2
$\begingroup$

Here is an example of hierarchical clustering of genes in the microarray data using the weighted pair gene method in Spotfire. I am not sure how to do this in R. In the hclust function, I see ward", "single", "complete", "average", "mcquitty", "median" or "centroid" as the methods.

Also, lets say I have performed hierarchical clustering and found groups of genes using cuttree method. I wanted to plot the expression of genes in a group across columns (which may represent treatment, time, etc.). And I want to do this for all the groups separately. In a way similar to the Mfuzz package's way of showing clusters.

Can any one please help me?

TIA for any pointers.

$\endgroup$
2
$\begingroup$

About your first question, it seems that the mcquitty option corresponds to WPGMA clustering, while average is for UPGMA. It is just by looking at the source code, so it is worth to double check it. But it also referred as is in the upgma() function from the phangorn package.

About your second question, I think you just have to subset your genes by the group labels found after cutree, and then plot expression profiles as usual.

$\endgroup$
  • $\begingroup$ Thanks a lot. I was dumb not to look at the source code. It mentions this clearly... $\endgroup$ – suncoolsu Nov 19 '10 at 15:52

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.