.012 0.624
#> GSM955047 1 0.3663 0.76381 0.792 0.012 0.000 0.156 0.000 0.040
#> GSM955050 4 0.5372 0.57791 0.000 0.160 0.000 0.600 0.004 0.236
#> GSM955052 3 0.2288 0.52554 0.000 0.004 0.876 0.000 0.004 0.116
#> GSM955053 1 0.1930 0.78956 0.924 0.036 0.000 0.000 0.012 0.028
#> GSM955056 3 0.3839 0.50797 0.000 0.032 0.768 0.008 0.004 0.188
#> GSM955058 5 0.1555 0.73293 0.000 0.040 0.012 0.000 0.940 0.008
#> GSM955059 6 0.3819 0.42634 0.000 0.000 0.372 0.004 0.000 0.624
#> GSM955060 1 0.2588 0.79152 0.888 0.008 0.004 0.060 0.000 0.040
#> GSM955061 5 0.1699 0.73321 0.000 0.040 0.012 0.004 0.936 0.008
#> GSM955065 1 0.2224 0.78763 0.912 0.036 0.004 0.000 0.012 0.036
#> GSM955066 6 0.4316 0.67656 0.000 0.000 0.144 0.128 0.000 0.728
#> GSM955067 1 0.4450 0.66884 0.652 0.016 0.000 0.308 0.000 0.024
#> GSM955073 3 0.2700 0.47729 0.000 0.004 0.836 0.000 0.004 0.156
#> GSM955074 4 0.2196 0.56331 0.108 0.004 0.000 0.884 0.000 0.004
#> GSM955076 2 0.3667 0.55999 0.000 0.824 0.092 0.004 0.048 0.032
#> GSM955078 2 0.4390 -0.03585 0.000 0.508 0.004 0.000 0.472 0.016
#> GSM955083 4 0.3796 0.59661 0.000 0.012 0.000 0.768 0.032 0.188
#> GSM955084 5 0.4561 0.22605 0.000 0.404 0.000 0.008 0.564 0.024
#> GSM955086 3 0.4193 0.42819 0.000 0.028 0.688 0.008 0.000 0.276
#> GSM955091 2 0.5376 0.31126 0.000 0.576 0.080 0.000 0.324 0.020
#> GSM955092 3 0.7175 0.14551 0.000 0.148 0.408 0.004 0.324 0.116
#> GSM955093 3 0.2823 0.44367 0.000 0.000 0.796 0.000 0.000 0.204
#> GSM955098 2 0.3426 0.56067 0.000 0.852 0.016 0.048 0.048 0.036
#> GSM955099 2 0.5476 0.22909 0.000 0.536 0.072 0.000 0.368 0.024
#> GSM955100 4 0.5918 0.52588 0.176 0.016 0.000 0.536 0.000 0.272
#> GSM955103 3 0.6313 0.28071 0.000 0.044 0.476 0.012 0.376 0.092
#> GSM955104 6 0.5307 0.41539 0.000 0.004 0.128 0.276 0.000 0.592
#> GSM955106 5 0.1938 0.72052 0.000 0.016 0.004 0.024 0.928 0.028
#> GSM955000 1 0.4591 0.61554 0.700 0.016 0.004 0.048 0.000 0.232
#> GSM955006 1 0.3724 0.74970 0.772 0.012 0.000 0.188 0.000 0.028
#> GSM955007 3 0.4865 0.13910 0.000 0.008 0.572 0.000 0.048 0.372
#> GSM955010 4 0.4653 0.29094 0.000 0.012 0.020 0.488 0.000 0.480
#> GSM955014 1 0.4239 0.70601 0.696 0.016 0.000 0.264 0.000 0.024
#> GSM955018 3 0.3878 0.36370 0.000 0.004 0.668 0.008 0.000 0.320
#> GSM955020 1 0.4019 0.74363 0.740 0.028 0.000 0.216 0.000 0.016
#> GSM955024 3 0.5646 0.44235 0.000 0.048 0.616 0.000 0.240 0.096
#> GSM955026 2 0.3516 0.55923 0.000 0.848 0.020 0.048 0.044 0.040
#> GSM955031 2 0.7351 0.25887 0.020 0.464 0.168 0.108 0.000 0.240
#> GSM955038 4 0.4089 0.47832 0.000 0.264 0.000 0.696 0.000 0.040
#> GSM955040 4 0.5156 0.58469 0.000 0.144 0.000 0.612 0.000 0.244
#> GSM955044 2 0.6323 0.12391 0.000 0.444 0.100 0.008 0.404 0.044
#> GSM955051 1 0.4130 0.71325 0.704 0.012 0.000 0.260 0.000 0.024
#> GSM955055 2 0.5497 0.24202 0.000 0.556 0.052 0.000 0.348 0.044
#> GSM955057 1 0.0665 0.79805 0.980 0.008 0.000 0.008 0.000 0.004
#> GSM955062 2 0.6544 0.34297 0.000 0.452 0.320 0.000 0.184 0.044
#> GSM955063 3 0.3214 0.44543 0.000 0.004 0.788 0.004 0.004 0.200
#> GSM955068 2 0.3425 0.55589 0.000 0.844 0.008 0.032 0.080 0.036
#> GSM955069 6 0.4652 0.60575 0.000 0.000 0.288 0.072 0.000 0.640
#> GSM955070 2 0.8090 0.38918 0.000 0.444 0.144 0.100 0.156 0.156
#> GSM955071 4 0.5261 0.57861 0.000 0.092 0.016 0.612 0.000 0.280
#> GSM955077 2 0.6441 0.39518 0.000 0.596 0.032 0.160 0.048 0.164
#> GSM955080 5 0.1074 0.72409 0.000 0.000 0.000 0.028 0.960 0.012
#> GSM955081 3 0.6059 0.33951 0.000 0.268 0.524 0.008 0.008 0.192
#> GSM955082 3 0.6638 0.26167 0.000 0.068 0.468 0.004 0.332 0.128
#> GSM955085 5 0.5436 0.05360 0.000 0.448 0.040 0.004 0.476 0.032
#> GSM955090 1 0.4019 0.66792 0.652 0.004 0.000 0.332 0.000 0.012
#> GSM955094 2 0.8127 0.26890 0.000 0.368 0.052 0.128 0.212 0.240
#> GSM955096 3 0.4080 0.46421 0.000 0.036 0.724 0.008 0.000 0.232
#> GSM955102 6 0.5089 0.69134 0.008 0.004 0.208 0.104 0.004 0.672
#> GSM955105 3 0.4130 0.43735 0.000 0.028 0.700 0.008 0.000 0.264
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> MAD:kmeans 107 0.912 2
#> MAD:kmeans 107 0.982 3
#> MAD:kmeans 83 0.673 4
#> MAD:kmeans 63 0.520 5
#> MAD:kmeans 54 0.466 6
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 31589 rows and 108 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 0.923 0.940 0.975 0.4895 0.516 0.516
#> 3 3 0.811 0.871 0.940 0.3598 0.771 0.575
#> 4 4 0.588 0.536 0.739 0.1181 0.940 0.825
#> 5 5 0.596 0.468 0.704 0.0616 0.854 0.552
#> 6 6 0.609 0.403 0.654 0.0400 0.898 0.591
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
#> GSM955002 2 0.0000 0.964 0.000 1.000
#> GSM955008 2 0.0000 0.964 0.000 1.000
#> GSM955016 1 0.0000 0.989 1.000 0.000
#> GSM955019 2 0.0000 0.964 0.000 1.000
#> GSM955022 2 0.0000 0.964 0.000 1.000
#> GSM955023 2 0.0000 0.964 0.000 1.000
#> GSM955027 2 0.0000 0.964 0.000 1.000
#> GSM955043 2 0.0000 0.964 0.000 1.000
#> GSM955048 1 0.0000 0.989 1.000 0.000
#> GSM955049 2 0.0000 0.964 0.000 1.000
#> GSM955054 2 0.0000 0.964 0.000 1.000
#> GSM955064 2 0.0000 0.964 0.000 1.000
#> GSM955072 2 0.0000 0.964 0.000 1.000
#> GSM955075 2 0.0000 0.964 0.000 1.000
#> GSM955079 2 0.5737 0.832 0.136 0.864
#> GSM955087 1 0.0000 0.989 1.000 0.000
#> GSM955088 2 0.9323 0.497 0.348 0.652
#> GSM955089 1 0.0000 0.989 1.000 0.000
#> GSM955095 2 0.0000 0.964 0.000 1.000
#> GSM955097 2 0.9608 0.413 0.384 0.616
#> GSM955101 2 0.0000 0.964 0.000 1.000
#> GSM954999 1 0.0000 0.989 1.000 0.000
#> GSM955001 2 0.0000 0.964 0.000 1.000
#> GSM955003 2 0.0000 0.964 0.000 1.000
#> GSM955004 2 0.0000 0.964 0.000 1.000
#> GSM955005 1 0.0000 0.989 1.000 0.000
#> GSM955009 2 0.0000 0.964 0.000 1.000
#> GSM955011 1 0.0000 0.989 1.000 0.000
#> GSM955012 2 0.0000 0.964 0.000 1.000
#> GSM955013 2 0.9896 0.261 0.440 0.560
#> GSM955015 2 0.0000 0.964 0.000 1.000
#> GSM955017 1 0.0000 0.989 1.000 0.000
#> GSM955021 2 0.0000 0.964 0.000 1.000
#> GSM955025 2 0.0376 0.960 0.004 0.996
#> GSM955028 1 0.0000 0.989 1.000 0.000
#> GSM955029 2 0.0000 0.964 0.000 1.000
#> GSM955030 1 0.0000 0.989 1.000 0.000
#> GSM955032 2 0.0000 0.964 0.000 1.000
#> GSM955033 1 0.0000 0.989 1.000 0.000
#> GSM955034 1 0.0000 0.989 1.000 0.000
#> GSM955035 2 0.0000 0.964 0.000 1.000
#> GSM955036 1 0.0000 0.989 1.000 0.000
#> GSM955037 1 0.0000 0.989 1.000 0.000
#> GSM955039 2 0.4690 0.870 0.100 0.900
#> GSM955041 2 0.0000 0.964 0.000 1.000
#> GSM955042 1 0.0000 0.989 1.000 0.000
#> GSM955045 2 0.0000 0.964 0.000 1.000
#> GSM955046 2 0.9248 0.514 0.340 0.660
#> GSM955047 1 0.0000 0.989 1.000 0.000
#> GSM955050 1 0.0000 0.989 1.000 0.000
#> GSM955052 2 0.0000 0.964 0.000 1.000
#> GSM955053 1 0.0000 0.989 1.000 0.000
#> GSM955056 2 0.0000 0.964 0.000 1.000
#> GSM955058 2 0.0000 0.964 0.000 1.000
#> GSM955059 2 0.9393 0.480 0.356 0.644
#> GSM955060 1 0.0000 0.989 1.000 0.000
#> GSM955061 2 0.0000 0.964 0.000 1.000
#> GSM955065 1 0.0000 0.989 1.000 0.000
#> GSM955066 1 0.0000 0.989 1.000 0.000
#> GSM955067 1 0.0000 0.989 1.000 0.000
#> GSM955073 2 0.0000 0.964 0.000 1.000
#> GSM955074 1 0.0000 0.989 1.000 0.000
#> GSM955076 2 0.0000 0.964 0.000 1.000
#> GSM955078 2 0.0000 0.964 0.000 1.000
#> GSM955083 1 0.0000 0.989 1.000 0.000
#> GSM955084 2 0.0000 0.964 0.000 1.000
#> GSM955086 1 0.8861 0.531 0.696 0.304
#> GSM955091 2 0.0000 0.964 0.000 1.000
#> GSM955092 2 0.0000 0.964 0.000 1.000
#> GSM955093 2 0.1414 0.948 0.020 0.980
#> GSM955098 2 0.0000 0.964 0.000 1.000
#> GSM955099 2 0.0000 0.964 0.000 1.000
#> GSM955100 1 0.0000 0.989 1.000 0.000
#> GSM955103 2 0.0000 0.964 0.000 1.000
#> GSM955104 1 0.0000 0.989 1.000 0.000
#> GSM955106 2 0.0000 0.964 0.000 1.000
#> GSM955000 1 0.0000 0.989 1.000 0.000
#> GSM955006 1 0.0000 0.989 1.000 0.000
#> GSM955007 2 0.0000 0.964 0.000 1.000
#> GSM955010 1 0.0000 0.989 1.000 0.000
#> GSM955014 1 0.0000 0.989 1.000 0.000
#> GSM955018 2 0.5946 0.824 0.144 0.856
#> GSM955020 1 0.0000 0.989 1.000 0.000
#> GSM955024 2 0.0000 0.964 0.000 1.000
#> GSM955026 2 0.0000 0.964 0.000 1.000
#> GSM955031 1 0.0000 0.989 1.000 0.000
#> GSM955038 1 0.5294 0.854 0.880 0.120
#> GSM955040 1 0.0000 0.989 1.000 0.000
#> GSM955044 2 0.0000 0.964 0.000 1.000
#> GSM955051 1 0.0000 0.989 1.000 0.000
#> GSM955055 2 0.0000 0.964 0.000 1.000
#> GSM955057 1 0.0000 0.989 1.000 0.000
#> GSM955062 2 0.0000 0.964 0.000 1.000
#> GSM955063 2 0.0000 0.964 0.000 1.000
#> GSM955068 2 0.0000 0.964 0.000 1.000
#> GSM955069 1 0.0376 0.985 0.996 0.004
#> GSM955070 2 0.0000 0.964 0.000 1.000
#> GSM955071 1 0.0000 0.989 1.000 0.000
#> GSM955077 1 0.0376 0.985 0.996 0.004
#> GSM955080 2 0.0000 0.964 0.000 1.000
#> GSM955081 2 0.0000 0.964 0.000 1.000
#> GSM955082 2 0.0000 0.964 0.000 1.000
#> GSM955085 2 0.0000 0.964 0.000 1.000
#> GSM955090 1 0.0000 0.989 1.000 0.000
#> GSM955094 2 0.0000 0.964 0.000 1.000
#> GSM955096 2 0.0000 0.964 0.000 1.000
#> GSM955102 1 0.0000 0.989 1.000 0.000
#> GSM955105 1 0.1184 0.973 0.984 0.016
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.5178 0.658 0.000 0.744 0.256
#> GSM955008 3 0.2448 0.878 0.000 0.076 0.924
#> GSM955016 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955019 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955022 3 0.0237 0.910 0.000 0.004 0.996
#> GSM955023 3 0.2625 0.875 0.000 0.084 0.916
#> GSM955027 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955043 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955048 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955049 2 0.1289 0.929 0.000 0.968 0.032
#> GSM955054 3 0.4654 0.750 0.000 0.208 0.792
#> GSM955064 2 0.2537 0.898 0.000 0.920 0.080
#> GSM955072 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955075 2 0.0424 0.939 0.000 0.992 0.008
#> GSM955079 3 0.0000 0.911 0.000 0.000 1.000
#> GSM955087 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955088 3 0.0237 0.910 0.004 0.000 0.996
#> GSM955089 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955095 2 0.1289 0.929 0.000 0.968 0.032
#> GSM955097 2 0.3193 0.851 0.100 0.896 0.004
#> GSM955101 3 0.3267 0.850 0.000 0.116 0.884
#> GSM954999 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955001 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955003 3 0.5138 0.687 0.000 0.252 0.748
#> GSM955004 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955005 3 0.4887 0.686 0.228 0.000 0.772
#> GSM955009 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955011 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955012 2 0.0424 0.939 0.000 0.992 0.008
#> GSM955013 3 0.4097 0.863 0.060 0.060 0.880
#> GSM955015 3 0.5733 0.561 0.000 0.324 0.676
#> GSM955017 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955021 2 0.2448 0.898 0.000 0.924 0.076
#> GSM955025 2 0.0237 0.940 0.004 0.996 0.000
#> GSM955028 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955029 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955030 1 0.6225 0.231 0.568 0.000 0.432
#> GSM955032 3 0.0237 0.911 0.000 0.004 0.996
#> GSM955033 1 0.0747 0.934 0.984 0.016 0.000
#> GSM955034 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955035 2 0.2711 0.888 0.000 0.912 0.088
#> GSM955036 1 0.5058 0.667 0.756 0.000 0.244
#> GSM955037 1 0.1411 0.920 0.964 0.000 0.036
#> GSM955039 3 0.4682 0.770 0.004 0.192 0.804
#> GSM955041 2 0.4974 0.710 0.000 0.764 0.236
#> GSM955042 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955045 2 0.1964 0.917 0.000 0.944 0.056
#> GSM955046 3 0.0000 0.911 0.000 0.000 1.000
#> GSM955047 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955050 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955052 3 0.0000 0.911 0.000 0.000 1.000
#> GSM955053 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955056 3 0.1163 0.903 0.000 0.028 0.972
#> GSM955058 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955059 3 0.0000 0.911 0.000 0.000 1.000
#> GSM955060 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955061 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955065 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955066 3 0.5178 0.647 0.256 0.000 0.744
#> GSM955067 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955073 3 0.0000 0.911 0.000 0.000 1.000
#> GSM955074 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955076 2 0.3412 0.850 0.000 0.876 0.124
#> GSM955078 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955083 1 0.0424 0.940 0.992 0.008 0.000
#> GSM955084 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955086 3 0.0424 0.909 0.008 0.000 0.992
#> GSM955091 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955092 2 0.1964 0.915 0.000 0.944 0.056
#> GSM955093 3 0.0000 0.911 0.000 0.000 1.000
#> GSM955098 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955099 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955100 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955103 2 0.5560 0.603 0.000 0.700 0.300
#> GSM955104 1 0.6299 0.129 0.524 0.000 0.476
#> GSM955106 2 0.1031 0.933 0.000 0.976 0.024
#> GSM955000 1 0.0892 0.932 0.980 0.000 0.020
#> GSM955006 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955007 3 0.0592 0.909 0.000 0.012 0.988
#> GSM955010 1 0.0747 0.935 0.984 0.000 0.016
#> GSM955014 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955018 3 0.0000 0.911 0.000 0.000 1.000
#> GSM955020 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955024 3 0.5016 0.698 0.000 0.240 0.760
#> GSM955026 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955031 1 0.1950 0.910 0.952 0.008 0.040
#> GSM955038 1 0.4235 0.758 0.824 0.176 0.000
#> GSM955040 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955044 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955051 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955055 2 0.0237 0.940 0.000 0.996 0.004
#> GSM955057 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955062 2 0.1529 0.925 0.000 0.960 0.040
#> GSM955063 3 0.0000 0.911 0.000 0.000 1.000
#> GSM955068 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955069 3 0.0237 0.910 0.004 0.000 0.996
#> GSM955070 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955071 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955077 1 0.5968 0.427 0.636 0.364 0.000
#> GSM955080 2 0.0424 0.939 0.000 0.992 0.008
#> GSM955081 2 0.6140 0.325 0.000 0.596 0.404
#> GSM955082 2 0.5650 0.584 0.000 0.688 0.312
#> GSM955085 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955090 1 0.0000 0.945 1.000 0.000 0.000
#> GSM955094 2 0.0000 0.941 0.000 1.000 0.000
#> GSM955096 3 0.0237 0.911 0.000 0.004 0.996
#> GSM955102 3 0.4235 0.763 0.176 0.000 0.824
#> GSM955105 3 0.0592 0.907 0.012 0.000 0.988
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 4 0.6764 -0.10387 0.000 0.404 0.096 0.500
#> GSM955008 3 0.4411 0.54677 0.000 0.108 0.812 0.080
#> GSM955016 1 0.0707 0.88578 0.980 0.000 0.000 0.020
#> GSM955019 2 0.3612 0.58141 0.000 0.856 0.044 0.100
#> GSM955022 4 0.5250 0.18481 0.000 0.024 0.316 0.660
#> GSM955023 3 0.6745 0.33660 0.000 0.152 0.604 0.244
#> GSM955027 2 0.2197 0.61691 0.000 0.928 0.024 0.048
#> GSM955043 2 0.4382 0.50052 0.000 0.704 0.000 0.296
#> GSM955048 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955049 2 0.5507 0.53520 0.000 0.732 0.156 0.112
#> GSM955054 3 0.7357 0.20946 0.000 0.296 0.512 0.192
#> GSM955064 2 0.6617 0.43094 0.000 0.608 0.128 0.264
#> GSM955072 2 0.4716 0.57458 0.000 0.764 0.040 0.196
#> GSM955075 2 0.5004 0.39676 0.000 0.604 0.004 0.392
#> GSM955079 3 0.1733 0.63315 0.000 0.024 0.948 0.028
#> GSM955087 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955088 3 0.3768 0.59331 0.000 0.008 0.808 0.184
#> GSM955089 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955095 2 0.5137 0.30086 0.000 0.544 0.004 0.452
#> GSM955097 2 0.5273 0.28488 0.008 0.536 0.000 0.456
#> GSM955101 3 0.6142 0.42104 0.000 0.184 0.676 0.140
#> GSM954999 1 0.2345 0.83194 0.900 0.000 0.000 0.100
#> GSM955001 2 0.2670 0.61778 0.000 0.904 0.024 0.072
#> GSM955003 3 0.7386 0.17267 0.000 0.320 0.496 0.184
#> GSM955004 2 0.3219 0.58196 0.000 0.836 0.000 0.164
#> GSM955005 3 0.7252 0.29676 0.180 0.000 0.528 0.292
#> GSM955009 2 0.2882 0.59321 0.000 0.892 0.024 0.084
#> GSM955011 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955012 2 0.4819 0.44251 0.000 0.652 0.004 0.344
#> GSM955013 4 0.4821 0.42717 0.008 0.048 0.160 0.784
#> GSM955015 3 0.7669 0.08765 0.000 0.312 0.452 0.236
#> GSM955017 1 0.0188 0.89260 0.996 0.000 0.000 0.004
#> GSM955021 2 0.6731 0.34098 0.000 0.604 0.248 0.148
#> GSM955025 2 0.4153 0.53683 0.004 0.784 0.008 0.204
#> GSM955028 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955029 2 0.4483 0.50241 0.000 0.712 0.004 0.284
#> GSM955030 1 0.7863 -0.11762 0.396 0.000 0.304 0.300
#> GSM955032 3 0.1820 0.63814 0.000 0.020 0.944 0.036
#> GSM955033 4 0.5444 0.38139 0.264 0.048 0.000 0.688
#> GSM955034 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955035 2 0.6508 0.40544 0.000 0.640 0.192 0.168
#> GSM955036 4 0.6037 0.35871 0.140 0.004 0.156 0.700
#> GSM955037 1 0.3894 0.77003 0.844 0.000 0.068 0.088
#> GSM955039 4 0.5918 0.32757 0.004 0.092 0.208 0.696
#> GSM955041 2 0.7412 0.26215 0.000 0.504 0.200 0.296
#> GSM955042 1 0.0188 0.89266 0.996 0.000 0.000 0.004
#> GSM955045 2 0.6215 0.40046 0.000 0.600 0.072 0.328
#> GSM955046 3 0.4989 0.25217 0.000 0.000 0.528 0.472
#> GSM955047 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955050 1 0.3047 0.81236 0.872 0.012 0.000 0.116
#> GSM955052 3 0.1975 0.64041 0.000 0.016 0.936 0.048
#> GSM955053 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955056 3 0.3533 0.59254 0.000 0.056 0.864 0.080
#> GSM955058 2 0.4608 0.48643 0.000 0.692 0.004 0.304
#> GSM955059 3 0.3801 0.55721 0.000 0.000 0.780 0.220
#> GSM955060 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955061 2 0.4608 0.48605 0.000 0.692 0.004 0.304
#> GSM955065 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955066 3 0.7251 0.30650 0.192 0.000 0.536 0.272
#> GSM955067 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955073 3 0.2216 0.63372 0.000 0.000 0.908 0.092
#> GSM955074 1 0.0336 0.89072 0.992 0.000 0.000 0.008
#> GSM955076 2 0.7122 0.29452 0.000 0.560 0.248 0.192
#> GSM955078 2 0.1743 0.61657 0.000 0.940 0.004 0.056
#> GSM955083 1 0.4914 0.52116 0.676 0.012 0.000 0.312
#> GSM955084 2 0.3219 0.59566 0.000 0.836 0.000 0.164
#> GSM955086 3 0.2131 0.63741 0.016 0.008 0.936 0.040
#> GSM955091 2 0.2623 0.61765 0.000 0.908 0.028 0.064
#> GSM955092 2 0.6083 0.47028 0.000 0.672 0.216 0.112
#> GSM955093 3 0.2530 0.62716 0.000 0.000 0.888 0.112
#> GSM955098 2 0.5968 0.44661 0.000 0.672 0.092 0.236
#> GSM955099 2 0.2730 0.61898 0.000 0.896 0.016 0.088
#> GSM955100 1 0.0188 0.89257 0.996 0.000 0.000 0.004
#> GSM955103 4 0.7368 -0.06943 0.000 0.376 0.164 0.460
#> GSM955104 3 0.7890 0.05009 0.308 0.000 0.380 0.312
#> GSM955106 2 0.5112 0.33082 0.000 0.560 0.004 0.436
#> GSM955000 1 0.1284 0.87343 0.964 0.000 0.024 0.012
#> GSM955006 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955007 3 0.5078 0.47149 0.000 0.028 0.700 0.272
#> GSM955010 1 0.5359 0.54884 0.676 0.000 0.036 0.288
#> GSM955014 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955018 3 0.2125 0.63323 0.000 0.004 0.920 0.076
#> GSM955020 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955024 3 0.7581 -0.17739 0.000 0.196 0.424 0.380
#> GSM955026 2 0.5851 0.45347 0.000 0.680 0.084 0.236
#> GSM955031 1 0.8024 0.40800 0.600 0.136 0.128 0.136
#> GSM955038 1 0.6259 0.47240 0.652 0.232 0.000 0.116
#> GSM955040 1 0.2125 0.85067 0.920 0.004 0.000 0.076
#> GSM955044 2 0.4826 0.55339 0.000 0.716 0.020 0.264
#> GSM955051 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955055 2 0.2214 0.61169 0.000 0.928 0.028 0.044
#> GSM955057 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955062 2 0.4864 0.52839 0.000 0.768 0.172 0.060
#> GSM955063 3 0.2216 0.63291 0.000 0.000 0.908 0.092
#> GSM955068 2 0.4956 0.52022 0.000 0.756 0.056 0.188
#> GSM955069 3 0.4401 0.50406 0.004 0.000 0.724 0.272
#> GSM955070 2 0.5355 0.44583 0.000 0.620 0.020 0.360
#> GSM955071 1 0.2814 0.81019 0.868 0.000 0.000 0.132
#> GSM955077 1 0.7834 0.12916 0.496 0.340 0.028 0.136
#> GSM955080 2 0.5088 0.34854 0.000 0.572 0.004 0.424
#> GSM955081 2 0.7663 0.00532 0.000 0.408 0.380 0.212
#> GSM955082 2 0.7302 0.17359 0.000 0.500 0.332 0.168
#> GSM955085 2 0.1637 0.61583 0.000 0.940 0.000 0.060
#> GSM955090 1 0.0000 0.89406 1.000 0.000 0.000 0.000
#> GSM955094 4 0.5372 -0.22313 0.000 0.444 0.012 0.544
#> GSM955096 3 0.2197 0.63361 0.000 0.024 0.928 0.048
#> GSM955102 3 0.6641 0.38482 0.124 0.000 0.600 0.276
#> GSM955105 3 0.2686 0.63377 0.032 0.012 0.916 0.040
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.6228 0.37549 0.000 0.624 0.068 0.240 0.068
#> GSM955008 3 0.4211 0.61488 0.000 0.156 0.788 0.028 0.028
#> GSM955016 1 0.2970 0.76392 0.828 0.004 0.000 0.168 0.000
#> GSM955019 2 0.5687 0.27860 0.000 0.580 0.052 0.020 0.348
#> GSM955022 4 0.6761 0.31276 0.000 0.012 0.220 0.496 0.272
#> GSM955023 3 0.7617 0.32152 0.000 0.224 0.500 0.120 0.156
#> GSM955027 5 0.5767 0.29874 0.000 0.292 0.080 0.016 0.612
#> GSM955043 5 0.3134 0.53918 0.000 0.120 0.000 0.032 0.848
#> GSM955048 1 0.0162 0.85402 0.996 0.000 0.000 0.004 0.000
#> GSM955049 5 0.7034 0.00211 0.000 0.328 0.228 0.016 0.428
#> GSM955054 2 0.6036 -0.10593 0.000 0.464 0.456 0.044 0.036
#> GSM955064 5 0.7527 0.18802 0.000 0.248 0.172 0.088 0.492
#> GSM955072 2 0.4536 0.27240 0.000 0.640 0.008 0.008 0.344
#> GSM955075 5 0.1741 0.56020 0.000 0.024 0.000 0.040 0.936
#> GSM955079 3 0.4059 0.65659 0.008 0.116 0.816 0.048 0.012
#> GSM955087 1 0.0404 0.85224 0.988 0.000 0.000 0.012 0.000
#> GSM955088 3 0.5605 0.44228 0.000 0.076 0.660 0.240 0.024
#> GSM955089 1 0.0000 0.85397 1.000 0.000 0.000 0.000 0.000
#> GSM955095 5 0.2520 0.54400 0.000 0.012 0.004 0.096 0.888
#> GSM955097 5 0.2623 0.53976 0.004 0.016 0.000 0.096 0.884
#> GSM955101 3 0.5949 0.47137 0.000 0.236 0.644 0.076 0.044
#> GSM954999 1 0.4944 0.53228 0.652 0.020 0.004 0.312 0.012
#> GSM955001 5 0.5087 0.29969 0.000 0.344 0.028 0.012 0.616
#> GSM955003 3 0.5564 0.14216 0.000 0.444 0.504 0.024 0.028
#> GSM955004 5 0.4380 0.38055 0.000 0.304 0.000 0.020 0.676
#> GSM955005 4 0.6694 0.41933 0.168 0.020 0.292 0.520 0.000
#> GSM955009 2 0.5256 0.22075 0.000 0.592 0.024 0.020 0.364
#> GSM955011 1 0.0162 0.85369 0.996 0.000 0.000 0.004 0.000
#> GSM955012 5 0.1153 0.56659 0.000 0.024 0.004 0.008 0.964
#> GSM955013 4 0.7230 0.35340 0.008 0.060 0.120 0.516 0.296
#> GSM955015 2 0.7548 0.08014 0.000 0.428 0.332 0.172 0.068
#> GSM955017 1 0.1043 0.84250 0.960 0.000 0.000 0.040 0.000
#> GSM955021 2 0.6037 0.43215 0.000 0.612 0.232 0.012 0.144
#> GSM955025 2 0.5539 0.40816 0.004 0.692 0.020 0.092 0.192
#> GSM955028 1 0.0510 0.85100 0.984 0.000 0.000 0.016 0.000
#> GSM955029 5 0.1410 0.56199 0.000 0.060 0.000 0.000 0.940
#> GSM955030 4 0.6408 0.45277 0.344 0.004 0.160 0.492 0.000
#> GSM955032 3 0.4203 0.64432 0.000 0.128 0.780 0.092 0.000
#> GSM955033 4 0.6569 0.39344 0.076 0.192 0.004 0.628 0.100
#> GSM955034 1 0.0162 0.85369 0.996 0.000 0.000 0.004 0.000
#> GSM955035 2 0.6676 0.39248 0.000 0.568 0.188 0.032 0.212
#> GSM955036 4 0.4579 0.51090 0.040 0.012 0.028 0.788 0.132
#> GSM955037 1 0.3621 0.64934 0.788 0.000 0.020 0.192 0.000
#> GSM955039 4 0.6472 0.38772 0.000 0.156 0.144 0.632 0.068
#> GSM955041 5 0.7404 0.18655 0.000 0.192 0.244 0.068 0.496
#> GSM955042 1 0.2068 0.82059 0.904 0.004 0.000 0.092 0.000
#> GSM955045 5 0.3542 0.55062 0.000 0.048 0.052 0.044 0.856
#> GSM955046 4 0.4881 0.39104 0.004 0.004 0.268 0.684 0.040
#> GSM955047 1 0.0404 0.85396 0.988 0.000 0.000 0.012 0.000
#> GSM955050 1 0.5308 0.60742 0.688 0.168 0.000 0.140 0.004
#> GSM955052 3 0.2026 0.65879 0.000 0.056 0.924 0.012 0.008
#> GSM955053 1 0.0000 0.85397 1.000 0.000 0.000 0.000 0.000
#> GSM955056 3 0.4706 0.64255 0.000 0.148 0.764 0.060 0.028
#> GSM955058 5 0.1443 0.56559 0.000 0.044 0.004 0.004 0.948
#> GSM955059 3 0.4516 0.15757 0.000 0.004 0.576 0.416 0.004
#> GSM955060 1 0.0290 0.85321 0.992 0.000 0.000 0.008 0.000
#> GSM955061 5 0.1569 0.56604 0.000 0.044 0.004 0.008 0.944
#> GSM955065 1 0.0609 0.84969 0.980 0.000 0.000 0.020 0.000
#> GSM955066 4 0.6198 0.39758 0.128 0.008 0.320 0.544 0.000
#> GSM955067 1 0.1701 0.83926 0.936 0.016 0.000 0.048 0.000
#> GSM955073 3 0.2540 0.63527 0.000 0.024 0.888 0.088 0.000
#> GSM955074 1 0.1638 0.83669 0.932 0.004 0.000 0.064 0.000
#> GSM955076 2 0.4176 0.50622 0.000 0.792 0.108 0.004 0.096
#> GSM955078 5 0.4480 0.22121 0.000 0.400 0.004 0.004 0.592
#> GSM955083 1 0.6903 0.09210 0.460 0.056 0.000 0.388 0.096
#> GSM955084 5 0.4781 0.16613 0.000 0.428 0.000 0.020 0.552
#> GSM955086 3 0.4689 0.61873 0.024 0.096 0.772 0.108 0.000
#> GSM955091 2 0.4974 -0.05682 0.000 0.488 0.020 0.004 0.488
#> GSM955092 5 0.7265 0.08748 0.000 0.236 0.316 0.028 0.420
#> GSM955093 3 0.3163 0.58716 0.000 0.012 0.824 0.164 0.000
#> GSM955098 2 0.2267 0.51278 0.000 0.916 0.008 0.028 0.048
#> GSM955099 5 0.5120 0.11405 0.000 0.428 0.008 0.024 0.540
#> GSM955100 1 0.1041 0.84661 0.964 0.004 0.000 0.032 0.000
#> GSM955103 5 0.6494 0.32928 0.000 0.052 0.228 0.116 0.604
#> GSM955104 4 0.7205 0.44878 0.240 0.004 0.228 0.496 0.032
#> GSM955106 5 0.2720 0.53892 0.000 0.020 0.004 0.096 0.880
#> GSM955000 1 0.2470 0.78173 0.884 0.000 0.012 0.104 0.000
#> GSM955006 1 0.0162 0.85436 0.996 0.000 0.000 0.004 0.000
#> GSM955007 3 0.6993 0.23986 0.000 0.040 0.512 0.284 0.164
#> GSM955010 4 0.5338 0.05629 0.456 0.024 0.016 0.504 0.000
#> GSM955014 1 0.1251 0.84561 0.956 0.008 0.000 0.036 0.000
#> GSM955018 3 0.2612 0.61163 0.000 0.008 0.868 0.124 0.000
#> GSM955020 1 0.0671 0.85227 0.980 0.004 0.000 0.016 0.000
#> GSM955024 5 0.7103 0.21518 0.000 0.064 0.288 0.132 0.516
#> GSM955026 2 0.2227 0.50693 0.000 0.916 0.004 0.032 0.048
#> GSM955031 1 0.7412 0.04432 0.420 0.372 0.136 0.072 0.000
#> GSM955038 1 0.6500 0.21130 0.460 0.384 0.000 0.148 0.008
#> GSM955040 1 0.5510 0.56201 0.652 0.164 0.000 0.184 0.000
#> GSM955044 5 0.5937 0.10780 0.000 0.408 0.020 0.060 0.512
#> GSM955051 1 0.0671 0.85227 0.980 0.004 0.000 0.016 0.000
#> GSM955055 5 0.5639 0.03378 0.000 0.448 0.048 0.012 0.492
#> GSM955057 1 0.0290 0.85423 0.992 0.000 0.000 0.008 0.000
#> GSM955062 2 0.7003 0.14279 0.000 0.444 0.144 0.036 0.376
#> GSM955063 3 0.3523 0.61369 0.000 0.032 0.824 0.140 0.004
#> GSM955068 2 0.3812 0.46448 0.000 0.780 0.004 0.020 0.196
#> GSM955069 3 0.5471 -0.05504 0.028 0.004 0.492 0.464 0.012
#> GSM955070 2 0.6340 0.31788 0.000 0.596 0.032 0.120 0.252
#> GSM955071 1 0.4985 0.60275 0.708 0.088 0.004 0.200 0.000
#> GSM955077 2 0.8227 0.16235 0.284 0.468 0.056 0.092 0.100
#> GSM955080 5 0.2331 0.54888 0.000 0.020 0.000 0.080 0.900
#> GSM955081 3 0.7371 -0.02541 0.000 0.376 0.420 0.068 0.136
#> GSM955082 5 0.6550 0.26098 0.000 0.084 0.332 0.048 0.536
#> GSM955085 5 0.4874 0.25958 0.000 0.388 0.008 0.016 0.588
#> GSM955090 1 0.1251 0.84607 0.956 0.008 0.000 0.036 0.000
#> GSM955094 5 0.6942 0.09420 0.000 0.296 0.012 0.244 0.448
#> GSM955096 3 0.3465 0.64283 0.000 0.104 0.840 0.052 0.004
#> GSM955102 4 0.5882 0.29734 0.092 0.004 0.376 0.528 0.000
#> GSM955105 3 0.4254 0.62340 0.024 0.076 0.812 0.084 0.004
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 6 0.6660 -0.04102 0.000 0.396 0.036 0.084 0.044 0.440
#> GSM955008 4 0.4719 0.48771 0.000 0.124 0.080 0.748 0.008 0.040
#> GSM955016 1 0.4086 0.64926 0.708 0.000 0.028 0.000 0.008 0.256
#> GSM955019 2 0.4893 0.43802 0.000 0.704 0.000 0.072 0.184 0.040
#> GSM955022 3 0.7080 0.22552 0.000 0.004 0.472 0.168 0.240 0.116
#> GSM955023 4 0.8002 0.32098 0.000 0.208 0.228 0.404 0.084 0.076
#> GSM955027 5 0.6538 0.10071 0.000 0.332 0.004 0.140 0.472 0.052
#> GSM955043 5 0.5164 0.52710 0.000 0.176 0.024 0.028 0.704 0.068
#> GSM955048 1 0.0458 0.83852 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM955049 2 0.7491 0.15386 0.000 0.348 0.020 0.276 0.288 0.068
#> GSM955054 2 0.5809 -0.12227 0.000 0.456 0.052 0.440 0.004 0.048
#> GSM955064 4 0.7926 -0.12200 0.000 0.212 0.024 0.320 0.304 0.140
#> GSM955072 2 0.4926 0.41401 0.000 0.680 0.004 0.040 0.236 0.040
#> GSM955075 5 0.0837 0.62330 0.000 0.004 0.000 0.004 0.972 0.020
#> GSM955079 4 0.5035 0.44944 0.004 0.072 0.152 0.720 0.004 0.048
#> GSM955087 1 0.0935 0.83370 0.964 0.000 0.032 0.000 0.000 0.004
#> GSM955088 3 0.6764 0.09131 0.004 0.044 0.476 0.336 0.020 0.120
#> GSM955089 1 0.0891 0.83937 0.968 0.000 0.008 0.000 0.000 0.024
#> GSM955095 5 0.3478 0.59493 0.000 0.024 0.032 0.020 0.844 0.080
#> GSM955097 5 0.2683 0.59287 0.000 0.004 0.020 0.004 0.868 0.104
#> GSM955101 4 0.5213 0.44293 0.000 0.172 0.048 0.700 0.012 0.068
#> GSM954999 1 0.6247 0.26651 0.512 0.008 0.128 0.000 0.032 0.320
#> GSM955001 5 0.6025 0.06643 0.000 0.368 0.004 0.116 0.488 0.024
#> GSM955003 4 0.5075 0.20048 0.000 0.392 0.012 0.548 0.004 0.044
#> GSM955004 5 0.4686 0.40039 0.000 0.280 0.008 0.012 0.664 0.036
#> GSM955005 3 0.5295 0.52465 0.116 0.012 0.712 0.084 0.000 0.076
#> GSM955009 2 0.5389 0.36662 0.000 0.652 0.012 0.032 0.236 0.068
#> GSM955011 1 0.1088 0.83943 0.960 0.000 0.016 0.000 0.000 0.024
#> GSM955012 5 0.1922 0.63011 0.000 0.040 0.000 0.024 0.924 0.012
#> GSM955013 6 0.8134 0.05068 0.012 0.032 0.272 0.092 0.292 0.300
#> GSM955015 4 0.7804 0.19209 0.000 0.272 0.124 0.420 0.052 0.132
#> GSM955017 1 0.1657 0.82200 0.928 0.000 0.056 0.000 0.000 0.016
#> GSM955021 2 0.5955 0.27594 0.000 0.568 0.020 0.308 0.064 0.040
#> GSM955025 2 0.5919 0.35998 0.004 0.596 0.016 0.020 0.104 0.260
#> GSM955028 1 0.0713 0.83415 0.972 0.000 0.028 0.000 0.000 0.000
#> GSM955029 5 0.2365 0.61919 0.000 0.084 0.004 0.012 0.892 0.008
#> GSM955030 3 0.5742 0.25292 0.292 0.000 0.572 0.036 0.000 0.100
#> GSM955032 4 0.5324 0.40996 0.000 0.100 0.244 0.632 0.000 0.024
#> GSM955033 6 0.5752 0.29616 0.032 0.060 0.180 0.004 0.052 0.672
#> GSM955034 1 0.0632 0.83516 0.976 0.000 0.024 0.000 0.000 0.000
#> GSM955035 2 0.6251 0.34811 0.000 0.544 0.000 0.272 0.112 0.072
#> GSM955036 3 0.5390 0.03854 0.000 0.000 0.508 0.016 0.072 0.404
#> GSM955037 1 0.4078 0.48320 0.656 0.000 0.320 0.000 0.000 0.024
#> GSM955039 6 0.7342 0.05427 0.000 0.052 0.276 0.204 0.036 0.432
#> GSM955041 5 0.7692 0.00534 0.000 0.180 0.048 0.336 0.364 0.072
#> GSM955042 1 0.3154 0.75086 0.800 0.004 0.012 0.000 0.000 0.184
#> GSM955045 5 0.5134 0.53472 0.000 0.064 0.028 0.104 0.736 0.068
#> GSM955046 3 0.4517 0.48029 0.000 0.000 0.732 0.096 0.016 0.156
#> GSM955047 1 0.1082 0.83684 0.956 0.000 0.004 0.000 0.000 0.040
#> GSM955050 1 0.5272 0.47435 0.596 0.084 0.016 0.000 0.000 0.304
#> GSM955052 4 0.4759 0.45338 0.000 0.040 0.192 0.716 0.004 0.048
#> GSM955053 1 0.0547 0.83601 0.980 0.000 0.020 0.000 0.000 0.000
#> GSM955056 4 0.6359 0.45831 0.000 0.176 0.140 0.604 0.028 0.052
#> GSM955058 5 0.2365 0.62382 0.000 0.068 0.000 0.024 0.896 0.012
#> GSM955059 3 0.3163 0.45493 0.000 0.004 0.780 0.212 0.000 0.004
#> GSM955060 1 0.0725 0.83870 0.976 0.000 0.012 0.000 0.000 0.012
#> GSM955061 5 0.1872 0.62656 0.000 0.064 0.004 0.008 0.920 0.004
#> GSM955065 1 0.0713 0.83415 0.972 0.000 0.028 0.000 0.000 0.000
#> GSM955066 3 0.4012 0.54801 0.072 0.000 0.800 0.056 0.000 0.072
#> GSM955067 1 0.1806 0.82247 0.908 0.004 0.000 0.000 0.000 0.088
#> GSM955073 4 0.3977 0.38539 0.000 0.008 0.240 0.728 0.004 0.020
#> GSM955074 1 0.2890 0.79441 0.852 0.004 0.016 0.000 0.008 0.120
#> GSM955076 2 0.3565 0.48063 0.000 0.812 0.004 0.136 0.032 0.016
#> GSM955078 2 0.4874 -0.07967 0.000 0.484 0.000 0.020 0.472 0.024
#> GSM955083 6 0.6776 0.13573 0.348 0.004 0.096 0.004 0.092 0.456
#> GSM955084 5 0.4717 0.07406 0.000 0.456 0.004 0.000 0.504 0.036
#> GSM955086 4 0.6745 0.34960 0.032 0.092 0.220 0.576 0.008 0.072
#> GSM955091 2 0.5499 0.16145 0.000 0.536 0.004 0.068 0.372 0.020
#> GSM955092 4 0.7778 -0.12270 0.000 0.184 0.040 0.344 0.340 0.092
#> GSM955093 4 0.4617 0.29691 0.000 0.012 0.304 0.644 0.000 0.040
#> GSM955098 2 0.3544 0.46255 0.000 0.828 0.008 0.024 0.032 0.108
#> GSM955099 2 0.5790 -0.02528 0.000 0.484 0.004 0.044 0.412 0.056
#> GSM955100 1 0.2433 0.80739 0.884 0.000 0.044 0.000 0.000 0.072
#> GSM955103 5 0.6849 0.30242 0.000 0.040 0.068 0.220 0.552 0.120
#> GSM955104 3 0.7160 0.28942 0.200 0.008 0.532 0.128 0.020 0.112
#> GSM955106 5 0.2578 0.60590 0.000 0.012 0.008 0.012 0.884 0.084
#> GSM955000 1 0.3089 0.70306 0.800 0.000 0.188 0.004 0.000 0.008
#> GSM955006 1 0.0972 0.83960 0.964 0.000 0.008 0.000 0.000 0.028
#> GSM955007 3 0.7115 0.06005 0.000 0.028 0.440 0.328 0.144 0.060
#> GSM955010 6 0.6762 0.02099 0.324 0.008 0.308 0.020 0.000 0.340
#> GSM955014 1 0.1700 0.82460 0.916 0.004 0.000 0.000 0.000 0.080
#> GSM955018 4 0.5105 0.19303 0.000 0.008 0.388 0.540 0.000 0.064
#> GSM955020 1 0.1411 0.83035 0.936 0.004 0.000 0.000 0.000 0.060
#> GSM955024 4 0.8063 0.17708 0.000 0.076 0.140 0.344 0.332 0.108
#> GSM955026 2 0.3921 0.43976 0.000 0.792 0.008 0.028 0.028 0.144
#> GSM955031 2 0.7945 -0.05368 0.312 0.364 0.048 0.136 0.000 0.140
#> GSM955038 1 0.6586 -0.07367 0.384 0.284 0.012 0.000 0.008 0.312
#> GSM955040 1 0.5433 0.33466 0.540 0.056 0.024 0.000 0.004 0.376
#> GSM955044 5 0.7468 -0.06186 0.000 0.348 0.020 0.096 0.368 0.168
#> GSM955051 1 0.0790 0.83810 0.968 0.000 0.000 0.000 0.000 0.032
#> GSM955055 2 0.6535 0.23062 0.000 0.484 0.008 0.144 0.320 0.044
#> GSM955057 1 0.0363 0.83823 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM955062 2 0.7283 0.24729 0.000 0.428 0.020 0.204 0.280 0.068
#> GSM955063 4 0.4526 0.33116 0.000 0.020 0.312 0.648 0.004 0.016
#> GSM955068 2 0.4258 0.48608 0.000 0.780 0.008 0.028 0.120 0.064
#> GSM955069 3 0.4857 0.50263 0.028 0.004 0.720 0.184 0.008 0.056
#> GSM955070 2 0.7497 0.12570 0.000 0.372 0.020 0.096 0.176 0.336
#> GSM955071 1 0.5643 0.49492 0.608 0.036 0.072 0.004 0.004 0.276
#> GSM955077 2 0.8350 0.10533 0.168 0.404 0.052 0.036 0.084 0.256
#> GSM955080 5 0.2854 0.61205 0.000 0.024 0.020 0.004 0.872 0.080
#> GSM955081 4 0.8114 0.13844 0.000 0.288 0.088 0.368 0.088 0.168
#> GSM955082 4 0.7875 0.02573 0.000 0.092 0.080 0.364 0.344 0.120
#> GSM955085 5 0.5835 0.14446 0.000 0.396 0.012 0.032 0.500 0.060
#> GSM955090 1 0.1897 0.82051 0.908 0.004 0.004 0.000 0.000 0.084
#> GSM955094 6 0.7674 0.09736 0.000 0.216 0.108 0.020 0.284 0.372
#> GSM955096 4 0.6015 0.38734 0.000 0.108 0.220 0.596 0.000 0.076
#> GSM955102 3 0.3788 0.56985 0.056 0.000 0.812 0.092 0.000 0.040
#> GSM955105 4 0.5883 0.34280 0.012 0.052 0.256 0.612 0.004 0.064
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> MAD:skmeans 104 0.116 2
#> MAD:skmeans 104 0.621 3
#> MAD:skmeans 64 0.844 4
#> MAD:skmeans 55 0.699 5
#> MAD:skmeans 38 0.346 6
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 31589 rows and 108 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 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 0.642 0.893 0.927 0.4476 0.551 0.551
#> 3 3 0.514 0.774 0.857 0.3721 0.714 0.534
#> 4 4 0.678 0.772 0.883 0.1680 0.861 0.663
#> 5 5 0.631 0.609 0.789 0.0515 0.907 0.710
#> 6 6 0.711 0.735 0.861 0.0521 0.929 0.734
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
#> GSM955002 2 0.6048 0.873 0.148 0.852
#> GSM955008 2 0.4161 0.911 0.084 0.916
#> GSM955016 1 0.3584 0.946 0.932 0.068
#> GSM955019 2 0.0000 0.912 0.000 1.000
#> GSM955022 2 0.8144 0.766 0.252 0.748
#> GSM955023 2 0.5059 0.898 0.112 0.888
#> GSM955027 2 0.0000 0.912 0.000 1.000
#> GSM955043 2 0.1633 0.917 0.024 0.976
#> GSM955048 1 0.0000 0.943 1.000 0.000
#> GSM955049 2 0.3879 0.914 0.076 0.924
#> GSM955054 2 0.2603 0.917 0.044 0.956
#> GSM955064 2 0.0000 0.912 0.000 1.000
#> GSM955072 2 0.0000 0.912 0.000 1.000
#> GSM955075 2 0.0000 0.912 0.000 1.000
#> GSM955079 2 0.4298 0.911 0.088 0.912
#> GSM955087 1 0.0000 0.943 1.000 0.000
#> GSM955088 2 0.4161 0.912 0.084 0.916
#> GSM955089 1 0.0000 0.943 1.000 0.000
#> GSM955095 2 0.5946 0.825 0.144 0.856
#> GSM955097 1 0.7528 0.813 0.784 0.216
#> GSM955101 2 0.0000 0.912 0.000 1.000
#> GSM954999 1 0.3733 0.943 0.928 0.072
#> GSM955001 2 0.0000 0.912 0.000 1.000
#> GSM955003 2 0.0000 0.912 0.000 1.000
#> GSM955004 2 0.5629 0.838 0.132 0.868
#> GSM955005 2 0.8386 0.744 0.268 0.732
#> GSM955009 2 0.0000 0.912 0.000 1.000
#> GSM955011 1 0.3584 0.946 0.932 0.068
#> GSM955012 2 0.2043 0.917 0.032 0.968
#> GSM955013 2 0.8016 0.776 0.244 0.756
#> GSM955015 2 0.1184 0.916 0.016 0.984
#> GSM955017 1 0.3584 0.946 0.932 0.068
#> GSM955021 2 0.0000 0.912 0.000 1.000
#> GSM955025 2 0.9000 0.615 0.316 0.684
#> GSM955028 1 0.0000 0.943 1.000 0.000
#> GSM955029 2 0.0000 0.912 0.000 1.000
#> GSM955030 1 0.3584 0.946 0.932 0.068
#> GSM955032 2 0.4431 0.908 0.092 0.908
#> GSM955033 1 0.4690 0.923 0.900 0.100
#> GSM955034 1 0.0000 0.943 1.000 0.000
#> GSM955035 2 0.0000 0.912 0.000 1.000
#> GSM955036 1 0.3584 0.946 0.932 0.068
#> GSM955037 1 0.3584 0.946 0.932 0.068
#> GSM955039 2 0.5294 0.893 0.120 0.880
#> GSM955041 2 0.3733 0.914 0.072 0.928
#> GSM955042 1 0.3584 0.946 0.932 0.068
#> GSM955045 2 0.0000 0.912 0.000 1.000
#> GSM955046 2 0.7745 0.797 0.228 0.772
#> GSM955047 1 0.0000 0.943 1.000 0.000
#> GSM955050 1 0.4298 0.936 0.912 0.088
#> GSM955052 2 0.4298 0.910 0.088 0.912
#> GSM955053 1 0.0000 0.943 1.000 0.000
#> GSM955056 2 0.4161 0.911 0.084 0.916
#> GSM955058 2 0.0000 0.912 0.000 1.000
#> GSM955059 2 0.6887 0.843 0.184 0.816
#> GSM955060 1 0.0000 0.943 1.000 0.000
#> GSM955061 2 0.0000 0.912 0.000 1.000
#> GSM955065 1 0.0000 0.943 1.000 0.000
#> GSM955066 1 0.3584 0.946 0.932 0.068
#> GSM955067 1 0.0000 0.943 1.000 0.000
#> GSM955073 2 0.4161 0.911 0.084 0.916
#> GSM955074 1 0.3584 0.946 0.932 0.068
#> GSM955076 2 0.3274 0.916 0.060 0.940
#> GSM955078 2 0.0000 0.912 0.000 1.000
#> GSM955083 1 0.5629 0.891 0.868 0.132
#> GSM955084 2 0.0672 0.912 0.008 0.992
#> GSM955086 2 0.5629 0.885 0.132 0.868
#> GSM955091 2 0.1414 0.916 0.020 0.980
#> GSM955092 2 0.0000 0.912 0.000 1.000
#> GSM955093 2 0.4562 0.907 0.096 0.904
#> GSM955098 2 0.4431 0.909 0.092 0.908
#> GSM955099 2 0.0000 0.912 0.000 1.000
#> GSM955100 1 0.3584 0.946 0.932 0.068
#> GSM955103 2 0.0672 0.914 0.008 0.992
#> GSM955104 2 0.9323 0.604 0.348 0.652
#> GSM955106 2 0.4939 0.902 0.108 0.892
#> GSM955000 1 0.3584 0.946 0.932 0.068
#> GSM955006 1 0.0000 0.943 1.000 0.000
#> GSM955007 2 0.3584 0.915 0.068 0.932
