K Means Clustering Two Matrices for ComplexHeatmap
0
0
Entering edit mode
pthom010 • 0
@pthom010-23694
Last seen 9 weeks ago
United States

I have a csv file with the log2 scores of eight different timepoints. The header of the table looks like this:

head(templogs)

     SB         SC         SD         SE
TRINITY_DN1001_c0_g1_i1  -0.5638283 -1.2861425 -0.8790812 -1.9667007
TRINITY_DN1001_c0_g1_i5  -0.3484778 -0.8097831 -0.3951722 -1.2755624
TRINITY_DN1001_c0_g2_i1  -0.4141790 -1.4300189 -1.0538773 -2.3604466
TRINITY_DN1001_c2_g1_i1  -0.3890476 -1.5069918 -0.9539496 -2.4254780
TRINITY_DN10027_c0_g1_i2 -0.2425431  0.4412087  0.4699400  0.7566083
TRINITY_DN10030_c0_g1_i1  1.0605554  0.4989614  0.2710047  0.8756346
                                  RB         RC         RD        RE
TRINITY_DN1001_c0_g1_i1  -0.29717574 -0.8332547 -0.8467823 -1.343256
TRINITY_DN1001_c0_g1_i5  -0.45046536 -0.9659265 -1.1268979 -1.572577
TRINITY_DN1001_c0_g2_i1  -0.49264872 -1.0463790 -1.1199727 -1.916905
TRINITY_DN1001_c2_g1_i1  -0.58782459 -1.0346161 -1.0258695 -1.920455
TRINITY_DN10027_c0_g1_i2 -0.03957106  0.7577178  0.6700604  1.681934
TRINITY_DN10030_c0_g1_i1  4.94468049  5.6052340  6.0095423  4.954922

The table has about 2100 rows. What I would like to do is k-means clustering on the matrix and use those results to cluster my rows on a heatmap. However, I seem to be having issues with the hclust function in R. Here is how far I have gotten:

km = kmeans(templogs, centers = 2)$cluster

I then try to run

rows = hclust(templogs)$order

but get the following error message:

Error in if is.na(n) || n > 65536L) stop("size cannot be NA nor exceed 65536") :
  missing value where TRUE/FALSE needed

Would anybody by chance know how to resolve this issue. I am also trying to use the split function with the km$cluster object I made before but I am getting this error message:

Error in Heatmap(templogs, row_order = rows, split = cluster) :
  object 'cluster' not found
complexheatmap R • 202 views
ADD COMMENT
0
Entering edit mode

Try rows = hclust(dist(temploogs))$order.

ADD REPLY

Login before adding your answer.

Traffic: 470 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6