[R] Question

[Martin Morgan]

Hi Tyler --

On 08/08/2011 12:54 PM, Tyler Gruhn wrote:
> I just signed up for R Help, so please let me know if I'm doing this
> incorrectly.

Better to provide an informative subject line -- "microarray heatmap 
memory use" ?

> I've been working with R for a couple of weeks, attempting to process
> microarray data.  This means 20,000+ rows of data to work with x 24
> columns.  I am trying to produce heatmaps and found that the best
> computer I have available to me can process the data without any
> clustering (Rowv=NA, Colv=NA), but my supervisor has made it clear that
> I need to have the clusters present.  I have been messing around with
> the memory allocation commands, but I can't seem to get it to process
> even still.  Are there any methods of getting large amounts of data to
> process into heatmaps that I should look into?

The Bioconductor project has many users experienced in analysis of 
microarray data. Have you tried posting your question there?

http://bioconductor.org/help/mailing-list/

A common practice is to reduce the number of features (rows) by 
filtering to exclude, e.g., those that are known to be control probes 
and those with low across-sample variability. The genefilter package 
contains functions for this.

http://bioconductor.org/packages/release/bioc/html/genefilter.html

It is important to include the output of

   sessionInfo()

in your mailing list posts, so that the R and package versions you're 
using are obvious. It also helps to create a small but realistic example 
that others can execute, e.g. (although not very realistic)

   m <- matrix(rnorm(25 * 20000), ncol=25)
   heatmap(m)

Martin

>
> Thank you very much,
>
> Tyler
>
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> 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.


-- 
Computational Biology
Fred Hutchinson Cancer Research Center
1100 Fairview Ave. N. PO Box 19024 Seattle, WA 98109

Location: M1-B861
Telephone: 206 667-2793