#> GSM955010 2 1.0000 0.140 0.496 0.504
#> GSM955014 1 0.0000 0.943 1.000 0.000
#> GSM955018 2 0.5842 0.878 0.140 0.860
#> GSM955020 1 0.0000 0.943 1.000 0.000
#> GSM955024 2 0.1843 0.917 0.028 0.972
#> GSM955026 2 0.3879 0.913 0.076 0.924
#> GSM955031 2 0.4161 0.912 0.084 0.916
#> GSM955038 2 0.7883 0.787 0.236 0.764
#> GSM955040 1 0.5737 0.883 0.864 0.136
#> GSM955044 2 0.1184 0.916 0.016 0.984
#> GSM955051 1 0.0000 0.943 1.000 0.000
#> GSM955055 2 0.0000 0.912 0.000 1.000
#> GSM955057 1 0.0000 0.943 1.000 0.000
#> GSM955062 2 0.0000 0.912 0.000 1.000
#> GSM955063 2 0.4298 0.910 0.088 0.912
#> GSM955068 2 0.2778 0.917 0.048 0.952
#> GSM955069 2 0.9286 0.612 0.344 0.656
#> GSM955070 2 0.0000 0.912 0.000 1.000
#> GSM955071 1 0.4022 0.938 0.920 0.080
#> GSM955077 1 0.6343 0.852 0.840 0.160
#> GSM955080 2 0.1633 0.910 0.024 0.976
#> GSM955081 2 0.4161 0.911 0.084 0.916
#> GSM955082 2 0.2236 0.918 0.036 0.964
#> GSM955085 2 0.0000 0.912 0.000 1.000
#> GSM955090 1 0.0000 0.943 1.000 0.000
#> GSM955094 2 0.5294 0.895 0.120 0.880
#> GSM955096 2 0.4161 0.911 0.084 0.916
#> GSM955102 1 0.3733 0.943 0.928 0.072
#> GSM955105 2 0.7602 0.806 0.220 0.780
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.5926 0.628 0.000 0.644 0.356
#> GSM955008 2 0.5785 0.655 0.000 0.668 0.332
#> GSM955016 3 0.4178 0.816 0.172 0.000 0.828
#> GSM955019 2 0.0892 0.813 0.000 0.980 0.020
#> GSM955022 3 0.2152 0.831 0.016 0.036 0.948
#> GSM955023 2 0.6235 0.539 0.000 0.564 0.436
#> GSM955027 2 0.1289 0.804 0.000 0.968 0.032
#> GSM955043 3 0.6140 0.218 0.000 0.404 0.596
#> GSM955048 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955049 2 0.5291 0.718 0.000 0.732 0.268
#> GSM955054 2 0.3192 0.800 0.000 0.888 0.112
#> GSM955064 2 0.0424 0.813 0.000 0.992 0.008
#> GSM955072 2 0.1289 0.806 0.000 0.968 0.032
#> GSM955075 2 0.3116 0.771 0.000 0.892 0.108
#> GSM955079 3 0.3340 0.794 0.000 0.120 0.880
#> GSM955087 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955088 2 0.6062 0.552 0.000 0.616 0.384
#> GSM955089 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955095 2 0.3412 0.764 0.000 0.876 0.124
#> GSM955097 3 0.5785 0.457 0.000 0.332 0.668
#> GSM955101 2 0.0892 0.813 0.000 0.980 0.020
#> GSM954999 3 0.3340 0.836 0.120 0.000 0.880
#> GSM955001 2 0.0747 0.809 0.000 0.984 0.016
#> GSM955003 2 0.0892 0.813 0.000 0.980 0.020
#> GSM955004 2 0.3116 0.771 0.000 0.892 0.108
#> GSM955005 3 0.2681 0.837 0.028 0.040 0.932
#> GSM955009 2 0.0747 0.809 0.000 0.984 0.016
#> GSM955011 3 0.4121 0.819 0.168 0.000 0.832
#> GSM955012 3 0.3879 0.714 0.000 0.152 0.848
#> GSM955013 3 0.2384 0.824 0.008 0.056 0.936
#> GSM955015 2 0.1860 0.816 0.000 0.948 0.052
#> GSM955017 3 0.4002 0.824 0.160 0.000 0.840
#> GSM955021 2 0.0592 0.813 0.000 0.988 0.012
#> GSM955025 3 0.3921 0.826 0.036 0.080 0.884
#> GSM955028 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955029 2 0.3267 0.768 0.000 0.884 0.116
#> GSM955030 3 0.2878 0.840 0.096 0.000 0.904
#> GSM955032 3 0.6299 -0.140 0.000 0.476 0.524
#> GSM955033 3 0.4062 0.821 0.164 0.000 0.836
#> GSM955034 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955035 2 0.0747 0.813 0.000 0.984 0.016
#> GSM955036 3 0.2261 0.839 0.068 0.000 0.932
#> GSM955037 3 0.4002 0.824 0.160 0.000 0.840
#> GSM955039 3 0.5905 0.303 0.000 0.352 0.648
#> GSM955041 2 0.5254 0.743 0.000 0.736 0.264
#> GSM955042 3 0.4178 0.816 0.172 0.000 0.828
#> GSM955045 2 0.4931 0.636 0.000 0.768 0.232
#> GSM955046 3 0.1170 0.828 0.008 0.016 0.976
#> GSM955047 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955050 3 0.6529 0.775 0.152 0.092 0.756
#> GSM955052 2 0.5785 0.655 0.000 0.668 0.332
#> GSM955053 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955056 2 0.5785 0.655 0.000 0.668 0.332
#> GSM955058 2 0.2165 0.792 0.000 0.936 0.064
#> GSM955059 3 0.1753 0.820 0.000 0.048 0.952
#> GSM955060 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955061 3 0.5785 0.457 0.000 0.332 0.668
#> GSM955065 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955066 3 0.3116 0.839 0.108 0.000 0.892
#> GSM955067 1 0.0237 0.994 0.996 0.000 0.004
#> GSM955073 2 0.5785 0.655 0.000 0.668 0.332
#> GSM955074 3 0.3879 0.828 0.152 0.000 0.848
#> GSM955076 2 0.3267 0.799 0.000 0.884 0.116
#> GSM955078 2 0.0892 0.808 0.000 0.980 0.020
#> GSM955083 3 0.4485 0.833 0.136 0.020 0.844
#> GSM955084 2 0.2165 0.792 0.000 0.936 0.064
#> GSM955086 2 0.5219 0.748 0.016 0.788 0.196
#> GSM955091 2 0.3038 0.803 0.000 0.896 0.104
#> GSM955092 2 0.0592 0.812 0.000 0.988 0.012
#> GSM955093 2 0.5785 0.655 0.000 0.668 0.332
#> GSM955098 2 0.5760 0.659 0.000 0.672 0.328
#> GSM955099 2 0.0592 0.812 0.000 0.988 0.012
#> GSM955100 3 0.4178 0.816 0.172 0.000 0.828
#> GSM955103 2 0.1289 0.816 0.000 0.968 0.032
#> GSM955104 3 0.2689 0.838 0.036 0.032 0.932
#> GSM955106 2 0.6154 0.522 0.000 0.592 0.408
#> GSM955000 3 0.3752 0.831 0.144 0.000 0.856
#> GSM955006 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955007 3 0.4346 0.719 0.000 0.184 0.816
#> GSM955010 3 0.8242 0.298 0.092 0.336 0.572
#> GSM955014 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955018 3 0.3116 0.793 0.000 0.108 0.892
#> GSM955020 1 0.0424 0.990 0.992 0.000 0.008
#> GSM955024 2 0.3619 0.792 0.000 0.864 0.136
#> GSM955026 2 0.4702 0.754 0.000 0.788 0.212
#> GSM955031 2 0.5365 0.725 0.004 0.744 0.252
#> GSM955038 3 0.4121 0.811 0.024 0.108 0.868
#> GSM955040 3 0.4172 0.825 0.156 0.004 0.840
#> GSM955044 2 0.2356 0.815 0.000 0.928 0.072
#> GSM955051 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955055 2 0.0747 0.809 0.000 0.984 0.016
#> GSM955057 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955062 2 0.0592 0.812 0.000 0.988 0.012
#> GSM955063 2 0.5785 0.655 0.000 0.668 0.332
#> GSM955068 2 0.5678 0.661 0.000 0.684 0.316
#> GSM955069 3 0.3039 0.839 0.036 0.044 0.920
#> GSM955070 2 0.0747 0.813 0.000 0.984 0.016
#> GSM955071 3 0.4586 0.839 0.096 0.048 0.856
#> GSM955077 3 0.4059 0.836 0.128 0.012 0.860
#> GSM955080 2 0.3116 0.771 0.000 0.892 0.108
#> GSM955081 2 0.5905 0.630 0.000 0.648 0.352
#> GSM955082 2 0.4796 0.764 0.000 0.780 0.220
#> GSM955085 2 0.0592 0.812 0.000 0.988 0.012
#> GSM955090 1 0.0000 0.999 1.000 0.000 0.000
#> GSM955094 2 0.6045 0.633 0.000 0.620 0.380
#> GSM955096 2 0.6126 0.546 0.000 0.600 0.400
#> GSM955102 3 0.2625 0.840 0.084 0.000 0.916
#> GSM955105 2 0.6773 0.633 0.024 0.636 0.340
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.3311 0.7216 0.000 0.828 0.172 0.000
#> GSM955008 2 0.0188 0.7974 0.000 0.996 0.004 0.000
#> GSM955016 3 0.2921 0.8792 0.140 0.000 0.860 0.000
#> GSM955019 2 0.0188 0.7978 0.000 0.996 0.000 0.004
#> GSM955022 3 0.0336 0.9080 0.000 0.000 0.992 0.008
#> GSM955023 2 0.2859 0.7579 0.000 0.880 0.112 0.008
#> GSM955027 4 0.4713 0.3308 0.000 0.360 0.000 0.640
#> GSM955043 4 0.4054 0.6927 0.000 0.016 0.188 0.796
#> GSM955048 1 0.0188 0.9941 0.996 0.000 0.000 0.004
#> GSM955049 2 0.0188 0.7974 0.000 0.996 0.004 0.000
#> GSM955054 2 0.0000 0.7969 0.000 1.000 0.000 0.000
#> GSM955064 2 0.2149 0.7800 0.000 0.912 0.000 0.088
#> GSM955072 2 0.4948 0.3707 0.000 0.560 0.000 0.440
#> GSM955075 4 0.0376 0.8099 0.000 0.004 0.004 0.992
#> GSM955079 3 0.1610 0.9040 0.000 0.016 0.952 0.032
#> GSM955087 1 0.0188 0.9941 0.996 0.000 0.000 0.004
#> GSM955088 2 0.4194 0.6309 0.000 0.764 0.228 0.008
#> GSM955089 1 0.0188 0.9953 0.996 0.000 0.004 0.000
#> GSM955095 4 0.3808 0.6570 0.000 0.176 0.012 0.812
#> GSM955097 4 0.0376 0.8099 0.000 0.004 0.004 0.992
#> GSM955101 2 0.1557 0.7911 0.000 0.944 0.000 0.056
#> GSM954999 3 0.0817 0.9141 0.024 0.000 0.976 0.000
#> GSM955001 2 0.4948 0.3692 0.000 0.560 0.000 0.440
#> GSM955003 2 0.0000 0.7969 0.000 1.000 0.000 0.000
#> GSM955004 4 0.0188 0.8108 0.000 0.004 0.000 0.996
#> GSM955005 3 0.0000 0.9098 0.000 0.000 1.000 0.000
#> GSM955009 2 0.4948 0.3692 0.000 0.560 0.000 0.440
#> GSM955011 3 0.2760 0.8869 0.128 0.000 0.872 0.000
#> GSM955012 4 0.4382 0.5492 0.000 0.000 0.296 0.704
#> GSM955013 3 0.0804 0.9056 0.000 0.012 0.980 0.008
#> GSM955015 2 0.3400 0.7274 0.000 0.820 0.000 0.180
#> GSM955017 3 0.1940 0.9088 0.076 0.000 0.924 0.000
#> GSM955021 2 0.2647 0.7671 0.000 0.880 0.000 0.120
#> GSM955025 3 0.1520 0.9050 0.000 0.024 0.956 0.020
#> GSM955028 1 0.0188 0.9941 0.996 0.000 0.000 0.004
#> GSM955029 4 0.0188 0.8108 0.000 0.004 0.000 0.996
#> GSM955030 3 0.0707 0.9149 0.020 0.000 0.980 0.000
#> GSM955032 2 0.4522 0.4846 0.000 0.680 0.320 0.000
#> GSM955033 3 0.3380 0.8785 0.136 0.008 0.852 0.004
#> GSM955034 1 0.0188 0.9941 0.996 0.000 0.000 0.004
#> GSM955035 2 0.0817 0.7979 0.000 0.976 0.000 0.024
#> GSM955036 3 0.1151 0.9129 0.024 0.000 0.968 0.008
#> GSM955037 3 0.2593 0.8993 0.104 0.000 0.892 0.004
#> GSM955039 3 0.4941 0.1636 0.000 0.436 0.564 0.000
#> GSM955041 2 0.4804 0.2164 0.000 0.616 0.000 0.384
#> GSM955042 3 0.2973 0.8762 0.144 0.000 0.856 0.000
#> GSM955045 4 0.7301 -0.0205 0.000 0.396 0.152 0.452
#> GSM955046 3 0.0188 0.9087 0.000 0.000 0.996 0.004
#> GSM955047 1 0.0188 0.9953 0.996 0.000 0.004 0.000
#> GSM955050 3 0.4428 0.8125 0.068 0.000 0.808 0.124
#> GSM955052 2 0.0188 0.7974 0.000 0.996 0.004 0.000
#> GSM955053 1 0.0188 0.9941 0.996 0.000 0.000 0.004
#> GSM955056 2 0.0188 0.7974 0.000 0.996 0.004 0.000
#> GSM955058 4 0.0469 0.8086 0.000 0.012 0.000 0.988
#> GSM955059 3 0.0336 0.9080 0.000 0.000 0.992 0.008
#> GSM955060 1 0.0188 0.9953 0.996 0.000 0.004 0.000
#> GSM955061 4 0.0188 0.8108 0.000 0.004 0.000 0.996
#> GSM955065 1 0.0188 0.9941 0.996 0.000 0.000 0.004
#> GSM955066 3 0.0817 0.9142 0.024 0.000 0.976 0.000
#> GSM955067 1 0.0336 0.9925 0.992 0.000 0.008 0.000
#> GSM955073 2 0.0469 0.7984 0.000 0.988 0.012 0.000
#> GSM955074 3 0.2266 0.9059 0.084 0.000 0.912 0.004
#> GSM955076 2 0.0000 0.7969 0.000 1.000 0.000 0.000
#> GSM955078 2 0.4855 0.4202 0.000 0.600 0.000 0.400
#> GSM955083 3 0.2867 0.8961 0.104 0.000 0.884 0.012
#> GSM955084 4 0.0336 0.8101 0.000 0.008 0.000 0.992
#> GSM955086 2 0.5993 0.6552 0.008 0.712 0.144 0.136
#> GSM955091 2 0.1209 0.7956 0.000 0.964 0.004 0.032
#> GSM955092 2 0.4406 0.5881 0.000 0.700 0.000 0.300
#> GSM955093 2 0.0188 0.7974 0.000 0.996 0.004 0.000
#> GSM955098 2 0.0188 0.7974 0.000 0.996 0.004 0.000
#> GSM955099 2 0.3486 0.7170 0.000 0.812 0.000 0.188
#> GSM955100 3 0.2973 0.8762 0.144 0.000 0.856 0.000
#> GSM955103 2 0.3569 0.7164 0.000 0.804 0.000 0.196
#> GSM955104 3 0.0000 0.9098 0.000 0.000 1.000 0.000
#> GSM955106 4 0.5384 0.6592 0.000 0.076 0.196 0.728
#> GSM955000 3 0.1474 0.9138 0.052 0.000 0.948 0.000
#> GSM955006 1 0.0188 0.9953 0.996 0.000 0.004 0.000
#> GSM955007 3 0.3751 0.7157 0.000 0.004 0.800 0.196
#> GSM955010 2 0.7044 0.0209 0.092 0.460 0.440 0.008
#> GSM955014 1 0.0188 0.9953 0.996 0.000 0.004 0.000
#> GSM955018 3 0.2589 0.8446 0.000 0.116 0.884 0.000
#> GSM955020 1 0.0469 0.9840 0.988 0.000 0.012 0.000
#> GSM955024 2 0.5464 0.6516 0.000 0.708 0.064 0.228
#> GSM955026 2 0.2197 0.7893 0.000 0.928 0.048 0.024
#> GSM955031 2 0.0707 0.7982 0.000 0.980 0.020 0.000
#> GSM955038 3 0.1520 0.9049 0.000 0.024 0.956 0.020
#> GSM955040 3 0.2814 0.8828 0.132 0.000 0.868 0.000
#> GSM955044 4 0.4855 0.2743 0.000 0.400 0.000 0.600
#> GSM955051 1 0.0188 0.9953 0.996 0.000 0.004 0.000
#> GSM955055 2 0.4948 0.3692 0.000 0.560 0.000 0.440
#> GSM955057 1 0.0188 0.9953 0.996 0.000 0.004 0.000
#> GSM955062 2 0.4477 0.5877 0.000 0.688 0.000 0.312
#> GSM955063 2 0.0188 0.7974 0.000 0.996 0.004 0.000
#> GSM955068 2 0.5619 0.5194 0.000 0.640 0.320 0.040
#> GSM955069 3 0.0336 0.9120 0.008 0.000 0.992 0.000
#> GSM955070 2 0.0921 0.7974 0.000 0.972 0.000 0.028
#> GSM955071 3 0.3400 0.8814 0.064 0.064 0.872 0.000
#> GSM955077 3 0.1474 0.9135 0.052 0.000 0.948 0.000
#> GSM955080 4 0.0188 0.8108 0.000 0.004 0.000 0.996
#> GSM955081 2 0.1118 0.7926 0.000 0.964 0.036 0.000
#> GSM955082 2 0.1902 0.7901 0.000 0.932 0.064 0.004
#> GSM955085 2 0.4477 0.5690 0.000 0.688 0.000 0.312
#> GSM955090 1 0.0188 0.9953 0.996 0.000 0.004 0.000
#> GSM955094 2 0.4468 0.6654 0.000 0.752 0.232 0.016
#> GSM955096 2 0.3873 0.6483 0.000 0.772 0.228 0.000
#> GSM955102 3 0.0188 0.9095 0.004 0.000 0.996 0.000
#> GSM955105 2 0.1042 0.7981 0.008 0.972 0.020 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.2732 0.7412 0.000 0.000 0.840 0.160 0.000
#> GSM955008 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955016 1 0.4350 0.2200 0.588 0.004 0.000 0.408 0.000
#> GSM955019 3 0.0162 0.8098 0.000 0.000 0.996 0.000 0.004
#> GSM955022 4 0.0794 0.7952 0.000 0.028 0.000 0.972 0.000
#> GSM955023 3 0.3238 0.7419 0.000 0.028 0.836 0.136 0.000
#> GSM955027 5 0.4642 0.4337 0.000 0.032 0.308 0.000 0.660
#> GSM955043 5 0.6767 0.4650 0.000 0.336 0.020 0.160 0.484
#> GSM955048 2 0.4138 0.9542 0.384 0.616 0.000 0.000 0.000
#> GSM955049 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955054 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955064 3 0.2020 0.7789 0.000 0.000 0.900 0.000 0.100
#> GSM955072 5 0.4192 0.1439 0.000 0.000 0.404 0.000 0.596
#> GSM955075 5 0.4108 0.5756 0.000 0.308 0.000 0.008 0.684
#> GSM955079 4 0.1997 0.7983 0.000 0.000 0.036 0.924 0.040
#> GSM955087 2 0.4350 0.9109 0.408 0.588 0.000 0.004 0.000
#> GSM955088 3 0.3612 0.6350 0.000 0.000 0.764 0.228 0.008
#> GSM955089 1 0.1282 0.5086 0.952 0.044 0.000 0.004 0.000
#> GSM955095 5 0.2866 0.6025 0.000 0.020 0.076 0.020 0.884
#> GSM955097 5 0.0290 0.6038 0.000 0.000 0.000 0.008 0.992
#> GSM955101 3 0.1410 0.7986 0.000 0.000 0.940 0.000 0.060
#> GSM954999 4 0.1365 0.8088 0.040 0.004 0.004 0.952 0.000
#> GSM955001 5 0.4138 0.1965 0.000 0.000 0.384 0.000 0.616
#> GSM955003 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955004 5 0.0000 0.6039 0.000 0.000 0.000 0.000 1.000
#> GSM955005 4 0.1041 0.8085 0.032 0.004 0.000 0.964 0.000
#> GSM955009 5 0.4138 0.1965 0.000 0.000 0.384 0.000 0.616
#> GSM955011 4 0.3928 0.5930 0.296 0.004 0.000 0.700 0.000
#> GSM955012 5 0.6638 0.3895 0.000 0.364 0.000 0.224 0.412
#> GSM955013 4 0.1082 0.7949 0.000 0.028 0.008 0.964 0.000
#> GSM955015 3 0.3003 0.7111 0.000 0.000 0.812 0.000 0.188
#> GSM955017 4 0.3366 0.7120 0.212 0.004 0.000 0.784 0.000
#> GSM955021 3 0.2732 0.7435 0.000 0.000 0.840 0.000 0.160
#> GSM955025 4 0.1907 0.7979 0.000 0.000 0.044 0.928 0.028
#> GSM955028 2 0.4074 0.9635 0.364 0.636 0.000 0.000 0.000
#> GSM955029 5 0.3966 0.5684 0.000 0.336 0.000 0.000 0.664
#> GSM955030 4 0.1697 0.8081 0.060 0.008 0.000 0.932 0.000
#> GSM955032 3 0.3876 0.4930 0.000 0.000 0.684 0.316 0.000
#> GSM955033 1 0.4807 0.1663 0.532 0.020 0.000 0.448 0.000
#> GSM955034 2 0.4088 0.9629 0.368 0.632 0.000 0.000 0.000
#> GSM955035 3 0.0703 0.8093 0.000 0.000 0.976 0.000 0.024
#> GSM955036 4 0.2795 0.7530 0.100 0.028 0.000 0.872 0.000
#> GSM955037 4 0.5261 0.3420 0.048 0.424 0.000 0.528 0.000
#> GSM955039 4 0.4268 0.1826 0.000 0.000 0.444 0.556 0.000
#> GSM955041 3 0.6554 -0.1022 0.000 0.272 0.476 0.000 0.252
#> GSM955042 1 0.4138 0.2794 0.616 0.000 0.000 0.384 0.000
#> GSM955045 5 0.6062 0.3850 0.000 0.008 0.248 0.148 0.596
#> GSM955046 4 0.0162 0.8015 0.000 0.004 0.000 0.996 0.000
#> GSM955047 1 0.1701 0.5225 0.936 0.048 0.000 0.016 0.000
#> GSM955050 4 0.3645 0.7410 0.168 0.004 0.000 0.804 0.024
#> GSM955052 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955053 2 0.4126 0.9623 0.380 0.620 0.000 0.000 0.000
#> GSM955056 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955058 5 0.3966 0.5684 0.000 0.336 0.000 0.000 0.664
#> GSM955059 4 0.0794 0.7952 0.000 0.028 0.000 0.972 0.000
#> GSM955060 1 0.1197 0.5261 0.952 0.048 0.000 0.000 0.000
#> GSM955061 5 0.3966 0.5684 0.000 0.336 0.000 0.000 0.664
#> GSM955065 2 0.4171 0.9445 0.396 0.604 0.000 0.000 0.000
#> GSM955066 4 0.0963 0.8088 0.036 0.000 0.000 0.964 0.000
#> GSM955067 1 0.2616 0.4842 0.888 0.076 0.000 0.036 0.000
#> GSM955073 3 0.0404 0.8103 0.000 0.000 0.988 0.012 0.000
#> GSM955074 4 0.3318 0.7402 0.180 0.012 0.000 0.808 0.000
#> GSM955076 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955078 3 0.6383 0.1773 0.000 0.228 0.516 0.000 0.256
#> GSM955083 4 0.4121 0.5748 0.264 0.004 0.000 0.720 0.012
#> GSM955084 5 0.0000 0.6039 0.000 0.000 0.000 0.000 1.000
#> GSM955086 3 0.5584 0.6254 0.028 0.000 0.696 0.144 0.132
#> GSM955091 3 0.2103 0.7922 0.000 0.056 0.920 0.004 0.020
#> GSM955092 3 0.4294 0.1614 0.000 0.000 0.532 0.000 0.468
#> GSM955093 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955098 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955099 3 0.3074 0.6981 0.000 0.000 0.804 0.000 0.196
#> GSM955100 1 0.4276 0.2800 0.616 0.004 0.000 0.380 0.000
#> GSM955103 3 0.3109 0.7000 0.000 0.000 0.800 0.000 0.200
#> GSM955104 4 0.1041 0.8085 0.032 0.004 0.000 0.964 0.000
#> GSM955106 5 0.6732 0.4789 0.000 0.364 0.028 0.128 0.480
#> GSM955000 4 0.2077 0.8000 0.084 0.008 0.000 0.908 0.000
#> GSM955006 1 0.0162 0.5426 0.996 0.000 0.000 0.004 0.000
#> GSM955007 4 0.3745 0.6403 0.000 0.024 0.000 0.780 0.196
#> GSM955010 4 0.7113 0.1334 0.184 0.028 0.376 0.412 0.000
#> GSM955014 1 0.1671 0.5077 0.924 0.076 0.000 0.000 0.000
#> GSM955018 4 0.2439 0.7563 0.004 0.000 0.120 0.876 0.000
#> GSM955020 1 0.3913 -0.2715 0.676 0.324 0.000 0.000 0.000
#> GSM955024 3 0.5615 0.5996 0.000 0.028 0.680 0.092 0.200
#> GSM955026 3 0.1893 0.7998 0.000 0.000 0.928 0.048 0.024
#> GSM955031 3 0.0609 0.8093 0.000 0.000 0.980 0.020 0.000
#> GSM955038 4 0.2246 0.8079 0.028 0.004 0.028 0.924 0.016
#> GSM955040 1 0.4743 0.1095 0.512 0.000 0.016 0.472 0.000
#> GSM955044 5 0.6610 0.4632 0.000 0.280 0.260 0.000 0.460
#> GSM955051 1 0.1041 0.5345 0.964 0.032 0.000 0.004 0.000
#> GSM955055 5 0.4138 0.1965 0.000 0.000 0.384 0.000 0.616
#> GSM955057 1 0.1197 0.5308 0.952 0.048 0.000 0.000 0.000
#> GSM955062 3 0.4171 0.3735 0.000 0.000 0.604 0.000 0.396
#> GSM955063 3 0.0000 0.8099 0.000 0.000 1.000 0.000 0.000
#> GSM955068 3 0.5480 0.4910 0.000 0.000 0.616 0.288 0.096
#> GSM955069 4 0.2915 0.7795 0.116 0.024 0.000 0.860 0.000
#> GSM955070 3 0.0794 0.8083 0.000 0.000 0.972 0.000 0.028
#> GSM955071 4 0.5380 0.0289 0.464 0.004 0.044 0.488 0.000
#> GSM955077 4 0.2511 0.7941 0.080 0.000 0.028 0.892 0.000
#> GSM955080 5 0.0451 0.6033 0.000 0.004 0.000 0.008 0.988
#> GSM955081 3 0.0880 0.8049 0.000 0.000 0.968 0.032 0.000
#> GSM955082 3 0.2054 0.7956 0.000 0.008 0.916 0.072 0.004
#> GSM955085 3 0.4300 0.1366 0.000 0.000 0.524 0.000 0.476
#> GSM955090 1 0.1410 0.5239 0.940 0.060 0.000 0.000 0.000
#> GSM955094 3 0.4415 0.6483 0.000 0.028 0.728 0.236 0.008
#> GSM955096 3 0.3305 0.6515 0.000 0.000 0.776 0.224 0.000
#> GSM955102 4 0.1331 0.8045 0.008 0.040 0.000 0.952 0.000
#> GSM955105 3 0.2589 0.7731 0.092 0.008 0.888 0.012 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.2697 0.758 0.000 0.812 0.188 0.000 0.000 0.000
#> GSM955008 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955016 1 0.1957 0.799 0.888 0.000 0.112 0.000 0.000 0.000
#> GSM955019 2 0.0146 0.841 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM955022 3 0.2219 0.801 0.000 0.000 0.864 0.000 0.136 0.000
#> GSM955023 2 0.3707 0.743 0.000 0.784 0.080 0.000 0.136 0.000
#> GSM955027 6 0.5939 0.096 0.000 0.276 0.000 0.000 0.264 0.460
#> GSM955043 5 0.2726 0.728 0.000 0.000 0.112 0.000 0.856 0.032
#> GSM955048 4 0.0865 0.900 0.036 0.000 0.000 0.964 0.000 0.000
#> GSM955049 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955054 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955064 2 0.1814 0.810 0.000 0.900 0.000 0.000 0.000 0.100
#> GSM955072 6 0.3126 0.565 0.000 0.248 0.000 0.000 0.000 0.752
#> GSM955075 5 0.3244 0.644 0.000 0.000 0.000 0.000 0.732 0.268
#> GSM955079 3 0.1092 0.832 0.000 0.020 0.960 0.000 0.000 0.020
#> GSM955087 4 0.1501 0.875 0.076 0.000 0.000 0.924 0.000 0.000
#> GSM955088 2 0.3245 0.680 0.000 0.764 0.228 0.000 0.000 0.008
#> GSM955089 1 0.1075 0.844 0.952 0.000 0.000 0.048 0.000 0.000
#> GSM955095 6 0.1444 0.755 0.000 0.000 0.000 0.000 0.072 0.928
#> GSM955097 6 0.0146 0.793 0.000 0.000 0.000 0.000 0.004 0.996
#> GSM955101 2 0.1267 0.829 0.000 0.940 0.000 0.000 0.000 0.060
#> GSM954999 3 0.0405 0.834 0.004 0.000 0.988 0.000 0.008 0.000
#> GSM955001 6 0.0000 0.794 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955003 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955004 6 0.0000 0.794 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955005 3 0.0146 0.834 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM955009 6 0.0000 0.794 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955011 3 0.3823 0.400 0.436 0.000 0.564 0.000 0.000 0.000
#> GSM955012 5 0.0000 0.743 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955013 3 0.2473 0.800 0.000 0.008 0.856 0.000 0.136 0.000
#> GSM955015 2 0.2697 0.746 0.000 0.812 0.000 0.000 0.000 0.188
#> GSM955017 3 0.3446 0.653 0.308 0.000 0.692 0.000 0.000 0.000
#> GSM955021 2 0.2562 0.761 0.000 0.828 0.000 0.000 0.000 0.172
#> GSM955025 3 0.0870 0.835 0.004 0.012 0.972 0.000 0.000 0.012
#> GSM955028 4 0.0000 0.916 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM955029 5 0.2219 0.786 0.000 0.000 0.000 0.000 0.864 0.136
#> GSM955030 3 0.1644 0.834 0.040 0.000 0.932 0.000 0.028 0.000
#> GSM955032 2 0.3482 0.523 0.000 0.684 0.316 0.000 0.000 0.000
#> GSM955033 1 0.3168 0.795 0.828 0.000 0.116 0.000 0.056 0.000
#> GSM955034 4 0.0146 0.916 0.004 0.000 0.000 0.996 0.000 0.000
#> GSM955035 2 0.0632 0.839 0.000 0.976 0.000 0.000 0.000 0.024
#> GSM955036 3 0.4716 0.671 0.184 0.000 0.680 0.000 0.136 0.000
#> GSM955037 4 0.4046 0.691 0.084 0.000 0.168 0.748 0.000 0.000
#> GSM955039 3 0.4051 0.157 0.000 0.432 0.560 0.000 0.008 0.000
#> GSM955041 5 0.3620 0.469 0.000 0.352 0.000 0.000 0.648 0.000
#> GSM955042 1 0.1141 0.845 0.948 0.000 0.052 0.000 0.000 0.000
#> GSM955045 6 0.1471 0.758 0.000 0.000 0.004 0.000 0.064 0.932
#> GSM955046 3 0.0146 0.833 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM955047 1 0.2230 0.845 0.892 0.000 0.024 0.084 0.000 0.000
#> GSM955050 3 0.3290 0.752 0.208 0.000 0.776 0.000 0.000 0.016
#> GSM955052 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955053 4 0.0363 0.917 0.012 0.000 0.000 0.988 0.000 0.000
#> GSM955056 2 0.0146 0.841 0.000 0.996 0.000 0.000 0.004 0.000
#> GSM955058 5 0.2219 0.786 0.000 0.000 0.000 0.000 0.864 0.136
#> GSM955059 3 0.2135 0.805 0.000 0.000 0.872 0.000 0.128 0.000
#> GSM955060 1 0.1663 0.847 0.912 0.000 0.000 0.088 0.000 0.000
#> GSM955061 5 0.2219 0.786 0.000 0.000 0.000 0.000 0.864 0.136
#> GSM955065 4 0.0790 0.905 0.032 0.000 0.000 0.968 0.000 0.000
#> GSM955066 3 0.0000 0.834 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955067 1 0.2979 0.826 0.840 0.000 0.044 0.116 0.000 0.000
#> GSM955073 2 0.0508 0.841 0.000 0.984 0.012 0.000 0.004 0.000
#> GSM955074 3 0.3518 0.713 0.256 0.000 0.732 0.000 0.012 0.000
#> GSM955076 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955078 2 0.5181 0.045 0.000 0.484 0.000 0.000 0.428 0.088
#> GSM955083 3 0.4245 0.507 0.328 0.000 0.644 0.000 0.024 0.004
#> GSM955084 6 0.0000 0.794 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955086 2 0.5016 0.666 0.028 0.696 0.144 0.000 0.000 0.132
#> GSM955091 2 0.2488 0.784 0.000 0.864 0.004 0.000 0.124 0.008
#> GSM955092 6 0.2378 0.697 0.000 0.152 0.000 0.000 0.000 0.848
#> GSM955093 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955098 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955099 2 0.2793 0.732 0.000 0.800 0.000 0.000 0.000 0.200
#> GSM955100 1 0.0937 0.842 0.960 0.000 0.040 0.000 0.000 0.000
#> GSM955103 2 0.2854 0.723 0.000 0.792 0.000 0.000 0.000 0.208
#> GSM955104 3 0.0146 0.834 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM955106 5 0.0146 0.742 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM955000 3 0.1124 0.834 0.036 0.000 0.956 0.008 0.000 0.000
#> GSM955006 1 0.0000 0.849 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955007 3 0.5346 0.423 0.000 0.000 0.548 0.000 0.128 0.324
#> GSM955010 2 0.7401 -0.173 0.288 0.304 0.296 0.000 0.112 0.000
#> GSM955014 1 0.2003 0.839 0.884 0.000 0.000 0.116 0.000 0.000
#> GSM955018 3 0.1958 0.793 0.004 0.100 0.896 0.000 0.000 0.000
#> GSM955020 1 0.3810 0.383 0.572 0.000 0.000 0.428 0.000 0.000
#> GSM955024 2 0.5219 0.654 0.000 0.684 0.040 0.000 0.136 0.140
#> GSM955026 2 0.1700 0.832 0.000 0.928 0.048 0.000 0.000 0.024
#> GSM955031 2 0.0547 0.840 0.000 0.980 0.020 0.000 0.000 0.000
#> GSM955038 3 0.1003 0.835 0.020 0.016 0.964 0.000 0.000 0.000
#> GSM955040 1 0.2730 0.766 0.808 0.000 0.192 0.000 0.000 0.000
#> GSM955044 5 0.5040 0.568 0.000 0.212 0.000 0.000 0.636 0.152
#> GSM955051 1 0.1082 0.851 0.956 0.000 0.004 0.040 0.000 0.000
#> GSM955055 6 0.0000 0.794 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM955057 1 0.1588 0.853 0.924 0.000 0.004 0.072 0.000 0.000
#> GSM955062 6 0.3737 0.342 0.000 0.392 0.000 0.000 0.000 0.608
#> GSM955063 2 0.0000 0.841 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955068 2 0.5583 0.353 0.000 0.508 0.336 0.000 0.000 0.156
#> GSM955069 3 0.3202 0.790 0.144 0.000 0.816 0.000 0.040 0.000
#> GSM955070 2 0.0713 0.839 0.000 0.972 0.000 0.000 0.000 0.028
#> GSM955071 1 0.3835 0.472 0.668 0.012 0.320 0.000 0.000 0.000
#> GSM955077 3 0.2135 0.789 0.128 0.000 0.872 0.000 0.000 0.000
#> GSM955080 6 0.0858 0.784 0.000 0.000 0.004 0.000 0.028 0.968
#> GSM955081 2 0.0790 0.837 0.000 0.968 0.032 0.000 0.000 0.000
#> GSM955082 2 0.2272 0.823 0.000 0.900 0.040 0.000 0.056 0.004
#> GSM955085 6 0.3309 0.577 0.000 0.280 0.000 0.000 0.000 0.720
#> GSM955090 1 0.1814 0.847 0.900 0.000 0.000 0.100 0.000 0.000
#> GSM955094 2 0.4527 0.696 0.000 0.724 0.132 0.000 0.136 0.008
#> GSM955096 2 0.2969 0.698 0.000 0.776 0.224 0.000 0.000 0.000
#> GSM955102 3 0.0146 0.833 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM955105 2 0.2651 0.802 0.088 0.872 0.004 0.000 0.036 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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> MAD:pam 107 0.566 2
#> MAD:pam 102 0.421 3
#> MAD:pam 96 0.290 4
#> MAD:pam 80 0.143 5
#> MAD:pam 97 0.584 6
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 31589 rows and 108 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 0.989 0.995 0.3485 0.651 0.651
#> 3 3 0.598 0.799 0.847 0.6686 0.709 0.553
#> 4 4 0.639 0.761 0.877 0.1847 0.896 0.733
#> 5 5 0.613 0.693 0.798 0.0690 0.845 0.570
#> 6 6 0.558 0.565 0.755 0.0514 0.917 0.695
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
#> GSM955002 2 0.0000 0.998 0.000 1.000
#> GSM955008 2 0.0000 0.998 0.000 1.000
#> GSM955016 1 0.0376 0.984 0.996 0.004
#> GSM955019 2 0.0000 0.998 0.000 1.000
#> GSM955022 2 0.0000 0.998 0.000 1.000
#> GSM955023 2 0.0000 0.998 0.000 1.000
#> GSM955027 2 0.0000 0.998 0.000 1.000
#> GSM955043 2 0.0000 0.998 0.000 1.000
#> GSM955048 1 0.0000 0.987 1.000 0.000
#> GSM955049 2 0.0000 0.998 0.000 1.000
#> GSM955054 2 0.0000 0.998 0.000 1.000
#> GSM955064 2 0.0000 0.998 0.000 1.000
#> GSM955072 2 0.0000 0.998 0.000 1.000
#> GSM955075 2 0.0000 0.998 0.000 1.000
#> GSM955079 2 0.0000 0.998 0.000 1.000
#> GSM955087 1 0.0000 0.987 1.000 0.000
#> GSM955088 2 0.0000 0.998 0.000 1.000
#> GSM955089 1 0.0000 0.987 1.000 0.000
#> GSM955095 2 0.0000 0.998 0.000 1.000
#> GSM955097 2 0.0000 0.998 0.000 1.000
#> GSM955101 2 0.0000 0.998 0.000 1.000
#> GSM954999 2 0.0000 0.998 0.000 1.000
#> GSM955001 2 0.0000 0.998 0.000 1.000
#> GSM955003 2 0.0000 0.998 0.000 1.000
#> GSM955004 2 0.0000 0.998 0.000 1.000
#> GSM955005 2 0.0000 0.998 0.000 1.000
#> GSM955009 2 0.0000 0.998 0.000 1.000
#> GSM955011 1 0.0000 0.987 1.000 0.000
#> GSM955012 2 0.0000 0.998 0.000 1.000
#> GSM955013 2 0.0000 0.998 0.000 1.000
#> GSM955015 2 0.0000 0.998 0.000 1.000
#> GSM955017 1 0.0000 0.987 1.000 0.000
#> GSM955021 2 0.0000 0.998 0.000 1.000
#> GSM955025 2 0.0000 0.998 0.000 1.000
#> GSM955028 1 0.0000 0.987 1.000 0.000
#> GSM955029 2 0.0000 0.998 0.000 1.000
#> GSM955030 2 0.0000 0.998 0.000 1.000
#> GSM955032 2 0.0000 0.998 0.000 1.000
#> GSM955033 2 0.0000 0.998 0.000 1.000
#> GSM955034 1 0.0000 0.987 1.000 0.000
#> GSM955035 2 0.0000 0.998 0.000 1.000
#> GSM955036 2 0.0000 0.998 0.000 1.000
#> GSM955037 1 0.0000 0.987 1.000 0.000
#> GSM955039 2 0.0000 0.998 0.000 1.000
#> GSM955041 2 0.0000 0.998 0.000 1.000
#> GSM955042 1 0.8661 0.598 0.712 0.288
#> GSM955045 2 0.0000 0.998 0.000 1.000
#> GSM955046 2 0.0000 0.998 0.000 1.000
#> GSM955047 1 0.0000 0.987 1.000 0.000
#> GSM955050 2 0.0000 0.998 0.000 1.000
#> GSM955052 2 0.0000 0.998 0.000 1.000
#> GSM955053 1 0.0000 0.987 1.000 0.000
#> GSM955056 2 0.0000 0.998 0.000 1.000
#> GSM955058 2 0.0000 0.998 0.000 1.000
#> GSM955059 2 0.0000 0.998 0.000 1.000
#> GSM955060 1 0.0000 0.987 1.000 0.000
#> GSM955061 2 0.0000 0.998 0.000 1.000
#> GSM955065 1 0.0000 0.987 1.000 0.000
#> GSM955066 2 0.0000 0.998 0.000 1.000
#> GSM955067 1 0.0000 0.987 1.000 0.000
#> GSM955073 2 0.0000 0.998 0.000 1.000
#> GSM955074 1 0.0376 0.984 0.996 0.004
#> GSM955076 2 0.0000 0.998 0.000 1.000
#> GSM955078 2 0.0000 0.998 0.000 1.000
#> GSM955083 2 0.0000 0.998 0.000 1.000
#> GSM955084 2 0.0000 0.998 0.000 1.000
#> GSM955086 2 0.0000 0.998 0.000 1.000
#> GSM955091 2 0.0000 0.998 0.000 1.000
#> GSM955092 2 0.0000 0.998 0.000 1.000
#> GSM955093 2 0.0000 0.998 0.000 1.000
#> GSM955098 2 0.0000 0.998 0.000 1.000
#> GSM955099 2 0.0000 0.998 0.000 1.000
#> GSM955100 1 0.0376 0.984 0.996 0.004
#> GSM955103 2 0.0000 0.998 0.000 1.000
#> GSM955104 2 0.0000 0.998 0.000 1.000
#> GSM955106 2 0.0000 0.998 0.000 1.000
#> GSM955000 1 0.0000 0.987 1.000 0.000
#> GSM955006 1 0.0000 0.987 1.000 0.000
#> GSM955007 2 0.0000 0.998 0.000 1.000
#> GSM955010 2 0.4161 0.908 0.084 0.916
#> GSM955014 1 0.0000 0.987 1.000 0.000
#> GSM955018 2 0.0000 0.998 0.000 1.000
#> GSM955020 1 0.0000 0.987 1.000 0.000
#> GSM955024 2 0.0000 0.998 0.000 1.000
#> GSM955026 2 0.0000 0.998 0.000 1.000
#> GSM955031 2 0.0000 0.998 0.000 1.000
#> GSM955038 2 0.0000 0.998 0.000 1.000
#> GSM955040 2 0.0000 0.998 0.000 1.000
#> GSM955044 2 0.0000 0.998 0.000 1.000
#> GSM955051 1 0.0000 0.987 1.000 0.000
#> GSM955055 2 0.0000 0.998 0.000 1.000
#> GSM955057 1 0.0000 0.987 1.000 0.000
#> GSM955062 2 0.0000 0.998 0.000 1.000
#> GSM955063 2 0.0000 0.998 0.000 1.000
#> GSM955068 2 0.0000 0.998 0.000 1.000
#> GSM955069 2 0.0000 0.998 0.000 1.000
#> GSM955070 2 0.0000 0.998 0.000 1.000
#> GSM955071 2 0.0000 0.998 0.000 1.000
#> GSM955077 2 0.0000 0.998 0.000 1.000
#> GSM955080 2 0.0000 0.998 0.000 1.000
#> GSM955081 2 0.0000 0.998 0.000 1.000
#> GSM955082 2 0.0000 0.998 0.000 1.000
#> GSM955085 2 0.0000 0.998 0.000 1.000
#> GSM955090 1 0.0000 0.987 1.000 0.000
#> GSM955094 2 0.0000 0.998 0.000 1.000
#> GSM955096 2 0.0000 0.998 0.000 1.000
#> GSM955102 2 0.5178 0.869 0.116 0.884
#> GSM955105 2 0.0000 0.998 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.5678 0.8072 0.000 0.684 0.316
#> GSM955008 3 0.4974 0.5772 0.000 0.236 0.764
#> GSM955016 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955019 2 0.4796 0.8704 0.000 0.780 0.220
#> GSM955022 3 0.3192 0.7718 0.000 0.112 0.888
#> GSM955023 3 0.6309 -0.4297 0.000 0.496 0.504
#> GSM955027 2 0.4605 0.8680 0.000 0.796 0.204
#> GSM955043 2 0.4702 0.8696 0.000 0.788 0.212
#> GSM955048 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955049 2 0.5178 0.8560 0.000 0.744 0.256
#> GSM955054 2 0.6235 0.6037 0.000 0.564 0.436
#> GSM955064 2 0.5397 0.8403 0.000 0.720 0.280
#> GSM955072 2 0.4399 0.8620 0.000 0.812 0.188
#> GSM955075 2 0.1289 0.6841 0.000 0.968 0.032
#> GSM955079 3 0.1964 0.8211 0.000 0.056 0.944
#> GSM955087 1 0.0424 0.9922 0.992 0.008 0.000
#> GSM955088 3 0.0424 0.8440 0.000 0.008 0.992
#> GSM955089 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955095 2 0.5621 0.8174 0.000 0.692 0.308
#> GSM955097 2 0.4931 0.8680 0.000 0.768 0.232
#> GSM955101 3 0.4346 0.6755 0.000 0.184 0.816
#> GSM954999 3 0.6140 -0.0239 0.000 0.404 0.596
#> GSM955001 2 0.4796 0.8704 0.000 0.780 0.220
#> GSM955003 2 0.6295 0.5055 0.000 0.528 0.472
#> GSM955004 2 0.4399 0.8620 0.000 0.812 0.188
#> GSM955005 3 0.0892 0.8423 0.000 0.020 0.980
#> GSM955009 2 0.4399 0.8620 0.000 0.812 0.188
#> GSM955011 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955012 2 0.1529 0.6869 0.000 0.960 0.040
#> GSM955013 3 0.5882 0.2379 0.000 0.348 0.652
#> GSM955015 2 0.6192 0.6393 0.000 0.580 0.420
#> GSM955017 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955021 2 0.4974 0.8663 0.000 0.764 0.236
#> GSM955025 2 0.4452 0.8641 0.000 0.808 0.192
#> GSM955028 1 0.0424 0.9922 0.992 0.008 0.000
#> GSM955029 2 0.1031 0.6769 0.000 0.976 0.024
#> GSM955030 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955032 3 0.1031 0.8408 0.000 0.024 0.976
#> GSM955033 2 0.5529 0.8286 0.000 0.704 0.296
#> GSM955034 1 0.0424 0.9922 0.992 0.008 0.000
#> GSM955035 2 0.4931 0.8677 0.000 0.768 0.232
#> GSM955036 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955037 1 0.3295 0.9034 0.896 0.008 0.096
#> GSM955039 3 0.5678 0.3669 0.000 0.316 0.684
#> GSM955041 2 0.6026 0.7222 0.000 0.624 0.376
#> GSM955042 1 0.0475 0.9871 0.992 0.004 0.004
#> GSM955045 2 0.5678 0.8077 0.000 0.684 0.316
#> GSM955046 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955047 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955050 2 0.5956 0.7960 0.004 0.672 0.324
#> GSM955052 3 0.0424 0.8440 0.000 0.008 0.992
#> GSM955053 1 0.0424 0.9922 0.992 0.008 0.000
#> GSM955056 3 0.3412 0.7587 0.000 0.124 0.876
#> GSM955058 2 0.1163 0.6794 0.000 0.972 0.028
#> GSM955059 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955060 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955061 2 0.1411 0.6862 0.000 0.964 0.036
#> GSM955065 1 0.0424 0.9922 0.992 0.008 0.000
#> GSM955066 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955067 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955073 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955074 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955076 2 0.4887 0.8658 0.000 0.772 0.228
#> GSM955078 2 0.4399 0.8620 0.000 0.812 0.188
#> GSM955083 2 0.6026 0.7224 0.000 0.624 0.376
#> GSM955084 2 0.4399 0.8620 0.000 0.812 0.188
#> GSM955086 3 0.0892 0.8422 0.000 0.020 0.980
#> GSM955091 2 0.4654 0.8689 0.000 0.792 0.208
#> GSM955092 2 0.5678 0.8078 0.000 0.684 0.316
#> GSM955093 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955098 2 0.4399 0.8620 0.000 0.812 0.188
#> GSM955099 2 0.4504 0.8656 0.000 0.804 0.196
#> GSM955100 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955103 2 0.6299 0.4962 0.000 0.524 0.476
#> GSM955104 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955106 2 0.4750 0.8703 0.000 0.784 0.216
#> GSM955000 1 0.0424 0.9922 0.992 0.008 0.000
#> GSM955006 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955007 3 0.1163 0.8390 0.000 0.028 0.972
#> GSM955010 3 0.1289 0.8267 0.032 0.000 0.968
#> GSM955014 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955018 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955020 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955024 2 0.6267 0.5678 0.000 0.548 0.452
#> GSM955026 2 0.4399 0.8620 0.000 0.812 0.188
#> GSM955031 3 0.5905 0.2393 0.000 0.352 0.648
#> GSM955038 2 0.4842 0.8693 0.000 0.776 0.224
#> GSM955040 2 0.6587 0.6208 0.008 0.568 0.424
#> GSM955044 2 0.4452 0.8640 0.000 0.808 0.192
#> GSM955051 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955055 2 0.4750 0.8703 0.000 0.784 0.216
#> GSM955057 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955062 2 0.5560 0.8236 0.000 0.700 0.300
#> GSM955063 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955068 2 0.4399 0.8620 0.000 0.812 0.188
#> GSM955069 3 0.0000 0.8433 0.000 0.000 1.000
#> GSM955070 2 0.4796 0.8704 0.000 0.780 0.220
#> GSM955071 3 0.4002 0.7120 0.000 0.160 0.840
#> GSM955077 2 0.4974 0.8666 0.000 0.764 0.236
#> GSM955080 2 0.4750 0.8703 0.000 0.784 0.216
#> GSM955081 2 0.6299 0.4932 0.000 0.524 0.476
#> GSM955082 3 0.6260 -0.2417 0.000 0.448 0.552
#> GSM955085 2 0.4654 0.8689 0.000 0.792 0.208
#> GSM955090 1 0.0000 0.9943 1.000 0.000 0.000
#> GSM955094 2 0.4796 0.8704 0.000 0.780 0.220
#> GSM955096 3 0.1411 0.8346 0.000 0.036 0.964
#> GSM955102 3 0.0237 0.8393 0.004 0.000 0.996
#> GSM955105 3 0.0592 0.8437 0.000 0.012 0.988
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.3583 0.6955 0.000 0.816 0.180 0.004
#> GSM955008 3 0.3311 0.7799 0.000 0.172 0.828 0.000
#> GSM955016 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955019 2 0.0524 0.7619 0.000 0.988 0.008 0.004
#> GSM955022 3 0.3143 0.8331 0.008 0.024 0.888 0.080
#> GSM955023 3 0.4522 0.6416 0.004 0.264 0.728 0.004
#> GSM955027 2 0.0927 0.7647 0.000 0.976 0.016 0.008
#> GSM955043 2 0.4335 0.6598 0.008 0.792 0.016 0.184
#> GSM955048 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955049 2 0.4284 0.6616 0.000 0.764 0.224 0.012
#> GSM955054 2 0.4936 0.4340 0.000 0.624 0.372 0.004
#> GSM955064 2 0.5513 0.3800 0.004 0.596 0.384 0.016
#> GSM955072 2 0.0524 0.7615 0.008 0.988 0.000 0.004
#> GSM955075 4 0.1302 0.9720 0.000 0.044 0.000 0.956
#> GSM955079 3 0.1209 0.8606 0.004 0.032 0.964 0.000
#> GSM955087 1 0.1022 0.9726 0.968 0.000 0.000 0.032
#> GSM955088 3 0.0000 0.8571 0.000 0.000 1.000 0.000
#> GSM955089 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955095 2 0.7913 0.2885 0.012 0.448 0.348 0.192
#> GSM955097 2 0.8724 0.0619 0.180 0.416 0.060 0.344
#> GSM955101 3 0.2760 0.8198 0.000 0.128 0.872 0.000
#> GSM954999 3 0.8335 0.5015 0.168 0.132 0.568 0.132
#> GSM955001 2 0.1174 0.7651 0.000 0.968 0.020 0.012
#> GSM955003 2 0.5190 0.3709 0.004 0.596 0.396 0.004
#> GSM955004 2 0.3900 0.6418 0.020 0.816 0.000 0.164
#> GSM955005 3 0.0657 0.8615 0.004 0.012 0.984 0.000
#> GSM955009 2 0.0657 0.7622 0.012 0.984 0.000 0.004
#> GSM955011 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955012 4 0.1302 0.9720 0.000 0.044 0.000 0.956
#> GSM955013 3 0.4073 0.8208 0.012 0.064 0.848 0.076
#> GSM955015 2 0.5168 0.0397 0.000 0.504 0.492 0.004
#> GSM955017 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955021 2 0.1492 0.7657 0.004 0.956 0.036 0.004
#> GSM955025 2 0.0895 0.7613 0.020 0.976 0.000 0.004
#> GSM955028 1 0.1022 0.9726 0.968 0.000 0.000 0.032
#> GSM955029 4 0.2149 0.9493 0.000 0.088 0.000 0.912
#> GSM955030 3 0.0707 0.8559 0.020 0.000 0.980 0.000
