An die Mitglieder des Clusters (k-means) zu extrahieren

Question

I Clusterungsanalyse

ich einen Datensatz mit R. am Ausführen haben, die wie folgt aussieht:

geneid S1 S2 S3 S4 M3 M4 M6 
ENSRNOG00000000012 0.8032270364 1.5058909297 1.0496307677 1.4168397419 0.2750070475 0.9708536543 1.1570437101 
ENSRNOG00000000021 3.0250287945 3.7782085764 3.4449320489 2.7004397181 3.2464080872 3.1795110503 2.9429835982 
ENSRNOG00000000024 2.0669502439 2.5210507369 2.2555007331 1.7949356628 1.4382928516 1.9373443922 1.5210507369 
ENSRNOG00000000033 2.7004397181 2.4724877715 2.1391420191 2.1309308698 1.8032270364 1.8757800631 1.7527485914 
ENSRNOG00000000034 1.4541758932 1.3617683594 0.9963887464 0.7136958148 0.8718436485 0.6690267655 0.516015147 
ENSRNOG00000000040 4.9420452599 5.0565835284 5.3527938294 4.8639384504 4.0891591319 4.2742616613 3.1731274335 
ENSRNOG00000000041 2.6194130106 3.2637856139 3.4489009511 3.2032011563 3.7015490569 3.5410191531 3.0976107966 
ENSRNOG00000000042 4.1263947376 4.6284819944 3.9731520379 3.014355293 3.0018022426 2.8972404256 2.5285713189 
ENSRNOG00000000043 5.1051751923 5.7436226761 6.3211163506 6.5046203924 6.6071823374 6.2467880938 5.8371863852 
ENSRNOG00000000044 3.2854022189 4.0465783666 4.1513717763 3.9250499647 4.5316933609 4.2727697324 3.7980505148 
ENSRNOG00000000047 2.5248159284 1.8933622108 1.5210507369 1.0908534305 1.6229303509 1.9523335664 2.0976107966 
ENSRNOG00000000048 3.5722833667 3.8569856898 3.8841094514 3.7202784652 4.2311251579 3.8399595875 3.6028844087 
ENSRNOG00000000054 2.0823619696 2.6241008946 2.5058909297 1.3729520979 0.748461233 0.9927684308 0.8073549221 
ENSRNOG00000000062 3.846994687 4.0609120496 4.1647058402 3.6644828404 3.6496154591 3.2957230245 3.1602748314 
ENSRNOG00000000064 4.971543554 4.9993235782 5.1185258489 4.194559886 3.8639384504 4.2883585622 4.0531113365 
ENSRNOG00000000066 3.2809563138 4.0413306068 4.0759604132 3.5422580498 3.7495342677 2.9411063109 2.6040713237 
ENSRNOG00000000068 3.2986583156 3.5204222485 3.7436226761 3.3132458518 3.6427015718 3.4019034716 3.166715445 
ENSRNOG00000000070 1.5235619561 2.266036894 2.2433644257 1.6229303509 2.1009776477 2.2630344058 1.9107326619 
ENSRNOG00000000073 2.6780719051 2.9269482479 1.8559896973 1.3950627995 2.0426443374 2.266036894 1.9297909977 
ENSRNOG00000000075 2.8559896973 2.9392265777 2.7235585615 2.2448870591 1.5109619193 1.8718436485 1.7092906357 
ENSRNOG00000000081 4.8609627979 5.1501534552 5.7869883453 5.7993463875 5.6383635059 4.5478199566 4.2764966656 
ENSRNOG00000000082 4.0018022426 4.1787146412 4.2067213574 3.5285713189 3.8063240574 4.0626398283 3.2913088598 
ENSRNOG00000000091 0.7697717392 1.0036022367 0.867896464 0.5459683691 1.4541758932 1.8032270364 1.7311832416 
ENSRNOG00000000095 3.5410191531 3.5348086612 3.9527994779 3.408711861 3.6028844087 3.0992952043 2.8011586561 
ENSRNOG00000000096 1.4568061492 1.5655971759 1.6135316529 1.7527485914 1.4594316186 1.8559896973 1.673556424 
ENSRNOG00000000098 2.414135533 3.5122268865 3.5147534984 3.3015876466 4.0755326312 3.8747969659 3.187451054 
ENSRNOG00000000104 2.7125957804 2.5969351424 2.5459683691 1.3219280949 1.5849625007 1.6088092427 1.3161457423 
ENSRNOG00000000105 1.6016965165 1.3015876466 1.1890338244 1.516015147 0.7570232465 0.6870606883 0.6040713237 
ENSRNOG00000000108 3.2854022189 3.6976626335 3.8865501473 2.6369145804 2.6040713237 2.3923174228 1.8953026213 
ENSRNOG00000000111 1.6229303509 2.09592442 2.0772429989 1.7782085764 1.673556424 0.9927684308 1.2570106182 
ENSRNOG00000000112 2.2078928516 2.1826922975 2.4249220882 2.0250287945 2.1110313124 2.0635029423 1.8953026213 
ENSRNOG00000000121 1.9202933002 2.5273206079 2.5741015081 2.2265085298 2.582556003 2.5753123307 2.1984941536 
ENSRNOG00000000122 4.1255684518 4.4299506574 4.5071603491 4.2637856139 4.34269696 3.5849625007 3.9040023163 
ENSRNOG0000000.7070829918 1.9616233283 2.1127001327 1.4222330007 1.9221978484 1.9708536543 1.5801454844 
ENSRNOG00000000127 2.3881895372 3.0347439493 2.9981955032 3.2295879227 4.0435194937 3.7729413378 3.2957230245 
ENSRNOG00000000129 2.3074285252 2.979110755 3.1992797213 2.2203299549 3.6322682155 3.8982083525 3.5801454844 
ENSRNOG00000000130 4.1622906135 4.7150696794 4.629 3.9772799235 4.5849625007 4.9236246114 4.7739963251 
ENSRNOG00000000133 3.2000648615 3.1168637577 3.1787146412 2.9579145986 2.7928553524 2.6780719051 2.2078928516 
ENSRNOG00000000138 0.516015147 0.5993177937 1.0356239097 1.5849625007 2.2326607568 1.9745293125 2.0285691522 
ENSRNOG00000000142 2.9278964537 2.3291235963 0.9671686075 1.4168397419 0.7048719645 1.9927684308 1.7224660245 
ENSRNOG00000000145 3.2164548651 3.5490530293 3.4195388915 2.8797057663 2.3362833879 2.5849625007 2.6937657122 
ENSRNOG00000000150 2.6380738372 2.9708536543 3.014355293 2.6870606883 2.6158870739 2.3161457423 2.4329594073 
ENSRNOG00000000151 2.7125957804 3.5484366247 3.8354188405 4.5447326559 5.6959938131 5.3077927961 5.1941658685 
ENSRNOG00000000155 3.0565835284 3.9354597478 3.6803243568 3.5134907456 3.8032270364 3.8865501473 3.2494453411 
ENSRNOG00000000156 3.34269696 3.2772408983 1.7761039881 1.1505596766 0.5360529002 0.2750070475 0.3334237337 
ENSRNOG00000000157 1.9164766444 2.1424134379 2.054848477 1.9145645235 2.2448870591 2.3305584 1.6599245584 
ENSRNOG00000000161 1.7202784652 2.0772429989 1.9945797242 1.4541758932 1.7655347464 2.1602748314 1.8757800631 
ENSRNOG00000000164 3.6616356023 4.2596491206 4.0635029423 3.2494453411 3.2418401836 3.1618876824 2.2295879227 
ENSRNOG00000000165 1.3504972471 1.6158870739 0.9373443922 0.4541758932 0.7311832416 4.6392321632 4.5403993056 
ENSRNOG00000000166 3.3441183345 3.3603642765 3.2494453411 1.9597701552 2.2357270598 3.1456774552 2.8698714062 

