[R] How to calculate correlation matrix for 128 * 12625 matrix

[R. Michael Weylandt]

On Tue, May 29, 2012 at 11:26 PM, mahdi <mahdi43 at gmail.com> wrote:
> In our dataset the samples/object are number of patients which is 128 and we
> are dealing with 12,625 genes which is our
> attributes of the dataset. So, it is obvious that if I calculate the
> correlation matrix of (128 * 12,625) the resulted dimension of the
> correlation matrix will be (12,625 * 12,625). I need some help about this
> calculation.
>
> 1. How I can make the transpose matrix of 12625 * 128  to 128 * 12625.
> Suppose I have written t(x) where x is a matrix of 12625 * 128. But after
> giving the command t(x) when I write x to see then I saw it has not been
> changed to 128 * 12625.

R functions (almost always) don't have side effects and use
copy-by-value semantics so if you want to make x permanently
transposed you need to write

x <- t(x)

which wil transpose x and then replace x with the resulting transposed matrix.

>
> 2. it is obvious that if I calculate the correlation matrix of (128 *
> 12,625) the resulted dimension of the correlation matrix will be (12,625 *
> 12,625). But I think this 12625 is huge to work with.....so is there any
> solution for that? What should I do now?

This seems domain specific but I might suggest you look at the
Bioconductor suite and mailing list -- this is a problem they've
likely faced before.

Best,
Michael

>
> Thanks in advance. Take care.
>
> --
> View this message in context: http://r.789695.n4.nabble.com/How-to-calculate-correlation-matrix-for-128-12625-matrix-tp4631790.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.