#> GSM955032 3 0.0817 0.8611 0.000 0.024 0.976 0.000
#> GSM955033 2 0.7287 0.5804 0.040 0.632 0.180 0.148
#> GSM955034 1 0.1022 0.9726 0.968 0.000 0.000 0.032
#> GSM955035 2 0.1576 0.7617 0.000 0.948 0.048 0.004
#> GSM955036 3 0.5287 0.6840 0.156 0.008 0.760 0.076
#> GSM955037 1 0.3342 0.8525 0.868 0.000 0.100 0.032
#> GSM955039 3 0.4567 0.7374 0.008 0.196 0.776 0.020
#> GSM955041 3 0.6252 0.4705 0.004 0.312 0.616 0.068
#> GSM955042 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955045 2 0.6958 0.1552 0.004 0.472 0.428 0.096
#> GSM955046 3 0.0336 0.8592 0.008 0.000 0.992 0.000
#> GSM955047 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955050 2 0.4616 0.6126 0.216 0.760 0.020 0.004
#> GSM955052 3 0.0188 0.8590 0.000 0.004 0.996 0.000
#> GSM955053 1 0.1022 0.9726 0.968 0.000 0.000 0.032
#> GSM955056 3 0.2921 0.8063 0.000 0.140 0.860 0.000
#> GSM955058 4 0.1867 0.9664 0.000 0.072 0.000 0.928
#> GSM955059 3 0.0188 0.8595 0.004 0.000 0.996 0.000
#> GSM955060 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955061 4 0.1474 0.9744 0.000 0.052 0.000 0.948
#> GSM955065 1 0.1022 0.9726 0.968 0.000 0.000 0.032
#> GSM955066 3 0.0188 0.8595 0.004 0.000 0.996 0.000
#> GSM955067 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955073 3 0.0188 0.8595 0.004 0.000 0.996 0.000
#> GSM955074 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955076 2 0.0524 0.7609 0.008 0.988 0.000 0.004
#> GSM955078 2 0.0672 0.7613 0.008 0.984 0.000 0.008
#> GSM955083 2 0.9442 0.2603 0.148 0.392 0.292 0.168
#> GSM955084 2 0.2843 0.7144 0.020 0.892 0.000 0.088
#> GSM955086 3 0.0817 0.8615 0.000 0.024 0.976 0.000
#> GSM955091 2 0.0657 0.7630 0.000 0.984 0.012 0.004
#> GSM955092 2 0.4584 0.5633 0.000 0.696 0.300 0.004
#> GSM955093 3 0.0188 0.8595 0.004 0.000 0.996 0.000
#> GSM955098 2 0.0895 0.7613 0.020 0.976 0.000 0.004
#> GSM955099 2 0.0188 0.7572 0.000 0.996 0.000 0.004
#> GSM955100 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955103 3 0.5801 0.7278 0.008 0.128 0.728 0.136
#> GSM955104 3 0.0469 0.8587 0.012 0.000 0.988 0.000
#> GSM955106 2 0.6438 0.1876 0.000 0.496 0.068 0.436
#> GSM955000 1 0.0707 0.9783 0.980 0.000 0.000 0.020
#> GSM955006 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955007 3 0.0188 0.8595 0.004 0.000 0.996 0.000
#> GSM955010 3 0.2469 0.8050 0.108 0.000 0.892 0.000
#> GSM955014 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955018 3 0.0188 0.8595 0.004 0.000 0.996 0.000
#> GSM955020 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955024 3 0.5099 0.7107 0.004 0.200 0.748 0.048
#> GSM955026 2 0.0779 0.7619 0.016 0.980 0.000 0.004
#> GSM955031 2 0.5486 0.6197 0.200 0.720 0.080 0.000
#> GSM955038 2 0.1398 0.7567 0.040 0.956 0.000 0.004
#> GSM955040 2 0.6832 0.4739 0.296 0.572 0.132 0.000
#> GSM955044 2 0.1909 0.7544 0.008 0.940 0.004 0.048
#> GSM955051 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955055 2 0.0895 0.7645 0.000 0.976 0.020 0.004
#> GSM955057 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955062 2 0.4535 0.5708 0.000 0.704 0.292 0.004
#> GSM955063 3 0.0188 0.8595 0.004 0.000 0.996 0.000
#> GSM955068 2 0.0657 0.7622 0.012 0.984 0.000 0.004
#> GSM955069 3 0.0188 0.8595 0.004 0.000 0.996 0.000
#> GSM955070 2 0.1211 0.7642 0.000 0.960 0.040 0.000
#> GSM955071 3 0.4224 0.8100 0.076 0.100 0.824 0.000
#> GSM955077 2 0.1229 0.7644 0.020 0.968 0.008 0.004
#> GSM955080 2 0.6310 0.2144 0.000 0.512 0.060 0.428
#> GSM955081 3 0.5143 0.1239 0.004 0.456 0.540 0.000
#> GSM955082 3 0.4220 0.6593 0.004 0.248 0.748 0.000
#> GSM955085 2 0.0804 0.7638 0.000 0.980 0.012 0.008
#> GSM955090 1 0.0000 0.9869 1.000 0.000 0.000 0.000
#> GSM955094 2 0.2676 0.7581 0.012 0.916 0.028 0.044
#> GSM955096 3 0.2081 0.8423 0.000 0.084 0.916 0.000
#> GSM955102 3 0.3123 0.7363 0.156 0.000 0.844 0.000
#> GSM955105 3 0.0707 0.8615 0.000 0.020 0.980 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.4473 0.171 0.000 0.580 0.412 0.008 0.000
#> GSM955008 3 0.4375 0.762 0.000 0.116 0.776 0.104 0.004
#> GSM955016 1 0.2362 0.839 0.916 0.024 0.000 0.032 0.028
#> GSM955019 2 0.0609 0.720 0.000 0.980 0.000 0.020 0.000
#> GSM955022 3 0.3615 0.796 0.004 0.080 0.844 0.008 0.064
#> GSM955023 3 0.5123 0.524 0.004 0.336 0.616 0.044 0.000
#> GSM955027 2 0.1716 0.718 0.000 0.944 0.016 0.016 0.024
#> GSM955043 2 0.6363 0.266 0.004 0.560 0.080 0.032 0.324
#> GSM955048 1 0.0451 0.855 0.988 0.000 0.000 0.008 0.004
#> GSM955049 2 0.0290 0.732 0.000 0.992 0.008 0.000 0.000
#> GSM955054 3 0.6028 0.281 0.000 0.372 0.524 0.096 0.008
#> GSM955064 2 0.4047 0.616 0.004 0.788 0.172 0.008 0.028
#> GSM955072 4 0.4375 0.747 0.004 0.420 0.000 0.576 0.000
#> GSM955075 5 0.0865 0.706 0.000 0.024 0.000 0.004 0.972
#> GSM955079 3 0.1525 0.819 0.004 0.036 0.948 0.012 0.000
#> GSM955087 1 0.2416 0.827 0.888 0.000 0.000 0.100 0.012
#> GSM955088 3 0.0404 0.814 0.000 0.012 0.988 0.000 0.000
#> GSM955089 1 0.2171 0.847 0.912 0.000 0.000 0.064 0.024
#> GSM955095 3 0.6900 0.520 0.008 0.212 0.576 0.040 0.164
#> GSM955097 5 0.9452 0.152 0.212 0.060 0.220 0.216 0.292
#> GSM955101 3 0.3062 0.806 0.000 0.080 0.868 0.048 0.004
#> GSM954999 3 0.7393 0.483 0.188 0.072 0.588 0.040 0.112
#> GSM955001 2 0.0451 0.729 0.000 0.988 0.004 0.008 0.000
#> GSM955003 3 0.5797 0.508 0.000 0.280 0.608 0.104 0.008
#> GSM955004 4 0.5829 0.760 0.008 0.200 0.000 0.636 0.156
#> GSM955005 3 0.0854 0.815 0.004 0.012 0.976 0.008 0.000
#> GSM955009 4 0.4101 0.852 0.004 0.332 0.000 0.664 0.000
#> GSM955011 1 0.1522 0.842 0.944 0.000 0.044 0.012 0.000
#> GSM955012 5 0.0865 0.706 0.000 0.024 0.000 0.004 0.972
#> GSM955013 3 0.3541 0.797 0.012 0.072 0.852 0.004 0.060
#> GSM955015 2 0.5764 0.215 0.000 0.548 0.364 0.084 0.004
#> GSM955017 1 0.0000 0.855 1.000 0.000 0.000 0.000 0.000
#> GSM955021 2 0.5479 0.446 0.000 0.660 0.216 0.120 0.004
#> GSM955025 4 0.4547 0.868 0.024 0.252 0.012 0.712 0.000
#> GSM955028 1 0.2416 0.827 0.888 0.000 0.000 0.100 0.012
#> GSM955029 5 0.1041 0.703 0.000 0.032 0.000 0.004 0.964
#> GSM955030 3 0.0798 0.806 0.008 0.000 0.976 0.016 0.000
#> GSM955032 3 0.1818 0.816 0.000 0.044 0.932 0.024 0.000
#> GSM955033 3 0.8878 0.265 0.156 0.204 0.444 0.088 0.108
#> GSM955034 1 0.2130 0.831 0.908 0.000 0.000 0.080 0.012
#> GSM955035 2 0.0807 0.732 0.000 0.976 0.012 0.012 0.000
#> GSM955036 3 0.6519 0.511 0.188 0.020 0.636 0.032 0.124
#> GSM955037 1 0.4777 0.711 0.748 0.000 0.128 0.116 0.008
#> GSM955039 3 0.3002 0.805 0.004 0.092 0.872 0.004 0.028
#> GSM955041 3 0.5550 0.684 0.004 0.212 0.680 0.016 0.088
#> GSM955042 1 0.2124 0.844 0.916 0.000 0.000 0.056 0.028
#> GSM955045 2 0.6064 0.335 0.004 0.568 0.328 0.012 0.088
#> GSM955046 3 0.1978 0.808 0.000 0.044 0.928 0.024 0.004
#> GSM955047 1 0.0000 0.855 1.000 0.000 0.000 0.000 0.000
#> GSM955050 1 0.8399 -0.234 0.324 0.172 0.200 0.304 0.000
#> GSM955052 3 0.2867 0.808 0.000 0.072 0.880 0.044 0.004
#> GSM955053 1 0.2416 0.827 0.888 0.000 0.000 0.100 0.012
#> GSM955056 3 0.4228 0.771 0.000 0.108 0.788 0.100 0.004
#> GSM955058 5 0.0955 0.706 0.000 0.028 0.000 0.004 0.968
#> GSM955059 3 0.0510 0.807 0.000 0.000 0.984 0.016 0.000
#> GSM955060 1 0.0000 0.855 1.000 0.000 0.000 0.000 0.000
#> GSM955061 5 0.0955 0.706 0.000 0.028 0.000 0.004 0.968
#> GSM955065 1 0.2416 0.827 0.888 0.000 0.000 0.100 0.012
#> GSM955066 3 0.0566 0.808 0.004 0.000 0.984 0.012 0.000
#> GSM955067 1 0.1357 0.849 0.948 0.000 0.000 0.048 0.004
#> GSM955073 3 0.1281 0.815 0.000 0.032 0.956 0.012 0.000
#> GSM955074 1 0.2302 0.844 0.916 0.016 0.000 0.048 0.020
#> GSM955076 4 0.4310 0.787 0.004 0.392 0.000 0.604 0.000
#> GSM955078 4 0.5152 0.846 0.004 0.312 0.000 0.632 0.052
#> GSM955083 3 0.8791 0.249 0.204 0.128 0.456 0.080 0.132
#> GSM955084 4 0.5537 0.819 0.008 0.220 0.000 0.660 0.112
#> GSM955086 3 0.1173 0.817 0.004 0.020 0.964 0.012 0.000
#> GSM955091 2 0.0290 0.725 0.000 0.992 0.000 0.008 0.000
#> GSM955092 2 0.2104 0.708 0.000 0.916 0.060 0.024 0.000
#> GSM955093 3 0.0404 0.807 0.000 0.000 0.988 0.012 0.000
#> GSM955098 4 0.3910 0.874 0.008 0.272 0.000 0.720 0.000
#> GSM955099 2 0.0404 0.723 0.000 0.988 0.000 0.012 0.000
#> GSM955100 1 0.1205 0.846 0.956 0.000 0.040 0.004 0.000
#> GSM955103 3 0.4643 0.755 0.004 0.124 0.768 0.008 0.096
#> GSM955104 3 0.1517 0.813 0.004 0.028 0.952 0.012 0.004
#> GSM955106 5 0.7445 0.379 0.000 0.116 0.276 0.112 0.496
#> GSM955000 1 0.1357 0.845 0.948 0.000 0.000 0.048 0.004
#> GSM955006 1 0.1787 0.850 0.936 0.000 0.004 0.044 0.016
#> GSM955007 3 0.2568 0.810 0.004 0.096 0.888 0.004 0.008
#> GSM955010 3 0.2669 0.748 0.104 0.000 0.876 0.020 0.000
#> GSM955014 1 0.0613 0.856 0.984 0.000 0.004 0.008 0.004
#> GSM955018 3 0.0290 0.808 0.000 0.000 0.992 0.008 0.000
#> GSM955020 1 0.1830 0.851 0.924 0.000 0.000 0.068 0.008
#> GSM955024 3 0.4809 0.684 0.004 0.244 0.708 0.012 0.032
#> GSM955026 4 0.4132 0.872 0.020 0.260 0.000 0.720 0.000
#> GSM955031 1 0.8603 -0.333 0.268 0.228 0.252 0.252 0.000
#> GSM955038 4 0.5123 0.833 0.056 0.224 0.020 0.700 0.000
#> GSM955040 1 0.8078 -0.142 0.352 0.140 0.352 0.156 0.000
#> GSM955044 2 0.5818 0.390 0.004 0.684 0.028 0.144 0.140
#> GSM955051 1 0.0451 0.855 0.988 0.000 0.004 0.008 0.000
#> GSM955055 2 0.0451 0.729 0.000 0.988 0.004 0.008 0.000
#> GSM955057 1 0.0324 0.855 0.992 0.000 0.000 0.004 0.004
#> GSM955062 2 0.1579 0.724 0.000 0.944 0.032 0.024 0.000
#> GSM955063 3 0.1522 0.817 0.000 0.044 0.944 0.012 0.000
#> GSM955068 4 0.4046 0.869 0.008 0.296 0.000 0.696 0.000
#> GSM955069 3 0.0703 0.804 0.000 0.000 0.976 0.024 0.000
#> GSM955070 2 0.0807 0.730 0.000 0.976 0.012 0.012 0.000
#> GSM955071 3 0.3369 0.770 0.092 0.028 0.856 0.024 0.000
#> GSM955077 4 0.5714 0.796 0.024 0.268 0.072 0.636 0.000
#> GSM955080 5 0.7520 0.327 0.000 0.232 0.224 0.068 0.476
#> GSM955081 3 0.3562 0.737 0.000 0.196 0.788 0.016 0.000
#> GSM955082 3 0.4323 0.742 0.004 0.200 0.752 0.044 0.000
#> GSM955085 2 0.0290 0.725 0.000 0.992 0.000 0.008 0.000
#> GSM955090 1 0.2166 0.848 0.912 0.004 0.000 0.072 0.012
#> GSM955094 2 0.4610 0.596 0.008 0.772 0.160 0.028 0.032
#> GSM955096 3 0.3081 0.805 0.000 0.072 0.868 0.056 0.004
#> GSM955102 3 0.2915 0.727 0.116 0.000 0.860 0.024 0.000
#> GSM955105 3 0.0566 0.814 0.000 0.012 0.984 0.004 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.4591 0.14515 0.000 0.588 0.376 0.024 0.012 0.000
#> GSM955008 6 0.6236 0.83124 0.000 0.280 0.288 0.008 0.000 0.424
#> GSM955016 1 0.3906 0.79291 0.780 0.004 0.000 0.068 0.004 0.144
#> GSM955019 2 0.0748 0.59221 0.000 0.976 0.004 0.016 0.004 0.000
#> GSM955022 3 0.5189 0.47876 0.000 0.276 0.612 0.008 0.104 0.000
#> GSM955023 2 0.4620 -0.04713 0.000 0.500 0.472 0.008 0.004 0.016
#> GSM955027 2 0.3003 0.54188 0.000 0.860 0.028 0.028 0.084 0.000
#> GSM955043 2 0.5401 -0.09757 0.000 0.476 0.052 0.028 0.444 0.000
#> GSM955048 1 0.1663 0.82236 0.912 0.000 0.000 0.000 0.000 0.088
#> GSM955049 2 0.0632 0.59367 0.000 0.976 0.024 0.000 0.000 0.000
#> GSM955054 6 0.5772 0.82335 0.000 0.348 0.184 0.000 0.000 0.468
#> GSM955064 2 0.2934 0.53829 0.000 0.844 0.112 0.000 0.044 0.000
#> GSM955072 4 0.3934 0.56078 0.000 0.376 0.000 0.616 0.008 0.000
#> GSM955075 5 0.0146 0.73207 0.000 0.004 0.000 0.000 0.996 0.000
#> GSM955079 3 0.2154 0.69291 0.000 0.064 0.908 0.004 0.004 0.020
#> GSM955087 1 0.3371 0.73710 0.708 0.000 0.000 0.000 0.000 0.292
#> GSM955088 3 0.1218 0.70243 0.000 0.028 0.956 0.004 0.000 0.012
#> GSM955089 1 0.3772 0.80797 0.772 0.000 0.000 0.068 0.000 0.160
#> GSM955095 2 0.6839 0.00587 0.000 0.348 0.336 0.044 0.272 0.000
#> GSM955097 5 0.7291 0.20956 0.088 0.000 0.260 0.208 0.432 0.012
#> GSM955101 3 0.5358 0.17443 0.000 0.272 0.596 0.008 0.000 0.124
#> GSM954999 3 0.7454 0.45550 0.120 0.128 0.536 0.044 0.160 0.012
#> GSM955001 2 0.0260 0.59431 0.000 0.992 0.008 0.000 0.000 0.000
#> GSM955003 6 0.5823 0.84809 0.000 0.332 0.200 0.000 0.000 0.468
#> GSM955004 4 0.4127 0.48026 0.000 0.028 0.000 0.684 0.284 0.004
#> GSM955005 3 0.1749 0.70216 0.000 0.044 0.932 0.004 0.004 0.016
#> GSM955009 4 0.3788 0.65809 0.000 0.280 0.012 0.704 0.004 0.000
#> GSM955011 1 0.2780 0.81646 0.868 0.000 0.016 0.092 0.000 0.024
#> GSM955012 5 0.0260 0.73236 0.000 0.008 0.000 0.000 0.992 0.000
#> GSM955013 3 0.5210 0.57200 0.004 0.160 0.664 0.012 0.160 0.000
#> GSM955015 2 0.5368 -0.47566 0.000 0.508 0.116 0.000 0.000 0.376
#> GSM955017 1 0.0603 0.83215 0.980 0.000 0.000 0.004 0.000 0.016
#> GSM955021 2 0.6649 -0.53761 0.000 0.484 0.160 0.072 0.000 0.284
#> GSM955025 4 0.3449 0.69135 0.000 0.116 0.076 0.808 0.000 0.000
#> GSM955028 1 0.3371 0.73710 0.708 0.000 0.000 0.000 0.000 0.292
#> GSM955029 5 0.0363 0.73223 0.000 0.012 0.000 0.000 0.988 0.000
#> GSM955030 3 0.0767 0.69753 0.004 0.000 0.976 0.008 0.000 0.012
#> GSM955032 3 0.4348 0.49310 0.000 0.160 0.732 0.004 0.000 0.104
#> GSM955033 3 0.8183 0.34302 0.080 0.156 0.456 0.072 0.208 0.028
#> GSM955034 1 0.3371 0.73710 0.708 0.000 0.000 0.000 0.000 0.292
#> GSM955035 2 0.0405 0.59538 0.000 0.988 0.008 0.000 0.000 0.004
#> GSM955036 3 0.6473 0.41815 0.100 0.028 0.580 0.020 0.248 0.024
#> GSM955037 1 0.5530 0.68806 0.628 0.004 0.132 0.020 0.000 0.216
#> GSM955039 3 0.4496 0.52839 0.000 0.272 0.672 0.008 0.048 0.000
#> GSM955041 2 0.5152 0.17537 0.000 0.532 0.376 0.000 0.092 0.000
#> GSM955042 1 0.3908 0.79677 0.784 0.008 0.000 0.104 0.000 0.104
#> GSM955045 2 0.4548 0.45407 0.000 0.720 0.156 0.008 0.116 0.000
#> GSM955046 3 0.2723 0.66873 0.000 0.128 0.852 0.004 0.000 0.016
#> GSM955047 1 0.0146 0.83171 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM955050 4 0.7047 0.25961 0.288 0.072 0.212 0.424 0.004 0.000
#> GSM955052 3 0.4430 0.51340 0.000 0.152 0.732 0.008 0.000 0.108
#> GSM955053 1 0.3371 0.73710 0.708 0.000 0.000 0.000 0.000 0.292
#> GSM955056 6 0.6260 0.82853 0.000 0.280 0.300 0.008 0.000 0.412
#> GSM955058 5 0.0363 0.73223 0.000 0.012 0.000 0.000 0.988 0.000
#> GSM955059 3 0.0622 0.70001 0.000 0.008 0.980 0.000 0.000 0.012
#> GSM955060 1 0.0000 0.83191 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955061 5 0.0146 0.73207 0.000 0.004 0.000 0.000 0.996 0.000
#> GSM955065 1 0.3371 0.73710 0.708 0.000 0.000 0.000 0.000 0.292
#> GSM955066 3 0.0653 0.70066 0.000 0.004 0.980 0.004 0.000 0.012
#> GSM955067 1 0.2474 0.82079 0.880 0.000 0.000 0.080 0.000 0.040
#> GSM955073 3 0.2658 0.65528 0.000 0.080 0.876 0.008 0.000 0.036
#> GSM955074 1 0.3602 0.79897 0.792 0.000 0.000 0.072 0.000 0.136
#> GSM955076 4 0.4988 0.44012 0.000 0.380 0.064 0.552 0.004 0.000
#> GSM955078 4 0.4791 0.64683 0.000 0.244 0.000 0.652 0.104 0.000
#> GSM955083 3 0.8279 0.31958 0.092 0.136 0.448 0.100 0.204 0.020
#> GSM955084 4 0.4248 0.54394 0.000 0.052 0.000 0.708 0.236 0.004
#> GSM955086 3 0.1988 0.70021 0.000 0.048 0.920 0.004 0.004 0.024
#> GSM955091 2 0.0291 0.59234 0.000 0.992 0.000 0.004 0.004 0.000
#> GSM955092 2 0.2129 0.54590 0.000 0.904 0.056 0.000 0.000 0.040
#> GSM955093 3 0.0692 0.69737 0.000 0.004 0.976 0.000 0.000 0.020
#> GSM955098 4 0.2163 0.67288 0.000 0.092 0.016 0.892 0.000 0.000
#> GSM955099 2 0.0458 0.58591 0.000 0.984 0.000 0.016 0.000 0.000
#> GSM955100 1 0.2772 0.81752 0.876 0.000 0.036 0.068 0.000 0.020
#> GSM955103 3 0.6052 0.37897 0.000 0.260 0.516 0.016 0.208 0.000
#> GSM955104 3 0.2623 0.68623 0.008 0.092 0.880 0.008 0.004 0.008
#> GSM955106 5 0.6741 0.41685 0.000 0.212 0.164 0.084 0.532 0.008
#> GSM955000 1 0.2163 0.81236 0.892 0.000 0.008 0.004 0.000 0.096
#> GSM955006 1 0.2605 0.81449 0.864 0.000 0.000 0.108 0.000 0.028
#> GSM955007 3 0.3759 0.57137 0.000 0.248 0.732 0.008 0.004 0.008
#> GSM955010 3 0.2624 0.65709 0.080 0.000 0.880 0.024 0.000 0.016
#> GSM955014 1 0.2034 0.83113 0.912 0.000 0.004 0.024 0.000 0.060
#> GSM955018 3 0.0405 0.69964 0.000 0.004 0.988 0.000 0.000 0.008
#> GSM955020 1 0.3914 0.81108 0.768 0.000 0.000 0.104 0.000 0.128
#> GSM955024 2 0.5043 0.20934 0.000 0.568 0.360 0.008 0.064 0.000
#> GSM955026 4 0.2527 0.69876 0.000 0.168 0.000 0.832 0.000 0.000
#> GSM955031 4 0.7843 0.17024 0.228 0.212 0.224 0.328 0.000 0.008
#> GSM955038 4 0.3940 0.66509 0.020 0.076 0.080 0.812 0.004 0.008
#> GSM955040 1 0.6935 -0.11698 0.344 0.040 0.312 0.300 0.000 0.004
#> GSM955044 2 0.5111 0.22170 0.000 0.596 0.016 0.064 0.324 0.000
#> GSM955051 1 0.1232 0.83145 0.956 0.000 0.004 0.024 0.000 0.016
#> GSM955055 2 0.0260 0.59582 0.000 0.992 0.008 0.000 0.000 0.000
#> GSM955057 1 0.1327 0.82707 0.936 0.000 0.000 0.000 0.000 0.064
#> GSM955062 2 0.1151 0.58755 0.000 0.956 0.032 0.000 0.000 0.012
#> GSM955063 3 0.2658 0.65324 0.000 0.080 0.876 0.008 0.000 0.036
#> GSM955068 4 0.3151 0.68122 0.000 0.252 0.000 0.748 0.000 0.000
#> GSM955069 3 0.1370 0.70298 0.000 0.036 0.948 0.004 0.000 0.012
#> GSM955070 2 0.0984 0.59792 0.000 0.968 0.012 0.008 0.012 0.000
#> GSM955071 3 0.4531 0.62981 0.104 0.056 0.776 0.040 0.000 0.024
#> GSM955077 4 0.3908 0.67225 0.008 0.104 0.104 0.784 0.000 0.000
#> GSM955080 5 0.6240 0.30652 0.000 0.316 0.116 0.056 0.512 0.000
#> GSM955081 3 0.4426 0.34414 0.000 0.296 0.664 0.008 0.004 0.028
#> GSM955082 2 0.4221 0.17341 0.000 0.588 0.396 0.008 0.000 0.008
#> GSM955085 2 0.0291 0.59234 0.000 0.992 0.000 0.004 0.004 0.000
#> GSM955090 1 0.3626 0.80235 0.788 0.000 0.000 0.068 0.000 0.144
#> GSM955094 2 0.3575 0.54251 0.000 0.824 0.080 0.024 0.072 0.000
#> GSM955096 3 0.5770 0.04516 0.000 0.212 0.564 0.012 0.000 0.212
#> GSM955102 3 0.2089 0.66666 0.072 0.004 0.908 0.004 0.000 0.012
#> GSM955105 3 0.1605 0.70104 0.000 0.044 0.936 0.004 0.000 0.016
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> MAD:mclust 108 0.910 2
#> MAD:mclust 100 0.954 3
#> MAD:mclust 95 0.840 4
#> MAD:mclust 92 0.767 5
#> MAD:mclust 79 0.481 6
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 31589 rows and 108 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 0.867 0.918 0.965 0.4625 0.534 0.534
#> 3 3 0.749 0.795 0.914 0.2788 0.802 0.658
#> 4 4 0.589 0.660 0.846 0.1716 0.776 0.528
#> 5 5 0.550 0.559 0.756 0.0920 0.862 0.605
#> 6 6 0.545 0.425 0.679 0.0592 0.877 0.580
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
#> GSM955002 2 0.0000 0.974 0.000 1.000
#> GSM955008 2 0.0000 0.974 0.000 1.000
#> GSM955016 1 0.0000 0.942 1.000 0.000
#> GSM955019 2 0.0000 0.974 0.000 1.000
#> GSM955022 2 0.0000 0.974 0.000 1.000
#> GSM955023 2 0.0000 0.974 0.000 1.000
#> GSM955027 2 0.0000 0.974 0.000 1.000
#> GSM955043 2 0.0000 0.974 0.000 1.000
#> GSM955048 1 0.0000 0.942 1.000 0.000
#> GSM955049 2 0.0000 0.974 0.000 1.000
#> GSM955054 2 0.0000 0.974 0.000 1.000
#> GSM955064 2 0.0000 0.974 0.000 1.000
#> GSM955072 2 0.0000 0.974 0.000 1.000
#> GSM955075 2 0.0000 0.974 0.000 1.000
#> GSM955079 2 0.0376 0.970 0.004 0.996
#> GSM955087 1 0.0000 0.942 1.000 0.000
#> GSM955088 2 0.7056 0.757 0.192 0.808
#> GSM955089 1 0.0000 0.942 1.000 0.000
#> GSM955095 2 0.0000 0.974 0.000 1.000
#> GSM955097 2 0.0938 0.963 0.012 0.988
#> GSM955101 2 0.0000 0.974 0.000 1.000
#> GSM954999 1 0.3114 0.905 0.944 0.056
#> GSM955001 2 0.0000 0.974 0.000 1.000
#> GSM955003 2 0.0000 0.974 0.000 1.000
#> GSM955004 2 0.0000 0.974 0.000 1.000
#> GSM955005 1 0.9933 0.248 0.548 0.452
#> GSM955009 2 0.0000 0.974 0.000 1.000
#> GSM955011 1 0.0000 0.942 1.000 0.000
#> GSM955012 2 0.0000 0.974 0.000 1.000
#> GSM955013 2 0.4298 0.888 0.088 0.912
#> GSM955015 2 0.0000 0.974 0.000 1.000
#> GSM955017 1 0.0000 0.942 1.000 0.000
#> GSM955021 2 0.0000 0.974 0.000 1.000
#> GSM955025 2 0.0000 0.974 0.000 1.000
#> GSM955028 1 0.0000 0.942 1.000 0.000
#> GSM955029 2 0.0000 0.974 0.000 1.000
#> GSM955030 1 0.0000 0.942 1.000 0.000
#> GSM955032 2 0.0000 0.974 0.000 1.000
#> GSM955033 2 0.9087 0.524 0.324 0.676
#> GSM955034 1 0.0000 0.942 1.000 0.000
#> GSM955035 2 0.0000 0.974 0.000 1.000
#> GSM955036 2 0.8267 0.650 0.260 0.740
#> GSM955037 1 0.0000 0.942 1.000 0.000
#> GSM955039 2 0.0000 0.974 0.000 1.000
#> GSM955041 2 0.0000 0.974 0.000 1.000
#> GSM955042 1 0.0000 0.942 1.000 0.000
#> GSM955045 2 0.0000 0.974 0.000 1.000
#> GSM955046 2 0.0000 0.974 0.000 1.000
#> GSM955047 1 0.0000 0.942 1.000 0.000
#> GSM955050 1 0.0000 0.942 1.000 0.000
#> GSM955052 2 0.0000 0.974 0.000 1.000
#> GSM955053 1 0.0000 0.942 1.000 0.000
#> GSM955056 2 0.0000 0.974 0.000 1.000
#> GSM955058 2 0.0000 0.974 0.000 1.000
#> GSM955059 2 0.5294 0.851 0.120 0.880
#> GSM955060 1 0.0000 0.942 1.000 0.000
#> GSM955061 2 0.0000 0.974 0.000 1.000
#> GSM955065 1 0.0000 0.942 1.000 0.000
#> GSM955066 1 0.5737 0.827 0.864 0.136
#> GSM955067 1 0.0000 0.942 1.000 0.000
#> GSM955073 2 0.0000 0.974 0.000 1.000
#> GSM955074 1 0.0000 0.942 1.000 0.000
#> GSM955076 2 0.0000 0.974 0.000 1.000
#> GSM955078 2 0.0000 0.974 0.000 1.000
#> GSM955083 1 0.9775 0.351 0.588 0.412
#> GSM955084 2 0.0000 0.974 0.000 1.000
#> GSM955086 2 0.9393 0.449 0.356 0.644
#> GSM955091 2 0.0000 0.974 0.000 1.000
#> GSM955092 2 0.0000 0.974 0.000 1.000
#> GSM955093 2 0.0000 0.974 0.000 1.000
#> GSM955098 2 0.0000 0.974 0.000 1.000
#> GSM955099 2 0.0000 0.974 0.000 1.000
#> GSM955100 1 0.0000 0.942 1.000 0.000
#> GSM955103 2 0.0000 0.974 0.000 1.000
#> GSM955104 1 0.7299 0.755 0.796 0.204
#> GSM955106 2 0.0000 0.974 0.000 1.000
#> GSM955000 1 0.0000 0.942 1.000 0.000
#> GSM955006 1 0.0000 0.942 1.000 0.000
#> GSM955007 2 0.0000 0.974 0.000 1.000
#> GSM955010 1 0.0000 0.942 1.000 0.000
#> GSM955014 1 0.0000 0.942 1.000 0.000
#> GSM955018 2 0.0000 0.974 0.000 1.000
#> GSM955020 1 0.0000 0.942 1.000 0.000
#> GSM955024 2 0.0000 0.974 0.000 1.000
#> GSM955026 2 0.0000 0.974 0.000 1.000
#> GSM955031 1 0.2043 0.922 0.968 0.032
#> GSM955038 1 0.7219 0.757 0.800 0.200
#> GSM955040 1 0.0000 0.942 1.000 0.000
#> GSM955044 2 0.0000 0.974 0.000 1.000
#> GSM955051 1 0.0000 0.942 1.000 0.000
#> GSM955055 2 0.0000 0.974 0.000 1.000
#> GSM955057 1 0.0000 0.942 1.000 0.000
#> GSM955062 2 0.0000 0.974 0.000 1.000
#> GSM955063 2 0.0000 0.974 0.000 1.000
#> GSM955068 2 0.0000 0.974 0.000 1.000
#> GSM955069 2 0.8861 0.567 0.304 0.696
#> GSM955070 2 0.0000 0.974 0.000 1.000
#> GSM955071 1 0.0000 0.942 1.000 0.000
#> GSM955077 1 0.5737 0.835 0.864 0.136
#> GSM955080 2 0.0000 0.974 0.000 1.000
#> GSM955081 2 0.0000 0.974 0.000 1.000
#> GSM955082 2 0.0000 0.974 0.000 1.000
#> GSM955085 2 0.0000 0.974 0.000 1.000
#> GSM955090 1 0.0000 0.942 1.000 0.000
#> GSM955094 2 0.0000 0.974 0.000 1.000
#> GSM955096 2 0.0000 0.974 0.000 1.000
#> GSM955102 1 0.4562 0.868 0.904 0.096
#> GSM955105 1 0.9775 0.314 0.588 0.412
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.1163 0.8807 0.000 0.028 0.972
#> GSM955008 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955016 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955019 3 0.2959 0.8418 0.000 0.100 0.900
#> GSM955022 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955023 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955027 3 0.1753 0.8725 0.000 0.048 0.952
#> GSM955043 3 0.3752 0.8009 0.000 0.144 0.856
#> GSM955048 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955049 3 0.1031 0.8820 0.000 0.024 0.976
#> GSM955054 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955064 3 0.0592 0.8851 0.000 0.012 0.988
#> GSM955072 2 0.6045 0.3198 0.000 0.620 0.380
#> GSM955075 3 0.6309 0.0132 0.000 0.496 0.504
#> GSM955079 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955087 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955088 3 0.0424 0.8836 0.008 0.000 0.992
#> GSM955089 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955095 3 0.3038 0.8308 0.000 0.104 0.896
#> GSM955097 2 0.1585 0.7572 0.028 0.964 0.008
#> GSM955101 3 0.0237 0.8865 0.000 0.004 0.996
#> GSM954999 1 0.0424 0.9570 0.992 0.008 0.000
#> GSM955001 3 0.2448 0.8559 0.000 0.076 0.924
#> GSM955003 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955004 2 0.0000 0.7654 0.000 1.000 0.000
#> GSM955005 3 0.2448 0.8297 0.076 0.000 0.924
#> GSM955009 2 0.6308 -0.0876 0.000 0.508 0.492
#> GSM955011 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955012 3 0.3340 0.8191 0.000 0.120 0.880
#> GSM955013 3 0.1031 0.8746 0.024 0.000 0.976
#> GSM955015 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955017 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955021 3 0.1031 0.8823 0.000 0.024 0.976
#> GSM955025 2 0.0000 0.7654 0.000 1.000 0.000
#> GSM955028 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955029 3 0.6154 0.3433 0.000 0.408 0.592
#> GSM955030 1 0.4002 0.7417 0.840 0.000 0.160
#> GSM955032 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955033 2 0.8998 0.2739 0.396 0.472 0.132
#> GSM955034 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955035 3 0.2066 0.8664 0.000 0.060 0.940
#> GSM955036 3 0.4750 0.6322 0.216 0.000 0.784
#> GSM955037 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955039 3 0.1529 0.8756 0.000 0.040 0.960
#> GSM955041 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955042 1 0.0237 0.9601 0.996 0.004 0.000
#> GSM955045 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955046 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955047 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955050 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955052 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955053 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955056 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955058 3 0.5760 0.5328 0.000 0.328 0.672
#> GSM955059 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955060 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955061 2 0.5948 0.3558 0.000 0.640 0.360
#> GSM955065 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955066 3 0.6286 0.1222 0.464 0.000 0.536
#> GSM955067 1 0.0237 0.9603 0.996 0.004 0.000
#> GSM955073 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955074 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955076 3 0.2711 0.8500 0.000 0.088 0.912
#> GSM955078 2 0.2537 0.7521 0.000 0.920 0.080
#> GSM955083 2 0.6513 0.0607 0.476 0.520 0.004
#> GSM955084 2 0.0000 0.7654 0.000 1.000 0.000
#> GSM955086 3 0.2796 0.8084 0.092 0.000 0.908
#> GSM955091 3 0.4555 0.7401 0.000 0.200 0.800
#> GSM955092 3 0.0424 0.8860 0.000 0.008 0.992
#> GSM955093 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955098 2 0.1289 0.7686 0.000 0.968 0.032
#> GSM955099 3 0.5178 0.6629 0.000 0.256 0.744
#> GSM955100 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955103 3 0.0424 0.8862 0.000 0.008 0.992
#> GSM955104 1 0.5926 0.3410 0.644 0.000 0.356
#> GSM955106 3 0.5397 0.6082 0.000 0.280 0.720
#> GSM955000 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955006 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955007 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955010 1 0.0747 0.9465 0.984 0.000 0.016
#> GSM955014 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955018 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955020 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955024 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955026 2 0.1411 0.7685 0.000 0.964 0.036
#> GSM955031 1 0.2796 0.8441 0.908 0.000 0.092
#> GSM955038 2 0.5431 0.4928 0.284 0.716 0.000
#> GSM955040 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955044 3 0.5988 0.4515 0.000 0.368 0.632
#> GSM955051 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955055 3 0.2711 0.8496 0.000 0.088 0.912
#> GSM955057 1 0.0000 0.9630 1.000 0.000 0.000
#> GSM955062 3 0.0424 0.8860 0.000 0.008 0.992
#> GSM955063 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955068 2 0.0000 0.7654 0.000 1.000 0.000
#> GSM955069 3 0.0424 0.8835 0.008 0.000 0.992
#> GSM955070 3 0.1753 0.8715 0.000 0.048 0.952
#> GSM955071 1 0.0237 0.9590 0.996 0.000 0.004
#> GSM955077 1 0.4842 0.6829 0.776 0.224 0.000
#> GSM955080 3 0.6280 0.1556 0.000 0.460 0.540
#> GSM955081 3 0.0237 0.8865 0.000 0.004 0.996
#> GSM955082 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955085 3 0.5591 0.5920 0.000 0.304 0.696
#> GSM955090 1 0.0237 0.9602 0.996 0.004 0.000
#> GSM955094 3 0.3851 0.8038 0.004 0.136 0.860
#> GSM955096 3 0.0000 0.8869 0.000 0.000 1.000
#> GSM955102 3 0.6192 0.2418 0.420 0.000 0.580
#> GSM955105 3 0.2356 0.8311 0.072 0.000 0.928
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 3 0.2408 0.7298 0.000 0.104 0.896 0.000
#> GSM955008 3 0.1302 0.7555 0.000 0.044 0.956 0.000
#> GSM955016 1 0.2011 0.9011 0.920 0.000 0.000 0.080
#> GSM955019 2 0.3172 0.7131 0.000 0.840 0.160 0.000
#> GSM955022 3 0.0564 0.7527 0.004 0.004 0.988 0.004
#> GSM955023 3 0.0592 0.7589 0.000 0.016 0.984 0.000
#> GSM955027 2 0.4955 0.3545 0.000 0.556 0.444 0.000
#> GSM955043 3 0.2918 0.6954 0.000 0.008 0.876 0.116
#> GSM955048 1 0.0336 0.9483 0.992 0.008 0.000 0.000
#> GSM955049 3 0.4679 0.2965 0.000 0.352 0.648 0.000
#> GSM955054 3 0.5000 -0.2345 0.000 0.500 0.500 0.000
#> GSM955064 3 0.2011 0.7367 0.000 0.080 0.920 0.000
#> GSM955072 2 0.5977 0.5449 0.000 0.688 0.120 0.192
#> GSM955075 4 0.4204 0.7380 0.000 0.020 0.192 0.788
#> GSM955079 3 0.5557 0.3738 0.040 0.308 0.652 0.000
#> GSM955087 1 0.0188 0.9494 0.996 0.000 0.000 0.004
#> GSM955088 3 0.0895 0.7591 0.004 0.020 0.976 0.000
#> GSM955089 1 0.0188 0.9494 0.996 0.000 0.000 0.004
#> GSM955095 3 0.4546 0.4921 0.000 0.012 0.732 0.256
#> GSM955097 4 0.0524 0.7000 0.000 0.008 0.004 0.988
#> GSM955101 3 0.4776 0.2798 0.000 0.376 0.624 0.000
#> GSM954999 1 0.2987 0.8378 0.880 0.000 0.104 0.016
#> GSM955001 2 0.4925 0.3912 0.000 0.572 0.428 0.000
#> GSM955003 2 0.3873 0.6981 0.000 0.772 0.228 0.000
#> GSM955004 4 0.0336 0.6985 0.000 0.008 0.000 0.992
#> GSM955005 3 0.5105 0.2465 0.432 0.004 0.564 0.000
#> GSM955009 2 0.1488 0.6736 0.000 0.956 0.032 0.012
#> GSM955011 1 0.0000 0.9497 1.000 0.000 0.000 0.000
#> GSM955012 3 0.4012 0.6181 0.000 0.016 0.800 0.184
#> GSM955013 3 0.2408 0.7117 0.060 0.004 0.920 0.016
#> GSM955015 3 0.1302 0.7559 0.000 0.044 0.956 0.000
#> GSM955017 1 0.0000 0.9497 1.000 0.000 0.000 0.000
#> GSM955021 2 0.3610 0.7105 0.000 0.800 0.200 0.000
#> GSM955025 2 0.1302 0.6388 0.000 0.956 0.000 0.044
#> GSM955028 1 0.0000 0.9497 1.000 0.000 0.000 0.000
#> GSM955029 4 0.6141 0.5615 0.000 0.072 0.312 0.616
#> GSM955030 3 0.4920 0.2772 0.368 0.004 0.628 0.000
#> GSM955032 3 0.4072 0.5321 0.000 0.252 0.748 0.000
#> GSM955033 4 0.7758 0.3165 0.164 0.012 0.368 0.456
#> GSM955034 1 0.0000 0.9497 1.000 0.000 0.000 0.000
#> GSM955035 2 0.4889 0.5344 0.000 0.636 0.360 0.004
#> GSM955036 3 0.3496 0.6681 0.072 0.004 0.872 0.052
#> GSM955037 1 0.2334 0.8679 0.908 0.000 0.088 0.004
#> GSM955039 3 0.2593 0.7090 0.004 0.104 0.892 0.000
#> GSM955041 3 0.0336 0.7572 0.000 0.008 0.992 0.000
#> GSM955042 1 0.0376 0.9494 0.992 0.004 0.000 0.004
#> GSM955045 3 0.1305 0.7573 0.000 0.036 0.960 0.004
#> GSM955046 3 0.0657 0.7510 0.012 0.004 0.984 0.000
#> GSM955047 1 0.0469 0.9468 0.988 0.012 0.000 0.000
#> GSM955050 1 0.2197 0.9004 0.916 0.080 0.004 0.000
#> GSM955052 3 0.1118 0.7566 0.000 0.036 0.964 0.000
#> GSM955053 1 0.0188 0.9494 0.996 0.000 0.000 0.004
#> GSM955056 3 0.4679 0.3006 0.000 0.352 0.648 0.000
#> GSM955058 4 0.5478 0.5398 0.000 0.028 0.344 0.628
#> GSM955059 3 0.0376 0.7562 0.004 0.004 0.992 0.000
#> GSM955060 1 0.0000 0.9497 1.000 0.000 0.000 0.000
#> GSM955061 4 0.3501 0.7436 0.000 0.020 0.132 0.848
#> GSM955065 1 0.0188 0.9494 0.996 0.000 0.000 0.004
#> GSM955066 3 0.3982 0.5420 0.220 0.004 0.776 0.000
#> GSM955067 1 0.1792 0.9107 0.932 0.068 0.000 0.000
#> GSM955073 3 0.0469 0.7575 0.000 0.012 0.988 0.000
#> GSM955074 1 0.0592 0.9460 0.984 0.000 0.000 0.016
#> GSM955076 2 0.1118 0.6768 0.000 0.964 0.036 0.000
#> GSM955078 2 0.4706 0.6449 0.000 0.788 0.072 0.140
#> GSM955083 1 0.4832 0.5725 0.680 0.004 0.004 0.312
#> GSM955084 4 0.1211 0.6854 0.000 0.040 0.000 0.960
#> GSM955086 3 0.7677 -0.2039 0.216 0.372 0.412 0.000
#> GSM955091 2 0.3751 0.7099 0.000 0.800 0.196 0.004
#> GSM955092 2 0.4907 0.4134 0.000 0.580 0.420 0.000
#> GSM955093 3 0.0469 0.7575 0.000 0.012 0.988 0.000
#> GSM955098 2 0.0707 0.6458 0.000 0.980 0.000 0.020
#> GSM955099 2 0.4391 0.6731 0.000 0.740 0.252 0.008
#> GSM955100 1 0.0188 0.9494 0.996 0.000 0.000 0.004
#> GSM955103 3 0.0592 0.7579 0.000 0.016 0.984 0.000
#> GSM955104 3 0.4401 0.4546 0.272 0.000 0.724 0.004
#> GSM955106 3 0.5158 -0.1744 0.000 0.004 0.524 0.472
#> GSM955000 1 0.0000 0.9497 1.000 0.000 0.000 0.000
#> GSM955006 1 0.0188 0.9494 0.996 0.000 0.000 0.004
#> GSM955007 3 0.0000 0.7557 0.000 0.000 1.000 0.000
#> GSM955010 1 0.4699 0.4785 0.676 0.004 0.320 0.000
#> GSM955014 1 0.1118 0.9351 0.964 0.036 0.000 0.000
#> GSM955018 3 0.1211 0.7556 0.000 0.040 0.960 0.000
#> GSM955020 1 0.0376 0.9494 0.992 0.004 0.000 0.004
#> GSM955024 3 0.0000 0.7557 0.000 0.000 1.000 0.000
#> GSM955026 2 0.0707 0.6460 0.000 0.980 0.000 0.020
#> GSM955031 2 0.2266 0.6105 0.084 0.912 0.004 0.000
#> GSM955038 2 0.5760 -0.0939 0.448 0.524 0.000 0.028
#> GSM955040 1 0.1059 0.9409 0.972 0.016 0.012 0.000
#> GSM955044 3 0.6747 0.3204 0.000 0.140 0.596 0.264
#> GSM955051 1 0.0921 0.9394 0.972 0.028 0.000 0.000
#> GSM955055 2 0.3486 0.7131 0.000 0.812 0.188 0.000
#> GSM955057 1 0.0817 0.9414 0.976 0.024 0.000 0.000
#> GSM955062 3 0.4985 -0.1087 0.000 0.468 0.532 0.000
#> GSM955063 3 0.0336 0.7572 0.000 0.008 0.992 0.000
#> GSM955068 2 0.1004 0.6484 0.000 0.972 0.004 0.024
#> GSM955069 3 0.1890 0.7327 0.056 0.008 0.936 0.000
#> GSM955070 3 0.1059 0.7541 0.000 0.012 0.972 0.016
#> GSM955071 1 0.1624 0.9262 0.952 0.020 0.028 0.000
#> GSM955077 2 0.4647 0.3745 0.288 0.704 0.000 0.008
#> GSM955080 4 0.4990 0.7185 0.000 0.060 0.184 0.756
#> GSM955081 2 0.4817 0.4700 0.000 0.612 0.388 0.000
#> GSM955082 3 0.2271 0.7424 0.000 0.076 0.916 0.008
#> GSM955085 2 0.4332 0.7067 0.000 0.800 0.160 0.040
#> GSM955090 1 0.0524 0.9480 0.988 0.008 0.000 0.004
#> GSM955094 3 0.4371 0.6760 0.004 0.064 0.820 0.112
#> GSM955096 2 0.4996 0.2326 0.000 0.516 0.484 0.000
#> GSM955102 3 0.3074 0.6313 0.152 0.000 0.848 0.000
#> GSM955105 3 0.6955 0.3052 0.296 0.144 0.560 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.4846 0.3959 0.000 0.028 0.588 0.384 0.000
#> GSM955008 3 0.3694 0.6489 0.000 0.172 0.796 0.032 0.000
#> GSM955016 1 0.3070 0.8121 0.860 0.000 0.012 0.016 0.112
#> GSM955019 2 0.4165 0.3586 0.000 0.672 0.008 0.320 0.000
#> GSM955022 3 0.1364 0.7020 0.000 0.036 0.952 0.012 0.000
#> GSM955023 3 0.2570 0.6986 0.000 0.084 0.888 0.028 0.000
#> GSM955027 2 0.3688 0.6053 0.000 0.816 0.124 0.060 0.000
#> GSM955043 3 0.4252 0.6306 0.000 0.028 0.788 0.032 0.152
#> GSM955048 1 0.0404 0.8820 0.988 0.000 0.000 0.012 0.000
#> GSM955049 2 0.5092 0.1591 0.000 0.524 0.440 0.036 0.000
#> GSM955054 3 0.6776 -0.0580 0.000 0.292 0.392 0.316 0.000
#> GSM955064 3 0.4049 0.6787 0.000 0.084 0.792 0.124 0.000
#> GSM955072 2 0.6679 -0.2592 0.000 0.472 0.048 0.396 0.084
#> GSM955075 5 0.4847 0.6256 0.000 0.240 0.068 0.000 0.692
#> GSM955079 3 0.6887 0.1233 0.048 0.372 0.472 0.108 0.000
#> GSM955087 1 0.0579 0.8793 0.984 0.000 0.008 0.008 0.000
#> GSM955088 2 0.5260 0.2036 0.016 0.508 0.456 0.020 0.000
#> GSM955089 1 0.0451 0.8804 0.988 0.000 0.008 0.004 0.000
#> GSM955095 2 0.6771 -0.0619 0.000 0.368 0.360 0.000 0.272
#> GSM955097 5 0.0451 0.6316 0.000 0.008 0.004 0.000 0.988
#> GSM955101 3 0.6265 0.3532 0.000 0.240 0.540 0.220 0.000
#> GSM954999 1 0.5085 0.5948 0.704 0.004 0.232 0.028 0.032
#> GSM955001 2 0.2535 0.5889 0.000 0.892 0.076 0.032 0.000
#> GSM955003 2 0.6552 -0.1474 0.000 0.412 0.200 0.388 0.000
#> GSM955004 5 0.2629 0.6379 0.000 0.136 0.000 0.004 0.860
#> GSM955005 3 0.4928 0.5336 0.264 0.012 0.684 0.040 0.000
#> GSM955009 2 0.2077 0.5172 0.000 0.908 0.008 0.084 0.000
#> GSM955011 1 0.0671 0.8815 0.980 0.004 0.000 0.016 0.000
#> GSM955012 3 0.6252 0.3124 0.000 0.148 0.556 0.008 0.288
#> GSM955013 3 0.2348 0.6989 0.024 0.024 0.920 0.028 0.004
#> GSM955015 3 0.4969 0.4930 0.000 0.056 0.652 0.292 0.000
#> GSM955017 1 0.1251 0.8767 0.956 0.000 0.008 0.036 0.000
#> GSM955021 2 0.4649 0.4148 0.000 0.720 0.068 0.212 0.000
#> GSM955025 2 0.5463 0.1646 0.052 0.636 0.000 0.292 0.020
#> GSM955028 1 0.0579 0.8793 0.984 0.000 0.008 0.008 0.000
#> GSM955029 2 0.5183 0.4574 0.000 0.692 0.104 0.004 0.200
#> GSM955030 3 0.3692 0.6391 0.136 0.000 0.812 0.052 0.000
#> GSM955032 3 0.5681 0.3883 0.000 0.268 0.608 0.124 0.000
#> GSM955033 3 0.8075 -0.0438 0.076 0.020 0.376 0.372 0.156
#> GSM955034 1 0.0162 0.8821 0.996 0.000 0.000 0.004 0.000
#> GSM955035 4 0.6138 0.3679 0.000 0.176 0.272 0.552 0.000
#> GSM955036 3 0.2590 0.6830 0.028 0.000 0.900 0.060 0.012
#> GSM955037 1 0.2208 0.8316 0.908 0.000 0.072 0.020 0.000
#> GSM955039 3 0.4776 0.5348 0.008 0.028 0.668 0.296 0.000
#> GSM955041 3 0.2879 0.6914 0.000 0.100 0.868 0.032 0.000
#> GSM955042 1 0.0324 0.8813 0.992 0.000 0.004 0.004 0.000
#> GSM955045 2 0.4539 0.4821 0.000 0.660 0.320 0.012 0.008
#> GSM955046 3 0.1788 0.6882 0.008 0.004 0.932 0.056 0.000
#> GSM955047 1 0.0865 0.8815 0.972 0.004 0.000 0.024 0.000
#> GSM955050 1 0.5567 0.2428 0.480 0.020 0.032 0.468 0.000
#> GSM955052 3 0.3491 0.5807 0.000 0.228 0.768 0.004 0.000
#> GSM955053 1 0.0162 0.8821 0.996 0.000 0.000 0.004 0.000
#> GSM955056 2 0.4491 0.5128 0.000 0.652 0.328 0.020 0.000
#> GSM955058 5 0.6288 0.3141 0.000 0.304 0.180 0.000 0.516
#> GSM955059 3 0.1717 0.7025 0.004 0.052 0.936 0.008 0.000
#> GSM955060 1 0.0955 0.8805 0.968 0.004 0.000 0.028 0.000
#> GSM955061 5 0.3170 0.6636 0.000 0.124 0.024 0.004 0.848
#> GSM955065 1 0.1012 0.8765 0.968 0.000 0.012 0.020 0.000
#> GSM955066 3 0.3642 0.6523 0.124 0.004 0.824 0.048 0.000
#> GSM955067 1 0.4081 0.6361 0.696 0.004 0.000 0.296 0.004
#> GSM955073 3 0.2448 0.6918 0.000 0.088 0.892 0.020 0.000
#> GSM955074 1 0.0833 0.8814 0.976 0.004 0.000 0.004 0.016
#> GSM955076 4 0.3932 0.5462 0.000 0.328 0.000 0.672 0.000
#> GSM955078 2 0.4557 0.5110 0.000 0.760 0.004 0.132 0.104
#> GSM955083 1 0.5639 0.5385 0.628 0.000 0.048 0.032 0.292
#> GSM955084 5 0.1493 0.6190 0.000 0.024 0.000 0.028 0.948
#> GSM955086 2 0.5750 0.4836 0.144 0.696 0.108 0.052 0.000
#> GSM955091 2 0.4577 0.3944 0.000 0.676 0.024 0.296 0.004
#> GSM955092 2 0.2825 0.6085 0.000 0.860 0.124 0.016 0.000
#> GSM955093 3 0.2775 0.6883 0.004 0.100 0.876 0.020 0.000
#> GSM955098 4 0.2463 0.6987 0.004 0.100 0.008 0.888 0.000
#> GSM955099 2 0.4129 0.5221 0.000 0.756 0.040 0.204 0.000
#> GSM955100 1 0.0794 0.8803 0.972 0.000 0.000 0.028 0.000