Was ich tue, ist dies:

d=read.table("FPKM.1.SelectedSamples.txt", header=T, sep="\t", row.names=1) 
dm=data.matrix(d) 
log10.matrix <- log10(dm+1) 

Z.log10.A.matrix <- t(scale(t(log10.matrix[idx,]))) 
tmp <- Z.log10.A.matrix[which(is.finite(Z.log10.A.matrix[,1])),] 

length(which(!is.finite(tmp))) 
fin.Z.log10.A.matrix <- tmp 
set.seed(1) 
km9.fin.Z.log.A.matrix <- kmeans(fin.Z.log10.A.matrix, 2, iter.max=40, nstart=10) 
rowOrder <- names(sort(km9.fin.Z.log.A.matrix$cluster)) 
colorVector <- c("grey","purple") 
clusterColors <- colorVector[ sort(km9.fin.Z.log.A.matrix$cluster)] 
heatmap.2(fin.Z.log10.A.matrix[rowOrder,],trace="none",labRow=F,labCol=colnames(km9.fin.Z.log.A.matrix),col=hmcol,RowSideColors=clusterColors,Rowv=F,Colv=F,dendrogram="column",na.rm=T,main="Gene Expression") 

Die Befehle werden mir eine schöne Heatmap mit zwei Clustern geben.

Nun, wie kann ich Mitglieder dieser Cluster extrahieren?

Vielen Dank im Voraus.

Answer 1

Sobald Sie die k ausgeführt haben - menas Algorithmus:

km9.fin.Z.log.A.matrix <- kmeans(fin.Z.log10.A.matrix, 2, iter.max=40, nstart=10) 

Sie die Cluster-Zuordnung mit km9.fin.Z.log.A.matrix$cluster erhalten können, wobei jede Probe eine Nummer an den Cluster bezeichnet haben wird, wo es aufgenommen wurde.