#> GSM955103 3 0.3750 0.5623 0.000 0.232 0.756 0.012 0.000
#> GSM955104 3 0.5096 0.4488 0.320 0.024 0.636 0.020 0.000
#> GSM955106 5 0.4904 0.4476 0.000 0.036 0.316 0.004 0.644
#> GSM955000 1 0.0451 0.8825 0.988 0.000 0.004 0.008 0.000
#> GSM955006 1 0.0703 0.8810 0.976 0.000 0.000 0.024 0.000
#> GSM955007 3 0.0955 0.7024 0.000 0.028 0.968 0.004 0.000
#> GSM955010 3 0.5823 0.4152 0.268 0.008 0.612 0.112 0.000
#> GSM955014 1 0.1571 0.8658 0.936 0.004 0.000 0.060 0.000
#> GSM955018 3 0.5312 0.1889 0.016 0.388 0.568 0.028 0.000
#> GSM955020 1 0.0162 0.8816 0.996 0.000 0.000 0.004 0.000
#> GSM955024 3 0.2136 0.6917 0.000 0.088 0.904 0.008 0.000
#> GSM955026 4 0.4338 0.6640 0.008 0.300 0.000 0.684 0.008
#> GSM955031 2 0.6742 -0.1344 0.296 0.412 0.000 0.292 0.000
#> GSM955038 4 0.3614 0.5790 0.108 0.036 0.004 0.840 0.012
#> GSM955040 1 0.4973 0.6726 0.712 0.004 0.092 0.192 0.000
#> GSM955044 3 0.6988 0.0989 0.000 0.044 0.440 0.392 0.124
#> GSM955051 1 0.1571 0.8648 0.936 0.004 0.000 0.060 0.000
#> GSM955055 2 0.2153 0.5646 0.000 0.916 0.040 0.044 0.000
#> GSM955057 1 0.1168 0.8774 0.960 0.008 0.000 0.032 0.000
#> GSM955062 2 0.3565 0.6005 0.000 0.800 0.176 0.024 0.000
#> GSM955063 3 0.1502 0.7008 0.000 0.056 0.940 0.004 0.000
#> GSM955068 4 0.3700 0.6980 0.000 0.240 0.000 0.752 0.008
#> GSM955069 3 0.3956 0.6652 0.068 0.096 0.820 0.016 0.000
#> GSM955070 3 0.5269 0.5494 0.000 0.120 0.688 0.188 0.004
#> GSM955071 1 0.5391 0.6244 0.688 0.008 0.140 0.164 0.000
#> GSM955077 2 0.5372 0.2505 0.284 0.640 0.000 0.068 0.008
#> GSM955080 5 0.5556 0.3014 0.000 0.404 0.072 0.000 0.524
#> GSM955081 2 0.5150 0.5329 0.000 0.692 0.136 0.172 0.000
#> GSM955082 2 0.4420 0.5281 0.000 0.712 0.260 0.016 0.012
#> GSM955085 2 0.2956 0.5434 0.000 0.872 0.020 0.096 0.012
#> GSM955090 1 0.0854 0.8815 0.976 0.004 0.000 0.008 0.012
#> GSM955094 3 0.5548 0.5301 0.000 0.084 0.668 0.228 0.020
#> GSM955096 2 0.3757 0.5837 0.000 0.772 0.208 0.020 0.000
#> GSM955102 3 0.3463 0.6321 0.156 0.008 0.820 0.016 0.000
#> GSM955105 1 0.7365 -0.1561 0.416 0.284 0.268 0.032 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 4 0.4582 0.6620 0.000 0.008 0.256 0.676 0.000 0.060
#> GSM955008 3 0.4164 0.4336 0.000 0.040 0.756 0.028 0.000 0.176
#> GSM955016 1 0.3097 0.8047 0.852 0.000 0.016 0.020 0.104 0.008
#> GSM955019 6 0.5406 0.3534 0.000 0.260 0.136 0.008 0.000 0.596
#> GSM955022 3 0.3023 0.3402 0.000 0.000 0.768 0.232 0.000 0.000
#> GSM955023 3 0.3564 0.4745 0.000 0.040 0.808 0.136 0.000 0.016
#> GSM955027 2 0.5771 0.2202 0.000 0.508 0.248 0.000 0.000 0.244
#> GSM955043 3 0.6028 -0.1879 0.000 0.012 0.472 0.340 0.176 0.000
#> GSM955048 1 0.1889 0.8455 0.920 0.004 0.000 0.056 0.000 0.020
#> GSM955049 3 0.5927 -0.1081 0.000 0.192 0.464 0.004 0.000 0.340
#> GSM955054 3 0.7518 -0.1402 0.000 0.148 0.336 0.240 0.000 0.276
#> GSM955064 3 0.6258 0.2233 0.000 0.032 0.512 0.192 0.000 0.264
#> GSM955072 2 0.5188 0.2104 0.000 0.528 0.020 0.032 0.008 0.412
#> GSM955075 5 0.4891 0.3737 0.000 0.360 0.060 0.004 0.576 0.000
#> GSM955079 3 0.7118 -0.0317 0.112 0.084 0.460 0.020 0.004 0.320
#> GSM955087 1 0.1381 0.8411 0.952 0.000 0.020 0.020 0.004 0.004
#> GSM955088 2 0.6336 0.2268 0.024 0.572 0.228 0.144 0.000 0.032
#> GSM955089 1 0.1686 0.8436 0.940 0.000 0.016 0.024 0.004 0.016
#> GSM955095 2 0.6193 0.0859 0.004 0.504 0.172 0.020 0.300 0.000
#> GSM955097 5 0.0291 0.6516 0.004 0.004 0.000 0.000 0.992 0.000
#> GSM955101 6 0.5253 0.1081 0.000 0.032 0.456 0.036 0.000 0.476
#> GSM954999 1 0.3943 0.7836 0.824 0.004 0.072 0.048 0.024 0.028
#> GSM955001 2 0.4700 0.4998 0.000 0.716 0.144 0.008 0.004 0.128
#> GSM955003 6 0.6621 0.3558 0.000 0.140 0.256 0.092 0.000 0.512
#> GSM955004 5 0.3482 0.5139 0.000 0.316 0.000 0.000 0.684 0.000
#> GSM955005 3 0.6239 0.0665 0.340 0.000 0.480 0.144 0.000 0.036
#> GSM955009 2 0.1624 0.4465 0.000 0.936 0.004 0.040 0.000 0.020
#> GSM955011 1 0.1464 0.8479 0.944 0.004 0.000 0.036 0.000 0.016
#> GSM955012 3 0.5666 0.1625 0.000 0.020 0.560 0.008 0.328 0.084
#> GSM955013 3 0.2988 0.4581 0.016 0.000 0.836 0.140 0.004 0.004
#> GSM955015 4 0.5559 0.5233 0.000 0.028 0.376 0.524 0.000 0.072
#> GSM955017 1 0.2785 0.8222 0.852 0.008 0.004 0.128 0.000 0.008
#> GSM955021 2 0.5924 0.3411 0.000 0.568 0.088 0.060 0.000 0.284
#> GSM955025 2 0.6757 0.0556 0.124 0.508 0.000 0.260 0.004 0.104
#> GSM955028 1 0.1232 0.8436 0.956 0.000 0.016 0.024 0.004 0.000
#> GSM955029 2 0.6137 0.2661 0.000 0.528 0.160 0.004 0.284 0.024
#> GSM955030 3 0.5169 0.0182 0.120 0.000 0.588 0.292 0.000 0.000
#> GSM955032 3 0.6331 -0.1702 0.000 0.304 0.464 0.024 0.000 0.208
#> GSM955033 4 0.3879 0.6566 0.004 0.008 0.176 0.772 0.000 0.040
#> GSM955034 1 0.1015 0.8483 0.968 0.004 0.012 0.012 0.000 0.004
#> GSM955035 6 0.5250 0.4028 0.000 0.008 0.172 0.184 0.000 0.636
#> GSM955036 3 0.4908 -0.2010 0.028 0.000 0.528 0.424 0.020 0.000
#> GSM955037 1 0.2980 0.7816 0.848 0.000 0.116 0.028 0.004 0.004
#> GSM955039 4 0.5308 0.5583 0.004 0.000 0.352 0.544 0.000 0.100
#> GSM955041 3 0.3025 0.4942 0.000 0.000 0.820 0.024 0.000 0.156
#> GSM955042 1 0.0767 0.8506 0.976 0.000 0.000 0.012 0.004 0.008
#> GSM955045 2 0.3805 0.4773 0.004 0.664 0.328 0.000 0.004 0.000
#> GSM955046 3 0.4169 0.0385 0.008 0.004 0.620 0.364 0.000 0.004
#> GSM955047 1 0.3576 0.7996 0.820 0.044 0.000 0.108 0.000 0.028
#> GSM955050 4 0.5579 0.1507 0.228 0.016 0.000 0.600 0.000 0.156
#> GSM955052 3 0.3515 0.4948 0.000 0.064 0.828 0.024 0.000 0.084
#> GSM955053 1 0.1059 0.8434 0.964 0.000 0.016 0.016 0.004 0.000
#> GSM955056 2 0.5706 0.3693 0.000 0.480 0.392 0.012 0.000 0.116
#> GSM955058 5 0.6538 0.3763 0.000 0.080 0.248 0.004 0.536 0.132
#> GSM955059 3 0.3163 0.4218 0.008 0.012 0.808 0.172 0.000 0.000
#> GSM955060 1 0.1806 0.8379 0.908 0.004 0.000 0.088 0.000 0.000
#> GSM955061 5 0.3411 0.6599 0.000 0.016 0.092 0.004 0.836 0.052
#> GSM955065 1 0.1528 0.8445 0.944 0.000 0.016 0.028 0.000 0.012
#> GSM955066 3 0.6349 -0.3169 0.140 0.016 0.424 0.404 0.000 0.016
#> GSM955067 1 0.5333 0.6032 0.612 0.004 0.000 0.180 0.000 0.204
#> GSM955073 3 0.1643 0.5315 0.000 0.000 0.924 0.008 0.000 0.068
#> GSM955074 1 0.2781 0.8185 0.872 0.004 0.000 0.032 0.084 0.008
#> GSM955076 6 0.3182 0.4138 0.000 0.124 0.008 0.036 0.000 0.832
#> GSM955078 2 0.6289 0.3412 0.000 0.532 0.064 0.008 0.088 0.308
#> GSM955083 1 0.6360 0.0801 0.416 0.008 0.008 0.144 0.412 0.012
#> GSM955084 5 0.1719 0.6512 0.000 0.032 0.000 0.004 0.932 0.032
#> GSM955086 2 0.6725 0.4070 0.080 0.524 0.268 0.016 0.000 0.112
#> GSM955091 6 0.5278 0.3452 0.000 0.192 0.204 0.000 0.000 0.604
#> GSM955092 2 0.4599 0.4545 0.000 0.684 0.212 0.000 0.000 0.104
#> GSM955093 3 0.2546 0.5267 0.012 0.000 0.888 0.040 0.000 0.060
#> GSM955098 6 0.4153 0.3252 0.000 0.024 0.000 0.340 0.000 0.636
#> GSM955099 6 0.5810 0.1466 0.000 0.380 0.160 0.004 0.000 0.456
#> GSM955100 1 0.3690 0.7880 0.808 0.024 0.008 0.136 0.000 0.024
#> GSM955103 3 0.4965 0.3856 0.012 0.084 0.724 0.016 0.008 0.156
#> GSM955104 3 0.4622 0.2438 0.404 0.000 0.564 0.020 0.004 0.008
#> GSM955106 5 0.3918 0.5771 0.000 0.020 0.248 0.004 0.724 0.004
#> GSM955000 1 0.1699 0.8496 0.936 0.000 0.016 0.032 0.000 0.016
#> GSM955006 1 0.2703 0.8238 0.860 0.008 0.000 0.116 0.000 0.016
#> GSM955007 3 0.3232 0.4340 0.000 0.020 0.812 0.160 0.000 0.008
#> GSM955010 4 0.4895 0.5698 0.068 0.000 0.328 0.600 0.000 0.004
#> GSM955014 1 0.3334 0.8088 0.820 0.004 0.000 0.124 0.000 0.052
#> GSM955018 3 0.5700 0.3416 0.136 0.124 0.672 0.020 0.000 0.048
#> GSM955020 1 0.0551 0.8492 0.984 0.000 0.000 0.008 0.004 0.004
#> GSM955024 3 0.2257 0.5185 0.000 0.040 0.904 0.048 0.000 0.008
#> GSM955026 6 0.5671 0.4004 0.012 0.172 0.000 0.240 0.000 0.576
#> GSM955031 1 0.7691 -0.1383 0.300 0.256 0.000 0.216 0.000 0.228
#> GSM955038 6 0.5942 0.1619 0.140 0.008 0.000 0.340 0.008 0.504
#> GSM955040 4 0.4742 0.3335 0.236 0.020 0.020 0.696 0.000 0.028
#> GSM955044 4 0.7174 0.3376 0.000 0.008 0.168 0.444 0.100 0.280
#> GSM955051 1 0.2784 0.8324 0.872 0.004 0.000 0.048 0.004 0.072
#> GSM955055 2 0.2908 0.4958 0.000 0.864 0.048 0.012 0.000 0.076
#> GSM955057 1 0.2058 0.8441 0.908 0.008 0.000 0.072 0.000 0.012
#> GSM955062 2 0.4734 0.4889 0.000 0.692 0.224 0.024 0.000 0.060
#> GSM955063 3 0.2100 0.4693 0.000 0.004 0.884 0.112 0.000 0.000
#> GSM955068 6 0.4102 0.4134 0.000 0.080 0.000 0.164 0.004 0.752
#> GSM955069 3 0.4460 0.4808 0.128 0.040 0.756 0.076 0.000 0.000
#> GSM955070 4 0.5200 0.6470 0.000 0.048 0.280 0.628 0.000 0.044
#> GSM955071 1 0.6239 0.0918 0.448 0.000 0.076 0.400 0.000 0.076
#> GSM955077 2 0.6050 0.1072 0.292 0.540 0.000 0.128 0.000 0.040
#> GSM955080 2 0.6168 0.1021 0.000 0.528 0.068 0.024 0.340 0.040
#> GSM955081 6 0.6565 0.1990 0.000 0.356 0.168 0.048 0.000 0.428
#> GSM955082 3 0.6464 -0.2063 0.024 0.412 0.432 0.020 0.004 0.108
#> GSM955085 2 0.2992 0.4285 0.000 0.852 0.016 0.016 0.004 0.112
#> GSM955090 1 0.2594 0.8402 0.892 0.004 0.000 0.040 0.048 0.016
#> GSM955094 4 0.4189 0.6652 0.000 0.016 0.232 0.724 0.004 0.024
#> GSM955096 2 0.5910 0.2914 0.004 0.460 0.376 0.004 0.000 0.156
#> GSM955102 3 0.4686 0.3744 0.092 0.012 0.716 0.176 0.000 0.004
#> GSM955105 3 0.7364 -0.0489 0.228 0.220 0.452 0.016 0.004 0.080
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> MAD:NMF 104 0.152 2
#> MAD:NMF 95 0.517 3
#> MAD:NMF 85 0.878 4
#> MAD:NMF 76 0.489 5
#> MAD:NMF 40 0.767 6
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 31589 rows and 108 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 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 0.978 0.949 0.974 0.3412 0.684 0.684
#> 3 3 0.432 0.726 0.821 0.6255 0.760 0.649
#> 4 4 0.471 0.660 0.784 0.1730 0.971 0.935
#> 5 5 0.463 0.419 0.615 0.0772 0.783 0.516
#> 6 6 0.547 0.589 0.748 0.0704 0.876 0.592
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
#> GSM955002 2 0.0000 0.969 0.000 1.000
#> GSM955008 2 0.0000 0.969 0.000 1.000
#> GSM955016 2 0.9460 0.493 0.364 0.636
#> GSM955019 2 0.0000 0.969 0.000 1.000
#> GSM955022 2 0.0000 0.969 0.000 1.000
#> GSM955023 2 0.0000 0.969 0.000 1.000
#> GSM955027 2 0.0000 0.969 0.000 1.000
#> GSM955043 2 0.0000 0.969 0.000 1.000
#> GSM955048 1 0.0000 0.995 1.000 0.000
#> GSM955049 2 0.0000 0.969 0.000 1.000
#> GSM955054 2 0.0000 0.969 0.000 1.000
#> GSM955064 2 0.0000 0.969 0.000 1.000
#> GSM955072 2 0.0000 0.969 0.000 1.000
#> GSM955075 2 0.0000 0.969 0.000 1.000
#> GSM955079 2 0.0938 0.963 0.012 0.988
#> GSM955087 1 0.0000 0.995 1.000 0.000
#> GSM955088 2 0.0000 0.969 0.000 1.000
#> GSM955089 1 0.0000 0.995 1.000 0.000
#> GSM955095 2 0.0000 0.969 0.000 1.000
#> GSM955097 2 0.0000 0.969 0.000 1.000
#> GSM955101 2 0.0000 0.969 0.000 1.000
#> GSM954999 2 0.3879 0.920 0.076 0.924
#> GSM955001 2 0.0000 0.969 0.000 1.000
#> GSM955003 2 0.0000 0.969 0.000 1.000
#> GSM955004 2 0.0000 0.969 0.000 1.000
#> GSM955005 2 0.3114 0.935 0.056 0.944
#> GSM955009 2 0.0000 0.969 0.000 1.000
#> GSM955011 1 0.3114 0.939 0.944 0.056
#> GSM955012 2 0.0000 0.969 0.000 1.000
#> GSM955013 2 0.2778 0.940 0.048 0.952
#> GSM955015 2 0.0000 0.969 0.000 1.000
#> GSM955017 1 0.0938 0.987 0.988 0.012
#> GSM955021 2 0.0000 0.969 0.000 1.000
#> GSM955025 2 0.0000 0.969 0.000 1.000
#> GSM955028 1 0.0000 0.995 1.000 0.000
#> GSM955029 2 0.0000 0.969 0.000 1.000
#> GSM955030 2 0.4161 0.913 0.084 0.916
#> GSM955032 2 0.0000 0.969 0.000 1.000
#> GSM955033 2 0.3114 0.935 0.056 0.944
#> GSM955034 1 0.0000 0.995 1.000 0.000
#> GSM955035 2 0.0000 0.969 0.000 1.000
#> GSM955036 2 0.2236 0.949 0.036 0.964
#> GSM955037 1 0.0938 0.987 0.988 0.012
#> GSM955039 2 0.3114 0.935 0.056 0.944
#> GSM955041 2 0.0000 0.969 0.000 1.000
#> GSM955042 2 0.9460 0.493 0.364 0.636
#> GSM955045 2 0.0000 0.969 0.000 1.000
#> GSM955046 2 0.0000 0.969 0.000 1.000
#> GSM955047 1 0.0000 0.995 1.000 0.000
#> GSM955050 2 0.4431 0.905 0.092 0.908
#> GSM955052 2 0.0000 0.969 0.000 1.000
#> GSM955053 1 0.0000 0.995 1.000 0.000
#> GSM955056 2 0.0000 0.969 0.000 1.000
#> GSM955058 2 0.0000 0.969 0.000 1.000
#> GSM955059 2 0.0000 0.969 0.000 1.000
#> GSM955060 1 0.0376 0.993 0.996 0.004
#> GSM955061 2 0.0000 0.969 0.000 1.000
#> GSM955065 1 0.0000 0.995 1.000 0.000
#> GSM955066 2 0.0000 0.969 0.000 1.000
#> GSM955067 1 0.0000 0.995 1.000 0.000
#> GSM955073 2 0.0000 0.969 0.000 1.000
#> GSM955074 1 0.0376 0.993 0.996 0.004
#> GSM955076 2 0.0000 0.969 0.000 1.000
#> GSM955078 2 0.0000 0.969 0.000 1.000
#> GSM955083 2 0.3114 0.935 0.056 0.944
#> GSM955084 2 0.0000 0.969 0.000 1.000
#> GSM955086 2 0.0938 0.963 0.012 0.988
#> GSM955091 2 0.0000 0.969 0.000 1.000
#> GSM955092 2 0.0000 0.969 0.000 1.000
#> GSM955093 2 0.0000 0.969 0.000 1.000
#> GSM955098 2 0.0000 0.969 0.000 1.000
#> GSM955099 2 0.0000 0.969 0.000 1.000
#> GSM955100 2 0.9209 0.554 0.336 0.664
#> GSM955103 2 0.0000 0.969 0.000 1.000
#> GSM955104 2 0.5946 0.852 0.144 0.856
#> GSM955106 2 0.0000 0.969 0.000 1.000
#> GSM955000 1 0.0938 0.987 0.988 0.012
#> GSM955006 1 0.0000 0.995 1.000 0.000
#> GSM955007 2 0.0000 0.969 0.000 1.000
#> GSM955010 2 0.3584 0.926 0.068 0.932
#> GSM955014 1 0.0000 0.995 1.000 0.000
#> GSM955018 2 0.0000 0.969 0.000 1.000
#> GSM955020 1 0.0000 0.995 1.000 0.000
#> GSM955024 2 0.0000 0.969 0.000 1.000
#> GSM955026 2 0.0000 0.969 0.000 1.000
#> GSM955031 2 0.4431 0.905 0.092 0.908
#> GSM955038 2 0.7602 0.754 0.220 0.780
#> GSM955040 2 0.7950 0.724 0.240 0.760
#> GSM955044 2 0.0000 0.969 0.000 1.000
#> GSM955051 1 0.0000 0.995 1.000 0.000
#> GSM955055 2 0.0000 0.969 0.000 1.000
#> GSM955057 1 0.0000 0.995 1.000 0.000
#> GSM955062 2 0.0000 0.969 0.000 1.000
#> GSM955063 2 0.0000 0.969 0.000 1.000
#> GSM955068 2 0.0000 0.969 0.000 1.000
#> GSM955069 2 0.2778 0.940 0.048 0.952
#> GSM955070 2 0.0000 0.969 0.000 1.000
#> GSM955071 2 0.4815 0.894 0.104 0.896
#> GSM955077 2 0.4431 0.905 0.092 0.908
#> GSM955080 2 0.0000 0.969 0.000 1.000
#> GSM955081 2 0.0000 0.969 0.000 1.000
#> GSM955082 2 0.0000 0.969 0.000 1.000
#> GSM955085 2 0.0000 0.969 0.000 1.000
#> GSM955090 1 0.0000 0.995 1.000 0.000
#> GSM955094 2 0.0000 0.969 0.000 1.000
#> GSM955096 2 0.0000 0.969 0.000 1.000
#> GSM955102 2 0.1414 0.958 0.020 0.980
#> GSM955105 2 0.1414 0.959 0.020 0.980
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.5733 0.578 0.000 0.676 0.324
#> GSM955008 2 0.3412 0.762 0.000 0.876 0.124
#> GSM955016 3 0.7458 0.564 0.244 0.084 0.672
#> GSM955019 2 0.2625 0.764 0.000 0.916 0.084
#> GSM955022 2 0.4842 0.702 0.000 0.776 0.224
#> GSM955023 2 0.4842 0.702 0.000 0.776 0.224
#> GSM955027 2 0.0000 0.761 0.000 1.000 0.000
#> GSM955043 2 0.0000 0.761 0.000 1.000 0.000
#> GSM955048 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955049 2 0.3412 0.763 0.000 0.876 0.124
#> GSM955054 2 0.3412 0.762 0.000 0.876 0.124
#> GSM955064 2 0.3412 0.756 0.000 0.876 0.124
#> GSM955072 2 0.5216 0.653 0.000 0.740 0.260
#> GSM955075 2 0.0000 0.761 0.000 1.000 0.000
#> GSM955079 2 0.5926 0.523 0.000 0.644 0.356
#> GSM955087 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955088 2 0.1643 0.770 0.000 0.956 0.044
#> GSM955089 1 0.0892 0.968 0.980 0.000 0.020
#> GSM955095 2 0.4062 0.734 0.000 0.836 0.164
#> GSM955097 2 0.5785 0.538 0.000 0.668 0.332
#> GSM955101 2 0.5733 0.579 0.000 0.676 0.324
#> GSM954999 3 0.6252 0.762 0.024 0.268 0.708
#> GSM955001 2 0.0237 0.763 0.000 0.996 0.004
#> GSM955003 2 0.3412 0.762 0.000 0.876 0.124
#> GSM955004 2 0.3879 0.609 0.000 0.848 0.152
#> GSM955005 3 0.5884 0.755 0.012 0.272 0.716
#> GSM955009 2 0.3879 0.609 0.000 0.848 0.152
#> GSM955011 1 0.3816 0.890 0.852 0.000 0.148
#> GSM955012 2 0.0424 0.765 0.000 0.992 0.008
#> GSM955013 3 0.6404 0.627 0.012 0.344 0.644
#> GSM955015 2 0.4931 0.683 0.000 0.768 0.232
#> GSM955017 1 0.2878 0.936 0.904 0.000 0.096
#> GSM955021 2 0.0237 0.763 0.000 0.996 0.004
#> GSM955025 2 0.5016 0.594 0.000 0.760 0.240
#> GSM955028 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955029 2 0.0000 0.761 0.000 1.000 0.000
#> GSM955030 3 0.5414 0.782 0.016 0.212 0.772
#> GSM955032 2 0.6045 0.464 0.000 0.620 0.380
#> GSM955033 3 0.5848 0.763 0.012 0.268 0.720
#> GSM955034 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955035 2 0.4399 0.721 0.000 0.812 0.188
#> GSM955036 3 0.5431 0.739 0.000 0.284 0.716
#> GSM955037 1 0.2878 0.936 0.904 0.000 0.096
#> GSM955039 3 0.5953 0.747 0.012 0.280 0.708
#> GSM955041 2 0.4399 0.721 0.000 0.812 0.188
#> GSM955042 3 0.7458 0.564 0.244 0.084 0.672
#> GSM955045 2 0.1289 0.770 0.000 0.968 0.032
#> GSM955046 2 0.6260 0.236 0.000 0.552 0.448
#> GSM955047 1 0.1529 0.962 0.960 0.000 0.040
#> GSM955050 3 0.5363 0.706 0.000 0.276 0.724
#> GSM955052 2 0.3412 0.762 0.000 0.876 0.124
#> GSM955053 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955056 2 0.5529 0.616 0.000 0.704 0.296
#> GSM955058 2 0.0424 0.765 0.000 0.992 0.008
#> GSM955059 2 0.5529 0.616 0.000 0.704 0.296
#> GSM955060 1 0.2448 0.948 0.924 0.000 0.076
#> GSM955061 2 0.0424 0.765 0.000 0.992 0.008
#> GSM955065 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955066 2 0.5988 0.467 0.000 0.632 0.368
#> GSM955067 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955073 2 0.5016 0.673 0.000 0.760 0.240
#> GSM955074 1 0.2625 0.943 0.916 0.000 0.084
#> GSM955076 2 0.6126 0.408 0.000 0.600 0.400
#> GSM955078 2 0.0892 0.768 0.000 0.980 0.020
#> GSM955083 3 0.5919 0.756 0.012 0.276 0.712
#> GSM955084 2 0.3879 0.609 0.000 0.848 0.152
#> GSM955086 2 0.5926 0.523 0.000 0.644 0.356
#> GSM955091 2 0.1289 0.770 0.000 0.968 0.032
#> GSM955092 2 0.0424 0.765 0.000 0.992 0.008
#> GSM955093 2 0.6235 0.293 0.000 0.564 0.436
#> GSM955098 2 0.3879 0.609 0.000 0.848 0.152
#> GSM955099 2 0.0237 0.759 0.000 0.996 0.004
#> GSM955100 3 0.7610 0.633 0.216 0.108 0.676
#> GSM955103 2 0.6215 0.319 0.000 0.572 0.428
#> GSM955104 3 0.5659 0.766 0.052 0.152 0.796
#> GSM955106 2 0.5835 0.546 0.000 0.660 0.340
#> GSM955000 1 0.2878 0.936 0.904 0.000 0.096
#> GSM955006 1 0.1860 0.959 0.948 0.000 0.052
#> GSM955007 2 0.4399 0.721 0.000 0.812 0.188
#> GSM955010 3 0.5406 0.779 0.012 0.224 0.764
#> GSM955014 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955018 2 0.6111 0.428 0.000 0.604 0.396
#> GSM955020 1 0.0424 0.969 0.992 0.000 0.008
#> GSM955024 2 0.3686 0.758 0.000 0.860 0.140
#> GSM955026 2 0.5650 0.597 0.000 0.688 0.312
#> GSM955031 3 0.5363 0.706 0.000 0.276 0.724
#> GSM955038 3 0.5892 0.726 0.100 0.104 0.796
#> GSM955040 3 0.6634 0.709 0.144 0.104 0.752
#> GSM955044 2 0.1163 0.769 0.000 0.972 0.028
#> GSM955051 1 0.1031 0.966 0.976 0.000 0.024
#> GSM955055 2 0.0000 0.761 0.000 1.000 0.000
#> GSM955057 1 0.0000 0.969 1.000 0.000 0.000
#> GSM955062 2 0.0424 0.765 0.000 0.992 0.008
#> GSM955063 2 0.4002 0.741 0.000 0.840 0.160
#> GSM955068 2 0.5216 0.653 0.000 0.740 0.260
#> GSM955069 3 0.6404 0.627 0.012 0.344 0.644
#> GSM955070 2 0.0892 0.765 0.000 0.980 0.020
#> GSM955071 3 0.5728 0.781 0.032 0.196 0.772
#> GSM955077 3 0.5363 0.706 0.000 0.276 0.724
#> GSM955080 2 0.5621 0.590 0.000 0.692 0.308
#> GSM955081 2 0.4178 0.729 0.000 0.828 0.172
#> GSM955082 2 0.0747 0.767 0.000 0.984 0.016
#> GSM955085 2 0.0424 0.765 0.000 0.992 0.008
#> GSM955090 1 0.0424 0.969 0.992 0.000 0.008
#> GSM955094 2 0.0237 0.759 0.000 0.996 0.004
#> GSM955096 2 0.3267 0.766 0.000 0.884 0.116
#> GSM955102 3 0.6225 0.319 0.000 0.432 0.568
#> GSM955105 2 0.6204 0.337 0.000 0.576 0.424
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.7158 0.3275 0.000 0.512 0.340 0.148
#> GSM955008 2 0.3611 0.7365 0.000 0.860 0.060 0.080
#> GSM955016 3 0.5690 0.5272 0.060 0.000 0.672 0.268
#> GSM955019 2 0.3453 0.7338 0.000 0.868 0.080 0.052
#> GSM955022 2 0.5351 0.6791 0.000 0.744 0.152 0.104
#> GSM955023 2 0.5351 0.6791 0.000 0.744 0.152 0.104
#> GSM955027 2 0.1022 0.7375 0.000 0.968 0.000 0.032
#> GSM955043 2 0.1118 0.7366 0.000 0.964 0.000 0.036
#> GSM955048 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955049 2 0.3679 0.7366 0.000 0.856 0.060 0.084
#> GSM955054 2 0.3611 0.7365 0.000 0.860 0.060 0.080
#> GSM955064 2 0.3647 0.7313 0.000 0.852 0.040 0.108
#> GSM955072 2 0.6352 0.5533 0.000 0.632 0.260 0.108
#> GSM955075 2 0.1389 0.7335 0.000 0.952 0.000 0.048
#> GSM955079 2 0.6961 0.4460 0.000 0.548 0.316 0.136
#> GSM955087 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955088 2 0.2032 0.7446 0.000 0.936 0.028 0.036
#> GSM955089 1 0.1733 0.9048 0.948 0.000 0.028 0.024
#> GSM955095 2 0.4735 0.6906 0.000 0.784 0.148 0.068
#> GSM955097 2 0.6660 0.5092 0.000 0.592 0.288 0.120
#> GSM955101 2 0.6702 0.5659 0.000 0.616 0.216 0.168
#> GSM954999 3 0.4458 0.7350 0.000 0.116 0.808 0.076
#> GSM955001 2 0.0921 0.7404 0.000 0.972 0.000 0.028
#> GSM955003 2 0.3611 0.7365 0.000 0.860 0.060 0.080
#> GSM955004 2 0.5168 0.2551 0.000 0.500 0.004 0.496
#> GSM955005 3 0.3972 0.7347 0.000 0.080 0.840 0.080
#> GSM955009 2 0.5168 0.2551 0.000 0.500 0.004 0.496
#> GSM955011 1 0.5977 0.7979 0.680 0.000 0.104 0.216
#> GSM955012 2 0.0707 0.7407 0.000 0.980 0.000 0.020
#> GSM955013 3 0.5050 0.6723 0.000 0.152 0.764 0.084
#> GSM955015 2 0.5250 0.6668 0.000 0.736 0.068 0.196
#> GSM955017 1 0.5609 0.8279 0.712 0.000 0.088 0.200
#> GSM955021 2 0.0921 0.7386 0.000 0.972 0.000 0.028
#> GSM955025 2 0.6615 0.3261 0.000 0.512 0.084 0.404
#> GSM955028 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955029 2 0.1022 0.7375 0.000 0.968 0.000 0.032
#> GSM955030 3 0.2589 0.7424 0.000 0.044 0.912 0.044
#> GSM955032 2 0.7281 0.4497 0.000 0.532 0.272 0.196
#> GSM955033 3 0.4336 0.7137 0.000 0.128 0.812 0.060
#> GSM955034 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955035 2 0.4686 0.6987 0.000 0.788 0.068 0.144
#> GSM955036 3 0.6243 0.6180 0.000 0.160 0.668 0.172
#> GSM955037 1 0.5609 0.8279 0.712 0.000 0.088 0.200
#> GSM955039 3 0.4106 0.7314 0.000 0.084 0.832 0.084
#> GSM955041 2 0.4686 0.6987 0.000 0.788 0.068 0.144
#> GSM955042 3 0.5690 0.5272 0.060 0.000 0.672 0.268
#> GSM955045 2 0.1584 0.7473 0.000 0.952 0.012 0.036
#> GSM955046 2 0.7606 0.3136 0.000 0.468 0.304 0.228
#> GSM955047 1 0.3653 0.8903 0.844 0.000 0.028 0.128
#> GSM955050 3 0.5628 0.6971 0.000 0.132 0.724 0.144
#> GSM955052 2 0.3611 0.7365 0.000 0.860 0.060 0.080
#> GSM955053 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955056 2 0.6357 0.6115 0.000 0.656 0.160 0.184
#> GSM955058 2 0.0707 0.7407 0.000 0.980 0.000 0.020
#> GSM955059 2 0.6360 0.6103 0.000 0.656 0.164 0.180
#> GSM955060 1 0.4996 0.8518 0.752 0.000 0.056 0.192
#> GSM955061 2 0.0707 0.7407 0.000 0.980 0.000 0.020
#> GSM955065 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955066 2 0.7221 0.4517 0.000 0.540 0.272 0.188
#> GSM955067 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955073 2 0.5356 0.6595 0.000 0.728 0.072 0.200
#> GSM955074 1 0.5250 0.8430 0.736 0.000 0.068 0.196
#> GSM955076 2 0.7321 0.3733 0.000 0.500 0.328 0.172
#> GSM955078 2 0.1913 0.7438 0.000 0.940 0.020 0.040
#> GSM955083 3 0.4440 0.7078 0.000 0.136 0.804 0.060
#> GSM955084 2 0.5168 0.2551 0.000 0.500 0.004 0.496
#> GSM955086 2 0.6904 0.4570 0.000 0.556 0.312 0.132
#> GSM955091 2 0.1610 0.7475 0.000 0.952 0.016 0.032
#> GSM955092 2 0.1635 0.7421 0.000 0.948 0.008 0.044
#> GSM955093 2 0.7565 0.3163 0.000 0.472 0.312 0.216
#> GSM955098 2 0.5168 0.2551 0.000 0.500 0.004 0.496
#> GSM955099 2 0.1557 0.7295 0.000 0.944 0.000 0.056
#> GSM955100 3 0.5113 0.5544 0.032 0.000 0.704 0.264
#> GSM955103 3 0.7206 -0.0641 0.000 0.400 0.460 0.140
#> GSM955104 3 0.4431 0.7339 0.020 0.032 0.820 0.128
#> GSM955106 2 0.7033 0.2931 0.000 0.508 0.364 0.128
#> GSM955000 1 0.5609 0.8279 0.712 0.000 0.088 0.200
#> GSM955006 1 0.4010 0.8809 0.816 0.000 0.028 0.156
#> GSM955007 2 0.4686 0.6987 0.000 0.788 0.068 0.144
#> GSM955010 3 0.2670 0.7496 0.000 0.072 0.904 0.024
#> GSM955014 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955018 2 0.7385 0.4041 0.000 0.508 0.296 0.196
#> GSM955020 1 0.2973 0.8975 0.884 0.000 0.020 0.096
#> GSM955024 2 0.3858 0.7360 0.000 0.844 0.056 0.100
#> GSM955026 2 0.7164 0.3256 0.000 0.524 0.320 0.156
#> GSM955031 3 0.5628 0.6971 0.000 0.132 0.724 0.144
#> GSM955038 3 0.3625 0.6503 0.012 0.000 0.828 0.160
#> GSM955040 3 0.4245 0.6367 0.064 0.000 0.820 0.116
#> GSM955044 2 0.1211 0.7426 0.000 0.960 0.000 0.040
#> GSM955051 1 0.3307 0.8955 0.868 0.000 0.028 0.104
#> GSM955055 2 0.1022 0.7375 0.000 0.968 0.000 0.032
#> GSM955057 1 0.0000 0.9057 1.000 0.000 0.000 0.000
#> GSM955062 2 0.0921 0.7412 0.000 0.972 0.000 0.028
#> GSM955063 2 0.4336 0.7160 0.000 0.812 0.060 0.128
#> GSM955068 2 0.6352 0.5533 0.000 0.632 0.260 0.108
#> GSM955069 3 0.5050 0.6723 0.000 0.152 0.764 0.084
#> GSM955070 2 0.2048 0.7318 0.000 0.928 0.008 0.064
#> GSM955071 3 0.2466 0.7275 0.000 0.028 0.916 0.056
#> GSM955077 3 0.5628 0.6971 0.000 0.132 0.724 0.144
#> GSM955080 2 0.6432 0.5748 0.000 0.636 0.236 0.128
#> GSM955081 2 0.4898 0.6833 0.000 0.772 0.156 0.072
#> GSM955082 2 0.1584 0.7424 0.000 0.952 0.012 0.036
#> GSM955085 2 0.1489 0.7408 0.000 0.952 0.004 0.044
#> GSM955090 1 0.1042 0.9055 0.972 0.000 0.020 0.008
#> GSM955094 2 0.1474 0.7352 0.000 0.948 0.000 0.052
#> GSM955096 2 0.3679 0.7375 0.000 0.856 0.084 0.060
#> GSM955102 3 0.7641 0.0840 0.000 0.344 0.440 0.216
#> GSM955105 3 0.7113 -0.0292 0.000 0.416 0.456 0.128
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.758 0.33735 0.000 0.332 0.404 0.208 0.056
#> GSM955008 2 0.499 0.36642 0.000 0.520 0.456 0.016 0.008
#> GSM955016 4 0.385 0.51735 0.004 0.000 0.016 0.768 0.212
#> GSM955019 2 0.513 0.38747 0.000 0.548 0.420 0.016 0.016
#> GSM955022 3 0.461 0.18456 0.000 0.360 0.620 0.020 0.000
#> GSM955023 3 0.461 0.18456 0.000 0.360 0.620 0.020 0.000
#> GSM955027 2 0.384 0.64222 0.000 0.716 0.280 0.000 0.004
#> GSM955043 2 0.381 0.64083 0.000 0.720 0.276 0.000 0.004
#> GSM955048 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955049 2 0.489 0.34593 0.000 0.512 0.468 0.016 0.004
#> GSM955054 2 0.499 0.35903 0.000 0.516 0.460 0.016 0.008
#> GSM955064 2 0.463 0.43068 0.000 0.572 0.416 0.008 0.004
#> GSM955072 3 0.605 0.40925 0.000 0.300 0.592 0.080 0.028
#> GSM955075 2 0.394 0.62955 0.000 0.728 0.260 0.000 0.012
#> GSM955079 3 0.515 0.51255 0.000 0.196 0.696 0.104 0.004
#> GSM955087 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955088 2 0.459 0.55989 0.000 0.624 0.360 0.008 0.008
#> GSM955089 1 0.491 -0.66554 0.560 0.000 0.000 0.028 0.412
#> GSM955095 3 0.564 -0.06673 0.000 0.448 0.496 0.032 0.024
#> GSM955097 3 0.464 0.49219 0.000 0.200 0.736 0.056 0.008
#> GSM955101 3 0.365 0.43416 0.000 0.228 0.764 0.004 0.004
#> GSM954999 4 0.457 0.68687 0.000 0.008 0.328 0.652 0.012
#> GSM955001 2 0.373 0.64287 0.000 0.712 0.288 0.000 0.000
#> GSM955003 2 0.488 0.37353 0.000 0.524 0.456 0.016 0.004
#> GSM955004 2 0.465 0.04141 0.000 0.632 0.012 0.008 0.348
#> GSM955005 4 0.423 0.66923 0.000 0.000 0.424 0.576 0.000
#> GSM955009 2 0.465 0.04141 0.000 0.632 0.012 0.008 0.348
#> GSM955011 1 0.642 -0.39418 0.420 0.000 0.000 0.172 0.408
#> GSM955012 2 0.373 0.64163 0.000 0.712 0.288 0.000 0.000
#> GSM955013 4 0.456 0.56373 0.000 0.008 0.488 0.504 0.000
#> GSM955015 3 0.479 0.00826 0.000 0.392 0.588 0.012 0.008
#> GSM955017 1 0.564 0.26704 0.632 0.000 0.000 0.152 0.216
#> GSM955021 2 0.386 0.64233 0.000 0.712 0.284 0.000 0.004
#> GSM955025 2 0.636 -0.07292 0.000 0.556 0.252 0.008 0.184
#> GSM955028 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955029 2 0.384 0.64222 0.000 0.716 0.280 0.000 0.004
#> GSM955030 4 0.358 0.73144 0.000 0.000 0.240 0.756 0.004
#> GSM955032 3 0.351 0.53242 0.000 0.132 0.828 0.036 0.004
#> GSM955033 4 0.464 0.62091 0.000 0.004 0.424 0.564 0.008
#> GSM955034 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955035 3 0.481 -0.20851 0.000 0.468 0.516 0.008 0.008
#> GSM955036 3 0.465 -0.49944 0.000 0.004 0.560 0.428 0.008
#> GSM955037 1 0.564 0.26704 0.632 0.000 0.000 0.152 0.216
#> GSM955039 4 0.425 0.66333 0.000 0.000 0.432 0.568 0.000
#> GSM955041 3 0.481 -0.20851 0.000 0.468 0.516 0.008 0.008
#> GSM955042 4 0.385 0.51735 0.004 0.000 0.016 0.768 0.212
#> GSM955045 2 0.428 0.54695 0.000 0.616 0.380 0.000 0.004
#> GSM955046 3 0.255 0.48939 0.000 0.036 0.904 0.048 0.012
#> GSM955047 5 0.497 0.85642 0.408 0.000 0.000 0.032 0.560
#> GSM955050 4 0.570 0.62811 0.000 0.156 0.100 0.696 0.048
#> GSM955052 2 0.488 0.37353 0.000 0.524 0.456 0.016 0.004
#> GSM955053 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955056 3 0.394 0.38066 0.000 0.260 0.728 0.012 0.000
#> GSM955058 2 0.373 0.64163 0.000 0.712 0.288 0.000 0.000
#> GSM955059 3 0.394 0.38582 0.000 0.260 0.728 0.012 0.000
#> GSM955060 1 0.594 -0.40076 0.492 0.000 0.000 0.108 0.400
#> GSM955061 2 0.373 0.64163 0.000 0.712 0.288 0.000 0.000
#> GSM955065 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955066 3 0.421 0.51255 0.000 0.140 0.788 0.064 0.008
#> GSM955067 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955073 3 0.477 0.02457 0.000 0.384 0.596 0.012 0.008
#> GSM955074 1 0.541 0.28074 0.656 0.000 0.000 0.128 0.216
#> GSM955076 3 0.380 0.53907 0.000 0.100 0.820 0.076 0.004
#> GSM955078 2 0.462 0.58182 0.000 0.636 0.344 0.004 0.016
#> GSM955083 4 0.466 0.61080 0.000 0.004 0.436 0.552 0.008
#> GSM955084 2 0.465 0.04141 0.000 0.632 0.012 0.008 0.348
#> GSM955086 3 0.514 0.51007 0.000 0.200 0.696 0.100 0.004
#> GSM955091 2 0.430 0.59654 0.000 0.640 0.352 0.000 0.008
#> GSM955092 2 0.430 0.61726 0.000 0.672 0.316 0.004 0.008
#> GSM955093 3 0.215 0.51211 0.000 0.032 0.920 0.044 0.004
#> GSM955098 2 0.465 0.04141 0.000 0.632 0.012 0.008 0.348
#> GSM955099 2 0.401 0.62271 0.000 0.728 0.256 0.000 0.016
#> GSM955100 4 0.398 0.55618 0.016 0.000 0.024 0.792 0.168
#> GSM955103 3 0.420 0.35925 0.000 0.044 0.752 0.204 0.000
#> GSM955104 4 0.458 0.71306 0.000 0.000 0.268 0.692 0.040
#> GSM955106 3 0.716 0.36691 0.000 0.324 0.440 0.208 0.028
#> GSM955000 1 0.564 0.26704 0.632 0.000 0.000 0.152 0.216
#> GSM955006 5 0.532 0.81474 0.428 0.000 0.000 0.052 0.520
#> GSM955007 3 0.481 -0.20851 0.000 0.468 0.516 0.008 0.008
#> GSM955010 4 0.412 0.71217 0.000 0.000 0.336 0.660 0.004
#> GSM955014 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955018 3 0.314 0.53621 0.000 0.096 0.860 0.040 0.004
#> GSM955020 5 0.474 0.86362 0.472 0.000 0.000 0.016 0.512
#> GSM955024 2 0.489 0.28349 0.000 0.492 0.488 0.016 0.004
#> GSM955026 3 0.766 0.30320 0.000 0.352 0.384 0.200 0.064
#> GSM955031 4 0.570 0.62811 0.000 0.156 0.100 0.696 0.048
#> GSM955038 4 0.226 0.63196 0.000 0.000 0.028 0.908 0.064
#> GSM955040 4 0.361 0.64246 0.004 0.000 0.064 0.832 0.100
#> GSM955044 2 0.397 0.62946 0.000 0.692 0.304 0.000 0.004
#> GSM955051 5 0.496 0.88405 0.452 0.000 0.000 0.028 0.520
#> GSM955055 2 0.384 0.64222 0.000 0.716 0.280 0.000 0.004
#> GSM955057 1 0.000 0.59537 1.000 0.000 0.000 0.000 0.000
#> GSM955062 2 0.375 0.64165 0.000 0.708 0.292 0.000 0.000
#> GSM955063 2 0.481 0.27251 0.000 0.504 0.480 0.008 0.008
#> GSM955068 3 0.605 0.40925 0.000 0.300 0.592 0.080 0.028
#> GSM955069 4 0.456 0.56373 0.000 0.008 0.488 0.504 0.000
#> GSM955070 2 0.434 0.61762 0.000 0.712 0.264 0.008 0.016
#> GSM955071 4 0.321 0.72212 0.000 0.000 0.180 0.812 0.008
#> GSM955077 4 0.570 0.62811 0.000 0.156 0.100 0.696 0.048
#> GSM955080 3 0.483 0.47334 0.000 0.220 0.720 0.040 0.020
#> GSM955081 3 0.562 0.02676 0.000 0.428 0.516 0.032 0.024
#> GSM955082 2 0.432 0.61775 0.000 0.668 0.320 0.004 0.008
#> GSM955085 2 0.428 0.61958 0.000 0.676 0.312 0.004 0.008
#> GSM955090 1 0.451 -0.65521 0.560 0.000 0.000 0.008 0.432
#> GSM955094 2 0.409 0.63355 0.000 0.704 0.284 0.000 0.012
#> GSM955096 2 0.505 0.28347 0.000 0.500 0.472 0.024 0.004
#> GSM955102 3 0.377 0.19856 0.000 0.016 0.788 0.188 0.008
#> GSM955105 3 0.698 0.30950 0.000 0.232 0.456 0.296 0.016
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 3 0.7424 0.4295 0.000 0.320 0.344 0.156 0.180 0.000
#> GSM955008 2 0.3636 0.6452 0.000 0.764 0.208 0.012 0.016 0.000
#> GSM955016 4 0.3801 0.4797 0.000 0.000 0.012 0.740 0.016 0.232
#> GSM955019 2 0.4201 0.5503 0.000 0.732 0.196 0.004 0.068 0.000
#> GSM955022 2 0.4406 -0.0293 0.000 0.516 0.464 0.012 0.008 0.000
#> GSM955023 2 0.4406 -0.0293 0.000 0.516 0.464 0.012 0.008 0.000
#> GSM955027 2 0.0603 0.7548 0.000 0.980 0.004 0.000 0.016 0.000
#> GSM955043 2 0.0891 0.7526 0.000 0.968 0.008 0.000 0.024 0.000
#> GSM955048 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955049 2 0.3712 0.6189 0.000 0.744 0.232 0.012 0.012 0.000
#> GSM955054 2 0.3665 0.6425 0.000 0.760 0.212 0.012 0.016 0.000
#> GSM955064 2 0.3279 0.6801 0.000 0.816 0.148 0.008 0.028 0.000
#> GSM955072 3 0.6200 0.5220 0.000 0.336 0.504 0.060 0.100 0.000
#> GSM955075 2 0.1007 0.7473 0.000 0.956 0.000 0.000 0.044 0.000
#> GSM955079 3 0.5643 0.5953 0.000 0.284 0.592 0.072 0.052 0.000
#> GSM955087 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955088 2 0.2954 0.7094 0.000 0.852 0.096 0.004 0.048 0.000
#> GSM955089 6 0.3812 0.7162 0.264 0.000 0.000 0.024 0.000 0.712
#> GSM955095 2 0.5304 0.1836 0.000 0.588 0.316 0.020 0.076 0.000
#> GSM955097 3 0.5440 0.5946 0.000 0.248 0.640 0.064 0.040 0.008
#> GSM955101 3 0.4284 0.3427 0.000 0.392 0.588 0.004 0.016 0.000
#> GSM954999 4 0.3964 0.6391 0.000 0.008 0.308 0.676 0.004 0.004
#> GSM955001 2 0.0508 0.7564 0.000 0.984 0.004 0.000 0.012 0.000
#> GSM955003 2 0.3547 0.6479 0.000 0.768 0.208 0.012 0.012 0.000
#> GSM955004 5 0.2491 0.8742 0.000 0.164 0.000 0.000 0.836 0.000
#> GSM955005 4 0.3890 0.5796 0.000 0.004 0.400 0.596 0.000 0.000
#> GSM955009 5 0.2491 0.8742 0.000 0.164 0.000 0.000 0.836 0.000
#> GSM955011 6 0.5468 0.3796 0.292 0.000 0.000 0.140 0.004 0.564
#> GSM955012 2 0.0622 0.7565 0.000 0.980 0.012 0.000 0.008 0.000
#> GSM955013 4 0.4175 0.4685 0.000 0.012 0.464 0.524 0.000 0.000
#> GSM955015 2 0.4406 0.4261 0.000 0.640 0.324 0.008 0.028 0.000
#> GSM955017 1 0.5937 0.4334 0.584 0.000 0.020 0.108 0.020 0.268
#> GSM955021 2 0.0508 0.7554 0.000 0.984 0.004 0.000 0.012 0.000
#> GSM955025 5 0.5814 0.3950 0.000 0.248 0.224 0.004 0.524 0.000
#> GSM955028 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955029 2 0.0603 0.7548 0.000 0.980 0.004 0.000 0.016 0.000
#> GSM955030 4 0.2823 0.6812 0.000 0.000 0.204 0.796 0.000 0.000
#> GSM955032 3 0.4035 0.6102 0.000 0.256 0.712 0.016 0.016 0.000
#> GSM955033 4 0.4409 0.5766 0.000 0.004 0.380 0.596 0.008 0.012
#> GSM955034 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955035 2 0.4015 0.5685 0.000 0.720 0.244 0.008 0.028 0.000
#> GSM955036 3 0.4869 -0.4508 0.000 0.008 0.512 0.448 0.020 0.012
#> GSM955037 1 0.5937 0.4334 0.584 0.000 0.020 0.108 0.020 0.268
#> GSM955039 4 0.3907 0.5709 0.000 0.004 0.408 0.588 0.000 0.000
#> GSM955041 2 0.4015 0.5685 0.000 0.720 0.244 0.008 0.028 0.000
#> GSM955042 4 0.3801 0.4797 0.000 0.000 0.012 0.740 0.016 0.232
#> GSM955045 2 0.2346 0.7228 0.000 0.868 0.124 0.000 0.008 0.000
#> GSM955046 3 0.3748 0.4188 0.000 0.084 0.824 0.056 0.024 0.012
#> GSM955047 6 0.2265 0.7426 0.076 0.000 0.004 0.000 0.024 0.896
#> GSM955050 4 0.5678 0.4749 0.000 0.088 0.092 0.648 0.172 0.000
#> GSM955052 2 0.3547 0.6479 0.000 0.768 0.208 0.012 0.012 0.000
#> GSM955053 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955056 3 0.3923 0.2751 0.000 0.416 0.580 0.004 0.000 0.000
#> GSM955058 2 0.0622 0.7565 0.000 0.980 0.012 0.000 0.008 0.000
#> GSM955059 3 0.4049 0.2891 0.000 0.412 0.580 0.004 0.004 0.000
#> GSM955060 6 0.4981 0.3590 0.340 0.000 0.000 0.072 0.004 0.584
#> GSM955061 2 0.0622 0.7565 0.000 0.980 0.012 0.000 0.008 0.000
#> GSM955065 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955066 3 0.5047 0.5591 0.000 0.184 0.704 0.056 0.048 0.008
#> GSM955067 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955073 2 0.4436 0.4100 0.000 0.632 0.332 0.008 0.028 0.000
#> GSM955074 1 0.5693 0.4573 0.608 0.000 0.020 0.084 0.020 0.268
#> GSM955076 3 0.3932 0.6083 0.000 0.156 0.780 0.048 0.012 0.004
#> GSM955078 2 0.2609 0.7203 0.000 0.868 0.096 0.000 0.036 0.000
#> GSM955083 4 0.4437 0.5655 0.000 0.004 0.392 0.584 0.008 0.012
#> GSM955084 5 0.2491 0.8742 0.000 0.164 0.000 0.000 0.836 0.000
#> GSM955086 3 0.5642 0.5861 0.000 0.296 0.584 0.068 0.052 0.000
#> GSM955091 2 0.2112 0.7438 0.000 0.896 0.088 0.000 0.016 0.000
#> GSM955092 2 0.1995 0.7454 0.000 0.912 0.052 0.000 0.036 0.000
#> GSM955093 3 0.2838 0.5440 0.000 0.116 0.852 0.028 0.004 0.000
#> GSM955098 5 0.2562 0.8688 0.000 0.172 0.000 0.000 0.828 0.000
#> GSM955099 2 0.1204 0.7417 0.000 0.944 0.000 0.000 0.056 0.000
#> GSM955100 4 0.4061 0.5206 0.016 0.000 0.020 0.764 0.016 0.184
#> GSM955103 3 0.4461 0.4217 0.000 0.104 0.704 0.192 0.000 0.000
#> GSM955104 4 0.4108 0.6608 0.000 0.000 0.260 0.704 0.028 0.008
#> GSM955106 3 0.7254 0.4404 0.000 0.336 0.368 0.152 0.144 0.000
#> GSM955000 1 0.5937 0.4334 0.584 0.000 0.020 0.108 0.020 0.268
#> GSM955006 6 0.2988 0.7455 0.144 0.000 0.000 0.028 0.000 0.828
#> GSM955007 2 0.4015 0.5685 0.000 0.720 0.244 0.008 0.028 0.000
#> GSM955010 4 0.3634 0.6552 0.000 0.000 0.296 0.696 0.000 0.008
#> GSM955014 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955018 3 0.3564 0.6289 0.000 0.200 0.772 0.020 0.008 0.000
#> GSM955020 6 0.2859 0.7705 0.156 0.000 0.000 0.000 0.016 0.828
#> GSM955024 2 0.4056 0.5562 0.000 0.696 0.276 0.012 0.016 0.000
#> GSM955026 3 0.7459 0.3852 0.000 0.320 0.332 0.152 0.196 0.000
#> GSM955031 4 0.5678 0.4749 0.000 0.088 0.092 0.648 0.172 0.000
#> GSM955038 4 0.2972 0.5957 0.000 0.000 0.032 0.868 0.052 0.048
#> GSM955040 4 0.3427 0.6148 0.000 0.000 0.056 0.828 0.016 0.100
#> GSM955044 2 0.1480 0.7537 0.000 0.940 0.040 0.000 0.020 0.000
#> GSM955051 6 0.2623 0.7680 0.132 0.000 0.000 0.000 0.016 0.852
#> GSM955055 2 0.0603 0.7548 0.000 0.980 0.004 0.000 0.016 0.000
#> GSM955057 1 0.0000 0.8127 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955062 2 0.0806 0.7589 0.000 0.972 0.020 0.000 0.008 0.000
#> GSM955063 2 0.3820 0.6231 0.000 0.756 0.204 0.008 0.032 0.000
#> GSM955068 3 0.6200 0.5220 0.000 0.336 0.504 0.060 0.100 0.000
#> GSM955069 4 0.4175 0.4685 0.000 0.012 0.464 0.524 0.000 0.000
#> GSM955070 2 0.1615 0.7406 0.000 0.928 0.004 0.004 0.064 0.000
#> GSM955071 4 0.2482 0.6866 0.000 0.000 0.148 0.848 0.000 0.004
#> GSM955077 4 0.5678 0.4749 0.000 0.088 0.092 0.648 0.172 0.000
#> GSM955080 3 0.4991 0.5846 0.000 0.276 0.652 0.020 0.040 0.012
#> GSM955081 2 0.5466 0.0769 0.000 0.556 0.340 0.020 0.084 0.000
#> GSM955082 2 0.1970 0.7445 0.000 0.912 0.060 0.000 0.028 0.000
#> GSM955085 2 0.1930 0.7453 0.000 0.916 0.048 0.000 0.036 0.000
#> GSM955090 6 0.3695 0.6876 0.272 0.000 0.000 0.000 0.016 0.712
#> GSM955094 2 0.1492 0.7489 0.000 0.940 0.024 0.000 0.036 0.000
#> GSM955096 2 0.4273 0.5266 0.000 0.696 0.260 0.012 0.032 0.000
#> GSM955102 3 0.4741 0.1342 0.000 0.048 0.716 0.200 0.024 0.012
#> GSM955105 3 0.7329 0.4480 0.000 0.244 0.396 0.232 0.128 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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> ATC:hclust 106 0.824 2
#> ATC:hclust 99 0.195 3
#> ATC:hclust 89 0.148 4
#> ATC:hclust 61 0.550 5
#> ATC:hclust 77 0.241 6
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 31589 rows and 108 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 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 0.986 0.994 0.3703 0.631 0.631
#> 3 3 0.866 0.889 0.952 0.7087 0.695 0.528
#> 4 4 0.594 0.608 0.766 0.1292 0.930 0.811
#> 5 5 0.627 0.600 0.754 0.0762 0.877 0.639
#> 6 6 0.656 0.473 0.658 0.0490 0.873 0.558
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
#> GSM955002 2 0.000 0.995 0.000 1.000
#> GSM955008 2 0.000 0.995 0.000 1.000
#> GSM955016 1 0.000 0.988 1.000 0.000
#> GSM955019 2 0.000 0.995 0.000 1.000
#> GSM955022 2 0.000 0.995 0.000 1.000
#> GSM955023 2 0.000 0.995 0.000 1.000
#> GSM955027 2 0.000 0.995 0.000 1.000
#> GSM955043 2 0.000 0.995 0.000 1.000
#> GSM955048 1 0.000 0.988 1.000 0.000
#> GSM955049 2 0.000 0.995 0.000 1.000
#> GSM955054 2 0.000 0.995 0.000 1.000
#> GSM955064 2 0.000 0.995 0.000 1.000
#> GSM955072 2 0.000 0.995 0.000 1.000
#> GSM955075 2 0.000 0.995 0.000 1.000
#> GSM955079 2 0.000 0.995 0.000 1.000
#> GSM955087 1 0.000 0.988 1.000 0.000
#> GSM955088 2 0.000 0.995 0.000 1.000
#> GSM955089 1 0.000 0.988 1.000 0.000
#> GSM955095 2 0.000 0.995 0.000 1.000
#> GSM955097 2 0.000 0.995 0.000 1.000
#> GSM955101 2 0.000 0.995 0.000 1.000
#> GSM954999 2 0.000 0.995 0.000 1.000
#> GSM955001 2 0.000 0.995 0.000 1.000
#> GSM955003 2 0.000 0.995 0.000 1.000
#> GSM955004 2 0.000 0.995 0.000 1.000
#> GSM955005 2 0.000 0.995 0.000 1.000
#> GSM955009 2 0.000 0.995 0.000 1.000
#> GSM955011 1 0.000 0.988 1.000 0.000
#> GSM955012 2 0.000 0.995 0.000 1.000
#> GSM955013 2 0.000 0.995 0.000 1.000
#> GSM955015 2 0.000 0.995 0.000 1.000
#> GSM955017 1 0.000 0.988 1.000 0.000
#> GSM955021 2 0.000 0.995 0.000 1.000
#> GSM955025 2 0.000 0.995 0.000 1.000
#> GSM955028 1 0.000 0.988 1.000 0.000
#> GSM955029 2 0.000 0.995 0.000 1.000
#> GSM955030 2 0.689 0.773 0.184 0.816
#> GSM955032 2 0.000 0.995 0.000 1.000
#> GSM955033 2 0.000 0.995 0.000 1.000
#> GSM955034 1 0.000 0.988 1.000 0.000
#> GSM955035 2 0.000 0.995 0.000 1.000
#> GSM955036 2 0.000 0.995 0.000 1.000
#> GSM955037 1 0.000 0.988 1.000 0.000
#> GSM955039 2 0.000 0.995 0.000 1.000
#> GSM955041 2 0.000 0.995 0.000 1.000
#> GSM955042 1 0.000 0.988 1.000 0.000
#> GSM955045 2 0.000 0.995 0.000 1.000
#> GSM955046 2 0.000 0.995 0.000 1.000
#> GSM955047 1 0.000 0.988 1.000 0.000
#> GSM955050 2 0.000 0.995 0.000 1.000
#> GSM955052 2 0.000 0.995 0.000 1.000
#> GSM955053 1 0.000 0.988 1.000 0.000
#> GSM955056 2 0.000 0.995 0.000 1.000
#> GSM955058 2 0.000 0.995 0.000 1.000
#> GSM955059 2 0.000 0.995 0.000 1.000
#> GSM955060 1 0.000 0.988 1.000 0.000
#> GSM955061 2 0.000 0.995 0.000 1.000
#> GSM955065 1 0.000 0.988 1.000 0.000
#> GSM955066 2 0.000 0.995 0.000 1.000
#> GSM955067 1 0.000 0.988 1.000 0.000
#> GSM955073 2 0.000 0.995 0.000 1.000
#> GSM955074 1 0.000 0.988 1.000 0.000
#> GSM955076 2 0.000 0.995 0.000 1.000
#> GSM955078 2 0.000 0.995 0.000 1.000
#> GSM955083 2 0.000 0.995 0.000 1.000
#> GSM955084 2 0.000 0.995 0.000 1.000
#> GSM955086 2 0.000 0.995 0.000 1.000
#> GSM955091 2 0.000 0.995 0.000 1.000
#> GSM955092 2 0.000 0.995 0.000 1.000
#> GSM955093 2 0.000 0.995 0.000 1.000
#> GSM955098 2 0.000 0.995 0.000 1.000
#> GSM955099 2 0.000 0.995 0.000 1.000
#> GSM955100 1 0.000 0.988 1.000 0.000
#> GSM955103 2 0.000 0.995 0.000 1.000
#> GSM955104 2 0.714 0.755 0.196 0.804
#> GSM955106 2 0.000 0.995 0.000 1.000
#> GSM955000 1 0.000 0.988 1.000 0.000
#> GSM955006 1 0.000 0.988 1.000 0.000
#> GSM955007 2 0.000 0.995 0.000 1.000
#> GSM955010 2 0.000 0.995 0.000 1.000
#> GSM955014 1 0.000 0.988 1.000 0.000
#> GSM955018 2 0.000 0.995 0.000 1.000
#> GSM955020 1 0.000 0.988 1.000 0.000
#> GSM955024 2 0.000 0.995 0.000 1.000
#> GSM955026 2 0.000 0.995 0.000 1.000
#> GSM955031 2 0.000 0.995 0.000 1.000
#> GSM955038 1 0.000 0.988 1.000 0.000
#> GSM955040 1 0.866 0.590 0.712 0.288
#> GSM955044 2 0.000 0.995 0.000 1.000
#> GSM955051 1 0.000 0.988 1.000 0.000
#> GSM955055 2 0.000 0.995 0.000 1.000
#> GSM955057 1 0.000 0.988 1.000 0.000
#> GSM955062 2 0.000 0.995 0.000 1.000
#> GSM955063 2 0.000 0.995 0.000 1.000
#> GSM955068 2 0.000 0.995 0.000 1.000
#> GSM955069 2 0.000 0.995 0.000 1.000
#> GSM955070 2 0.000 0.995 0.000 1.000
#> GSM955071 2 0.000 0.995 0.000 1.000
#> GSM955077 2 0.000 0.995 0.000 1.000
#> GSM955080 2 0.000 0.995 0.000 1.000
#> GSM955081 2 0.000 0.995 0.000 1.000
#> GSM955082 2 0.000 0.995 0.000 1.000
#> GSM955085 2 0.000 0.995 0.000 1.000
#> GSM955090 1 0.000 0.988 1.000 0.000
#> GSM955094 2 0.000 0.995 0.000 1.000
#> GSM955096 2 0.000 0.995 0.000 1.000
#> GSM955102 2 0.000 0.995 0.000 1.000
#> GSM955105 2 0.000 0.995 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.2796 0.8420 0.000 0.092 0.908
#> GSM955008 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955016 1 0.5216 0.6921 0.740 0.000 0.260
#> GSM955019 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955022 3 0.6140 0.4170 0.000 0.404 0.596
#> GSM955023 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955027 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955043 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955048 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955049 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955054 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955064 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955072 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955075 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955079 3 0.4346 0.7796 0.000 0.184 0.816
#> GSM955087 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955088 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955089 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955095 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955097 3 0.4555 0.7687 0.000 0.200 0.800
#> GSM955101 3 0.6291 0.2308 0.000 0.468 0.532
#> GSM954999 3 0.0000 0.8814 0.000 0.000 1.000
#> GSM955001 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955003 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955004 2 0.0237 0.9750 0.000 0.996 0.004
#> GSM955005 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955009 2 0.0237 0.9750 0.000 0.996 0.004
#> GSM955011 1 0.6192 0.3714 0.580 0.000 0.420
#> GSM955012 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955013 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955015 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955017 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955021 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955025 2 0.0237 0.9750 0.000 0.996 0.004
#> GSM955028 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955029 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955030 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955032 3 0.5178 0.7053 0.000 0.256 0.744
#> GSM955033 3 0.0000 0.8814 0.000 0.000 1.000
#> GSM955034 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955035 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955036 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955037 1 0.2711 0.8850 0.912 0.000 0.088
#> GSM955039 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955041 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955042 3 0.6154 0.1595 0.408 0.000 0.592
#> GSM955045 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955046 3 0.0592 0.8804 0.000 0.012 0.988
#> GSM955047 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955050 3 0.0000 0.8814 0.000 0.000 1.000
#> GSM955052 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955053 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955056 2 0.5397 0.5620 0.000 0.720 0.280
#> GSM955058 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955059 3 0.5016 0.7280 0.000 0.240 0.760
#> GSM955060 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955061 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955065 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955066 3 0.5016 0.7280 0.000 0.240 0.760
#> GSM955067 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955073 2 0.3686 0.8095 0.000 0.860 0.140
#> GSM955074 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955076 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955078 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955083 3 0.0000 0.8814 0.000 0.000 1.000
#> GSM955084 2 0.0237 0.9750 0.000 0.996 0.004
#> GSM955086 3 0.2796 0.8430 0.000 0.092 0.908
#> GSM955091 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955092 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955093 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955098 2 0.0237 0.9750 0.000 0.996 0.004
#> GSM955099 2 0.0237 0.9750 0.000 0.996 0.004
#> GSM955100 1 0.5363 0.6684 0.724 0.000 0.276
#> GSM955103 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955104 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955106 2 0.0237 0.9750 0.000 0.996 0.004
#> GSM955000 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955006 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955007 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955010 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955014 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955018 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955020 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955024 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955026 2 0.2261 0.9062 0.000 0.932 0.068
#> GSM955031 3 0.0000 0.8814 0.000 0.000 1.000
#> GSM955038 3 0.0000 0.8814 0.000 0.000 1.000
#> GSM955040 3 0.0000 0.8814 0.000 0.000 1.000
#> GSM955044 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955051 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955055 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955057 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955062 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955063 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955068 2 0.6252 0.0586 0.000 0.556 0.444
#> GSM955069 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955070 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955071 3 0.0000 0.8814 0.000 0.000 1.000
#> GSM955077 3 0.4887 0.7289 0.000 0.228 0.772
#> GSM955080 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955081 3 0.4346 0.7796 0.000 0.184 0.816
#> GSM955082 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955085 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955090 1 0.0000 0.9526 1.000 0.000 0.000
#> GSM955094 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955096 2 0.0000 0.9779 0.000 1.000 0.000
#> GSM955102 3 0.0237 0.8831 0.000 0.004 0.996
#> GSM955105 3 0.2711 0.8437 0.000 0.088 0.912
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 3 0.4856 0.4843 0.000 0.084 0.780 0.136
#> GSM955008 2 0.4008 0.7130 0.000 0.756 0.244 0.000
#> GSM955016 4 0.5434 0.6423 0.188 0.000 0.084 0.728
#> GSM955019 2 0.5174 0.7312 0.000 0.760 0.116 0.124
#> GSM955022 3 0.3123 0.5014 0.000 0.156 0.844 0.000
#> GSM955023 2 0.4605 0.6420 0.000 0.664 0.336 0.000
#> GSM955027 2 0.0000 0.8126 0.000 1.000 0.000 0.000
#> GSM955043 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955048 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955049 2 0.3801 0.7275 0.000 0.780 0.220 0.000
#> GSM955054 2 0.3975 0.7162 0.000 0.760 0.240 0.000
#> GSM955064 2 0.0817 0.8115 0.000 0.976 0.024 0.000
#> GSM955072 2 0.5747 0.7030 0.000 0.704 0.196 0.100
#> GSM955075 2 0.2928 0.7802 0.000 0.880 0.012 0.108
#> GSM955079 3 0.1576 0.5807 0.000 0.048 0.948 0.004
#> GSM955087 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955088 2 0.3051 0.7863 0.000 0.884 0.028 0.088
#> GSM955089 1 0.1118 0.8925 0.964 0.000 0.000 0.036
#> GSM955095 2 0.6770 0.5545 0.000 0.580 0.292 0.128
#> GSM955097 3 0.4539 0.3813 0.000 0.272 0.720 0.008
#> GSM955101 3 0.3688 0.4529 0.000 0.208 0.792 0.000
#> GSM954999 3 0.4992 -0.1071 0.000 0.000 0.524 0.476
#> GSM955001 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955003 2 0.3975 0.7162 0.000 0.760 0.240 0.000
#> GSM955004 2 0.4720 0.6830 0.000 0.720 0.016 0.264
#> GSM955005 3 0.4972 -0.0571 0.000 0.000 0.544 0.456
#> GSM955009 2 0.4606 0.6848 0.000 0.724 0.012 0.264
#> GSM955011 4 0.5470 0.6752 0.148 0.000 0.116 0.736
#> GSM955012 2 0.0592 0.8126 0.000 0.984 0.016 0.000
#> GSM955013 3 0.2281 0.5255 0.000 0.000 0.904 0.096
#> GSM955015 2 0.4454 0.6479 0.000 0.692 0.308 0.000
#> GSM955017 1 0.3123 0.8543 0.844 0.000 0.000 0.156
#> GSM955021 2 0.0707 0.8120 0.000 0.980 0.020 0.000
#> GSM955025 2 0.6402 0.6135 0.000 0.624 0.108 0.268
#> GSM955028 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955029 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955030 3 0.4994 -0.1348 0.000 0.000 0.520 0.480
#> GSM955032 3 0.2216 0.5549 0.000 0.092 0.908 0.000
#> GSM955033 3 0.4989 -0.0965 0.000 0.000 0.528 0.472
#> GSM955034 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955035 2 0.4304 0.6777 0.000 0.716 0.284 0.000
#> GSM955036 3 0.4855 0.0794 0.000 0.000 0.600 0.400
#> GSM955037 1 0.5816 0.4232 0.572 0.000 0.036 0.392
#> GSM955039 3 0.4817 0.1047 0.000 0.000 0.612 0.388
#> GSM955041 2 0.4040 0.7101 0.000 0.752 0.248 0.000
#> GSM955042 4 0.5440 0.6812 0.104 0.000 0.160 0.736
#> GSM955045 2 0.1474 0.8065 0.000 0.948 0.052 0.000
#> GSM955046 3 0.0895 0.5766 0.000 0.004 0.976 0.020
#> GSM955047 1 0.4103 0.7984 0.744 0.000 0.000 0.256
#> GSM955050 4 0.4830 0.4455 0.000 0.000 0.392 0.608
#> GSM955052 2 0.4008 0.7130 0.000 0.756 0.244 0.000
#> GSM955053 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955056 3 0.4933 -0.1552 0.000 0.432 0.568 0.000
#> GSM955058 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955059 3 0.1637 0.5758 0.000 0.060 0.940 0.000
#> GSM955060 1 0.3569 0.8400 0.804 0.000 0.000 0.196
#> GSM955061 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955065 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955066 3 0.1474 0.5778 0.000 0.052 0.948 0.000
#> GSM955067 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955073 2 0.4830 0.5038 0.000 0.608 0.392 0.000
#> GSM955074 1 0.3528 0.8416 0.808 0.000 0.000 0.192
#> GSM955076 3 0.0895 0.5770 0.000 0.004 0.976 0.020
#> GSM955078 2 0.2662 0.7923 0.000 0.900 0.016 0.084
#> GSM955083 3 0.4992 -0.1071 0.000 0.000 0.524 0.476
#> GSM955084 2 0.4720 0.6830 0.000 0.720 0.016 0.264
#> GSM955086 3 0.1388 0.5832 0.000 0.028 0.960 0.012
#> GSM955091 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955092 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955093 3 0.0895 0.5770 0.000 0.004 0.976 0.020
#> GSM955098 2 0.4748 0.6794 0.000 0.716 0.016 0.268
#> GSM955099 2 0.3764 0.7479 0.000 0.816 0.012 0.172
#> GSM955100 4 0.5434 0.6423 0.188 0.000 0.084 0.728
#> GSM955103 3 0.0895 0.5770 0.000 0.004 0.976 0.020
#> GSM955104 3 0.4998 -0.1620 0.000 0.000 0.512 0.488
#> GSM955106 2 0.5923 0.7051 0.000 0.696 0.176 0.128
#> GSM955000 1 0.3123 0.8543 0.844 0.000 0.000 0.156
#> GSM955006 1 0.4134 0.7946 0.740 0.000 0.000 0.260
#> GSM955007 2 0.4500 0.6372 0.000 0.684 0.316 0.000
#> GSM955010 3 0.4972 -0.0571 0.000 0.000 0.544 0.456
#> GSM955014 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955018 3 0.1406 0.5832 0.000 0.024 0.960 0.016
#> GSM955020 1 0.1637 0.8858 0.940 0.000 0.000 0.060
#> GSM955024 2 0.4193 0.6940 0.000 0.732 0.268 0.000
#> GSM955026 2 0.7445 0.4532 0.000 0.508 0.224 0.268
#> GSM955031 4 0.4933 0.3390 0.000 0.000 0.432 0.568
#> GSM955038 4 0.4250 0.6272 0.000 0.000 0.276 0.724
#> GSM955040 4 0.4406 0.6048 0.000 0.000 0.300 0.700
#> GSM955044 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955051 1 0.4072 0.8018 0.748 0.000 0.000 0.252
#> GSM955055 2 0.0188 0.8132 0.000 0.996 0.004 0.000
#> GSM955057 1 0.0000 0.8962 1.000 0.000 0.000 0.000
#> GSM955062 2 0.0921 0.8107 0.000 0.972 0.028 0.000
#> GSM955063 2 0.3726 0.7299 0.000 0.788 0.212 0.000
#> GSM955068 3 0.7806 -0.0736 0.000 0.324 0.412 0.264
#> GSM955069 3 0.4134 0.3207 0.000 0.000 0.740 0.260
#> GSM955070 2 0.0895 0.8094 0.000 0.976 0.004 0.020
#> GSM955071 3 0.4998 -0.1453 0.000 0.000 0.512 0.488
#> GSM955077 4 0.7049 0.2181 0.000 0.192 0.236 0.572
#> GSM955080 2 0.5857 0.5868 0.000 0.636 0.308 0.056
#> GSM955081 3 0.1854 0.5807 0.000 0.048 0.940 0.012
#> GSM955082 2 0.4499 0.7521 0.000 0.804 0.072 0.124
#> GSM955085 2 0.2480 0.7889 0.000 0.904 0.008 0.088
#> GSM955090 1 0.1118 0.8925 0.964 0.000 0.000 0.036
#> GSM955094 2 0.0657 0.8121 0.000 0.984 0.004 0.012
#> GSM955096 2 0.4624 0.6373 0.000 0.660 0.340 0.000
#> GSM955102 3 0.4730 0.1536 0.000 0.000 0.636 0.364
#> GSM955105 3 0.2131 0.5770 0.000 0.032 0.932 0.036
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.5235 0.6473 0.000 0.032 0.732 0.112 0.124
#> GSM955008 2 0.4840 0.6319 0.000 0.688 0.248 0.000 0.064
#> GSM955016 4 0.3583 0.5993 0.012 0.000 0.004 0.792 0.192
#> GSM955019 2 0.5659 0.1573 0.000 0.632 0.164 0.000 0.204
#> GSM955022 3 0.1399 0.7052 0.000 0.020 0.952 0.000 0.028
#> GSM955023 2 0.5523 0.5069 0.000 0.572 0.348 0.000 0.080
#> GSM955027 2 0.1732 0.5877 0.000 0.920 0.000 0.000 0.080
#> GSM955043 2 0.1671 0.5903 0.000 0.924 0.000 0.000 0.076
#> GSM955048 1 0.0609 0.8568 0.980 0.000 0.000 0.000 0.020
#> GSM955049 2 0.4349 0.6560 0.000 0.756 0.176 0.000 0.068
#> GSM955054 2 0.4788 0.6351 0.000 0.696 0.240 0.000 0.064
#> GSM955064 2 0.3586 0.6474 0.000 0.828 0.076 0.000 0.096
#> GSM955072 2 0.6515 -0.1927 0.000 0.440 0.364 0.000 0.196
#> GSM955075 2 0.3143 0.3877 0.000 0.796 0.000 0.000 0.204
#> GSM955079 3 0.2141 0.7214 0.000 0.016 0.916 0.004 0.064
#> GSM955087 1 0.0290 0.8586 0.992 0.000 0.008 0.000 0.000
#> GSM955088 2 0.4010 0.4770 0.000 0.792 0.072 0.000 0.136
#> GSM955089 1 0.2393 0.8488 0.900 0.000 0.004 0.016 0.080
#> GSM955095 3 0.6422 -0.1175 0.000 0.360 0.460 0.000 0.180
#> GSM955097 3 0.5840 0.5745 0.000 0.200 0.672 0.072 0.056
#> GSM955101 3 0.2193 0.6825 0.000 0.028 0.912 0.000 0.060
#> GSM954999 4 0.3562 0.6760 0.000 0.000 0.196 0.788 0.016
#> GSM955001 2 0.1732 0.5877 0.000 0.920 0.000 0.000 0.080
#> GSM955003 2 0.4762 0.6366 0.000 0.700 0.236 0.000 0.064
#> GSM955004 5 0.4517 0.8469 0.000 0.388 0.012 0.000 0.600
#> GSM955005 4 0.3671 0.6562 0.000 0.000 0.236 0.756 0.008
#> GSM955009 5 0.4192 0.8216 0.000 0.404 0.000 0.000 0.596
#> GSM955011 4 0.3618 0.5968 0.012 0.000 0.004 0.788 0.196
#> GSM955012 2 0.3375 0.6622 0.000 0.840 0.104 0.000 0.056
#> GSM955013 3 0.3961 0.6035 0.000 0.000 0.760 0.212 0.028
#> GSM955015 2 0.4937 0.6218 0.000 0.672 0.264 0.000 0.064
#> GSM955017 1 0.4991 0.7784 0.728 0.000 0.008 0.120 0.144
#> GSM955021 2 0.3532 0.6468 0.000 0.832 0.076 0.000 0.092
#> GSM955025 5 0.5459 0.8153 0.000 0.316 0.084 0.000 0.600
#> GSM955028 1 0.0290 0.8586 0.992 0.000 0.008 0.000 0.000
#> GSM955029 2 0.1732 0.5877 0.000 0.920 0.000 0.000 0.080
#> GSM955030 4 0.3659 0.6685 0.000 0.000 0.220 0.768 0.012
#> GSM955032 3 0.1386 0.7051 0.000 0.016 0.952 0.000 0.032
#> GSM955033 4 0.3821 0.6637 0.000 0.000 0.216 0.764 0.020
#> GSM955034 1 0.0290 0.8586 0.992 0.000 0.008 0.000 0.000
#> GSM955035 2 0.4937 0.6218 0.000 0.672 0.264 0.000 0.064
#> GSM955036 4 0.4686 0.3886 0.000 0.000 0.384 0.596 0.020
#> GSM955037 4 0.6614 -0.2565 0.396 0.000 0.008 0.432 0.164
#> GSM955039 4 0.4811 0.2019 0.000 0.000 0.452 0.528 0.020
#> GSM955041 2 0.4914 0.6249 0.000 0.676 0.260 0.000 0.064
#> GSM955042 4 0.3474 0.6042 0.008 0.000 0.004 0.796 0.192
#> GSM955045 2 0.3692 0.6619 0.000 0.812 0.136 0.000 0.052
#> GSM955046 3 0.3615 0.6619 0.000 0.000 0.808 0.156 0.036
#> GSM955047 1 0.6101 0.7076 0.580 0.000 0.004 0.164 0.252
#> GSM955050 4 0.2962 0.6803 0.000 0.000 0.048 0.868 0.084
#> GSM955052 2 0.4840 0.6319 0.000 0.688 0.248 0.000 0.064
#> GSM955053 1 0.0000 0.8584 1.000 0.000 0.000 0.000 0.000
#> GSM955056 3 0.4878 0.3100 0.000 0.264 0.676 0.000 0.060
#> GSM955058 2 0.1732 0.5877 0.000 0.920 0.000 0.000 0.080
#> GSM955059 3 0.0693 0.7228 0.000 0.012 0.980 0.008 0.000
#> GSM955060 1 0.5787 0.7570 0.648 0.000 0.012 0.140 0.200
#> GSM955061 2 0.1732 0.5877 0.000 0.920 0.000 0.000 0.080
#> GSM955065 1 0.0290 0.8586 0.992 0.000 0.008 0.000 0.000
#> GSM955066 3 0.2417 0.7294 0.000 0.016 0.912 0.040 0.032
#> GSM955067 1 0.0290 0.8586 0.992 0.000 0.008 0.000 0.000
#> GSM955073 2 0.5087 0.5923 0.000 0.644 0.292 0.000 0.064
#> GSM955074 1 0.5703 0.7581 0.660 0.000 0.012 0.144 0.184
#> GSM955076 3 0.3236 0.6714 0.000 0.000 0.828 0.152 0.020
#> GSM955078 2 0.3035 0.5673 0.000 0.856 0.032 0.000 0.112
#> GSM955083 4 0.3353 0.6783 0.000 0.000 0.196 0.796 0.008
#> GSM955084 5 0.4517 0.8469 0.000 0.388 0.012 0.000 0.600
#> GSM955086 3 0.2661 0.7237 0.000 0.008 0.896 0.044 0.052
#> GSM955091 2 0.1836 0.6318 0.000 0.932 0.032 0.000 0.036
#> GSM955092 2 0.1331 0.6161 0.000 0.952 0.008 0.000 0.040
#> GSM955093 3 0.3573 0.6653 0.000 0.000 0.812 0.152 0.036
#> GSM955098 5 0.4639 0.8418 0.000 0.344 0.024 0.000 0.632
#> GSM955099 2 0.3336 0.3189 0.000 0.772 0.000 0.000 0.228
#> GSM955100 4 0.3355 0.6082 0.012 0.000 0.000 0.804 0.184
#> GSM955103 3 0.3449 0.6621 0.000 0.000 0.812 0.164 0.024
#> GSM955104 4 0.3551 0.6703 0.000 0.000 0.220 0.772 0.008
#> GSM955106 2 0.6083 0.0997 0.000 0.572 0.204 0.000 0.224
#> GSM955000 1 0.4991 0.7784 0.728 0.000 0.008 0.120 0.144
#> GSM955006 1 0.6228 0.6849 0.568 0.000 0.004 0.200 0.228
#> GSM955007 2 0.4937 0.6218 0.000 0.672 0.264 0.000 0.064
#> GSM955010 4 0.3779 0.6536 0.000 0.000 0.236 0.752 0.012
#> GSM955014 1 0.0880 0.8560 0.968 0.000 0.000 0.000 0.032
#> GSM955018 3 0.2597 0.7073 0.000 0.000 0.884 0.092 0.024
#> GSM955020 1 0.3142 0.8369 0.856 0.000 0.004 0.032 0.108
#> GSM955024 2 0.4878 0.6255 0.000 0.676 0.264 0.000 0.060
#> GSM955026 5 0.6319 0.5396 0.000 0.216 0.256 0.000 0.528
#> GSM955031 4 0.4139 0.6766 0.000 0.000 0.132 0.784 0.084
#> GSM955038 4 0.2230 0.6636 0.000 0.000 0.000 0.884 0.116
#> GSM955040 4 0.1357 0.6855 0.000 0.000 0.004 0.948 0.048
#> GSM955044 2 0.1544 0.5952 0.000 0.932 0.000 0.000 0.068
#> GSM955051 1 0.6089 0.7104 0.584 0.000 0.004 0.168 0.244
#> GSM955055 2 0.1732 0.5877 0.000 0.920 0.000 0.000 0.080
#> GSM955057 1 0.0162 0.8584 0.996 0.000 0.000 0.000 0.004
#> GSM955062 2 0.3375 0.6618 0.000 0.840 0.104 0.000 0.056
#> GSM955063 2 0.4762 0.6354 0.000 0.700 0.236 0.000 0.064
#> GSM955068 3 0.6275 -0.0615 0.000 0.156 0.480 0.000 0.364
#> GSM955069 3 0.4540 0.3642 0.000 0.000 0.640 0.340 0.020
#> GSM955070 2 0.2020 0.5665 0.000 0.900 0.000 0.000 0.100
#> GSM955071 4 0.3003 0.6822 0.000 0.000 0.188 0.812 0.000
#> GSM955077 4 0.6949 0.0782 0.000 0.068 0.084 0.428 0.420
#> GSM955080 3 0.5290 0.1491 0.000 0.392 0.560 0.004 0.044
#> GSM955081 3 0.2333 0.7289 0.000 0.016 0.916 0.028 0.040
#> GSM955082 2 0.5365 0.1687 0.000 0.664 0.132 0.000 0.204
#> GSM955085 2 0.2338 0.5365 0.000 0.884 0.004 0.000 0.112
#> GSM955090 1 0.2393 0.8488 0.900 0.000 0.004 0.016 0.080
#> GSM955094 2 0.1915 0.6270 0.000 0.928 0.032 0.000 0.040
#> GSM955096 2 0.5672 0.4669 0.000 0.544 0.368 0.000 0.088
#> GSM955102 3 0.4781 0.0955 0.000 0.000 0.552 0.428 0.020
#> GSM955105 3 0.3205 0.7128 0.000 0.008 0.864 0.072 0.056
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 5 0.3881 0.4950 0.000 0.008 0.168 0.032 0.780 0.012
#> GSM955008 2 0.5034 0.5677 0.000 0.520 0.000 0.000 0.076 0.404
#> GSM955016 4 0.3239 0.6130 0.000 0.000 0.152 0.816 0.008 0.024
#> GSM955019 5 0.5368 0.0495 0.000 0.408 0.000 0.004 0.492 0.096
#> GSM955022 5 0.5571 0.3761 0.000 0.000 0.228 0.000 0.552 0.220
#> GSM955023 5 0.6131 -0.2645 0.000 0.336 0.000 0.000 0.336 0.328
#> GSM955027 2 0.0146 0.5881 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM955043 2 0.0000 0.5900 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955048 1 0.1542 0.7858 0.944 0.000 0.000 0.016 0.016 0.024
#> GSM955049 2 0.5082 0.5992 0.000 0.572 0.000 0.000 0.096 0.332
#> GSM955054 2 0.5195 0.5853 0.000 0.540 0.000 0.000 0.100 0.360
#> GSM955064 2 0.3284 0.6298 0.000 0.784 0.000 0.000 0.020 0.196
#> GSM955072 5 0.4839 0.2850 0.000 0.300 0.000 0.004 0.624 0.072
#> GSM955075 2 0.2594 0.4641 0.000 0.880 0.000 0.004 0.060 0.056
#> GSM955079 5 0.3485 0.5149 0.000 0.000 0.152 0.004 0.800 0.044
#> GSM955087 1 0.0000 0.7963 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955088 2 0.5260 0.0921 0.000 0.552 0.000 0.004 0.348 0.096
#> GSM955089 1 0.3717 0.7328 0.808 0.000 0.000 0.092 0.016 0.084
#> GSM955095 5 0.3933 0.3863 0.000 0.220 0.008 0.000 0.740 0.032
#> GSM955097 5 0.6270 0.2505 0.000 0.184 0.336 0.004 0.460 0.016
#> GSM955101 5 0.5973 0.3598 0.000 0.008 0.204 0.000 0.496 0.292
#> GSM954999 3 0.3121 0.5471 0.000 0.000 0.804 0.180 0.004 0.012
#> GSM955001 2 0.0146 0.5881 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM955003 2 0.5155 0.5933 0.000 0.556 0.000 0.000 0.100 0.344
#> GSM955004 6 0.6721 0.7005 0.000 0.356 0.000 0.092 0.120 0.432
#> GSM955005 3 0.2982 0.5742 0.000 0.000 0.820 0.164 0.012 0.004
#> GSM955009 6 0.6556 0.6857 0.000 0.380 0.000 0.092 0.096 0.432
#> GSM955011 4 0.2260 0.6150 0.000 0.000 0.140 0.860 0.000 0.000
#> GSM955012 2 0.3617 0.6369 0.000 0.736 0.000 0.000 0.020 0.244
#> GSM955013 3 0.4139 0.4279 0.000 0.000 0.644 0.008 0.336 0.012
#> GSM955015 2 0.5482 0.5215 0.000 0.468 0.008 0.000 0.096 0.428
#> GSM955017 1 0.4127 0.3747 0.588 0.000 0.000 0.400 0.004 0.008
#> GSM955021 2 0.3284 0.6294 0.000 0.784 0.000 0.000 0.020 0.196
#> GSM955025 6 0.7086 0.6370 0.000 0.260 0.000 0.100 0.208 0.432
#> GSM955028 1 0.0000 0.7963 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955029 2 0.0291 0.5868 0.000 0.992 0.000 0.004 0.004 0.000
#> GSM955030 3 0.3230 0.5484 0.000 0.000 0.792 0.192 0.008 0.008
#> GSM955032 5 0.5852 0.3471 0.000 0.000 0.240 0.004 0.516 0.240
#> GSM955033 3 0.2100 0.5982 0.000 0.000 0.884 0.112 0.004 0.000
#> GSM955034 1 0.0000 0.7963 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955035 2 0.5370 0.5353 0.000 0.480 0.008 0.000 0.084 0.428
#> GSM955036 3 0.1616 0.6410 0.000 0.000 0.940 0.028 0.020 0.012
#> GSM955037 4 0.5839 0.2420 0.316 0.000 0.148 0.524 0.004 0.008
#> GSM955039 3 0.1555 0.6517 0.000 0.000 0.932 0.004 0.060 0.004
#> GSM955041 2 0.5058 0.5526 0.000 0.500 0.000 0.000 0.076 0.424
#> GSM955042 4 0.3460 0.6086 0.000 0.000 0.168 0.796 0.008 0.028
#> GSM955045 2 0.4066 0.6336 0.000 0.692 0.000 0.000 0.036 0.272
#> GSM955046 3 0.4503 0.5132 0.000 0.000 0.696 0.000 0.204 0.100
#> GSM955047 4 0.5566 -0.0497 0.332 0.000 0.000 0.552 0.020 0.096
#> GSM955050 4 0.6218 0.2405 0.000 0.000 0.332 0.436 0.220 0.012
#> GSM955052 2 0.5034 0.5677 0.000 0.520 0.000 0.000 0.076 0.404
#> GSM955053 1 0.0508 0.7955 0.984 0.000 0.000 0.004 0.000 0.012
#> GSM955056 6 0.6844 -0.3022 0.000 0.136 0.096 0.000 0.340 0.428
#> GSM955058 2 0.0291 0.5868 0.000 0.992 0.000 0.004 0.004 0.000
#> GSM955059 5 0.5358 0.2568 0.000 0.000 0.328 0.000 0.544 0.128
#> GSM955060 1 0.4227 0.2594 0.496 0.000 0.000 0.492 0.008 0.004
#> GSM955061 2 0.0291 0.5868 0.000 0.992 0.000 0.004 0.004 0.000
#> GSM955065 1 0.0000 0.7963 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955066 5 0.3653 0.4551 0.000 0.000 0.228 0.004 0.748 0.020
#> GSM955067 1 0.0000 0.7963 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955073 2 0.5852 0.4903 0.000 0.444 0.024 0.000 0.104 0.428
#> GSM955074 1 0.4390 0.2677 0.508 0.000 0.000 0.472 0.004 0.016
#> GSM955076 3 0.5061 0.3105 0.000 0.000 0.568 0.004 0.352 0.076
#> GSM955078 2 0.4260 0.5281 0.000 0.744 0.000 0.004 0.136 0.116
#> GSM955083 3 0.3089 0.5377 0.000 0.000 0.800 0.188 0.004 0.008
#> GSM955084 6 0.6721 0.7005 0.000 0.356 0.000 0.092 0.120 0.432
#> GSM955086 5 0.3362 0.4914 0.000 0.000 0.184 0.012 0.792 0.012
#> GSM955091 2 0.3458 0.6025 0.000 0.808 0.000 0.000 0.080 0.112
#> GSM955092 2 0.2591 0.5956 0.000 0.880 0.000 0.004 0.052 0.064
#> GSM955093 3 0.4812 0.4456 0.000 0.000 0.640 0.000 0.264 0.096
#> GSM955098 6 0.7081 0.5782 0.000 0.204 0.000 0.100 0.264 0.432
#> GSM955099 2 0.2817 0.4491 0.000 0.868 0.000 0.008 0.072 0.052
#> GSM955100 4 0.2946 0.6005 0.000 0.000 0.184 0.808 0.004 0.004
#> GSM955103 3 0.4566 0.4568 0.000 0.000 0.652 0.000 0.280 0.068
#> GSM955104 3 0.3426 0.5447 0.000 0.000 0.784 0.192 0.012 0.012
#> GSM955106 5 0.5241 0.2412 0.000 0.288 0.000 0.008 0.600 0.104
#> GSM955000 1 0.4127 0.3747 0.588 0.000 0.000 0.400 0.004 0.008
#> GSM955006 4 0.4135 0.1594 0.292 0.000 0.000 0.680 0.012 0.016
#> GSM955007 2 0.5457 0.5316 0.000 0.476 0.012 0.000 0.084 0.428
#> GSM955010 3 0.2544 0.5880 0.000 0.000 0.852 0.140 0.004 0.004
#> GSM955014 1 0.1787 0.7829 0.932 0.000 0.000 0.020 0.016 0.032
#> GSM955018 3 0.5074 0.0648 0.000 0.000 0.472 0.000 0.452 0.076
#> GSM955020 1 0.4688 0.6589 0.720 0.000 0.000 0.156 0.020 0.104
#> GSM955024 2 0.5144 0.5826 0.000 0.536 0.000 0.000 0.092 0.372
#> GSM955026 5 0.4865 0.2228 0.000 0.088 0.000 0.040 0.716 0.156
#> GSM955031 4 0.6390 0.1405 0.000 0.000 0.336 0.368 0.284 0.012
#> GSM955038 4 0.4614 0.4602 0.000 0.000 0.332 0.624 0.028 0.016
#> GSM955040 4 0.4297 0.2777 0.000 0.000 0.452 0.532 0.004 0.012
#> GSM955044 2 0.0363 0.5958 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM955051 4 0.5689 -0.0590 0.336 0.000 0.000 0.536 0.020 0.108
#> GSM955055 2 0.0000 0.5900 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955057 1 0.0622 0.7952 0.980 0.000 0.000 0.008 0.000 0.012
#> GSM955062 2 0.3514 0.6357 0.000 0.752 0.000 0.000 0.020 0.228
#> GSM955063 2 0.4949 0.5787 0.000 0.548 0.000 0.000 0.072 0.380
#> GSM955068 5 0.3813 0.3457 0.000 0.084 0.000 0.012 0.796 0.108
#> GSM955069 3 0.3087 0.6078 0.000 0.000 0.808 0.004 0.176 0.012
#> GSM955070 2 0.0837 0.5797 0.000 0.972 0.000 0.004 0.020 0.004
#> GSM955071 3 0.3560 0.4410 0.000 0.000 0.732 0.256 0.008 0.004
#> GSM955077 5 0.7059 0.0540 0.000 0.008 0.152 0.220 0.496 0.124
#> GSM955080 2 0.6968 -0.3565 0.000 0.368 0.192 0.000 0.364 0.076
#> GSM955081 5 0.3071 0.4986 0.000 0.000 0.180 0.000 0.804 0.016
#> GSM955082 2 0.5451 -0.1295 0.000 0.468 0.000 0.004 0.424 0.104
#> GSM955085 2 0.3098 0.5351 0.000 0.844 0.000 0.004 0.064 0.088
#> GSM955090 1 0.3765 0.7302 0.804 0.000 0.000 0.096 0.016 0.084
#> GSM955094 2 0.3742 0.5921 0.000 0.792 0.000 0.004 0.088 0.116
#> GSM955096 5 0.5868 0.0920 0.000 0.224 0.000 0.000 0.472 0.304
#> GSM955102 3 0.2218 0.6505 0.000 0.000 0.884 0.000 0.104 0.012
#> GSM955105 5 0.3590 0.5149 0.000 0.000 0.136 0.032 0.808 0.024
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> ATC:kmeans 108 0.747 2
#> ATC:kmeans 103 0.552 3
#> ATC:kmeans 86 0.863 4
#> ATC:kmeans 90 0.554 5
#> ATC:kmeans 65 0.248 6
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 31589 rows and 108 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 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 0.999 0.999 0.4757 0.525 0.525
#> 3 3 0.896 0.886 0.952 0.2633 0.877 0.771
#> 4 4 0.757 0.836 0.894 0.1852 0.828 0.597
#> 5 5 0.745 0.746 0.848 0.0551 0.911 0.690
#> 6 6 0.725 0.669 0.772 0.0279 0.946 0.775
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
#> GSM955002 2 0.0000 1.000 0.000 1.000
#> GSM955008 2 0.0000 1.000 0.000 1.000
#> GSM955016 1 0.0000 0.999 1.000 0.000
#> GSM955019 2 0.0000 1.000 0.000 1.000
#> GSM955022 2 0.0000 1.000 0.000 1.000
#> GSM955023 2 0.0000 1.000 0.000 1.000
#> GSM955027 2 0.0000 1.000 0.000 1.000
#> GSM955043 2 0.0000 1.000 0.000 1.000
#> GSM955048 1 0.0000 0.999 1.000 0.000
#> GSM955049 2 0.0000 1.000 0.000 1.000
#> GSM955054 2 0.0000 1.000 0.000 1.000
#> GSM955064 2 0.0000 1.000 0.000 1.000
#> GSM955072 2 0.0000 1.000 0.000 1.000
#> GSM955075 2 0.0000 1.000 0.000 1.000
#> GSM955079 2 0.0000 1.000 0.000 1.000
#> GSM955087 1 0.0000 0.999 1.000 0.000
#> GSM955088 2 0.0000 1.000 0.000 1.000
#> GSM955089 1 0.0000 0.999 1.000 0.000
#> GSM955095 2 0.0000 1.000 0.000 1.000
#> GSM955097 2 0.0000 1.000 0.000 1.000
#> GSM955101 2 0.0000 1.000 0.000 1.000
#> GSM954999 1 0.0000 0.999 1.000 0.000
#> GSM955001 2 0.0000 1.000 0.000 1.000
#> GSM955003 2 0.0000 1.000 0.000 1.000
#> GSM955004 2 0.0000 1.000 0.000 1.000
#> GSM955005 1 0.0000 0.999 1.000 0.000
#> GSM955009 2 0.0000 1.000 0.000 1.000
#> GSM955011 1 0.0000 0.999 1.000 0.000
#> GSM955012 2 0.0000 1.000 0.000 1.000
#> GSM955013 2 0.0938 0.988 0.012 0.988
#> GSM955015 2 0.0000 1.000 0.000 1.000
#> GSM955017 1 0.0000 0.999 1.000 0.000
#> GSM955021 2 0.0000 1.000 0.000 1.000
#> GSM955025 2 0.0000 1.000 0.000 1.000
#> GSM955028 1 0.0000 0.999 1.000 0.000
#> GSM955029 2 0.0000 1.000 0.000 1.000
#> GSM955030 1 0.0000 0.999 1.000 0.000
#> GSM955032 2 0.0000 1.000 0.000 1.000
#> GSM955033 1 0.0000 0.999 1.000 0.000
#> GSM955034 1 0.0000 0.999 1.000 0.000
#> GSM955035 2 0.0000 1.000 0.000 1.000
#> GSM955036 1 0.0000 0.999 1.000 0.000
#> GSM955037 1 0.0000 0.999 1.000 0.000
#> GSM955039 1 0.0000 0.999 1.000 0.000
#> GSM955041 2 0.0000 1.000 0.000 1.000
#> GSM955042 1 0.0000 0.999 1.000 0.000
#> GSM955045 2 0.0000 1.000 0.000 1.000
#> GSM955046 2 0.0000 1.000 0.000 1.000
#> GSM955047 1 0.0000 0.999 1.000 0.000
#> GSM955050 1 0.0000 0.999 1.000 0.000
#> GSM955052 2 0.0000 1.000 0.000 1.000
#> GSM955053 1 0.0000 0.999 1.000 0.000
#> GSM955056 2 0.0000 1.000 0.000 1.000
#> GSM955058 2 0.0000 1.000 0.000 1.000
#> GSM955059 2 0.0000 1.000 0.000 1.000
#> GSM955060 1 0.0000 0.999 1.000 0.000
#> GSM955061 2 0.0000 1.000 0.000 1.000
#> GSM955065 1 0.0000 0.999 1.000 0.000
#> GSM955066 2 0.0000 1.000 0.000 1.000
#> GSM955067 1 0.0000 0.999 1.000 0.000
#> GSM955073 2 0.0000 1.000 0.000 1.000
#> GSM955074 1 0.0000 0.999 1.000 0.000
#> GSM955076 2 0.0000 1.000 0.000 1.000
#> GSM955078 2 0.0000 1.000 0.000 1.000
#> GSM955083 1 0.0000 0.999 1.000 0.000
#> GSM955084 2 0.0000 1.000 0.000 1.000
#> GSM955086 2 0.0000 1.000 0.000 1.000
#> GSM955091 2 0.0000 1.000 0.000 1.000
#> GSM955092 2 0.0000 1.000 0.000 1.000
#> GSM955093 2 0.0000 1.000 0.000 1.000
#> GSM955098 2 0.0000 1.000 0.000 1.000
#> GSM955099 2 0.0000 1.000 0.000 1.000
#> GSM955100 1 0.0000 0.999 1.000 0.000
#> GSM955103 2 0.0000 1.000 0.000 1.000
#> GSM955104 1 0.0000 0.999 1.000 0.000
#> GSM955106 2 0.0000 1.000 0.000 1.000
#> GSM955000 1 0.0000 0.999 1.000 0.000
#> GSM955006 1 0.0000 0.999 1.000 0.000
#> GSM955007 2 0.0000 1.000 0.000 1.000
#> GSM955010 1 0.0000 0.999 1.000 0.000
#> GSM955014 1 0.0000 0.999 1.000 0.000
#> GSM955018 2 0.0000 1.000 0.000 1.000
#> GSM955020 1 0.0000 0.999 1.000 0.000
#> GSM955024 2 0.0000 1.000 0.000 1.000
#> GSM955026 2 0.0000 1.000 0.000 1.000
#> GSM955031 1 0.0000 0.999 1.000 0.000
#> GSM955038 1 0.0000 0.999 1.000 0.000
#> GSM955040 1 0.0000 0.999 1.000 0.000
#> GSM955044 2 0.0000 1.000 0.000 1.000
#> GSM955051 1 0.0000 0.999 1.000 0.000
#> GSM955055 2 0.0000 1.000 0.000 1.000
#> GSM955057 1 0.0000 0.999 1.000 0.000
#> GSM955062 2 0.0000 1.000 0.000 1.000
#> GSM955063 2 0.0000 1.000 0.000 1.000
#> GSM955068 2 0.0000 1.000 0.000 1.000
#> GSM955069 1 0.3114 0.941 0.944 0.056
#> GSM955070 2 0.0000 1.000 0.000 1.000
#> GSM955071 1 0.0000 0.999 1.000 0.000
#> GSM955077 1 0.0000 0.999 1.000 0.000
#> GSM955080 2 0.0000 1.000 0.000 1.000
#> GSM955081 2 0.0000 1.000 0.000 1.000
#> GSM955082 2 0.0000 1.000 0.000 1.000
#> GSM955085 2 0.0000 1.000 0.000 1.000
#> GSM955090 1 0.0000 0.999 1.000 0.000
#> GSM955094 2 0.0000 1.000 0.000 1.000
#> GSM955096 2 0.0000 1.000 0.000 1.000
#> GSM955102 1 0.0000 0.999 1.000 0.000
#> GSM955105 2 0.0000 1.000 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955008 2 0.0424 0.930 0.000 0.992 0.008
#> GSM955016 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955019 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955022 2 0.6215 0.322 0.000 0.572 0.428
#> GSM955023 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955027 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955043 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955048 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955049 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955054 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955064 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955072 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955075 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955079 2 0.6168 0.361 0.000 0.588 0.412
#> GSM955087 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955088 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955089 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955095 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955097 2 0.3482 0.814 0.000 0.872 0.128
#> GSM955101 2 0.6204 0.333 0.000 0.576 0.424
#> GSM954999 1 0.6026 0.367 0.624 0.000 0.376
#> GSM955001 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955003 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955004 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955005 3 0.4887 0.755 0.228 0.000 0.772
#> GSM955009 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955011 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955012 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955013 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955015 2 0.0592 0.927 0.000 0.988 0.012
#> GSM955017 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955021 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955025 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955028 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955029 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955030 3 0.4887 0.755 0.228 0.000 0.772
#> GSM955032 2 0.6225 0.312 0.000 0.568 0.432
#> GSM955033 3 0.0592 0.912 0.012 0.000 0.988
#> GSM955034 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955035 2 0.0592 0.927 0.000 0.988 0.012
#> GSM955036 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955037 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955039 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955041 2 0.0424 0.930 0.000 0.992 0.008
#> GSM955042 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955045 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955046 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955047 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955050 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955052 2 0.0424 0.930 0.000 0.992 0.008
#> GSM955053 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955056 2 0.6204 0.333 0.000 0.576 0.424
#> GSM955058 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955059 2 0.6260 0.267 0.000 0.552 0.448
#> GSM955060 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955061 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955065 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955066 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955067 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955073 2 0.6192 0.342 0.000 0.580 0.420
#> GSM955074 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955076 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955078 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955083 1 0.2356 0.907 0.928 0.000 0.072
#> GSM955084 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955086 2 0.5988 0.455 0.000 0.632 0.368
#> GSM955091 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955092 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955093 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955098 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955099 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955100 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955103 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955104 3 0.5138 0.722 0.252 0.000 0.748
#> GSM955106 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955000 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955006 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955007 2 0.0592 0.927 0.000 0.988 0.012
#> GSM955010 3 0.4399 0.794 0.188 0.000 0.812
#> GSM955014 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955018 3 0.4062 0.744 0.000 0.164 0.836
#> GSM955020 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955024 2 0.0237 0.932 0.000 0.996 0.004
#> GSM955026 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955031 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955038 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955040 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955044 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955051 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955055 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955057 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955062 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955063 2 0.0424 0.930 0.000 0.992 0.008
#> GSM955068 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955069 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955070 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955071 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955077 1 0.0424 0.974 0.992 0.008 0.000
#> GSM955080 2 0.3340 0.823 0.000 0.880 0.120
#> GSM955081 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955082 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955085 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955090 1 0.0000 0.984 1.000 0.000 0.000
#> GSM955094 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955096 2 0.0000 0.934 0.000 1.000 0.000
#> GSM955102 3 0.0000 0.917 0.000 0.000 1.000
#> GSM955105 2 0.0237 0.932 0.000 0.996 0.004
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.0000 0.8376 0.000 1.000 0.000 0.000
#> GSM955008 3 0.3266 0.8791 0.000 0.168 0.832 0.000
#> GSM955016 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955019 2 0.2281 0.8692 0.000 0.904 0.096 0.000
#> GSM955022 3 0.2737 0.8499 0.000 0.104 0.888 0.008
#> GSM955023 3 0.3356 0.8741 0.000 0.176 0.824 0.000
#> GSM955027 2 0.3123 0.8529 0.000 0.844 0.156 0.000
#> GSM955043 2 0.3172 0.8505 0.000 0.840 0.160 0.000
#> GSM955048 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955049 3 0.3569 0.8550 0.000 0.196 0.804 0.000
#> GSM955054 3 0.3311 0.8771 0.000 0.172 0.828 0.000
#> GSM955064 2 0.4998 -0.0431 0.000 0.512 0.488 0.000
#> GSM955072 2 0.2149 0.8633 0.000 0.912 0.088 0.000
#> GSM955075 2 0.0921 0.8523 0.000 0.972 0.028 0.000
#> GSM955079 3 0.0000 0.7724 0.000 0.000 1.000 0.000
#> GSM955087 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955088 2 0.2408 0.8680 0.000 0.896 0.104 0.000
#> GSM955089 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955095 2 0.2011 0.8688 0.000 0.920 0.080 0.000
#> GSM955097 2 0.3157 0.8546 0.000 0.852 0.144 0.004
#> GSM955101 3 0.2704 0.8648 0.000 0.124 0.876 0.000
#> GSM954999 4 0.4543 0.5837 0.324 0.000 0.000 0.676
#> GSM955001 2 0.3219 0.8477 0.000 0.836 0.164 0.000
#> GSM955003 3 0.3311 0.8771 0.000 0.172 0.828 0.000
#> GSM955004 2 0.0000 0.8376 0.000 1.000 0.000 0.000
#> GSM955005 4 0.3688 0.7794 0.208 0.000 0.000 0.792
#> GSM955009 2 0.0000 0.8376 0.000 1.000 0.000 0.000
#> GSM955011 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955012 3 0.4941 0.3206 0.000 0.436 0.564 0.000
#> GSM955013 4 0.3123 0.8534 0.000 0.000 0.156 0.844
#> GSM955015 3 0.3266 0.8791 0.000 0.168 0.832 0.000
#> GSM955017 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955021 2 0.4998 -0.0431 0.000 0.512 0.488 0.000
#> GSM955025 2 0.0000 0.8376 0.000 1.000 0.000 0.000
#> GSM955028 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955029 2 0.3172 0.8505 0.000 0.840 0.160 0.000
#> GSM955030 4 0.3837 0.7626 0.224 0.000 0.000 0.776
#> GSM955032 3 0.0336 0.7649 0.000 0.000 0.992 0.008
#> GSM955033 4 0.0000 0.8941 0.000 0.000 0.000 1.000
#> GSM955034 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955035 3 0.3266 0.8791 0.000 0.168 0.832 0.000
#> GSM955036 4 0.0000 0.8941 0.000 0.000 0.000 1.000
#> GSM955037 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955039 4 0.0000 0.8941 0.000 0.000 0.000 1.000
#> GSM955041 3 0.3266 0.8791 0.000 0.168 0.832 0.000
#> GSM955042 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955045 3 0.4985 0.1963 0.000 0.468 0.532 0.000
#> GSM955046 4 0.0188 0.8942 0.000 0.000 0.004 0.996
#> GSM955047 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955050 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955052 3 0.3266 0.8791 0.000 0.168 0.832 0.000
#> GSM955053 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955056 3 0.2976 0.8592 0.000 0.120 0.872 0.008
#> GSM955058 2 0.3219 0.8477 0.000 0.836 0.164 0.000
#> GSM955059 3 0.2676 0.8397 0.000 0.092 0.896 0.012
#> GSM955060 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955061 2 0.3219 0.8477 0.000 0.836 0.164 0.000
#> GSM955065 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955066 3 0.3726 0.8336 0.000 0.212 0.788 0.000
#> GSM955067 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955073 3 0.3257 0.8741 0.000 0.152 0.844 0.004
#> GSM955074 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955076 4 0.3726 0.8176 0.000 0.000 0.212 0.788
#> GSM955078 2 0.2216 0.8690 0.000 0.908 0.092 0.000
#> GSM955083 1 0.3873 0.6682 0.772 0.000 0.000 0.228
#> GSM955084 2 0.0000 0.8376 0.000 1.000 0.000 0.000
#> GSM955086 3 0.0817 0.7577 0.000 0.024 0.976 0.000
#> GSM955091 2 0.3219 0.8477 0.000 0.836 0.164 0.000
#> GSM955092 2 0.3123 0.8528 0.000 0.844 0.156 0.000
#> GSM955093 4 0.2011 0.8786 0.000 0.000 0.080 0.920
#> GSM955098 2 0.0000 0.8376 0.000 1.000 0.000 0.000
#> GSM955099 2 0.1022 0.8528 0.000 0.968 0.032 0.000
#> GSM955100 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955103 4 0.1661 0.8847 0.000 0.004 0.052 0.944
#> GSM955104 4 0.4193 0.7051 0.268 0.000 0.000 0.732
#> GSM955106 2 0.1211 0.8385 0.000 0.960 0.040 0.000
#> GSM955000 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955006 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955007 3 0.3266 0.8791 0.000 0.168 0.832 0.000
#> GSM955010 4 0.1389 0.8847 0.048 0.000 0.000 0.952
#> GSM955014 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955018 3 0.1716 0.7065 0.000 0.000 0.936 0.064
#> GSM955020 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955024 3 0.3266 0.8791 0.000 0.168 0.832 0.000
#> GSM955026 2 0.0188 0.8345 0.000 0.996 0.004 0.000
#> GSM955031 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955038 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955040 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955044 2 0.3219 0.8477 0.000 0.836 0.164 0.000
#> GSM955051 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955055 2 0.3219 0.8477 0.000 0.836 0.164 0.000
#> GSM955057 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955062 2 0.4998 -0.0431 0.000 0.512 0.488 0.000
#> GSM955063 3 0.3266 0.8791 0.000 0.168 0.832 0.000
#> GSM955068 2 0.1389 0.7915 0.000 0.952 0.048 0.000
#> GSM955069 4 0.0188 0.8942 0.000 0.000 0.004 0.996
#> GSM955070 2 0.1474 0.8611 0.000 0.948 0.052 0.000
#> GSM955071 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955077 1 0.4790 0.4179 0.620 0.380 0.000 0.000
#> GSM955080 2 0.2944 0.8610 0.000 0.868 0.128 0.004
#> GSM955081 3 0.4382 0.7081 0.000 0.296 0.704 0.000
#> GSM955082 2 0.1867 0.8655 0.000 0.928 0.072 0.000
#> GSM955085 2 0.2281 0.8686 0.000 0.904 0.096 0.000
#> GSM955090 1 0.0000 0.9760 1.000 0.000 0.000 0.000
#> GSM955094 2 0.2814 0.8630 0.000 0.868 0.132 0.000
#> GSM955096 3 0.3400 0.8707 0.000 0.180 0.820 0.000
#> GSM955102 4 0.0000 0.8941 0.000 0.000 0.000 1.000
#> GSM955105 3 0.2973 0.6316 0.000 0.144 0.856 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 5 0.3399 0.823 0.000 0.172 0.012 0.004 0.812
#> GSM955008 3 0.4182 0.685 0.000 0.400 0.600 0.000 0.000
#> GSM955016 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955019 2 0.1205 0.823 0.000 0.956 0.004 0.000 0.040
#> GSM955022 3 0.3585 0.684 0.000 0.220 0.772 0.004 0.004
#> GSM955023 3 0.4283 0.614 0.000 0.456 0.544 0.000 0.000
#> GSM955027 2 0.0162 0.833 0.000 0.996 0.004 0.000 0.000
#> GSM955043 2 0.0162 0.833 0.000 0.996 0.004 0.000 0.000
#> GSM955048 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955049 2 0.4294 -0.447 0.000 0.532 0.468 0.000 0.000
#> GSM955054 3 0.4219 0.671 0.000 0.416 0.584 0.000 0.000
#> GSM955064 2 0.2127 0.739 0.000 0.892 0.108 0.000 0.000
#> GSM955072 2 0.3906 0.420 0.000 0.704 0.004 0.000 0.292
#> GSM955075 2 0.1732 0.799 0.000 0.920 0.000 0.000 0.080
#> GSM955079 3 0.2331 0.456 0.000 0.020 0.900 0.000 0.080
#> GSM955087 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955088 2 0.1082 0.826 0.000 0.964 0.008 0.000 0.028
#> GSM955089 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955095 2 0.2304 0.772 0.000 0.892 0.008 0.000 0.100
#> GSM955097 2 0.3702 0.697 0.000 0.840 0.036 0.032 0.092
#> GSM955101 3 0.3814 0.697 0.000 0.276 0.720 0.000 0.004
#> GSM954999 4 0.4937 0.261 0.428 0.000 0.000 0.544 0.028
#> GSM955001 2 0.0162 0.833 0.000 0.996 0.000 0.000 0.004
#> GSM955003 3 0.4268 0.635 0.000 0.444 0.556 0.000 0.000
#> GSM955004 5 0.3336 0.854 0.000 0.228 0.000 0.000 0.772
#> GSM955005 4 0.3430 0.686 0.220 0.000 0.000 0.776 0.004
#> GSM955009 5 0.3336 0.854 0.000 0.228 0.000 0.000 0.772
#> GSM955011 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955012 2 0.2424 0.699 0.000 0.868 0.132 0.000 0.000
#> GSM955013 4 0.4661 0.664 0.000 0.000 0.312 0.656 0.032
#> GSM955015 3 0.4150 0.690 0.000 0.388 0.612 0.000 0.000
#> GSM955017 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955021 2 0.2773 0.652 0.000 0.836 0.164 0.000 0.000
#> GSM955025 5 0.3210 0.857 0.000 0.212 0.000 0.000 0.788
#> GSM955028 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955029 2 0.0000 0.833 0.000 1.000 0.000 0.000 0.000
#> GSM955030 4 0.3430 0.686 0.220 0.000 0.000 0.776 0.004
#> GSM955032 3 0.2103 0.478 0.000 0.020 0.920 0.004 0.056
#> GSM955033 4 0.0794 0.779 0.000 0.000 0.000 0.972 0.028
#> GSM955034 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955035 3 0.4171 0.688 0.000 0.396 0.604 0.000 0.000
#> GSM955036 4 0.0794 0.779 0.000 0.000 0.000 0.972 0.028
#> GSM955037 1 0.0162 0.981 0.996 0.000 0.000 0.004 0.000
#> GSM955039 4 0.0404 0.783 0.000 0.000 0.012 0.988 0.000
#> GSM955041 3 0.4242 0.658 0.000 0.428 0.572 0.000 0.000
#> GSM955042 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955045 2 0.1908 0.757 0.000 0.908 0.092 0.000 0.000
#> GSM955046 4 0.1195 0.783 0.000 0.000 0.028 0.960 0.012
#> GSM955047 1 0.0566 0.973 0.984 0.000 0.004 0.000 0.012
#> GSM955050 1 0.0865 0.963 0.972 0.000 0.004 0.000 0.024
#> GSM955052 3 0.4182 0.685 0.000 0.400 0.600 0.000 0.000
#> GSM955053 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955056 3 0.3819 0.683 0.000 0.228 0.756 0.000 0.016
#> GSM955058 2 0.0162 0.832 0.000 0.996 0.004 0.000 0.000
#> GSM955059 3 0.3718 0.670 0.000 0.196 0.784 0.004 0.016
#> GSM955060 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955061 2 0.0162 0.832 0.000 0.996 0.004 0.000 0.000
#> GSM955065 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955066 2 0.4803 -0.354 0.000 0.536 0.444 0.000 0.020
#> GSM955067 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955073 3 0.3730 0.698 0.000 0.288 0.712 0.000 0.000
#> GSM955074 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955076 4 0.5447 0.537 0.000 0.000 0.440 0.500 0.060
#> GSM955078 2 0.1124 0.827 0.000 0.960 0.004 0.000 0.036
#> GSM955083 1 0.4503 0.460 0.664 0.000 0.000 0.312 0.024
#> GSM955084 5 0.3336 0.854 0.000 0.228 0.000 0.000 0.772
#> GSM955086 3 0.2824 0.421 0.000 0.020 0.864 0.000 0.116
#> GSM955091 2 0.0290 0.831 0.000 0.992 0.008 0.000 0.000
#> GSM955092 2 0.0000 0.833 0.000 1.000 0.000 0.000 0.000
#> GSM955093 4 0.4326 0.693 0.000 0.000 0.264 0.708 0.028
#> GSM955098 5 0.2516 0.842 0.000 0.140 0.000 0.000 0.860
#> GSM955099 2 0.4114 0.191 0.000 0.624 0.000 0.000 0.376
#> GSM955100 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955103 4 0.4312 0.716 0.000 0.032 0.176 0.772 0.020
#> GSM955104 4 0.3895 0.592 0.320 0.000 0.000 0.680 0.000
#> GSM955106 5 0.5016 0.504 0.000 0.348 0.044 0.000 0.608
#> GSM955000 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955006 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955007 3 0.4278 0.618 0.000 0.452 0.548 0.000 0.000
#> GSM955010 4 0.1485 0.777 0.032 0.000 0.000 0.948 0.020
#> GSM955014 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955018 3 0.2876 0.424 0.000 0.016 0.888 0.044 0.052
#> GSM955020 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955024 3 0.4302 0.563 0.000 0.480 0.520 0.000 0.000
#> GSM955026 5 0.2516 0.842 0.000 0.140 0.000 0.000 0.860
#> GSM955031 1 0.0865 0.963 0.972 0.000 0.004 0.000 0.024
#> GSM955038 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955040 1 0.0324 0.978 0.992 0.000 0.000 0.004 0.004
#> GSM955044 2 0.0404 0.830 0.000 0.988 0.012 0.000 0.000
#> GSM955051 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955055 2 0.0162 0.833 0.000 0.996 0.004 0.000 0.000
#> GSM955057 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955062 2 0.2074 0.743 0.000 0.896 0.104 0.000 0.000
#> GSM955063 3 0.4210 0.675 0.000 0.412 0.588 0.000 0.000
#> GSM955068 5 0.2971 0.844 0.000 0.156 0.008 0.000 0.836
#> GSM955069 4 0.1357 0.781 0.000 0.000 0.048 0.948 0.004
#> GSM955070 2 0.2563 0.764 0.000 0.872 0.008 0.000 0.120
#> GSM955071 1 0.0579 0.973 0.984 0.000 0.000 0.008 0.008
#> GSM955077 5 0.4668 0.432 0.276 0.028 0.008 0.000 0.688
#> GSM955080 2 0.2363 0.799 0.000 0.912 0.024 0.012 0.052
#> GSM955081 2 0.4768 0.258 0.000 0.656 0.304 0.000 0.040
#> GSM955082 2 0.1697 0.810 0.000 0.932 0.008 0.000 0.060
#> GSM955085 2 0.0880 0.828 0.000 0.968 0.000 0.000 0.032
#> GSM955090 1 0.0000 0.984 1.000 0.000 0.000 0.000 0.000
#> GSM955094 2 0.1399 0.826 0.000 0.952 0.020 0.000 0.028
#> GSM955096 3 0.4287 0.604 0.000 0.460 0.540 0.000 0.000
#> GSM955102 4 0.0798 0.783 0.000 0.000 0.008 0.976 0.016
#> GSM955105 3 0.4689 -0.120 0.000 0.016 0.560 0.000 0.424
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 6 0.3560 0.7413 0.000 0.068 0.004 0.048 0.044 0.836
#> GSM955008 2 0.0632 0.6753 0.000 0.976 0.000 0.000 0.024 0.000
#> GSM955016 1 0.1578 0.9204 0.936 0.000 0.000 0.048 0.012 0.004
#> GSM955019 5 0.5098 0.7677 0.000 0.304 0.000 0.012 0.608 0.076
#> GSM955022 2 0.2941 0.2855 0.000 0.780 0.000 0.220 0.000 0.000
#> GSM955023 2 0.2431 0.5746 0.000 0.860 0.000 0.008 0.132 0.000
#> GSM955027 5 0.3756 0.8037 0.000 0.400 0.000 0.000 0.600 0.000
#> GSM955043 5 0.3915 0.7951 0.000 0.412 0.000 0.004 0.584 0.000
#> GSM955048 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955049 2 0.2915 0.4620 0.000 0.808 0.000 0.008 0.184 0.000
#> GSM955054 2 0.1643 0.6503 0.000 0.924 0.000 0.008 0.068 0.000
#> GSM955064 2 0.3995 -0.6481 0.000 0.516 0.000 0.004 0.480 0.000
#> GSM955072 5 0.6149 0.4514 0.000 0.224 0.000 0.008 0.436 0.332
#> GSM955075 5 0.4928 0.7370 0.000 0.260 0.000 0.004 0.640 0.096
#> GSM955079 4 0.4322 0.6685 0.000 0.372 0.000 0.600 0.028 0.000
#> GSM955087 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955088 5 0.4585 0.7775 0.000 0.324 0.000 0.028 0.632 0.016
#> GSM955089 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955095 5 0.5665 0.6511 0.000 0.216 0.000 0.040 0.620 0.124
#> GSM955097 5 0.5755 0.4796 0.000 0.156 0.012 0.060 0.660 0.112
#> GSM955101 2 0.2593 0.4711 0.000 0.844 0.000 0.148 0.008 0.000
#> GSM954999 3 0.6960 0.2933 0.328 0.000 0.424 0.168 0.076 0.004
#> GSM955001 5 0.3717 0.8086 0.000 0.384 0.000 0.000 0.616 0.000
#> GSM955003 2 0.2261 0.6166 0.000 0.884 0.000 0.008 0.104 0.004
#> GSM955004 6 0.1957 0.8290 0.000 0.000 0.000 0.000 0.112 0.888
#> GSM955005 3 0.4035 0.6189 0.208 0.000 0.744 0.016 0.032 0.000
#> GSM955009 6 0.2003 0.8277 0.000 0.000 0.000 0.000 0.116 0.884
#> GSM955011 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955012 5 0.3857 0.7198 0.000 0.468 0.000 0.000 0.532 0.000
#> GSM955013 3 0.5274 0.4395 0.000 0.008 0.596 0.312 0.076 0.008
#> GSM955015 2 0.0260 0.6743 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM955017 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955021 2 0.3937 -0.5012 0.000 0.572 0.000 0.004 0.424 0.000
#> GSM955025 6 0.1910 0.8295 0.000 0.000 0.000 0.000 0.108 0.892
#> GSM955028 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955029 5 0.3727 0.8080 0.000 0.388 0.000 0.000 0.612 0.000
#> GSM955030 3 0.3915 0.5981 0.236 0.000 0.732 0.016 0.016 0.000
#> GSM955032 2 0.3997 -0.6002 0.000 0.508 0.000 0.488 0.004 0.000
#> GSM955033 3 0.2846 0.6737 0.000 0.000 0.856 0.084 0.060 0.000
#> GSM955034 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955035 2 0.0692 0.6733 0.000 0.976 0.000 0.004 0.020 0.000
#> GSM955036 3 0.1995 0.6953 0.000 0.000 0.912 0.052 0.036 0.000
#> GSM955037 1 0.0291 0.9526 0.992 0.000 0.004 0.000 0.004 0.000
#> GSM955039 3 0.0692 0.7047 0.000 0.000 0.976 0.004 0.020 0.000
#> GSM955041 2 0.1471 0.6521 0.000 0.932 0.000 0.004 0.064 0.000
#> GSM955042 1 0.1511 0.9231 0.940 0.000 0.000 0.044 0.012 0.004
#> GSM955045 5 0.3955 0.7608 0.000 0.436 0.000 0.004 0.560 0.000
#> GSM955046 3 0.3209 0.6859 0.000 0.024 0.856 0.056 0.060 0.004
#> GSM955047 1 0.1577 0.9176 0.940 0.000 0.000 0.036 0.016 0.008
#> GSM955050 1 0.2958 0.8481 0.864 0.000 0.000 0.060 0.060 0.016
#> GSM955052 2 0.0777 0.6748 0.000 0.972 0.000 0.004 0.024 0.000
#> GSM955053 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955056 2 0.3298 0.2385 0.000 0.756 0.000 0.236 0.008 0.000
#> GSM955058 5 0.3727 0.8080 0.000 0.388 0.000 0.000 0.612 0.000
#> GSM955059 2 0.3972 -0.0307 0.000 0.680 0.004 0.300 0.016 0.000
#> GSM955060 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955061 5 0.3717 0.8086 0.000 0.384 0.000 0.000 0.616 0.000
#> GSM955065 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955066 2 0.5686 0.3439 0.000 0.600 0.000 0.136 0.236 0.028
#> GSM955067 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955073 2 0.1908 0.5520 0.000 0.900 0.000 0.096 0.004 0.000
#> GSM955074 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955076 4 0.6105 0.0820 0.000 0.140 0.348 0.484 0.028 0.000
#> GSM955078 5 0.4699 0.8047 0.000 0.376 0.000 0.008 0.580 0.036
#> GSM955083 1 0.6840 -0.0347 0.456 0.000 0.308 0.160 0.072 0.004
#> GSM955084 6 0.2003 0.8277 0.000 0.000 0.000 0.000 0.116 0.884
#> GSM955086 4 0.4588 0.6808 0.000 0.320 0.000 0.632 0.040 0.008
#> GSM955091 5 0.4118 0.8069 0.000 0.396 0.000 0.004 0.592 0.008
#> GSM955092 5 0.3986 0.8095 0.000 0.384 0.000 0.004 0.608 0.004
#> GSM955093 3 0.5544 0.4188 0.000 0.076 0.620 0.260 0.040 0.004
#> GSM955098 6 0.1151 0.8063 0.000 0.000 0.000 0.012 0.032 0.956
#> GSM955099 5 0.6329 0.4129 0.000 0.300 0.000 0.008 0.356 0.336
#> GSM955100 1 0.0146 0.9544 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM955103 3 0.5745 0.5375 0.000 0.060 0.652 0.172 0.108 0.008
#> GSM955104 3 0.4452 0.5355 0.292 0.000 0.664 0.016 0.028 0.000
#> GSM955106 6 0.6409 0.2730 0.000 0.248 0.000 0.060 0.164 0.528
#> GSM955000 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955006 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955007 2 0.2006 0.6178 0.000 0.892 0.000 0.004 0.104 0.000
#> GSM955010 3 0.2450 0.6997 0.016 0.000 0.896 0.040 0.048 0.000
#> GSM955014 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955018 4 0.5522 0.6097 0.000 0.416 0.048 0.500 0.032 0.004
#> GSM955020 1 0.0146 0.9547 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM955024 2 0.2597 0.5064 0.000 0.824 0.000 0.000 0.176 0.000
#> GSM955026 6 0.1225 0.8079 0.000 0.000 0.000 0.012 0.036 0.952
#> GSM955031 1 0.3405 0.8188 0.836 0.000 0.000 0.080 0.060 0.024
#> GSM955038 1 0.1477 0.9255 0.940 0.000 0.000 0.048 0.008 0.004
#> GSM955040 1 0.1793 0.9172 0.932 0.000 0.008 0.040 0.016 0.004
#> GSM955044 5 0.3961 0.7658 0.000 0.440 0.000 0.004 0.556 0.000
#> GSM955051 1 0.0146 0.9547 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM955055 5 0.3737 0.8069 0.000 0.392 0.000 0.000 0.608 0.000
#> GSM955057 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955062 5 0.3868 0.6755 0.000 0.492 0.000 0.000 0.508 0.000
#> GSM955063 2 0.0937 0.6712 0.000 0.960 0.000 0.000 0.040 0.000
#> GSM955068 6 0.2095 0.8222 0.000 0.004 0.000 0.016 0.076 0.904
#> GSM955069 3 0.3419 0.6718 0.000 0.000 0.824 0.072 0.096 0.008
#> GSM955070 5 0.5955 0.6542 0.000 0.392 0.000 0.012 0.444 0.152
#> GSM955071 1 0.2335 0.8915 0.904 0.000 0.028 0.044 0.024 0.000
#> GSM955077 6 0.5958 0.4320 0.176 0.000 0.000 0.108 0.096 0.620
#> GSM955080 5 0.5923 0.6723 0.000 0.328 0.012 0.060 0.552 0.048
#> GSM955081 2 0.6327 0.1134 0.000 0.468 0.000 0.188 0.316 0.028
#> GSM955082 5 0.5064 0.7395 0.000 0.276 0.000 0.016 0.632 0.076
#> GSM955085 5 0.4241 0.8007 0.000 0.348 0.000 0.004 0.628 0.020
#> GSM955090 1 0.0000 0.9561 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955094 5 0.5241 0.7268 0.000 0.420 0.000 0.008 0.500 0.072
#> GSM955096 2 0.2838 0.5898 0.000 0.852 0.000 0.028 0.116 0.004
#> GSM955102 3 0.1682 0.7042 0.000 0.000 0.928 0.020 0.052 0.000
#> GSM955105 4 0.6771 0.4530 0.000 0.252 0.000 0.456 0.060 0.232
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> ATC:skmeans 108 0.1127 2
#> ATC:skmeans 99 0.0945 3
#> ATC:skmeans 102 0.1379 4
#> ATC:skmeans 95 0.2010 5
#> ATC:skmeans 87 0.7594 6
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 31589 rows and 108 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 0.972 0.989 0.3843 0.612 0.612
#> 3 3 0.899 0.925 0.969 0.5387 0.745 0.603
#> 4 4 0.718 0.790 0.841 0.0973 0.958 0.902
#> 5 5 0.701 0.707 0.858 0.1372 0.862 0.655
#> 6 6 0.799 0.730 0.877 0.0701 0.864 0.549
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
#> GSM955002 2 0.0000 0.994 0.000 1.000
#> GSM955008 2 0.0000 0.994 0.000 1.000
#> GSM955016 1 0.0000 0.970 1.000 0.000
#> GSM955019 2 0.0000 0.994 0.000 1.000
#> GSM955022 2 0.0000 0.994 0.000 1.000
#> GSM955023 2 0.0000 0.994 0.000 1.000
#> GSM955027 2 0.0000 0.994 0.000 1.000
#> GSM955043 2 0.0000 0.994 0.000 1.000
#> GSM955048 1 0.0000 0.970 1.000 0.000
#> GSM955049 2 0.0000 0.994 0.000 1.000
#> GSM955054 2 0.0000 0.994 0.000 1.000
#> GSM955064 2 0.0000 0.994 0.000 1.000
#> GSM955072 2 0.0000 0.994 0.000 1.000
#> GSM955075 2 0.0000 0.994 0.000 1.000
#> GSM955079 2 0.0000 0.994 0.000 1.000
#> GSM955087 1 0.0000 0.970 1.000 0.000
#> GSM955088 2 0.0000 0.994 0.000 1.000
#> GSM955089 1 0.0000 0.970 1.000 0.000
#> GSM955095 2 0.0000 0.994 0.000 1.000
#> GSM955097 2 0.0000 0.994 0.000 1.000
#> GSM955101 2 0.0000 0.994 0.000 1.000
#> GSM954999 2 0.0000 0.994 0.000 1.000
#> GSM955001 2 0.0000 0.994 0.000 1.000
#> GSM955003 2 0.0000 0.994 0.000 1.000
#> GSM955004 2 0.0000 0.994 0.000 1.000
#> GSM955005 2 0.0000 0.994 0.000 1.000
#> GSM955009 2 0.0000 0.994 0.000 1.000
#> GSM955011 1 0.0000 0.970 1.000 0.000
#> GSM955012 2 0.0000 0.994 0.000 1.000
#> GSM955013 2 0.0000 0.994 0.000 1.000
#> GSM955015 2 0.0000 0.994 0.000 1.000
#> GSM955017 1 0.0000 0.970 1.000 0.000
#> GSM955021 2 0.0000 0.994 0.000 1.000
#> GSM955025 2 0.0000 0.994 0.000 1.000
#> GSM955028 1 0.0000 0.970 1.000 0.000
#> GSM955029 2 0.0000 0.994 0.000 1.000
#> GSM955030 1 0.5842 0.843 0.860 0.140
#> GSM955032 2 0.0000 0.994 0.000 1.000
#> GSM955033 2 0.0000 0.994 0.000 1.000
#> GSM955034 1 0.0000 0.970 1.000 0.000
#> GSM955035 2 0.0000 0.994 0.000 1.000
#> GSM955036 2 0.0000 0.994 0.000 1.000
#> GSM955037 1 0.0000 0.970 1.000 0.000
#> GSM955039 2 0.0000 0.994 0.000 1.000
#> GSM955041 2 0.0000 0.994 0.000 1.000
#> GSM955042 1 0.0376 0.967 0.996 0.004
#> GSM955045 2 0.0000 0.994 0.000 1.000
#> GSM955046 2 0.0000 0.994 0.000 1.000
#> GSM955047 1 0.0000 0.970 1.000 0.000
#> GSM955050 1 0.9608 0.402 0.616 0.384
#> GSM955052 2 0.0000 0.994 0.000 1.000
#> GSM955053 1 0.0000 0.970 1.000 0.000
#> GSM955056 2 0.0000 0.994 0.000 1.000
#> GSM955058 2 0.0000 0.994 0.000 1.000
#> GSM955059 2 0.0000 0.994 0.000 1.000
#> GSM955060 1 0.0000 0.970 1.000 0.000
#> GSM955061 2 0.0000 0.994 0.000 1.000
#> GSM955065 1 0.0000 0.970 1.000 0.000
#> GSM955066 2 0.0000 0.994 0.000 1.000
#> GSM955067 1 0.0000 0.970 1.000 0.000
#> GSM955073 2 0.0000 0.994 0.000 1.000
#> GSM955074 1 0.0000 0.970 1.000 0.000
#> GSM955076 2 0.0000 0.994 0.000 1.000
#> GSM955078 2 0.0000 0.994 0.000 1.000
#> GSM955083 2 0.0000 0.994 0.000 1.000
#> GSM955084 2 0.0000 0.994 0.000 1.000
#> GSM955086 2 0.0000 0.994 0.000 1.000
#> GSM955091 2 0.0000 0.994 0.000 1.000
#> GSM955092 2 0.0000 0.994 0.000 1.000
#> GSM955093 2 0.0000 0.994 0.000 1.000
#> GSM955098 2 0.0000 0.994 0.000 1.000
#> GSM955099 2 0.0000 0.994 0.000 1.000
#> GSM955100 1 0.0000 0.970 1.000 0.000
#> GSM955103 2 0.0000 0.994 0.000 1.000
#> GSM955104 2 0.9775 0.253 0.412 0.588
#> GSM955106 2 0.0000 0.994 0.000 1.000
#> GSM955000 1 0.0000 0.970 1.000 0.000
#> GSM955006 1 0.0000 0.970 1.000 0.000
#> GSM955007 2 0.0000 0.994 0.000 1.000
#> GSM955010 2 0.0000 0.994 0.000 1.000
#> GSM955014 1 0.0000 0.970 1.000 0.000
#> GSM955018 2 0.0000 0.994 0.000 1.000
#> GSM955020 1 0.0000 0.970 1.000 0.000
#> GSM955024 2 0.0000 0.994 0.000 1.000
#> GSM955026 2 0.0000 0.994 0.000 1.000
#> GSM955031 2 0.0000 0.994 0.000 1.000
#> GSM955038 1 0.5842 0.843 0.860 0.140
#> GSM955040 1 0.5842 0.843 0.860 0.140
#> GSM955044 2 0.0000 0.994 0.000 1.000
#> GSM955051 1 0.0000 0.970 1.000 0.000
#> GSM955055 2 0.0000 0.994 0.000 1.000
#> GSM955057 1 0.0000 0.970 1.000 0.000
#> GSM955062 2 0.0000 0.994 0.000 1.000
#> GSM955063 2 0.0000 0.994 0.000 1.000
#> GSM955068 2 0.0000 0.994 0.000 1.000
#> GSM955069 2 0.0000 0.994 0.000 1.000
#> GSM955070 2 0.0000 0.994 0.000 1.000
#> GSM955071 2 0.0376 0.990 0.004 0.996
#> GSM955077 2 0.0000 0.994 0.000 1.000
#> GSM955080 2 0.0000 0.994 0.000 1.000
#> GSM955081 2 0.0000 0.994 0.000 1.000
#> GSM955082 2 0.0000 0.994 0.000 1.000
#> GSM955085 2 0.0000 0.994 0.000 1.000
#> GSM955090 1 0.0000 0.970 1.000 0.000
#> GSM955094 2 0.0000 0.994 0.000 1.000
#> GSM955096 2 0.0000 0.994 0.000 1.000
#> GSM955102 2 0.0000 0.994 0.000 1.000
#> GSM955105 2 0.0000 0.994 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 2 0.5810 0.546 0.000 0.664 0.336
#> GSM955008 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955016 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955019 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955022 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955023 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955027 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955043 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955048 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955049 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955054 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955064 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955072 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955075 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955079 2 0.5810 0.546 0.000 0.664 0.336
#> GSM955087 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955088 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955089 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955095 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955097 2 0.3267 0.857 0.000 0.884 0.116
#> GSM955101 2 0.0000 0.961 0.000 1.000 0.000
#> GSM954999 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955001 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955003 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955004 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955005 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955009 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955011 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955012 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955013 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955015 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955017 1 0.6180 0.315 0.584 0.000 0.416
#> GSM955021 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955025 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955028 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955029 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955030 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955032 2 0.4654 0.749 0.000 0.792 0.208
#> GSM955033 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955034 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955035 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955036 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955037 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955039 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955041 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955042 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955045 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955046 3 0.0424 0.972 0.000 0.008 0.992
#> GSM955047 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955050 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955052 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955053 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955056 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955058 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955059 2 0.0747 0.948 0.000 0.984 0.016
#> GSM955060 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955061 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955065 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955066 2 0.3116 0.865 0.000 0.892 0.108
#> GSM955067 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955073 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955074 1 0.4654 0.737 0.792 0.000 0.208
#> GSM955076 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955078 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955083 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955084 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955086 2 0.5810 0.546 0.000 0.664 0.336
#> GSM955091 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955092 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955093 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955098 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955099 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955100 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955103 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955104 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955106 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955000 3 0.6126 0.243 0.400 0.000 0.600
#> GSM955006 1 0.2066 0.909 0.940 0.000 0.060
#> GSM955007 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955010 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955014 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955018 3 0.1163 0.944 0.000 0.028 0.972
#> GSM955020 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955024 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955026 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955031 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955038 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955040 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955044 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955051 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955055 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955057 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955062 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955063 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955068 2 0.0237 0.958 0.000 0.996 0.004
#> GSM955069 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955070 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955071 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955077 2 0.6111 0.415 0.000 0.604 0.396
#> GSM955080 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955081 2 0.1289 0.935 0.000 0.968 0.032
#> GSM955082 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955085 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955090 1 0.0000 0.959 1.000 0.000 0.000
#> GSM955094 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955096 2 0.0000 0.961 0.000 1.000 0.000
#> GSM955102 3 0.0000 0.982 0.000 0.000 1.000
#> GSM955105 2 0.5835 0.538 0.000 0.660 0.340
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 2 0.2401 0.7800 0.000 0.904 0.092 0.004
#> GSM955008 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955016 1 0.4933 0.3122 0.568 0.000 0.432 0.000
#> GSM955019 2 0.2216 0.8519 0.000 0.908 0.000 0.092
#> GSM955022 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM955023 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM955027 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955043 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955048 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955049 2 0.0000 0.8364 0.000 1.000 0.000 0.000
#> GSM955054 2 0.0000 0.8364 0.000 1.000 0.000 0.000
#> GSM955064 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955072 2 0.3873 0.8598 0.000 0.772 0.000 0.228
#> GSM955075 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955079 2 0.2401 0.7800 0.000 0.904 0.092 0.004
#> GSM955087 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955088 2 0.3837 0.8597 0.000 0.776 0.000 0.224
#> GSM955089 1 0.2149 0.4541 0.912 0.000 0.000 0.088
#> GSM955095 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM955097 2 0.1398 0.8199 0.000 0.956 0.040 0.004
#> GSM955101 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM954999 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955001 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955003 2 0.0000 0.8364 0.000 1.000 0.000 0.000
#> GSM955004 2 0.4222 0.8530 0.000 0.728 0.000 0.272
#> GSM955005 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955009 2 0.4222 0.8530 0.000 0.728 0.000 0.272
#> GSM955011 1 0.4250 0.5239 0.724 0.000 0.276 0.000
#> GSM955012 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955013 3 0.0779 0.8925 0.000 0.016 0.980 0.004
#> GSM955015 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955017 1 0.4817 0.3840 0.612 0.000 0.388 0.000
#> GSM955021 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955025 2 0.0336 0.8354 0.000 0.992 0.000 0.008
#> GSM955028 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955029 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955030 3 0.1022 0.8906 0.032 0.000 0.968 0.000
#> GSM955032 2 0.2401 0.7809 0.000 0.904 0.092 0.004
#> GSM955033 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955034 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955035 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955036 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955037 3 0.4250 0.5169 0.276 0.000 0.724 0.000
#> GSM955039 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955041 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955042 1 0.4933 0.3122 0.568 0.000 0.432 0.000
#> GSM955045 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955046 3 0.3157 0.7167 0.000 0.144 0.852 0.004
#> GSM955047 1 0.0000 0.5493 1.000 0.000 0.000 0.000
#> GSM955050 3 0.1022 0.8906 0.032 0.000 0.968 0.000
#> GSM955052 2 0.3649 0.8589 0.000 0.796 0.000 0.204
#> GSM955053 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955056 2 0.1356 0.8261 0.000 0.960 0.032 0.008
#> GSM955058 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955059 2 0.1576 0.8162 0.000 0.948 0.048 0.004
#> GSM955060 1 0.0000 0.5493 1.000 0.000 0.000 0.000
#> GSM955061 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955065 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955066 2 0.1978 0.8005 0.000 0.928 0.068 0.004
#> GSM955067 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955073 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955074 1 0.4679 0.4335 0.648 0.000 0.352 0.000
#> GSM955076 3 0.0376 0.9030 0.000 0.004 0.992 0.004
#> GSM955078 2 0.4072 0.8579 0.000 0.748 0.000 0.252
#> GSM955083 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955084 2 0.4164 0.8556 0.000 0.736 0.000 0.264
#> GSM955086 2 0.2401 0.7800 0.000 0.904 0.092 0.004
#> GSM955091 2 0.0000 0.8364 0.000 1.000 0.000 0.000
#> GSM955092 2 0.2345 0.8545 0.000 0.900 0.000 0.100
#> GSM955093 3 0.0188 0.9056 0.000 0.000 0.996 0.004
#> GSM955098 2 0.0188 0.8360 0.000 0.996 0.000 0.004
#> GSM955099 2 0.2973 0.8567 0.000 0.856 0.000 0.144
#> GSM955100 3 0.4989 -0.1234 0.472 0.000 0.528 0.000
#> GSM955103 3 0.1576 0.8556 0.000 0.048 0.948 0.004
#> GSM955104 3 0.1022 0.8906 0.032 0.000 0.968 0.000
#> GSM955106 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM955000 1 0.4855 0.3612 0.600 0.000 0.400 0.000
#> GSM955006 1 0.0188 0.5516 0.996 0.000 0.004 0.000
#> GSM955007 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955010 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955014 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955018 3 0.3870 0.6087 0.000 0.208 0.788 0.004
#> GSM955020 1 0.1022 0.5144 0.968 0.000 0.000 0.032
#> GSM955024 2 0.0000 0.8364 0.000 1.000 0.000 0.000
#> GSM955026 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM955031 3 0.1022 0.8906 0.032 0.000 0.968 0.000
#> GSM955038 3 0.1022 0.8906 0.032 0.000 0.968 0.000
#> GSM955040 1 0.4933 0.3122 0.568 0.000 0.432 0.000
#> GSM955044 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955051 1 0.0000 0.5493 1.000 0.000 0.000 0.000
#> GSM955055 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955057 4 0.4250 1.0000 0.276 0.000 0.000 0.724
#> GSM955062 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955063 2 0.4134 0.8570 0.000 0.740 0.000 0.260
#> GSM955068 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM955069 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955070 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955071 3 0.1022 0.8906 0.032 0.000 0.968 0.000
#> GSM955077 2 0.4843 0.4985 0.000 0.604 0.396 0.000
#> GSM955080 2 0.4164 0.8564 0.000 0.736 0.000 0.264
#> GSM955081 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM955082 2 0.0336 0.8343 0.000 0.992 0.008 0.000
#> GSM955085 2 0.3311 0.8596 0.000 0.828 0.000 0.172
#> GSM955090 1 0.4164 0.0331 0.736 0.000 0.000 0.264
#> GSM955094 2 0.2281 0.8535 0.000 0.904 0.000 0.096
#> GSM955096 2 0.1209 0.8243 0.000 0.964 0.032 0.004
#> GSM955102 3 0.0000 0.9078 0.000 0.000 1.000 0.000
#> GSM955105 2 0.2999 0.7638 0.000 0.864 0.132 0.004
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.2020 0.689 0.000 0.000 0.900 0.100 0.000
#> GSM955008 3 0.4273 0.310 0.000 0.000 0.552 0.000 0.448
#> GSM955016 1 0.3508 0.634 0.748 0.000 0.000 0.252 0.000
#> GSM955019 3 0.3395 0.600 0.000 0.000 0.764 0.000 0.236
#> GSM955022 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955023 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955027 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955043 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955048 2 0.0000 0.943 0.000 1.000 0.000 0.000 0.000
#> GSM955049 3 0.0162 0.738 0.000 0.000 0.996 0.000 0.004
#> GSM955054 3 0.0162 0.738 0.000 0.000 0.996 0.000 0.004
#> GSM955064 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955072 3 0.4150 0.418 0.000 0.000 0.612 0.000 0.388
#> GSM955075 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955079 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955087 2 0.0162 0.943 0.004 0.996 0.000 0.000 0.000
#> GSM955088 3 0.4192 0.391 0.000 0.000 0.596 0.000 0.404
#> GSM955089 1 0.3932 0.263 0.672 0.328 0.000 0.000 0.000
#> GSM955095 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955097 3 0.4192 0.034 0.000 0.000 0.596 0.000 0.404
#> GSM955101 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM954999 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955001 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955003 3 0.0162 0.738 0.000 0.000 0.996 0.000 0.004
#> GSM955004 5 0.0000 0.754 0.000 0.000 0.000 0.000 1.000
#> GSM955005 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955009 5 0.0510 0.755 0.000 0.000 0.016 0.000 0.984
#> GSM955011 1 0.0162 0.673 0.996 0.000 0.000 0.004 0.000
#> GSM955012 5 0.3039 0.902 0.000 0.000 0.192 0.000 0.808
#> GSM955013 4 0.0404 0.956 0.000 0.000 0.012 0.988 0.000
#> GSM955015 3 0.4273 0.310 0.000 0.000 0.552 0.000 0.448
#> GSM955017 1 0.4138 0.478 0.616 0.000 0.000 0.384 0.000
#> GSM955021 3 0.4278 0.299 0.000 0.000 0.548 0.000 0.452
#> GSM955025 3 0.2891 0.587 0.000 0.000 0.824 0.000 0.176
#> GSM955028 2 0.0162 0.943 0.004 0.996 0.000 0.000 0.000
#> GSM955029 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955030 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955032 3 0.0290 0.734 0.000 0.000 0.992 0.008 0.000
#> GSM955033 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955034 2 0.0162 0.943 0.004 0.996 0.000 0.000 0.000
#> GSM955035 3 0.4273 0.310 0.000 0.000 0.552 0.000 0.448
#> GSM955036 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955037 1 0.4278 0.337 0.548 0.000 0.000 0.452 0.000
#> GSM955039 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955041 3 0.4273 0.310 0.000 0.000 0.552 0.000 0.448
#> GSM955042 1 0.4015 0.533 0.652 0.000 0.000 0.348 0.000
#> GSM955045 3 0.4273 0.310 0.000 0.000 0.552 0.000 0.448
#> GSM955046 4 0.1792 0.853 0.000 0.000 0.084 0.916 0.000
#> GSM955047 1 0.0162 0.672 0.996 0.004 0.000 0.000 0.000
#> GSM955050 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955052 3 0.3636 0.566 0.000 0.000 0.728 0.000 0.272
#> GSM955053 2 0.0162 0.943 0.004 0.996 0.000 0.000 0.000
#> GSM955056 3 0.1121 0.725 0.000 0.000 0.956 0.000 0.044
#> GSM955058 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955059 3 0.0510 0.729 0.000 0.000 0.984 0.016 0.000
#> GSM955060 1 0.0000 0.672 1.000 0.000 0.000 0.000 0.000
#> GSM955061 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955065 2 0.0162 0.943 0.004 0.996 0.000 0.000 0.000
#> GSM955066 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955067 2 0.0000 0.943 0.000 1.000 0.000 0.000 0.000
#> GSM955073 3 0.4273 0.310 0.000 0.000 0.552 0.000 0.448
#> GSM955074 1 0.3999 0.535 0.656 0.000 0.000 0.344 0.000
#> GSM955076 4 0.0162 0.964 0.000 0.000 0.004 0.996 0.000
#> GSM955078 3 0.4256 0.333 0.000 0.000 0.564 0.000 0.436
#> GSM955083 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955084 5 0.1341 0.739 0.000 0.000 0.056 0.000 0.944
#> GSM955086 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955091 3 0.0162 0.738 0.000 0.000 0.996 0.000 0.004
#> GSM955092 3 0.3816 0.502 0.000 0.000 0.696 0.000 0.304
#> GSM955093 4 0.0162 0.964 0.000 0.000 0.004 0.996 0.000
#> GSM955098 3 0.2329 0.643 0.000 0.000 0.876 0.000 0.124
#> GSM955099 3 0.2852 0.656 0.000 0.000 0.828 0.000 0.172
#> GSM955100 1 0.3999 0.566 0.656 0.000 0.000 0.344 0.000
#> GSM955103 4 0.0963 0.925 0.000 0.000 0.036 0.964 0.000
#> GSM955104 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955106 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955000 1 0.4161 0.464 0.608 0.000 0.000 0.392 0.000
#> GSM955006 1 0.0000 0.672 1.000 0.000 0.000 0.000 0.000
#> GSM955007 3 0.4297 0.235 0.000 0.000 0.528 0.000 0.472
#> GSM955010 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955014 2 0.0000 0.943 0.000 1.000 0.000 0.000 0.000
#> GSM955018 4 0.3612 0.528 0.000 0.000 0.268 0.732 0.000
#> GSM955020 1 0.0162 0.672 0.996 0.004 0.000 0.000 0.000
#> GSM955024 3 0.0162 0.738 0.000 0.000 0.996 0.000 0.004
#> GSM955026 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955031 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955038 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955040 1 0.4273 0.349 0.552 0.000 0.000 0.448 0.000
#> GSM955044 5 0.3305 0.855 0.000 0.000 0.224 0.000 0.776
#> GSM955051 1 0.0162 0.672 0.996 0.004 0.000 0.000 0.000
#> GSM955055 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955057 2 0.0000 0.943 0.000 1.000 0.000 0.000 0.000
#> GSM955062 3 0.4306 0.162 0.000 0.000 0.508 0.000 0.492
#> GSM955063 3 0.4150 0.406 0.000 0.000 0.612 0.000 0.388
#> GSM955068 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955069 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955070 3 0.4273 0.310 0.000 0.000 0.552 0.000 0.448
#> GSM955071 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955077 3 0.5434 0.375 0.000 0.000 0.588 0.336 0.076
#> GSM955080 5 0.2852 0.924 0.000 0.000 0.172 0.000 0.828
#> GSM955081 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955082 3 0.0162 0.738 0.000 0.000 0.996 0.000 0.004
#> GSM955085 3 0.3561 0.582 0.000 0.000 0.740 0.000 0.260
#> GSM955090 2 0.4291 0.211 0.464 0.536 0.000 0.000 0.000
#> GSM955094 3 0.2230 0.693 0.000 0.000 0.884 0.000 0.116
#> GSM955096 3 0.0000 0.738 0.000 0.000 1.000 0.000 0.000
#> GSM955102 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM955105 3 0.1965 0.692 0.000 0.000 0.904 0.096 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 2 0.3094 0.688100 0.000 0.824 0.140 0.000 0.000 0.036
#> GSM955008 5 0.2020 0.839666 0.000 0.096 0.000 0.000 0.896 0.008
#> GSM955016 1 0.4813 0.553368 0.648 0.000 0.248 0.000 0.000 0.104
#> GSM955019 5 0.4045 0.343101 0.000 0.428 0.000 0.000 0.564 0.008
#> GSM955022 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955023 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955027 5 0.0000 0.827172 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955043 5 0.0146 0.828885 0.000 0.004 0.000 0.000 0.996 0.000
#> GSM955048 4 0.0146 0.938100 0.004 0.000 0.000 0.996 0.000 0.000
#> GSM955049 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955054 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955064 5 0.0000 0.827172 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955072 5 0.3817 0.637588 0.000 0.252 0.000 0.000 0.720 0.028
#> GSM955075 5 0.0000 0.827172 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955079 2 0.0632 0.820659 0.000 0.976 0.000 0.000 0.000 0.024
#> GSM955087 4 0.0000 0.938531 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM955088 5 0.2178 0.811901 0.000 0.132 0.000 0.000 0.868 0.000
#> GSM955089 1 0.3515 0.259871 0.676 0.000 0.000 0.324 0.000 0.000
#> GSM955095 2 0.0632 0.821558 0.000 0.976 0.000 0.000 0.000 0.024
#> GSM955097 2 0.4494 0.190244 0.000 0.544 0.000 0.000 0.424 0.032
#> GSM955101 2 0.0914 0.818175 0.000 0.968 0.000 0.000 0.016 0.016
#> GSM954999 3 0.2092 0.860874 0.000 0.000 0.876 0.000 0.000 0.124
#> GSM955001 5 0.0000 0.827172 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955003 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955004 6 0.2996 0.714755 0.000 0.000 0.000 0.000 0.228 0.772
#> GSM955005 3 0.0790 0.947257 0.000 0.000 0.968 0.000 0.000 0.032
#> GSM955009 6 0.3175 0.694035 0.000 0.000 0.000 0.000 0.256 0.744
#> GSM955011 1 0.0146 0.633946 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM955012 5 0.3847 -0.000551 0.000 0.456 0.000 0.000 0.544 0.000
#> GSM955013 3 0.0858 0.943492 0.000 0.004 0.968 0.000 0.000 0.028
#> GSM955015 5 0.1918 0.843368 0.000 0.088 0.000 0.000 0.904 0.008
#> GSM955017 1 0.4845 0.407657 0.560 0.000 0.384 0.004 0.000 0.052
#> GSM955021 5 0.1610 0.845213 0.000 0.084 0.000 0.000 0.916 0.000
#> GSM955025 6 0.2941 0.588326 0.000 0.220 0.000 0.000 0.000 0.780
#> GSM955028 4 0.0000 0.938531 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM955029 5 0.0000 0.827172 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955030 3 0.0790 0.947257 0.000 0.000 0.968 0.000 0.000 0.032
#> GSM955032 2 0.1124 0.815108 0.000 0.956 0.008 0.000 0.000 0.036
#> GSM955033 3 0.0000 0.947661 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955034 4 0.0000 0.938531 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM955035 5 0.1866 0.844539 0.000 0.084 0.000 0.000 0.908 0.008
#> GSM955036 3 0.0000 0.947661 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955037 1 0.4921 0.295022 0.508 0.000 0.436 0.004 0.000 0.052
#> GSM955039 3 0.0000 0.947661 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955041 5 0.1866 0.844539 0.000 0.084 0.000 0.000 0.908 0.008
#> GSM955042 1 0.5333 0.495988 0.564 0.000 0.300 0.000 0.000 0.136
#> GSM955045 5 0.1714 0.842464 0.000 0.092 0.000 0.000 0.908 0.000
#> GSM955046 3 0.1334 0.915247 0.000 0.020 0.948 0.000 0.000 0.032
#> GSM955047 1 0.0000 0.632400 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955050 3 0.0000 0.947661 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955052 2 0.3266 0.544079 0.000 0.728 0.000 0.000 0.272 0.000
#> GSM955053 4 0.0000 0.938531 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM955056 2 0.4179 -0.065099 0.000 0.516 0.000 0.000 0.472 0.012
#> GSM955058 5 0.0000 0.827172 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955059 2 0.0914 0.815487 0.000 0.968 0.016 0.000 0.000 0.016
#> GSM955060 1 0.0405 0.630881 0.988 0.000 0.000 0.004 0.000 0.008
#> GSM955061 5 0.0000 0.827172 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955065 4 0.0000 0.938531 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM955066 2 0.0458 0.822339 0.000 0.984 0.000 0.000 0.000 0.016
#> GSM955067 4 0.0146 0.938100 0.004 0.000 0.000 0.996 0.000 0.000
#> GSM955073 5 0.2706 0.777933 0.000 0.160 0.000 0.000 0.832 0.008
#> GSM955074 1 0.4741 0.470728 0.600 0.000 0.344 0.004 0.000 0.052
#> GSM955076 3 0.1075 0.920435 0.000 0.000 0.952 0.000 0.000 0.048
#> GSM955078 5 0.2613 0.801277 0.000 0.140 0.000 0.000 0.848 0.012
#> GSM955083 3 0.0937 0.943614 0.000 0.000 0.960 0.000 0.000 0.040
#> GSM955084 6 0.2941 0.714537 0.000 0.000 0.000 0.000 0.220 0.780
#> GSM955086 2 0.0458 0.822339 0.000 0.984 0.000 0.000 0.000 0.016
#> GSM955091 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955092 5 0.3828 0.281814 0.000 0.440 0.000 0.000 0.560 0.000
#> GSM955093 3 0.0713 0.935663 0.000 0.000 0.972 0.000 0.000 0.028
#> GSM955098 6 0.3833 0.262716 0.000 0.444 0.000 0.000 0.000 0.556
#> GSM955099 2 0.2527 0.677830 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM955100 1 0.4799 0.509208 0.592 0.000 0.340 0.000 0.000 0.068
#> GSM955103 3 0.0717 0.937192 0.000 0.008 0.976 0.000 0.000 0.016
#> GSM955104 3 0.0790 0.947257 0.000 0.000 0.968 0.000 0.000 0.032
#> GSM955106 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955000 1 0.4853 0.400249 0.556 0.000 0.388 0.004 0.000 0.052
#> GSM955006 1 0.0146 0.632334 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM955007 5 0.1812 0.845427 0.000 0.080 0.000 0.000 0.912 0.008
#> GSM955010 3 0.0790 0.947257 0.000 0.000 0.968 0.000 0.000 0.032
#> GSM955014 4 0.0146 0.938100 0.004 0.000 0.000 0.996 0.000 0.000
#> GSM955018 3 0.3794 0.550333 0.000 0.248 0.724 0.000 0.000 0.028
#> GSM955020 1 0.0000 0.632400 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955024 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955026 2 0.0865 0.809609 0.000 0.964 0.000 0.000 0.000 0.036
#> GSM955031 3 0.0790 0.947257 0.000 0.000 0.968 0.000 0.000 0.032
#> GSM955038 3 0.0865 0.945882 0.000 0.000 0.964 0.000 0.000 0.036
#> GSM955040 1 0.3838 0.355165 0.552 0.000 0.448 0.000 0.000 0.000
#> GSM955044 2 0.3862 0.179530 0.000 0.524 0.000 0.000 0.476 0.000
#> GSM955051 1 0.1327 0.617898 0.936 0.000 0.000 0.000 0.000 0.064
#> GSM955055 5 0.0000 0.827172 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM955057 4 0.0146 0.938100 0.004 0.000 0.000 0.996 0.000 0.000
#> GSM955062 5 0.1444 0.844924 0.000 0.072 0.000 0.000 0.928 0.000
#> GSM955063 2 0.3852 0.331532 0.000 0.612 0.000 0.000 0.384 0.004
#> GSM955068 2 0.1267 0.807502 0.000 0.940 0.000 0.000 0.000 0.060
#> GSM955069 3 0.0000 0.947661 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM955070 5 0.1663 0.844371 0.000 0.088 0.000 0.000 0.912 0.000
#> GSM955071 3 0.0146 0.948139 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM955077 2 0.5348 0.259646 0.000 0.576 0.272 0.000 0.000 0.152
#> GSM955080 5 0.0547 0.821781 0.000 0.000 0.000 0.000 0.980 0.020
#> GSM955081 2 0.0458 0.822339 0.000 0.984 0.000 0.000 0.000 0.016
#> GSM955082 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955085 2 0.3823 0.153637 0.000 0.564 0.000 0.000 0.436 0.000
#> GSM955090 4 0.3857 0.189951 0.468 0.000 0.000 0.532 0.000 0.000
#> GSM955094 2 0.1910 0.743351 0.000 0.892 0.000 0.000 0.108 0.000
#> GSM955096 2 0.0000 0.824254 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM955102 3 0.0790 0.947257 0.000 0.000 0.968 0.000 0.000 0.032
#> GSM955105 2 0.2432 0.739642 0.000 0.876 0.100 0.000 0.000 0.024
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> ATC:pam 106 0.741 2
#> ATC:pam 105 0.109 3
#> ATC:pam 98 0.102 4
#> ATC:pam 86 0.348 5
#> ATC:pam 90 0.154 6
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 31589 rows and 108 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 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 0.990 0.993 0.3539 0.651 0.651
#> 3 3 0.470 0.629 0.803 0.7445 0.695 0.531
#> 4 4 0.585 0.674 0.805 0.1036 0.811 0.543
#> 5 5 0.587 0.664 0.768 0.0610 0.768 0.453
#> 6 6 0.611 0.660 0.789 0.0275 0.923 0.765
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
#> GSM955002 2 0.0000 0.991 0.000 1.000
#> GSM955008 2 0.0000 0.991 0.000 1.000
#> GSM955016 1 0.0000 1.000 1.000 0.000
#> GSM955019 2 0.0000 0.991 0.000 1.000
#> GSM955022 2 0.0000 0.991 0.000 1.000
#> GSM955023 2 0.0000 0.991 0.000 1.000
#> GSM955027 2 0.0000 0.991 0.000 1.000
#> GSM955043 2 0.0000 0.991 0.000 1.000
#> GSM955048 1 0.0000 1.000 1.000 0.000
#> GSM955049 2 0.0000 0.991 0.000 1.000
#> GSM955054 2 0.0000 0.991 0.000 1.000
#> GSM955064 2 0.0000 0.991 0.000 1.000
#> GSM955072 2 0.0000 0.991 0.000 1.000
#> GSM955075 2 0.0000 0.991 0.000 1.000
#> GSM955079 2 0.0376 0.990 0.004 0.996
#> GSM955087 1 0.0000 1.000 1.000 0.000
#> GSM955088 2 0.0000 0.991 0.000 1.000
#> GSM955089 1 0.0000 1.000 1.000 0.000
#> GSM955095 2 0.0000 0.991 0.000 1.000
#> GSM955097 2 0.1414 0.986 0.020 0.980
#> GSM955101 2 0.0000 0.991 0.000 1.000
#> GSM954999 2 0.1414 0.986 0.020 0.980
#> GSM955001 2 0.0000 0.991 0.000 1.000
#> GSM955003 2 0.0000 0.991 0.000 1.000
#> GSM955004 2 0.1414 0.986 0.020 0.980
#> GSM955005 2 0.1414 0.986 0.020 0.980
#> GSM955009 2 0.1414 0.986 0.020 0.980
#> GSM955011 1 0.0000 1.000 1.000 0.000
#> GSM955012 2 0.0000 0.991 0.000 1.000
#> GSM955013 2 0.1184 0.987 0.016 0.984
#> GSM955015 2 0.0000 0.991 0.000 1.000
#> GSM955017 1 0.0000 1.000 1.000 0.000
#> GSM955021 2 0.0000 0.991 0.000 1.000
#> GSM955025 2 0.1414 0.986 0.020 0.980
#> GSM955028 1 0.0000 1.000 1.000 0.000
#> GSM955029 2 0.0000 0.991 0.000 1.000
#> GSM955030 2 0.1414 0.986 0.020 0.980
#> GSM955032 2 0.0000 0.991 0.000 1.000
#> GSM955033 2 0.1414 0.986 0.020 0.980
#> GSM955034 1 0.0000 1.000 1.000 0.000
#> GSM955035 2 0.0000 0.991 0.000 1.000
#> GSM955036 2 0.1414 0.986 0.020 0.980
#> GSM955037 1 0.0000 1.000 1.000 0.000
#> GSM955039 2 0.1414 0.986 0.020 0.980
#> GSM955041 2 0.0000 0.991 0.000 1.000
#> GSM955042 1 0.0000 1.000 1.000 0.000
#> GSM955045 2 0.0000 0.991 0.000 1.000
#> GSM955046 2 0.1414 0.986 0.020 0.980
#> GSM955047 1 0.0000 1.000 1.000 0.000
#> GSM955050 2 0.1414 0.986 0.020 0.980
#> GSM955052 2 0.0000 0.991 0.000 1.000
#> GSM955053 1 0.0000 1.000 1.000 0.000
#> GSM955056 2 0.0000 0.991 0.000 1.000
#> GSM955058 2 0.0000 0.991 0.000 1.000
#> GSM955059 2 0.0000 0.991 0.000 1.000
#> GSM955060 1 0.0000 1.000 1.000 0.000
#> GSM955061 2 0.0000 0.991 0.000 1.000
#> GSM955065 1 0.0000 1.000 1.000 0.000
#> GSM955066 2 0.0000 0.991 0.000 1.000
#> GSM955067 1 0.0000 1.000 1.000 0.000
#> GSM955073 2 0.1414 0.986 0.020 0.980
#> GSM955074 1 0.0000 1.000 1.000 0.000
#> GSM955076 2 0.0672 0.989 0.008 0.992
#> GSM955078 2 0.0000 0.991 0.000 1.000
#> GSM955083 2 0.1414 0.986 0.020 0.980
#> GSM955084 2 0.1414 0.986 0.020 0.980
#> GSM955086 2 0.0376 0.990 0.004 0.996
#> GSM955091 2 0.0000 0.991 0.000 1.000
#> GSM955092 2 0.0000 0.991 0.000 1.000
#> GSM955093 2 0.1414 0.986 0.020 0.980
#> GSM955098 2 0.1414 0.986 0.020 0.980
#> GSM955099 2 0.0000 0.991 0.000 1.000
#> GSM955100 1 0.0000 1.000 1.000 0.000
#> GSM955103 2 0.0938 0.988 0.012 0.988
#> GSM955104 2 0.1414 0.986 0.020 0.980
#> GSM955106 2 0.0000 0.991 0.000 1.000
#> GSM955000 1 0.0000 1.000 1.000 0.000
#> GSM955006 1 0.0000 1.000 1.000 0.000
#> GSM955007 2 0.0000 0.991 0.000 1.000
#> GSM955010 2 0.1414 0.986 0.020 0.980
#> GSM955014 1 0.0000 1.000 1.000 0.000
#> GSM955018 2 0.1414 0.986 0.020 0.980
#> GSM955020 1 0.0000 1.000 1.000 0.000
#> GSM955024 2 0.0000 0.991 0.000 1.000
#> GSM955026 2 0.1414 0.986 0.020 0.980
#> GSM955031 2 0.1414 0.986 0.020 0.980
#> GSM955038 2 0.6247 0.832 0.156 0.844
#> GSM955040 2 0.1414 0.986 0.020 0.980
#> GSM955044 2 0.0000 0.991 0.000 1.000
#> GSM955051 1 0.0000 1.000 1.000 0.000
#> GSM955055 2 0.0000 0.991 0.000 1.000
#> GSM955057 1 0.0000 1.000 1.000 0.000
#> GSM955062 2 0.0000 0.991 0.000 1.000
#> GSM955063 2 0.0000 0.991 0.000 1.000
#> GSM955068 2 0.0000 0.991 0.000 1.000
#> GSM955069 2 0.1414 0.986 0.020 0.980
#> GSM955070 2 0.0000 0.991 0.000 1.000
#> GSM955071 2 0.1414 0.986 0.020 0.980
#> GSM955077 2 0.1414 0.986 0.020 0.980
#> GSM955080 2 0.1184 0.987 0.016 0.984
#> GSM955081 2 0.0000 0.991 0.000 1.000
#> GSM955082 2 0.0000 0.991 0.000 1.000
#> GSM955085 2 0.0000 0.991 0.000 1.000
#> GSM955090 1 0.0000 1.000 1.000 0.000
#> GSM955094 2 0.0000 0.991 0.000 1.000
#> GSM955096 2 0.0000 0.991 0.000 1.000
#> GSM955102 2 0.1414 0.986 0.020 0.980
#> GSM955105 2 0.1414 0.986 0.020 0.980
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.5591 0.55148 0.000 0.304 0.696
#> GSM955008 3 0.6180 0.37878 0.000 0.416 0.584
#> GSM955016 1 0.4291 0.83308 0.820 0.000 0.180
#> GSM955019 2 0.4062 0.67542 0.000 0.836 0.164
#> GSM955022 3 0.5363 0.55524 0.000 0.276 0.724
#> GSM955023 3 0.5785 0.48551 0.000 0.332 0.668
#> GSM955027 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955043 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955048 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955049 3 0.5968 0.42627 0.000 0.364 0.636
#> GSM955054 3 0.5835 0.47316 0.000 0.340 0.660
#> GSM955064 2 0.0237 0.74435 0.000 0.996 0.004
#> GSM955072 2 0.6126 0.19409 0.000 0.600 0.400
#> GSM955075 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955079 3 0.4504 0.61107 0.000 0.196 0.804
#> GSM955087 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955088 2 0.0892 0.74562 0.000 0.980 0.020
#> GSM955089 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955095 2 0.5016 0.54811 0.000 0.760 0.240
#> GSM955097 2 0.6829 0.50154 0.096 0.736 0.168
#> GSM955101 2 0.6373 0.16787 0.004 0.588 0.408
#> GSM954999 3 0.8132 0.35984 0.096 0.304 0.600
#> GSM955001 2 0.0237 0.74377 0.000 0.996 0.004
#> GSM955003 3 0.5785 0.48720 0.000 0.332 0.668
#> GSM955004 2 0.3295 0.68348 0.096 0.896 0.008
#> GSM955005 3 0.3722 0.61678 0.088 0.024 0.888
#> GSM955009 2 0.3295 0.68348 0.096 0.896 0.008
#> GSM955011 1 0.4178 0.83883 0.828 0.000 0.172
#> GSM955012 2 0.0747 0.74516 0.000 0.984 0.016
#> GSM955013 3 0.2945 0.62098 0.004 0.088 0.908
#> GSM955015 3 0.6140 0.40939 0.000 0.404 0.596
#> GSM955017 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955021 2 0.5465 0.45253 0.000 0.712 0.288
#> GSM955025 2 0.3295 0.68348 0.096 0.896 0.008
#> GSM955028 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955029 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955030 3 0.4586 0.59648 0.096 0.048 0.856
#> GSM955032 3 0.4555 0.60927 0.000 0.200 0.800
#> GSM955033 3 0.7911 0.39950 0.096 0.272 0.632
#> GSM955034 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955035 2 0.5905 0.33511 0.000 0.648 0.352
#> GSM955036 3 0.8288 0.31333 0.096 0.332 0.572
#> GSM955037 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955039 3 0.3587 0.61536 0.088 0.020 0.892
#> GSM955041 2 0.4605 0.60756 0.000 0.796 0.204
#> GSM955042 1 0.4504 0.81759 0.804 0.000 0.196
#> GSM955045 2 0.1753 0.74140 0.000 0.952 0.048
#> GSM955046 3 0.8452 0.28302 0.096 0.372 0.532
#> GSM955047 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955050 3 0.3886 0.61456 0.096 0.024 0.880
#> GSM955052 3 0.6079 0.43275 0.000 0.388 0.612
#> GSM955053 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955056 3 0.5591 0.52423 0.000 0.304 0.696
#> GSM955058 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955059 3 0.4796 0.60009 0.000 0.220 0.780
#> GSM955060 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955061 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955065 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955066 2 0.6192 0.14203 0.000 0.580 0.420
#> GSM955067 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955073 3 0.7995 0.53028 0.088 0.304 0.608
#> GSM955074 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955076 3 0.3941 0.62055 0.000 0.156 0.844
#> GSM955078 2 0.5497 0.46502 0.000 0.708 0.292
#> GSM955083 3 0.8157 0.35372 0.096 0.308 0.596
#> GSM955084 2 0.3295 0.68348 0.096 0.896 0.008
#> GSM955086 3 0.4504 0.61107 0.000 0.196 0.804
#> GSM955091 2 0.4002 0.67957 0.000 0.840 0.160
#> GSM955092 2 0.1163 0.74554 0.000 0.972 0.028
#> GSM955093 3 0.4689 0.62197 0.096 0.052 0.852
#> GSM955098 2 0.8527 -0.05473 0.096 0.504 0.400
#> GSM955099 2 0.5098 0.48633 0.000 0.752 0.248
#> GSM955100 1 0.4235 0.83594 0.824 0.000 0.176
#> GSM955103 3 0.7591 0.46141 0.068 0.300 0.632
#> GSM955104 3 0.3886 0.61456 0.096 0.024 0.880
#> GSM955106 3 0.6357 0.48541 0.012 0.336 0.652
#> GSM955000 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955006 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955007 2 0.6853 0.49664 0.064 0.712 0.224
#> GSM955010 3 0.3295 0.60465 0.096 0.008 0.896
#> GSM955014 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955018 2 0.8440 -0.10972 0.088 0.492 0.420
#> GSM955020 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955024 2 0.5058 0.55055 0.000 0.756 0.244
#> GSM955026 3 0.8425 0.43623 0.096 0.364 0.540
#> GSM955031 3 0.3886 0.61456 0.096 0.024 0.880
#> GSM955038 3 0.3832 0.61223 0.100 0.020 0.880
#> GSM955040 3 0.8226 0.33384 0.096 0.320 0.584
#> GSM955044 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955051 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955055 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955057 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955062 2 0.2448 0.73276 0.000 0.924 0.076
#> GSM955063 2 0.5431 0.50978 0.000 0.716 0.284
#> GSM955068 3 0.7864 0.50946 0.072 0.332 0.596
#> GSM955069 3 0.8068 0.36322 0.088 0.316 0.596
#> GSM955070 2 0.4399 0.63247 0.000 0.812 0.188
#> GSM955071 3 0.8157 0.35372 0.096 0.308 0.596
#> GSM955077 3 0.6829 0.62059 0.096 0.168 0.736
#> GSM955080 2 0.5165 0.66346 0.096 0.832 0.072
#> GSM955081 2 0.6291 -0.00465 0.000 0.532 0.468
#> GSM955082 2 0.3031 0.73508 0.012 0.912 0.076
#> GSM955085 2 0.0000 0.74345 0.000 1.000 0.000
#> GSM955090 1 0.0000 0.96999 1.000 0.000 0.000
#> GSM955094 2 0.3752 0.69121 0.000 0.856 0.144
#> GSM955096 3 0.5621 0.51946 0.000 0.308 0.692
#> GSM955102 3 0.8157 0.35372 0.096 0.308 0.596
#> GSM955105 3 0.4504 0.61107 0.000 0.196 0.804
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 3 0.3610 0.6573 0.000 0.200 0.800 0.000
#> GSM955008 2 0.5060 0.3037 0.000 0.584 0.412 0.004
#> GSM955016 1 0.4632 0.6994 0.688 0.000 0.004 0.308
#> GSM955019 2 0.2647 0.7448 0.000 0.880 0.120 0.000
#> GSM955022 3 0.2831 0.6899 0.000 0.120 0.876 0.004
#> GSM955023 2 0.5167 0.0973 0.000 0.508 0.488 0.004
#> GSM955027 2 0.0000 0.7745 0.000 1.000 0.000 0.000
#> GSM955043 2 0.0336 0.7738 0.000 0.992 0.000 0.008
#> GSM955048 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955049 2 0.5147 0.1784 0.000 0.536 0.460 0.004
#> GSM955054 2 0.5147 0.1784 0.000 0.536 0.460 0.004
#> GSM955064 2 0.0188 0.7742 0.000 0.996 0.000 0.004
#> GSM955072 2 0.4222 0.5832 0.000 0.728 0.272 0.000
#> GSM955075 2 0.0524 0.7740 0.000 0.988 0.008 0.004
#> GSM955079 3 0.2197 0.6864 0.000 0.080 0.916 0.004
#> GSM955087 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955088 2 0.0469 0.7749 0.000 0.988 0.012 0.000
#> GSM955089 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955095 2 0.2888 0.7336 0.000 0.872 0.124 0.004
#> GSM955097 4 0.5980 0.9476 0.008 0.024 0.456 0.512
#> GSM955101 3 0.4699 0.5427 0.000 0.320 0.676 0.004
#> GSM954999 4 0.5277 0.9805 0.008 0.000 0.460 0.532
#> GSM955001 2 0.0336 0.7738 0.000 0.992 0.000 0.008
#> GSM955003 2 0.5151 0.1669 0.000 0.532 0.464 0.004
#> GSM955004 2 0.5524 0.4518 0.008 0.560 0.008 0.424
#> GSM955005 3 0.2384 0.6727 0.004 0.072 0.916 0.008
#> GSM955009 2 0.5524 0.4518 0.008 0.560 0.008 0.424
#> GSM955011 1 0.3198 0.9128 0.880 0.000 0.080 0.040
#> GSM955012 2 0.0188 0.7752 0.000 0.996 0.004 0.000
#> GSM955013 3 0.1940 0.6834 0.000 0.076 0.924 0.000
#> GSM955015 2 0.5168 -0.0059 0.000 0.500 0.496 0.004
#> GSM955017 1 0.3056 0.9164 0.888 0.000 0.072 0.040
#> GSM955021 2 0.3444 0.6841 0.000 0.816 0.184 0.000
#> GSM955025 2 0.5640 0.4470 0.008 0.556 0.012 0.424
#> GSM955028 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955029 2 0.0336 0.7738 0.000 0.992 0.000 0.008
#> GSM955030 4 0.5296 0.9435 0.008 0.000 0.492 0.500
#> GSM955032 3 0.2081 0.6888 0.000 0.084 0.916 0.000
#> GSM955033 4 0.5292 0.9523 0.008 0.000 0.480 0.512
#> GSM955034 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955035 2 0.3668 0.6917 0.000 0.808 0.188 0.004
#> GSM955036 4 0.5277 0.9805 0.008 0.000 0.460 0.532
#> GSM955037 1 0.4122 0.7881 0.760 0.000 0.004 0.236
#> GSM955039 3 0.2871 0.6581 0.000 0.072 0.896 0.032
#> GSM955041 2 0.2480 0.7546 0.000 0.904 0.088 0.008
#> GSM955042 1 0.5360 0.4709 0.552 0.000 0.012 0.436
#> GSM955045 2 0.0188 0.7752 0.000 0.996 0.004 0.000
#> GSM955046 4 0.5277 0.9805 0.008 0.000 0.460 0.532
#> GSM955047 1 0.3056 0.9164 0.888 0.000 0.072 0.040
#> GSM955050 3 0.1139 0.5393 0.008 0.008 0.972 0.012
#> GSM955052 2 0.5126 0.2207 0.000 0.552 0.444 0.004
#> GSM955053 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955056 3 0.3942 0.6364 0.000 0.236 0.764 0.000
#> GSM955058 2 0.0336 0.7738 0.000 0.992 0.000 0.008
#> GSM955059 3 0.2831 0.6906 0.000 0.120 0.876 0.004
#> GSM955060 1 0.3056 0.9164 0.888 0.000 0.072 0.040
#> GSM955061 2 0.1902 0.7654 0.000 0.932 0.064 0.004
#> GSM955065 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955066 3 0.5080 0.3750 0.000 0.420 0.576 0.004
#> GSM955067 1 0.0336 0.9342 0.992 0.000 0.008 0.000
#> GSM955073 3 0.4011 0.6580 0.000 0.208 0.784 0.008
#> GSM955074 1 0.2983 0.9176 0.892 0.000 0.068 0.040
#> GSM955076 3 0.1940 0.6834 0.000 0.076 0.924 0.000
#> GSM955078 2 0.4193 0.5878 0.000 0.732 0.268 0.000
#> GSM955083 4 0.5277 0.9805 0.008 0.000 0.460 0.532
#> GSM955084 2 0.5524 0.4518 0.008 0.560 0.008 0.424
#> GSM955086 3 0.2197 0.6864 0.000 0.080 0.916 0.004
#> GSM955091 2 0.1211 0.7732 0.000 0.960 0.040 0.000
#> GSM955092 2 0.0188 0.7752 0.000 0.996 0.004 0.000
#> GSM955093 3 0.2522 0.6764 0.000 0.076 0.908 0.016
#> GSM955098 3 0.7888 0.3213 0.008 0.208 0.440 0.344
#> GSM955099 2 0.3539 0.6981 0.000 0.820 0.176 0.004
#> GSM955100 1 0.3156 0.9148 0.884 0.000 0.068 0.048
#> GSM955103 3 0.4057 0.6570 0.000 0.152 0.816 0.032
#> GSM955104 3 0.2530 0.6708 0.008 0.072 0.912 0.008
#> GSM955106 3 0.5132 0.0298 0.004 0.448 0.548 0.000
#> GSM955000 1 0.3056 0.9164 0.888 0.000 0.072 0.040
#> GSM955006 1 0.1211 0.9307 0.960 0.000 0.000 0.040
#> GSM955007 2 0.4086 0.6158 0.000 0.776 0.216 0.008
#> GSM955010 3 0.3975 0.0904 0.000 0.000 0.760 0.240
#> GSM955014 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955018 3 0.7310 -0.1521 0.000 0.212 0.532 0.256
#> GSM955020 1 0.0188 0.9341 0.996 0.000 0.000 0.004
#> GSM955024 2 0.2334 0.7562 0.000 0.908 0.088 0.004
#> GSM955026 3 0.4475 0.6372 0.008 0.240 0.748 0.004
#> GSM955031 3 0.2530 0.6708 0.008 0.072 0.912 0.008
#> GSM955038 3 0.1913 0.4965 0.020 0.000 0.940 0.040
#> GSM955040 4 0.5273 0.9768 0.008 0.000 0.456 0.536
#> GSM955044 2 0.0336 0.7738 0.000 0.992 0.000 0.008
#> GSM955051 1 0.1398 0.9302 0.956 0.000 0.004 0.040
#> GSM955055 2 0.0336 0.7738 0.000 0.992 0.000 0.008
#> GSM955057 1 0.0000 0.9343 1.000 0.000 0.000 0.000
#> GSM955062 2 0.0000 0.7745 0.000 1.000 0.000 0.000
#> GSM955063 2 0.3208 0.7264 0.000 0.848 0.148 0.004
#> GSM955068 3 0.3528 0.6707 0.000 0.192 0.808 0.000
#> GSM955069 3 0.6504 -0.7612 0.000 0.072 0.476 0.452
#> GSM955070 2 0.1867 0.7630 0.000 0.928 0.072 0.000
#> GSM955071 4 0.5277 0.9805 0.008 0.000 0.460 0.532
#> GSM955077 3 0.4364 0.6446 0.008 0.080 0.828 0.084
#> GSM955080 2 0.6818 0.4592 0.008 0.632 0.192 0.168
#> GSM955081 3 0.4936 0.4231 0.000 0.372 0.624 0.004
#> GSM955082 2 0.2081 0.7653 0.000 0.916 0.084 0.000
#> GSM955085 2 0.0188 0.7752 0.000 0.996 0.004 0.000
#> GSM955090 1 0.0188 0.9341 0.996 0.000 0.000 0.004
#> GSM955094 2 0.1716 0.7652 0.000 0.936 0.064 0.000
#> GSM955096 3 0.5168 -0.1122 0.000 0.496 0.500 0.004
#> GSM955102 4 0.4981 0.9704 0.000 0.000 0.464 0.536
#> GSM955105 3 0.2197 0.6864 0.000 0.080 0.916 0.004
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 3 0.5385 0.459 0.000 0.120 0.700 0.164 0.016
#> GSM955008 3 0.1772 0.683 0.000 0.020 0.940 0.032 0.008
#> GSM955016 1 0.2377 0.804 0.872 0.000 0.000 0.128 0.000
#> GSM955019 3 0.1399 0.691 0.000 0.028 0.952 0.000 0.020
#> GSM955022 3 0.4750 0.542 0.000 0.132 0.764 0.024 0.080
#> GSM955023 3 0.2754 0.639 0.000 0.040 0.880 0.000 0.080
#> GSM955027 3 0.5200 0.617 0.000 0.160 0.688 0.000 0.152
#> GSM955043 3 0.5237 0.614 0.000 0.160 0.684 0.000 0.156
#> GSM955048 5 0.3857 0.982 0.312 0.000 0.000 0.000 0.688
#> GSM955049 3 0.2124 0.658 0.000 0.028 0.916 0.000 0.056
#> GSM955054 3 0.2209 0.656 0.000 0.032 0.912 0.000 0.056
#> GSM955064 3 0.5237 0.614 0.000 0.160 0.684 0.000 0.156
#> GSM955072 3 0.1012 0.683 0.000 0.020 0.968 0.000 0.012
#> GSM955075 3 0.5237 0.614 0.000 0.160 0.684 0.000 0.156
#> GSM955079 3 0.7246 0.218 0.000 0.132 0.548 0.212 0.108
#> GSM955087 5 0.3837 0.982 0.308 0.000 0.000 0.000 0.692
#> GSM955088 3 0.4734 0.640 0.000 0.160 0.732 0.000 0.108
#> GSM955089 5 0.3983 0.957 0.340 0.000 0.000 0.000 0.660
#> GSM955095 3 0.3164 0.682 0.000 0.076 0.868 0.044 0.012
#> GSM955097 4 0.3852 0.491 0.000 0.020 0.220 0.760 0.000
#> GSM955101 3 0.3911 0.606 0.000 0.072 0.816 0.104 0.008
#> GSM954999 4 0.0404 0.775 0.000 0.012 0.000 0.988 0.000
#> GSM955001 3 0.5237 0.614 0.000 0.160 0.684 0.000 0.156
#> GSM955003 3 0.2370 0.652 0.000 0.040 0.904 0.000 0.056
#> GSM955004 2 0.2719 0.766 0.000 0.852 0.144 0.004 0.000
#> GSM955005 4 0.4405 0.748 0.000 0.036 0.124 0.792 0.048
#> GSM955009 2 0.2719 0.766 0.000 0.852 0.144 0.004 0.000
#> GSM955011 1 0.2305 0.817 0.896 0.000 0.000 0.092 0.012
#> GSM955012 3 0.4781 0.638 0.000 0.160 0.728 0.000 0.112
#> GSM955013 4 0.5957 0.661 0.000 0.084 0.148 0.684 0.084
#> GSM955015 3 0.1728 0.672 0.000 0.020 0.940 0.036 0.004
#> GSM955017 1 0.0609 0.869 0.980 0.000 0.000 0.000 0.020
#> GSM955021 3 0.3691 0.681 0.000 0.076 0.820 0.000 0.104
#> GSM955025 2 0.2953 0.763 0.000 0.844 0.144 0.012 0.000
#> GSM955028 5 0.3837 0.982 0.308 0.000 0.000 0.000 0.692
#> GSM955029 3 0.5237 0.614 0.000 0.160 0.684 0.000 0.156
#> GSM955030 4 0.0727 0.776 0.004 0.012 0.000 0.980 0.004
#> GSM955032 3 0.7490 -0.196 0.000 0.132 0.432 0.352 0.084
#> GSM955033 4 0.0609 0.785 0.000 0.000 0.020 0.980 0.000
#> GSM955034 5 0.3837 0.982 0.308 0.000 0.000 0.000 0.692
#> GSM955035 3 0.2376 0.687 0.000 0.052 0.904 0.044 0.000
#> GSM955036 4 0.0162 0.778 0.000 0.004 0.000 0.996 0.000
#> GSM955037 1 0.0963 0.868 0.964 0.000 0.000 0.036 0.000
#> GSM955039 4 0.3753 0.759 0.000 0.020 0.116 0.828 0.036
#> GSM955041 3 0.4669 0.669 0.000 0.156 0.764 0.048 0.032
#> GSM955042 1 0.3596 0.705 0.776 0.012 0.000 0.212 0.000
#> GSM955045 3 0.4496 0.649 0.000 0.156 0.752 0.000 0.092
#> GSM955046 4 0.0671 0.778 0.000 0.016 0.004 0.980 0.000
#> GSM955047 1 0.0451 0.869 0.988 0.004 0.000 0.000 0.008
#> GSM955050 4 0.7718 0.487 0.276 0.052 0.100 0.516 0.056
#> GSM955052 3 0.1820 0.670 0.000 0.020 0.940 0.020 0.020
#> GSM955053 5 0.3837 0.982 0.308 0.000 0.000 0.000 0.692
#> GSM955056 3 0.3040 0.638 0.000 0.044 0.876 0.012 0.068
#> GSM955058 3 0.5237 0.614 0.000 0.160 0.684 0.000 0.156
#> GSM955059 3 0.7384 -0.232 0.000 0.132 0.424 0.372 0.072
#> GSM955060 1 0.0510 0.868 0.984 0.000 0.000 0.000 0.016
#> GSM955061 3 0.5500 0.614 0.000 0.160 0.684 0.012 0.144
#> GSM955065 5 0.3837 0.982 0.308 0.000 0.000 0.000 0.692
#> GSM955066 3 0.5408 0.465 0.000 0.116 0.668 0.212 0.004
#> GSM955067 5 0.3837 0.982 0.308 0.000 0.000 0.000 0.692
#> GSM955073 3 0.3234 0.626 0.000 0.012 0.836 0.144 0.008
#> GSM955074 1 0.0510 0.868 0.984 0.000 0.000 0.000 0.016
#> GSM955076 4 0.7216 0.437 0.000 0.132 0.256 0.528 0.084
#> GSM955078 3 0.1408 0.690 0.000 0.044 0.948 0.000 0.008
#> GSM955083 4 0.0404 0.775 0.000 0.012 0.000 0.988 0.000
#> GSM955084 2 0.2719 0.766 0.000 0.852 0.144 0.004 0.000
#> GSM955086 3 0.7746 -0.227 0.000 0.132 0.400 0.356 0.112
#> GSM955091 3 0.2193 0.693 0.000 0.060 0.912 0.000 0.028
#> GSM955092 3 0.4559 0.648 0.000 0.152 0.748 0.000 0.100
#> GSM955093 4 0.4675 0.671 0.000 0.060 0.196 0.736 0.008
#> GSM955098 2 0.6081 0.491 0.016 0.628 0.272 0.044 0.040
#> GSM955099 3 0.2984 0.689 0.000 0.108 0.860 0.000 0.032
#> GSM955100 1 0.1281 0.867 0.956 0.000 0.000 0.032 0.012
#> GSM955103 4 0.3973 0.726 0.000 0.036 0.164 0.792 0.008
#> GSM955104 4 0.5706 0.725 0.072 0.036 0.096 0.740 0.056
#> GSM955106 3 0.4395 0.561 0.000 0.116 0.780 0.008 0.096
#> GSM955000 1 0.0609 0.869 0.980 0.000 0.000 0.000 0.020
#> GSM955006 1 0.0865 0.864 0.972 0.000 0.000 0.004 0.024
#> GSM955007 3 0.5597 0.570 0.000 0.160 0.640 0.200 0.000
#> GSM955010 4 0.2416 0.778 0.000 0.012 0.100 0.888 0.000
#> GSM955014 5 0.3876 0.979 0.316 0.000 0.000 0.000 0.684
#> GSM955018 4 0.2720 0.768 0.000 0.020 0.096 0.880 0.004
#> GSM955020 5 0.4299 0.879 0.388 0.000 0.000 0.004 0.608
#> GSM955024 3 0.4287 0.675 0.000 0.128 0.792 0.016 0.064
#> GSM955026 3 0.4497 0.566 0.000 0.136 0.776 0.072 0.016
#> GSM955031 4 0.7664 0.597 0.128 0.116 0.084 0.592 0.080
#> GSM955038 1 0.6294 0.547 0.676 0.020 0.060 0.160 0.084
#> GSM955040 4 0.4457 0.364 0.328 0.012 0.000 0.656 0.004
#> GSM955044 3 0.5237 0.614 0.000 0.160 0.684 0.000 0.156
#> GSM955051 1 0.0404 0.869 0.988 0.000 0.000 0.000 0.012
#> GSM955055 3 0.5237 0.614 0.000 0.160 0.684 0.000 0.156
#> GSM955057 5 0.3857 0.982 0.312 0.000 0.000 0.000 0.688
#> GSM955062 3 0.4926 0.638 0.000 0.132 0.716 0.000 0.152
#> GSM955063 3 0.3115 0.687 0.000 0.112 0.852 0.036 0.000
#> GSM955068 3 0.4250 0.568 0.000 0.140 0.792 0.048 0.020
#> GSM955069 4 0.1211 0.781 0.000 0.016 0.024 0.960 0.000
#> GSM955070 3 0.3868 0.673 0.000 0.060 0.800 0.000 0.140
#> GSM955071 4 0.0404 0.775 0.000 0.012 0.000 0.988 0.000
#> GSM955077 2 0.7928 -0.216 0.036 0.440 0.112 0.344 0.068
#> GSM955080 3 0.6088 0.428 0.000 0.156 0.548 0.296 0.000
#> GSM955081 3 0.6185 0.285 0.000 0.128 0.548 0.316 0.008
#> GSM955082 3 0.2625 0.691 0.000 0.108 0.876 0.000 0.016
#> GSM955085 3 0.4872 0.635 0.000 0.160 0.720 0.000 0.120
#> GSM955090 5 0.3913 0.974 0.324 0.000 0.000 0.000 0.676
#> GSM955094 3 0.3844 0.675 0.000 0.064 0.804 0.000 0.132
#> GSM955096 3 0.3590 0.600 0.000 0.092 0.828 0.000 0.080
#> GSM955102 4 0.0000 0.777 0.000 0.000 0.000 1.000 0.000
#> GSM955105 3 0.7513 0.189 0.000 0.132 0.516 0.220 0.132
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 4 0.5101 0.0866 0.000 0.424 0.068 0.504 0.000 0.004
#> GSM955008 2 0.4354 0.7126 0.000 0.732 0.032 0.200 0.000 0.036
#> GSM955016 1 0.0935 0.8973 0.964 0.000 0.032 0.000 0.004 0.000
#> GSM955019 2 0.3023 0.7351 0.000 0.808 0.008 0.180 0.000 0.004
#> GSM955022 2 0.5004 0.1815 0.000 0.492 0.028 0.456 0.000 0.024
#> GSM955023 2 0.3736 0.6902 0.000 0.716 0.008 0.268 0.000 0.008
#> GSM955027 2 0.0291 0.7529 0.004 0.992 0.000 0.004 0.000 0.000
#> GSM955043 2 0.0858 0.7412 0.004 0.968 0.000 0.028 0.000 0.000
#> GSM955048 6 0.2482 0.9485 0.148 0.000 0.000 0.004 0.000 0.848
#> GSM955049 2 0.3596 0.7188 0.000 0.740 0.008 0.244 0.000 0.008
#> GSM955054 2 0.3911 0.7054 0.000 0.720 0.008 0.252 0.000 0.020
#> GSM955064 2 0.0551 0.7519 0.004 0.984 0.004 0.008 0.000 0.000
#> GSM955072 2 0.3381 0.7323 0.000 0.772 0.008 0.212 0.000 0.008
#> GSM955075 2 0.0653 0.7548 0.004 0.980 0.012 0.004 0.000 0.000
#> GSM955079 4 0.5171 0.0911 0.000 0.416 0.088 0.496 0.000 0.000
#> GSM955087 6 0.2454 0.9433 0.160 0.000 0.000 0.000 0.000 0.840
#> GSM955088 2 0.0622 0.7599 0.000 0.980 0.008 0.012 0.000 0.000
#> GSM955089 6 0.4228 0.8738 0.212 0.000 0.000 0.072 0.000 0.716
#> GSM955095 2 0.3725 0.4984 0.000 0.676 0.008 0.316 0.000 0.000
#> GSM955097 3 0.5038 0.4366 0.008 0.180 0.696 0.096 0.000 0.020
#> GSM955101 2 0.5188 0.4570 0.000 0.592 0.080 0.316 0.000 0.012
#> GSM954999 3 0.0951 0.7588 0.008 0.004 0.968 0.000 0.000 0.020
#> GSM955001 2 0.0692 0.7456 0.004 0.976 0.000 0.020 0.000 0.000
#> GSM955003 2 0.3934 0.7022 0.000 0.716 0.008 0.256 0.000 0.020
#> GSM955004 5 0.2003 0.9018 0.000 0.116 0.000 0.000 0.884 0.000
#> GSM955005 3 0.4330 0.6867 0.000 0.004 0.748 0.156 0.084 0.008
#> GSM955009 5 0.2048 0.8989 0.000 0.120 0.000 0.000 0.880 0.000
#> GSM955011 1 0.0964 0.9028 0.968 0.000 0.012 0.000 0.004 0.016
#> GSM955012 2 0.0146 0.7571 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM955013 3 0.5431 0.5170 0.000 0.036 0.588 0.324 0.044 0.008
#> GSM955015 2 0.4516 0.7074 0.000 0.724 0.032 0.196 0.000 0.048
#> GSM955017 1 0.1245 0.9057 0.952 0.000 0.000 0.016 0.000 0.032
#> GSM955021 2 0.2878 0.7605 0.004 0.828 0.004 0.160 0.000 0.004
#> GSM955025 5 0.2003 0.9018 0.000 0.116 0.000 0.000 0.884 0.000
#> GSM955028 6 0.2340 0.9487 0.148 0.000 0.000 0.000 0.000 0.852
#> GSM955029 2 0.1116 0.7406 0.004 0.960 0.008 0.028 0.000 0.000
#> GSM955030 3 0.1109 0.7636 0.012 0.004 0.964 0.004 0.016 0.000
#> GSM955032 4 0.6188 0.3094 0.000 0.208 0.344 0.436 0.000 0.012
#> GSM955033 3 0.1313 0.7653 0.000 0.004 0.952 0.016 0.000 0.028
#> GSM955034 6 0.2340 0.9487 0.148 0.000 0.000 0.000 0.000 0.852
#> GSM955035 2 0.4330 0.7241 0.000 0.748 0.032 0.172 0.000 0.048
#> GSM955036 3 0.1425 0.7577 0.008 0.012 0.952 0.008 0.000 0.020
#> GSM955037 1 0.1514 0.9047 0.948 0.000 0.016 0.016 0.004 0.016
#> GSM955039 3 0.3184 0.7362 0.000 0.004 0.828 0.140 0.020 0.008
#> GSM955041 2 0.2851 0.7460 0.000 0.876 0.040 0.044 0.000 0.040
#> GSM955042 1 0.3103 0.7910 0.836 0.000 0.132 0.004 0.008 0.020
#> GSM955045 2 0.0363 0.7595 0.000 0.988 0.000 0.012 0.000 0.000
#> GSM955046 3 0.2317 0.7449 0.008 0.008 0.892 0.088 0.000 0.004
#> GSM955047 1 0.2395 0.8498 0.892 0.000 0.000 0.076 0.012 0.020
#> GSM955050 4 0.8141 -0.1151 0.180 0.000 0.224 0.400 0.124 0.072
#> GSM955052 2 0.4397 0.7038 0.000 0.720 0.032 0.216 0.000 0.032
#> GSM955053 6 0.2340 0.9487 0.148 0.000 0.000 0.000 0.000 0.852
#> GSM955056 2 0.4334 0.6905 0.000 0.708 0.028 0.240 0.000 0.024
#> GSM955058 2 0.1116 0.7406 0.004 0.960 0.008 0.028 0.000 0.000
#> GSM955059 4 0.6140 0.3108 0.000 0.216 0.348 0.428 0.000 0.008
#> GSM955060 1 0.0790 0.9085 0.968 0.000 0.000 0.000 0.000 0.032
#> GSM955061 2 0.1003 0.7515 0.004 0.964 0.028 0.004 0.000 0.000
#> GSM955065 6 0.2454 0.9433 0.160 0.000 0.000 0.000 0.000 0.840
#> GSM955066 2 0.5290 -0.0348 0.000 0.472 0.100 0.428 0.000 0.000
#> GSM955067 6 0.2340 0.9487 0.148 0.000 0.000 0.000 0.000 0.852
#> GSM955073 2 0.4600 0.6876 0.000 0.708 0.056 0.212 0.000 0.024
#> GSM955074 1 0.0790 0.9085 0.968 0.000 0.000 0.000 0.000 0.032
#> GSM955076 3 0.5820 0.1110 0.000 0.092 0.480 0.404 0.016 0.008
#> GSM955078 2 0.3166 0.7488 0.000 0.800 0.008 0.184 0.000 0.008
#> GSM955083 3 0.0951 0.7588 0.008 0.004 0.968 0.000 0.000 0.020
#> GSM955084 5 0.2003 0.9018 0.000 0.116 0.000 0.000 0.884 0.000
#> GSM955086 4 0.5321 0.2853 0.000 0.136 0.264 0.596 0.004 0.000
#> GSM955091 2 0.2512 0.7671 0.000 0.868 0.008 0.116 0.000 0.008
#> GSM955092 2 0.0622 0.7607 0.000 0.980 0.008 0.012 0.000 0.000
#> GSM955093 3 0.4817 0.4555 0.000 0.056 0.616 0.320 0.000 0.008
#> GSM955098 5 0.6606 0.4909 0.032 0.128 0.000 0.180 0.588 0.072
#> GSM955099 2 0.3196 0.7590 0.000 0.816 0.008 0.156 0.000 0.020
#> GSM955100 1 0.0777 0.9089 0.972 0.000 0.004 0.000 0.000 0.024
#> GSM955103 3 0.3589 0.6846 0.000 0.012 0.752 0.228 0.000 0.008
#> GSM955104 3 0.5796 0.6360 0.024 0.004 0.668 0.160 0.104 0.040
#> GSM955106 2 0.4630 0.3640 0.000 0.560 0.008 0.404 0.000 0.028
#> GSM955000 1 0.1245 0.9057 0.952 0.000 0.000 0.016 0.000 0.032
#> GSM955006 1 0.0935 0.9084 0.964 0.000 0.000 0.000 0.004 0.032
#> GSM955007 2 0.2755 0.7034 0.000 0.844 0.140 0.004 0.000 0.012
#> GSM955010 3 0.3414 0.7322 0.000 0.004 0.832 0.080 0.076 0.008
#> GSM955014 6 0.3432 0.9294 0.148 0.000 0.000 0.052 0.000 0.800
#> GSM955018 3 0.3071 0.7209 0.000 0.016 0.804 0.180 0.000 0.000
#> GSM955020 6 0.4694 0.7960 0.268 0.000 0.000 0.072 0.004 0.656
#> GSM955024 2 0.1718 0.7695 0.000 0.932 0.016 0.044 0.000 0.008
#> GSM955026 2 0.5267 0.0413 0.000 0.484 0.008 0.452 0.016 0.040
#> GSM955031 4 0.7678 -0.0735 0.124 0.000 0.188 0.488 0.128 0.072
#> GSM955038 1 0.7002 0.4416 0.572 0.000 0.088 0.160 0.112 0.068
#> GSM955040 3 0.4689 -0.0497 0.460 0.000 0.508 0.008 0.004 0.020
#> GSM955044 2 0.0858 0.7412 0.004 0.968 0.000 0.028 0.000 0.000
#> GSM955051 1 0.2501 0.8518 0.888 0.000 0.000 0.072 0.012 0.028
#> GSM955055 2 0.0858 0.7412 0.004 0.968 0.000 0.028 0.000 0.000
#> GSM955057 6 0.2482 0.9485 0.148 0.000 0.000 0.004 0.000 0.848
#> GSM955062 2 0.0291 0.7572 0.004 0.992 0.000 0.004 0.000 0.000
#> GSM955063 2 0.3622 0.7469 0.000 0.820 0.032 0.100 0.000 0.048
#> GSM955068 4 0.4874 -0.0628 0.000 0.456 0.008 0.504 0.012 0.020
#> GSM955069 3 0.2191 0.7455 0.000 0.004 0.876 0.120 0.000 0.000
#> GSM955070 2 0.2884 0.7648 0.004 0.848 0.008 0.128 0.000 0.012
#> GSM955071 3 0.0951 0.7588 0.008 0.004 0.968 0.000 0.000 0.020
#> GSM955077 4 0.7216 -0.1693 0.072 0.000 0.108 0.524 0.224 0.072
#> GSM955080 2 0.4682 0.4015 0.000 0.692 0.228 0.060 0.000 0.020
#> GSM955081 4 0.5800 0.2061 0.000 0.396 0.180 0.424 0.000 0.000
#> GSM955082 2 0.2308 0.7690 0.000 0.880 0.008 0.108 0.000 0.004
#> GSM955085 2 0.0520 0.7579 0.000 0.984 0.008 0.008 0.000 0.000
#> GSM955090 6 0.4228 0.8738 0.212 0.000 0.000 0.072 0.000 0.716
#> GSM955094 2 0.2654 0.7666 0.004 0.864 0.008 0.116 0.000 0.008
#> GSM955096 2 0.4114 0.5547 0.000 0.628 0.008 0.356 0.000 0.008
#> GSM955102 3 0.0964 0.7629 0.004 0.012 0.968 0.016 0.000 0.000
#> GSM955105 4 0.5784 0.3941 0.000 0.288 0.076 0.584 0.004 0.048
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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> ATC:mclust 108 0.9101 2
#> ATC:mclust 78 0.7427 3
#> ATC:mclust 86 0.8660 4
#> ATC:mclust 93 0.0901 5
#> ATC:mclust 84 0.1791 6
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 31589 rows and 108 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 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 0.970 0.987 0.4470 0.558 0.558
#> 3 3 0.657 0.748 0.887 0.3921 0.747 0.566
#> 4 4 0.491 0.435 0.687 0.1376 0.868 0.664
#> 5 5 0.532 0.506 0.715 0.0659 0.774 0.431
#> 6 6 0.572 0.476 0.705 0.0352 0.876 0.611
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
#> GSM955002 2 0.0000 0.984 0.000 1.000
#> GSM955008 2 0.0000 0.984 0.000 1.000
#> GSM955016 1 0.0000 0.990 1.000 0.000
#> GSM955019 2 0.0000 0.984 0.000 1.000
#> GSM955022 2 0.0000 0.984 0.000 1.000
#> GSM955023 2 0.0000 0.984 0.000 1.000
#> GSM955027 2 0.0000 0.984 0.000 1.000
#> GSM955043 2 0.0000 0.984 0.000 1.000
#> GSM955048 1 0.0000 0.990 1.000 0.000
#> GSM955049 2 0.0000 0.984 0.000 1.000
#> GSM955054 2 0.0000 0.984 0.000 1.000
#> GSM955064 2 0.0000 0.984 0.000 1.000
#> GSM955072 2 0.0000 0.984 0.000 1.000
#> GSM955075 2 0.0000 0.984 0.000 1.000
#> GSM955079 2 0.0000 0.984 0.000 1.000
#> GSM955087 1 0.0000 0.990 1.000 0.000
#> GSM955088 2 0.0000 0.984 0.000 1.000
#> GSM955089 1 0.0000 0.990 1.000 0.000
#> GSM955095 2 0.0000 0.984 0.000 1.000
#> GSM955097 2 0.0000 0.984 0.000 1.000
#> GSM955101 2 0.0000 0.984 0.000 1.000
#> GSM954999 1 0.4022 0.919 0.920 0.080
#> GSM955001 2 0.0000 0.984 0.000 1.000
#> GSM955003 2 0.0000 0.984 0.000 1.000
#> GSM955004 2 0.0000 0.984 0.000 1.000
#> GSM955005 1 0.4161 0.914 0.916 0.084
#> GSM955009 2 0.0000 0.984 0.000 1.000
#> GSM955011 1 0.0000 0.990 1.000 0.000
#> GSM955012 2 0.0000 0.984 0.000 1.000
#> GSM955013 2 0.0000 0.984 0.000 1.000
#> GSM955015 2 0.0000 0.984 0.000 1.000
#> GSM955017 1 0.0000 0.990 1.000 0.000
#> GSM955021 2 0.0000 0.984 0.000 1.000
#> GSM955025 2 0.0000 0.984 0.000 1.000
#> GSM955028 1 0.0000 0.990 1.000 0.000
#> GSM955029 2 0.0000 0.984 0.000 1.000
#> GSM955030 1 0.0000 0.990 1.000 0.000
#> GSM955032 2 0.0000 0.984 0.000 1.000
#> GSM955033 2 0.7602 0.723 0.220 0.780
#> GSM955034 1 0.0000 0.990 1.000 0.000
#> GSM955035 2 0.0000 0.984 0.000 1.000
#> GSM955036 2 0.6531 0.798 0.168 0.832
#> GSM955037 1 0.0000 0.990 1.000 0.000
#> GSM955039 2 0.8207 0.663 0.256 0.744
#> GSM955041 2 0.0000 0.984 0.000 1.000
#> GSM955042 1 0.0000 0.990 1.000 0.000
#> GSM955045 2 0.0000 0.984 0.000 1.000
#> GSM955046 2 0.0000 0.984 0.000 1.000
#> GSM955047 1 0.0000 0.990 1.000 0.000
#> GSM955050 1 0.0000 0.990 1.000 0.000
#> GSM955052 2 0.0000 0.984 0.000 1.000
#> GSM955053 1 0.0000 0.990 1.000 0.000
#> GSM955056 2 0.0000 0.984 0.000 1.000
#> GSM955058 2 0.0000 0.984 0.000 1.000
#> GSM955059 2 0.0000 0.984 0.000 1.000
#> GSM955060 1 0.0000 0.990 1.000 0.000
#> GSM955061 2 0.0000 0.984 0.000 1.000
#> GSM955065 1 0.0000 0.990 1.000 0.000
#> GSM955066 2 0.0000 0.984 0.000 1.000
#> GSM955067 1 0.0000 0.990 1.000 0.000
#> GSM955073 2 0.0000 0.984 0.000 1.000
#> GSM955074 1 0.0000 0.990 1.000 0.000
#> GSM955076 2 0.0000 0.984 0.000 1.000
#> GSM955078 2 0.0000 0.984 0.000 1.000
#> GSM955083 1 0.3733 0.928 0.928 0.072
#> GSM955084 2 0.0000 0.984 0.000 1.000
#> GSM955086 2 0.0000 0.984 0.000 1.000
#> GSM955091 2 0.0000 0.984 0.000 1.000
#> GSM955092 2 0.0000 0.984 0.000 1.000
#> GSM955093 2 0.0000 0.984 0.000 1.000
#> GSM955098 2 0.0000 0.984 0.000 1.000
#> GSM955099 2 0.0000 0.984 0.000 1.000
#> GSM955100 1 0.0000 0.990 1.000 0.000
#> GSM955103 2 0.0000 0.984 0.000 1.000
#> GSM955104 1 0.0000 0.990 1.000 0.000
#> GSM955106 2 0.0000 0.984 0.000 1.000
#> GSM955000 1 0.0000 0.990 1.000 0.000
#> GSM955006 1 0.0000 0.990 1.000 0.000
#> GSM955007 2 0.0000 0.984 0.000 1.000
#> GSM955010 1 0.2948 0.947 0.948 0.052
#> GSM955014 1 0.0000 0.990 1.000 0.000
#> GSM955018 2 0.0000 0.984 0.000 1.000
#> GSM955020 1 0.0000 0.990 1.000 0.000
#> GSM955024 2 0.0000 0.984 0.000 1.000
#> GSM955026 2 0.0000 0.984 0.000 1.000
#> GSM955031 1 0.0000 0.990 1.000 0.000
#> GSM955038 1 0.0000 0.990 1.000 0.000
#> GSM955040 1 0.0000 0.990 1.000 0.000
#> GSM955044 2 0.0000 0.984 0.000 1.000
#> GSM955051 1 0.0000 0.990 1.000 0.000
#> GSM955055 2 0.0000 0.984 0.000 1.000
#> GSM955057 1 0.0000 0.990 1.000 0.000
#> GSM955062 2 0.0000 0.984 0.000 1.000
#> GSM955063 2 0.0000 0.984 0.000 1.000
#> GSM955068 2 0.0000 0.984 0.000 1.000
#> GSM955069 2 0.0672 0.977 0.008 0.992
#> GSM955070 2 0.0000 0.984 0.000 1.000
#> GSM955071 1 0.2423 0.958 0.960 0.040
#> GSM955077 2 0.9661 0.367 0.392 0.608
#> GSM955080 2 0.0000 0.984 0.000 1.000
#> GSM955081 2 0.0000 0.984 0.000 1.000
#> GSM955082 2 0.0000 0.984 0.000 1.000
#> GSM955085 2 0.0000 0.984 0.000 1.000
#> GSM955090 1 0.0000 0.990 1.000 0.000
#> GSM955094 2 0.0000 0.984 0.000 1.000
#> GSM955096 2 0.0000 0.984 0.000 1.000
#> GSM955102 2 0.3733 0.914 0.072 0.928
#> GSM955105 2 0.0000 0.984 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM955002 3 0.6045 0.145 0.000 0.380 0.620
#> GSM955008 3 0.0424 0.841 0.000 0.008 0.992
#> GSM955016 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955019 2 0.5591 0.667 0.000 0.696 0.304
#> GSM955022 3 0.0424 0.841 0.000 0.008 0.992
#> GSM955023 3 0.5733 0.454 0.000 0.324 0.676
#> GSM955027 2 0.5216 0.698 0.000 0.740 0.260
#> GSM955043 2 0.6286 0.345 0.000 0.536 0.464
#> GSM955048 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955049 3 0.5465 0.542 0.000 0.288 0.712
#> GSM955054 3 0.4002 0.749 0.000 0.160 0.840
#> GSM955064 3 0.3116 0.796 0.000 0.108 0.892
#> GSM955072 2 0.6299 0.300 0.000 0.524 0.476
#> GSM955075 2 0.1753 0.741 0.000 0.952 0.048
#> GSM955079 3 0.3941 0.754 0.000 0.156 0.844
#> GSM955087 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955088 2 0.5431 0.683 0.000 0.716 0.284
#> GSM955089 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955095 3 0.5882 0.383 0.000 0.348 0.652
#> GSM955097 3 0.2878 0.805 0.000 0.096 0.904
#> GSM955101 3 0.0000 0.841 0.000 0.000 1.000
#> GSM954999 1 0.6189 0.471 0.632 0.004 0.364
#> GSM955001 2 0.5650 0.657 0.000 0.688 0.312
#> GSM955003 3 0.2261 0.820 0.000 0.068 0.932
#> GSM955004 2 0.0237 0.732 0.000 0.996 0.004
#> GSM955005 3 0.5443 0.551 0.260 0.004 0.736
#> GSM955009 2 0.0237 0.732 0.000 0.996 0.004
#> GSM955011 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955012 3 0.2165 0.822 0.000 0.064 0.936
#> GSM955013 3 0.0424 0.841 0.000 0.008 0.992
#> GSM955015 3 0.0237 0.841 0.000 0.004 0.996
#> GSM955017 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955021 3 0.6140 0.190 0.000 0.404 0.596
#> GSM955025 2 0.0237 0.732 0.000 0.996 0.004
#> GSM955028 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955029 2 0.5905 0.606 0.000 0.648 0.352
#> GSM955030 3 0.6228 0.301 0.372 0.004 0.624
#> GSM955032 3 0.0237 0.841 0.000 0.004 0.996
#> GSM955033 3 0.1399 0.818 0.028 0.004 0.968
#> GSM955034 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955035 3 0.0237 0.841 0.000 0.004 0.996
#> GSM955036 3 0.0237 0.838 0.000 0.004 0.996
#> GSM955037 1 0.0475 0.954 0.992 0.004 0.004
#> GSM955039 3 0.0475 0.835 0.004 0.004 0.992
#> GSM955041 3 0.0237 0.841 0.000 0.004 0.996
#> GSM955042 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955045 3 0.3267 0.789 0.000 0.116 0.884
#> GSM955046 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955047 1 0.1411 0.932 0.964 0.036 0.000
#> GSM955050 1 0.0892 0.943 0.980 0.020 0.000
#> GSM955052 3 0.0892 0.839 0.000 0.020 0.980
#> GSM955053 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955056 3 0.0237 0.841 0.000 0.004 0.996
#> GSM955058 3 0.6308 -0.217 0.000 0.492 0.508
#> GSM955059 3 0.0747 0.840 0.000 0.016 0.984
#> GSM955060 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955061 3 0.4178 0.737 0.000 0.172 0.828
#> GSM955065 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955066 3 0.4399 0.717 0.000 0.188 0.812
#> GSM955067 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955073 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955074 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955076 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955078 2 0.5327 0.692 0.000 0.728 0.272
#> GSM955083 1 0.5656 0.611 0.712 0.004 0.284
#> GSM955084 2 0.0237 0.732 0.000 0.996 0.004
#> GSM955086 3 0.4413 0.746 0.008 0.160 0.832
#> GSM955091 2 0.6008 0.570 0.000 0.628 0.372
#> GSM955092 2 0.6180 0.483 0.000 0.584 0.416
#> GSM955093 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955098 2 0.0237 0.732 0.000 0.996 0.004
#> GSM955099 2 0.0892 0.737 0.000 0.980 0.020
#> GSM955100 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955103 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955104 1 0.6468 0.206 0.552 0.004 0.444
#> GSM955106 2 0.4504 0.721 0.000 0.804 0.196
#> GSM955000 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955006 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955007 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955010 3 0.2096 0.788 0.052 0.004 0.944
#> GSM955014 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955018 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955020 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955024 3 0.0424 0.841 0.000 0.008 0.992
#> GSM955026 2 0.0237 0.732 0.000 0.996 0.004
#> GSM955031 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955038 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955040 1 0.0237 0.956 0.996 0.004 0.000
#> GSM955044 3 0.6302 -0.169 0.000 0.480 0.520
#> GSM955051 1 0.0237 0.954 0.996 0.004 0.000
#> GSM955055 2 0.6168 0.491 0.000 0.588 0.412
#> GSM955057 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955062 3 0.4555 0.700 0.000 0.200 0.800
#> GSM955063 3 0.0424 0.841 0.000 0.008 0.992
#> GSM955068 2 0.0747 0.737 0.000 0.984 0.016
#> GSM955069 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955070 2 0.5785 0.634 0.000 0.668 0.332
#> GSM955071 1 0.0424 0.950 0.992 0.000 0.008
#> GSM955077 2 0.2878 0.650 0.096 0.904 0.000
#> GSM955080 3 0.0000 0.841 0.000 0.000 1.000
#> GSM955081 3 0.2959 0.802 0.000 0.100 0.900
#> GSM955082 2 0.1643 0.741 0.000 0.956 0.044
#> GSM955085 2 0.3267 0.737 0.000 0.884 0.116
#> GSM955090 1 0.0000 0.956 1.000 0.000 0.000
#> GSM955094 2 0.6280 0.356 0.000 0.540 0.460
#> GSM955096 3 0.5465 0.534 0.000 0.288 0.712
#> GSM955102 3 0.0237 0.838 0.000 0.004 0.996
#> GSM955105 3 0.5506 0.648 0.016 0.220 0.764
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM955002 4 0.7258 0.07463 0.000 0.164 0.328 0.508
#> GSM955008 3 0.2408 0.53907 0.000 0.036 0.920 0.044
#> GSM955016 1 0.4103 0.64315 0.744 0.000 0.000 0.256
#> GSM955019 2 0.5220 0.52733 0.000 0.568 0.424 0.008
#> GSM955022 3 0.2761 0.53633 0.000 0.048 0.904 0.048
#> GSM955023 3 0.6262 0.15539 0.000 0.280 0.628 0.092
#> GSM955027 2 0.4936 0.59268 0.000 0.624 0.372 0.004
#> GSM955043 2 0.5057 0.60290 0.000 0.648 0.340 0.012
#> GSM955048 1 0.0336 0.83044 0.992 0.000 0.000 0.008
#> GSM955049 3 0.6690 0.26017 0.000 0.192 0.620 0.188
#> GSM955054 3 0.6075 0.36440 0.000 0.148 0.684 0.168
#> GSM955064 3 0.5249 0.31313 0.000 0.248 0.708 0.044
#> GSM955072 3 0.6936 0.12197 0.000 0.284 0.568 0.148
#> GSM955075 2 0.2489 0.57943 0.000 0.912 0.068 0.020
#> GSM955079 3 0.6797 0.27904 0.004 0.148 0.616 0.232
#> GSM955087 1 0.0592 0.82985 0.984 0.000 0.000 0.016
#> GSM955088 2 0.4507 0.61220 0.000 0.756 0.224 0.020
#> GSM955089 1 0.1022 0.82612 0.968 0.000 0.000 0.032
#> GSM955095 3 0.4992 -0.36205 0.000 0.476 0.524 0.000
#> GSM955097 3 0.8046 0.08072 0.004 0.324 0.376 0.296
#> GSM955101 3 0.1867 0.53275 0.000 0.000 0.928 0.072
#> GSM954999 4 0.7292 -0.01090 0.388 0.000 0.152 0.460
#> GSM955001 2 0.4991 0.57959 0.000 0.608 0.388 0.004
#> GSM955003 3 0.6296 0.31107 0.000 0.112 0.644 0.244
#> GSM955004 2 0.1767 0.51944 0.000 0.944 0.012 0.044
#> GSM955005 1 0.5263 0.06858 0.544 0.000 0.448 0.008
#> GSM955009 2 0.1833 0.55317 0.000 0.944 0.032 0.024
#> GSM955011 1 0.0707 0.82642 0.980 0.000 0.000 0.020
#> GSM955012 3 0.4964 0.30432 0.000 0.256 0.716 0.028
#> GSM955013 3 0.2573 0.54200 0.024 0.012 0.920 0.044
#> GSM955015 3 0.3024 0.49320 0.000 0.000 0.852 0.148
#> GSM955017 1 0.0469 0.82841 0.988 0.000 0.000 0.012
#> GSM955021 3 0.5659 -0.06522 0.000 0.368 0.600 0.032
#> GSM955025 2 0.2334 0.46621 0.000 0.908 0.004 0.088
#> GSM955028 1 0.0592 0.82985 0.984 0.000 0.000 0.016
#> GSM955029 2 0.4746 0.60058 0.000 0.632 0.368 0.000
#> GSM955030 1 0.7732 -0.17066 0.392 0.000 0.380 0.228
#> GSM955032 3 0.4467 0.45155 0.000 0.040 0.788 0.172
#> GSM955033 4 0.6755 -0.16884 0.092 0.000 0.452 0.456
#> GSM955034 1 0.0592 0.82985 0.984 0.000 0.000 0.016
#> GSM955035 3 0.3688 0.45340 0.000 0.000 0.792 0.208
#> GSM955036 3 0.5670 0.23078 0.020 0.004 0.572 0.404
#> GSM955037 1 0.3448 0.70031 0.828 0.000 0.004 0.168
#> GSM955039 3 0.4697 0.31077 0.000 0.000 0.644 0.356
#> GSM955041 3 0.4511 0.40249 0.000 0.008 0.724 0.268
#> GSM955042 1 0.3048 0.78930 0.876 0.016 0.000 0.108
#> GSM955045 3 0.4797 0.29288 0.000 0.260 0.720 0.020
#> GSM955046 3 0.4978 0.28432 0.000 0.004 0.612 0.384
#> GSM955047 1 0.3539 0.73046 0.820 0.004 0.000 0.176
#> GSM955050 1 0.3172 0.72921 0.840 0.000 0.000 0.160
#> GSM955052 3 0.3820 0.52292 0.000 0.088 0.848 0.064
#> GSM955053 1 0.0921 0.82774 0.972 0.000 0.000 0.028
#> GSM955056 3 0.2385 0.53894 0.000 0.028 0.920 0.052
#> GSM955058 2 0.5435 0.52527 0.000 0.564 0.420 0.016
#> GSM955059 3 0.1388 0.55267 0.000 0.028 0.960 0.012
#> GSM955060 1 0.0000 0.83009 1.000 0.000 0.000 0.000
#> GSM955061 2 0.7720 0.03907 0.000 0.412 0.360 0.228
#> GSM955065 1 0.0592 0.82985 0.984 0.000 0.000 0.016
#> GSM955066 3 0.6946 0.31072 0.000 0.252 0.580 0.168
#> GSM955067 1 0.0592 0.82889 0.984 0.000 0.000 0.016
#> GSM955073 3 0.2868 0.50592 0.000 0.000 0.864 0.136
#> GSM955074 1 0.1118 0.82826 0.964 0.000 0.000 0.036
#> GSM955076 3 0.4936 0.30430 0.000 0.012 0.672 0.316
#> GSM955078 3 0.6889 -0.21015 0.000 0.396 0.496 0.108
#> GSM955083 4 0.7009 -0.11942 0.440 0.000 0.116 0.444
#> GSM955084 2 0.1833 0.54102 0.000 0.944 0.024 0.032
#> GSM955086 3 0.6528 0.33335 0.008 0.140 0.660 0.192
#> GSM955091 2 0.5378 0.48943 0.000 0.540 0.448 0.012
#> GSM955092 2 0.5105 0.52913 0.000 0.564 0.432 0.004
#> GSM955093 3 0.4543 0.34631 0.000 0.000 0.676 0.324
#> GSM955098 2 0.5671 0.15557 0.000 0.572 0.028 0.400
#> GSM955099 2 0.5397 0.62560 0.000 0.720 0.212 0.068
#> GSM955100 1 0.0336 0.83072 0.992 0.000 0.000 0.008
#> GSM955103 3 0.3400 0.47703 0.000 0.000 0.820 0.180
#> GSM955104 1 0.6714 0.29988 0.612 0.000 0.228 0.160
#> GSM955106 4 0.7493 -0.03763 0.000 0.200 0.320 0.480
#> GSM955000 1 0.0469 0.82841 0.988 0.000 0.000 0.012
#> GSM955006 1 0.1557 0.81890 0.944 0.000 0.000 0.056
#> GSM955007 3 0.5040 0.30532 0.000 0.008 0.628 0.364
#> GSM955010 3 0.6306 0.17568 0.064 0.000 0.544 0.392
#> GSM955014 1 0.0921 0.82855 0.972 0.000 0.000 0.028
#> GSM955018 3 0.4711 0.43794 0.000 0.024 0.740 0.236
#> GSM955020 1 0.2345 0.80590 0.900 0.000 0.000 0.100
#> GSM955024 3 0.2983 0.55208 0.000 0.068 0.892 0.040
#> GSM955026 2 0.7580 0.36646 0.000 0.476 0.228 0.296
#> GSM955031 1 0.6282 0.25332 0.552 0.008 0.044 0.396
#> GSM955038 4 0.5648 -0.20184 0.444 0.016 0.004 0.536
#> GSM955040 1 0.5576 0.19570 0.496 0.012 0.004 0.488
#> GSM955044 2 0.5466 0.49595 0.000 0.548 0.436 0.016
#> GSM955051 1 0.3271 0.77850 0.856 0.012 0.000 0.132
#> GSM955055 2 0.4679 0.61430 0.000 0.648 0.352 0.000
#> GSM955057 1 0.0000 0.83009 1.000 0.000 0.000 0.000
#> GSM955062 3 0.4406 0.18502 0.000 0.300 0.700 0.000
#> GSM955063 3 0.2644 0.54764 0.000 0.032 0.908 0.060
#> GSM955068 4 0.7912 -0.18841 0.004 0.248 0.324 0.424
#> GSM955069 3 0.4944 0.42597 0.032 0.004 0.744 0.220
#> GSM955070 2 0.6878 0.44923 0.000 0.556 0.316 0.128
#> GSM955071 1 0.5713 0.38797 0.620 0.000 0.040 0.340
#> GSM955077 2 0.5976 0.27716 0.076 0.708 0.016 0.200
#> GSM955080 3 0.6583 0.21604 0.000 0.084 0.528 0.388
#> GSM955081 3 0.5172 0.28075 0.000 0.260 0.704 0.036
#> GSM955082 2 0.4999 0.61736 0.000 0.660 0.328 0.012
#> GSM955085 2 0.3583 0.64202 0.000 0.816 0.180 0.004
#> GSM955090 1 0.1557 0.82319 0.944 0.000 0.000 0.056
#> GSM955094 2 0.6507 0.34564 0.000 0.520 0.404 0.076
#> GSM955096 3 0.6373 0.22069 0.000 0.248 0.636 0.116
#> GSM955102 3 0.5733 0.31117 0.028 0.008 0.632 0.332
#> GSM955105 4 0.6837 -0.00625 0.000 0.100 0.428 0.472
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM955002 2 0.7486 0.3341 0.000 0.436 0.048 0.280 0.236
#> GSM955008 3 0.6100 0.4108 0.000 0.308 0.540 0.152 0.000
#> GSM955016 1 0.6126 0.1635 0.500 0.012 0.000 0.396 0.092
#> GSM955019 3 0.2751 0.5512 0.000 0.044 0.896 0.020 0.040
#> GSM955022 3 0.6295 0.4251 0.000 0.308 0.540 0.144 0.008
#> GSM955023 3 0.4752 0.5131 0.000 0.272 0.684 0.040 0.004
#> GSM955027 3 0.3779 0.3886 0.000 0.048 0.812 0.004 0.136
#> GSM955043 3 0.4713 0.2049 0.000 0.028 0.724 0.024 0.224
#> GSM955048 1 0.0854 0.8720 0.976 0.008 0.000 0.004 0.012
#> GSM955049 3 0.5073 0.4721 0.000 0.312 0.640 0.040 0.008
#> GSM955054 3 0.5469 0.3724 0.000 0.392 0.548 0.056 0.004
#> GSM955064 3 0.5144 0.5450 0.000 0.052 0.744 0.136 0.068
#> GSM955072 2 0.7051 0.0641 0.000 0.416 0.412 0.048 0.124
#> GSM955075 3 0.4911 -0.5639 0.000 0.012 0.504 0.008 0.476
#> GSM955079 3 0.6150 0.4423 0.008 0.316 0.588 0.044 0.044
#> GSM955087 1 0.0854 0.8704 0.976 0.004 0.000 0.008 0.012
#> GSM955088 3 0.4479 0.1661 0.000 0.000 0.700 0.036 0.264
#> GSM955089 1 0.1673 0.8699 0.944 0.016 0.000 0.008 0.032
#> GSM955095 3 0.2597 0.5464 0.000 0.004 0.896 0.060 0.040
#> GSM955097 3 0.6214 0.2602 0.024 0.004 0.632 0.144 0.196
#> GSM955101 3 0.6157 0.3056 0.000 0.140 0.496 0.364 0.000
#> GSM954999 4 0.4499 0.5734 0.136 0.012 0.016 0.788 0.048
#> GSM955001 3 0.2907 0.4753 0.000 0.008 0.864 0.012 0.116
#> GSM955003 2 0.4575 0.5286 0.000 0.744 0.184 0.068 0.004
#> GSM955004 5 0.4171 0.6650 0.000 0.000 0.396 0.000 0.604
#> GSM955005 1 0.6753 0.3464 0.592 0.084 0.104 0.220 0.000
#> GSM955009 5 0.4736 0.6603 0.000 0.020 0.404 0.000 0.576
#> GSM955011 1 0.1299 0.8696 0.960 0.008 0.000 0.012 0.020
#> GSM955012 3 0.2052 0.5691 0.000 0.004 0.912 0.080 0.004
#> GSM955013 3 0.7316 0.4040 0.032 0.280 0.512 0.156 0.020
#> GSM955015 2 0.6660 0.1399 0.000 0.444 0.268 0.288 0.000
#> GSM955017 1 0.1377 0.8693 0.956 0.020 0.000 0.004 0.020
#> GSM955021 3 0.5385 0.4670 0.000 0.248 0.660 0.008 0.084
#> GSM955025 5 0.3491 0.5905 0.000 0.004 0.228 0.000 0.768
#> GSM955028 1 0.0854 0.8704 0.976 0.004 0.000 0.008 0.012
#> GSM955029 3 0.3488 0.3166 0.000 0.008 0.804 0.008 0.180
#> GSM955030 4 0.5477 0.3991 0.352 0.004 0.064 0.580 0.000
#> GSM955032 3 0.6426 0.2710 0.000 0.416 0.468 0.088 0.028
#> GSM955033 4 0.3199 0.6241 0.048 0.056 0.008 0.876 0.012
#> GSM955034 1 0.0968 0.8694 0.972 0.004 0.000 0.012 0.012
#> GSM955035 4 0.6258 0.1086 0.000 0.140 0.344 0.512 0.004
#> GSM955036 4 0.1441 0.6537 0.004 0.008 0.024 0.956 0.008
#> GSM955037 1 0.2349 0.8347 0.900 0.004 0.000 0.084 0.012
#> GSM955039 4 0.2681 0.6481 0.004 0.052 0.052 0.892 0.000
#> GSM955041 4 0.4800 0.2665 0.000 0.028 0.368 0.604 0.000
#> GSM955042 1 0.4642 0.7433 0.736 0.016 0.000 0.040 0.208
#> GSM955045 3 0.2177 0.5701 0.000 0.004 0.908 0.080 0.008
#> GSM955046 4 0.2054 0.6542 0.000 0.008 0.072 0.916 0.004
#> GSM955047 1 0.5474 0.6814 0.656 0.072 0.000 0.016 0.256
#> GSM955050 1 0.4602 0.7653 0.776 0.100 0.000 0.020 0.104
#> GSM955052 3 0.6207 0.4265 0.000 0.312 0.548 0.132 0.008
#> GSM955053 1 0.1299 0.8675 0.960 0.012 0.000 0.008 0.020
#> GSM955056 3 0.6266 0.4240 0.000 0.300 0.548 0.144 0.008
#> GSM955058 3 0.2953 0.3845 0.000 0.000 0.844 0.012 0.144
#> GSM955059 3 0.5999 0.4992 0.000 0.160 0.612 0.220 0.008
#> GSM955060 1 0.1200 0.8703 0.964 0.012 0.000 0.008 0.016
#> GSM955061 3 0.5091 0.2744 0.000 0.000 0.692 0.112 0.196
#> GSM955065 1 0.0968 0.8694 0.972 0.004 0.000 0.012 0.012
#> GSM955066 3 0.4958 0.5150 0.000 0.012 0.728 0.176 0.084
#> GSM955067 1 0.1403 0.8694 0.952 0.024 0.000 0.000 0.024
#> GSM955073 3 0.6564 0.2819 0.000 0.212 0.444 0.344 0.000
#> GSM955074 1 0.1800 0.8640 0.932 0.020 0.000 0.000 0.048
#> GSM955076 2 0.5433 0.5314 0.004 0.720 0.108 0.140 0.028
#> GSM955078 3 0.6413 0.2563 0.000 0.336 0.532 0.024 0.108
#> GSM955083 4 0.4783 0.5336 0.224 0.004 0.008 0.720 0.044
#> GSM955084 5 0.4171 0.6529 0.000 0.000 0.396 0.000 0.604
#> GSM955086 3 0.6408 0.4694 0.028 0.288 0.600 0.044 0.040
#> GSM955091 3 0.2872 0.5269 0.000 0.048 0.884 0.008 0.060
#> GSM955092 3 0.1300 0.5305 0.000 0.016 0.956 0.000 0.028
#> GSM955093 4 0.3683 0.6171 0.000 0.096 0.072 0.828 0.004
#> GSM955098 2 0.5697 0.1783 0.000 0.512 0.084 0.000 0.404
#> GSM955099 5 0.6633 0.3559 0.000 0.220 0.384 0.000 0.396
#> GSM955100 1 0.2178 0.8627 0.920 0.008 0.000 0.048 0.024
#> GSM955103 4 0.5594 0.0769 0.000 0.064 0.400 0.532 0.004
#> GSM955104 1 0.6528 0.5494 0.636 0.224 0.056 0.040 0.044
#> GSM955106 2 0.3506 0.5614 0.000 0.852 0.076 0.020 0.052
#> GSM955000 1 0.1173 0.8703 0.964 0.012 0.000 0.004 0.020
#> GSM955006 1 0.3361 0.8301 0.840 0.020 0.000 0.012 0.128
#> GSM955007 4 0.2956 0.6273 0.000 0.008 0.140 0.848 0.004
#> GSM955010 4 0.3321 0.6246 0.032 0.092 0.012 0.860 0.004
#> GSM955014 1 0.1280 0.8712 0.960 0.008 0.000 0.008 0.024
#> GSM955018 3 0.5028 0.4616 0.004 0.024 0.648 0.312 0.012
#> GSM955020 1 0.3223 0.8332 0.852 0.016 0.000 0.016 0.116
#> GSM955024 3 0.4039 0.5704 0.000 0.036 0.776 0.184 0.004
#> GSM955026 2 0.5993 0.2613 0.000 0.580 0.172 0.000 0.248
#> GSM955031 1 0.6566 0.4441 0.560 0.308 0.016 0.020 0.096
#> GSM955038 2 0.4938 0.4086 0.176 0.740 0.000 0.044 0.040
#> GSM955040 4 0.5780 0.4680 0.228 0.012 0.000 0.640 0.120
#> GSM955044 3 0.4037 0.3296 0.000 0.012 0.784 0.028 0.176
#> GSM955051 1 0.4660 0.7691 0.752 0.044 0.000 0.024 0.180
#> GSM955055 3 0.3631 0.2809 0.000 0.008 0.788 0.008 0.196
#> GSM955057 1 0.0324 0.8717 0.992 0.004 0.000 0.000 0.004
#> GSM955062 3 0.4010 0.5477 0.000 0.044 0.828 0.060 0.068
#> GSM955063 3 0.6124 0.4450 0.000 0.200 0.564 0.236 0.000
#> GSM955068 2 0.4665 0.4791 0.000 0.752 0.156 0.008 0.084
#> GSM955069 3 0.5819 0.1420 0.024 0.028 0.496 0.444 0.008
#> GSM955070 2 0.6970 0.0634 0.000 0.480 0.228 0.020 0.272
#> GSM955071 4 0.5747 0.2080 0.404 0.008 0.016 0.536 0.036
#> GSM955077 5 0.6344 0.2846 0.052 0.152 0.112 0.016 0.668
#> GSM955080 4 0.2765 0.6252 0.000 0.036 0.044 0.896 0.024
#> GSM955081 3 0.4900 0.5690 0.000 0.068 0.764 0.120 0.048
#> GSM955082 3 0.3031 0.4595 0.000 0.020 0.856 0.004 0.120
#> GSM955085 3 0.4194 0.0213 0.000 0.012 0.708 0.004 0.276
#> GSM955090 1 0.1461 0.8703 0.952 0.004 0.000 0.016 0.028
#> GSM955094 5 0.7913 0.2878 0.000 0.176 0.276 0.116 0.432
#> GSM955096 3 0.5335 0.4763 0.000 0.300 0.632 0.060 0.008
#> GSM955102 4 0.3490 0.6091 0.008 0.008 0.164 0.816 0.004
#> GSM955105 2 0.3514 0.5709 0.000 0.852 0.072 0.056 0.020
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM955002 4 0.6848 0.0702 0.000 0.036 0.312 0.376 0.004 0.272
#> GSM955008 2 0.3296 0.5896 0.000 0.860 0.040 0.052 0.028 0.020
#> GSM955016 1 0.6237 -0.0258 0.452 0.000 0.404 0.040 0.008 0.096
#> GSM955019 2 0.3136 0.4931 0.000 0.768 0.000 0.000 0.228 0.004
#> GSM955022 2 0.3065 0.5852 0.000 0.864 0.020 0.080 0.024 0.012
#> GSM955023 2 0.2252 0.5862 0.000 0.900 0.000 0.012 0.072 0.016
#> GSM955027 2 0.4331 -0.0413 0.000 0.540 0.004 0.004 0.444 0.008
#> GSM955043 5 0.4760 0.4574 0.000 0.372 0.008 0.004 0.584 0.032
#> GSM955048 1 0.0458 0.8397 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM955049 2 0.2976 0.5842 0.000 0.872 0.004 0.048 0.048 0.028
#> GSM955054 2 0.3479 0.5736 0.000 0.836 0.004 0.088 0.044 0.028
#> GSM955064 2 0.4694 0.3577 0.000 0.636 0.044 0.000 0.308 0.012
#> GSM955072 4 0.7093 0.1719 0.000 0.100 0.020 0.456 0.316 0.108
#> GSM955075 5 0.4102 0.5283 0.000 0.164 0.004 0.000 0.752 0.080
#> GSM955079 2 0.2121 0.5938 0.000 0.916 0.004 0.032 0.040 0.008
#> GSM955087 1 0.0622 0.8378 0.980 0.000 0.008 0.000 0.000 0.012
#> GSM955088 2 0.5138 0.0179 0.000 0.520 0.020 0.000 0.416 0.044
#> GSM955089 1 0.1296 0.8381 0.948 0.000 0.004 0.004 0.000 0.044
#> GSM955095 2 0.4323 0.2273 0.000 0.600 0.020 0.004 0.376 0.000
#> GSM955097 5 0.6224 0.3658 0.016 0.144 0.048 0.028 0.652 0.112
#> GSM955101 2 0.3000 0.5771 0.000 0.824 0.156 0.004 0.016 0.000
#> GSM954999 3 0.4790 0.6237 0.116 0.004 0.752 0.044 0.008 0.076
#> GSM955001 5 0.4763 0.4284 0.000 0.388 0.004 0.016 0.572 0.020
#> GSM955003 2 0.5504 0.0532 0.000 0.536 0.016 0.384 0.024 0.040
#> GSM955004 5 0.3290 0.3752 0.000 0.044 0.000 0.004 0.820 0.132
#> GSM955005 1 0.7159 0.2012 0.488 0.224 0.188 0.084 0.012 0.004
#> GSM955009 5 0.3946 0.3851 0.000 0.076 0.000 0.004 0.768 0.152
#> GSM955011 1 0.1075 0.8352 0.952 0.000 0.000 0.000 0.000 0.048
#> GSM955012 2 0.3975 0.1529 0.000 0.600 0.000 0.000 0.392 0.008
#> GSM955013 2 0.5462 0.4836 0.008 0.708 0.024 0.140 0.080 0.040
#> GSM955015 2 0.5769 0.3793 0.000 0.616 0.148 0.204 0.008 0.024
#> GSM955017 1 0.1480 0.8324 0.940 0.000 0.000 0.020 0.000 0.040
#> GSM955021 2 0.4954 0.3470 0.000 0.644 0.004 0.072 0.272 0.008
#> GSM955025 5 0.4871 -0.2667 0.000 0.024 0.008 0.012 0.560 0.396
#> GSM955028 1 0.0363 0.8379 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM955029 5 0.3899 0.4655 0.000 0.404 0.004 0.000 0.592 0.000
#> GSM955030 3 0.5576 0.2135 0.416 0.076 0.488 0.004 0.000 0.016
#> GSM955032 2 0.4753 0.4822 0.000 0.716 0.012 0.200 0.028 0.044
#> GSM955033 3 0.1994 0.6998 0.008 0.004 0.920 0.052 0.000 0.016
#> GSM955034 1 0.0405 0.8379 0.988 0.000 0.004 0.000 0.000 0.008
#> GSM955035 2 0.5781 0.3056 0.000 0.536 0.332 0.104 0.028 0.000
#> GSM955036 3 0.1067 0.7070 0.000 0.024 0.964 0.004 0.004 0.004
#> GSM955037 1 0.1926 0.8162 0.912 0.000 0.068 0.000 0.000 0.020
#> GSM955039 3 0.3024 0.7047 0.004 0.048 0.868 0.064 0.004 0.012
#> GSM955041 2 0.4076 0.3959 0.000 0.620 0.364 0.000 0.016 0.000
#> GSM955042 1 0.4189 0.7486 0.780 0.000 0.056 0.024 0.008 0.132
#> GSM955045 2 0.3452 0.4553 0.000 0.736 0.004 0.000 0.256 0.004
#> GSM955046 3 0.2115 0.7049 0.000 0.052 0.916 0.012 0.012 0.008
#> GSM955047 1 0.4260 0.3763 0.512 0.000 0.000 0.016 0.000 0.472
#> GSM955050 1 0.5528 0.5002 0.572 0.008 0.000 0.100 0.008 0.312
#> GSM955052 2 0.3384 0.5865 0.000 0.852 0.020 0.044 0.064 0.020
#> GSM955053 1 0.1477 0.8310 0.940 0.000 0.008 0.004 0.000 0.048
#> GSM955056 2 0.3660 0.5689 0.000 0.824 0.008 0.080 0.072 0.016
#> GSM955058 5 0.3699 0.5578 0.000 0.336 0.000 0.000 0.660 0.004
#> GSM955059 2 0.5138 0.5182 0.000 0.728 0.084 0.044 0.120 0.024
#> GSM955060 1 0.0937 0.8354 0.960 0.000 0.000 0.000 0.000 0.040
#> GSM955061 5 0.4035 0.5843 0.000 0.272 0.016 0.000 0.700 0.012
#> GSM955065 1 0.0000 0.8379 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955066 2 0.7043 0.1984 0.000 0.456 0.152 0.016 0.304 0.072
#> GSM955067 1 0.1644 0.8317 0.932 0.000 0.000 0.028 0.000 0.040
#> GSM955073 2 0.3634 0.5564 0.000 0.792 0.168 0.024 0.008 0.008
#> GSM955074 1 0.3093 0.8013 0.852 0.000 0.004 0.044 0.008 0.092
#> GSM955076 4 0.5659 0.3720 0.000 0.100 0.052 0.696 0.044 0.108
#> GSM955078 2 0.6418 -0.0299 0.000 0.436 0.004 0.224 0.320 0.016
#> GSM955083 3 0.5623 0.5094 0.236 0.004 0.640 0.032 0.012 0.076
#> GSM955084 5 0.3679 0.3445 0.000 0.036 0.004 0.024 0.812 0.124
#> GSM955086 2 0.2557 0.5936 0.000 0.892 0.012 0.036 0.056 0.004
#> GSM955091 2 0.3390 0.3868 0.000 0.704 0.000 0.000 0.296 0.000
#> GSM955092 2 0.3351 0.4197 0.000 0.712 0.000 0.000 0.288 0.000
#> GSM955093 3 0.4354 0.6318 0.000 0.112 0.752 0.120 0.000 0.016
#> GSM955098 4 0.5840 0.0584 0.000 0.012 0.000 0.472 0.136 0.380
#> GSM955099 2 0.6825 -0.1127 0.000 0.416 0.004 0.060 0.352 0.168
#> GSM955100 1 0.2149 0.8179 0.900 0.000 0.080 0.004 0.000 0.016
#> GSM955103 2 0.4322 0.3610 0.000 0.600 0.372 0.000 0.028 0.000
#> GSM955104 1 0.6307 0.5608 0.640 0.116 0.012 0.132 0.016 0.084
#> GSM955106 4 0.5819 0.2665 0.000 0.268 0.004 0.560 0.012 0.156
#> GSM955000 1 0.1116 0.8371 0.960 0.000 0.004 0.008 0.000 0.028
#> GSM955006 1 0.3058 0.7971 0.836 0.000 0.016 0.008 0.004 0.136
#> GSM955007 3 0.3860 0.6108 0.000 0.152 0.784 0.008 0.052 0.004
#> GSM955010 3 0.2231 0.7049 0.008 0.020 0.912 0.048 0.000 0.012
#> GSM955014 1 0.1471 0.8380 0.932 0.000 0.004 0.000 0.000 0.064
#> GSM955018 2 0.4882 0.5378 0.012 0.732 0.100 0.012 0.136 0.008
#> GSM955020 1 0.3300 0.7858 0.816 0.000 0.008 0.020 0.004 0.152
#> GSM955024 2 0.4655 0.4575 0.000 0.688 0.032 0.016 0.252 0.012
#> GSM955026 4 0.7623 -0.1845 0.000 0.168 0.000 0.296 0.268 0.268
#> GSM955031 1 0.7233 0.2812 0.464 0.104 0.000 0.180 0.012 0.240
#> GSM955038 4 0.2799 0.3901 0.016 0.032 0.028 0.888 0.000 0.036
#> GSM955040 3 0.3357 0.6655 0.060 0.000 0.848 0.020 0.008 0.064
#> GSM955044 5 0.4031 0.5574 0.000 0.332 0.008 0.008 0.652 0.000
#> GSM955051 1 0.3593 0.7381 0.756 0.000 0.004 0.012 0.004 0.224
#> GSM955055 5 0.4146 0.5964 0.000 0.304 0.004 0.012 0.672 0.008
#> GSM955057 1 0.0000 0.8379 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM955062 2 0.3728 0.3036 0.000 0.652 0.004 0.000 0.344 0.000
#> GSM955063 2 0.3482 0.5918 0.000 0.832 0.088 0.004 0.060 0.016
#> GSM955068 4 0.5877 0.3227 0.000 0.040 0.008 0.624 0.180 0.148
#> GSM955069 2 0.7344 0.2416 0.060 0.488 0.284 0.028 0.116 0.024
#> GSM955070 2 0.8394 -0.4764 0.000 0.260 0.044 0.220 0.244 0.232
#> GSM955071 3 0.5387 0.1843 0.400 0.004 0.520 0.008 0.004 0.064
#> GSM955077 6 0.6087 0.1695 0.056 0.052 0.000 0.040 0.244 0.608
#> GSM955080 3 0.5017 0.6058 0.000 0.020 0.732 0.088 0.124 0.036
#> GSM955081 2 0.4821 0.4828 0.000 0.700 0.072 0.004 0.204 0.020
#> GSM955082 2 0.3853 0.3939 0.000 0.680 0.000 0.000 0.304 0.016
#> GSM955085 5 0.4291 0.5141 0.000 0.356 0.008 0.000 0.620 0.016
#> GSM955090 1 0.2118 0.8278 0.888 0.000 0.008 0.000 0.000 0.104
#> GSM955094 6 0.8583 0.1833 0.000 0.232 0.184 0.076 0.220 0.288
#> GSM955096 2 0.2555 0.5871 0.000 0.888 0.000 0.016 0.064 0.032
#> GSM955102 3 0.5132 0.5149 0.004 0.200 0.692 0.012 0.072 0.020
#> GSM955105 4 0.5805 0.2831 0.000 0.296 0.024 0.576 0.012 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)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n genotype/variation(p) k
#> ATC:NMF 107 0.305 2
#> ATC:NMF 94 0.927 3
#> ATC:NMF 51 0.792 4
#> ATC:NMF 56 0.271 5
#> ATC:NMF 57 0.059 6
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