[BioC] calculation of "M" in limma topTable

[James W. MacDonald]

Kimpel, Mark William wrote:
> I am unsure how to interpret the M-value produced by limma topTable
> when analyzing a multi-factoral, multi-level experiment.
> 
> As an example, suppose I test one gene under the same 2 conditions (1
> and 2) in two different experiments (A and B). The mean expressions
> in the two experiments are very different but in both cases condition
> 1 has higher expression levels than condition 2. I look at the
> contrast of condition 1 vs. condition 2 ((A1 + B1) - (A2 + B2)).

That is not a contrast, so your 'M' value will be off by a factor of 
two. The correct contrast would be (A1 + B1)/2 - (A2 + B2)/2, and then 
'M' will be calculated just like you would imagine:

(mean(A1) + mean(B1))/2 - (mean(A2) + mean(B2))/2

Best,

Jim



> 
> How does topTable calculate M?
> 
> Thanks,
> 
> Mark W. Kimpel MD
> 
> Department of Psychiatry Indiana University School of Medicine 
> Biotechnology, Research, & Training Center 1345 W. 16th Street 
> Indianapolis, IN  46202
> 
> 
> _______________________________________________ Bioconductor mailing
> list Bioconductor at stat.math.ethz.ch 
> https://stat.ethz.ch/mailman/listinfo/bioconductor


-- 
James W. MacDonald
Affymetrix and cDNA Microarray Core
University of Michigan Cancer Center
1500 E. Medical Center Drive
7410 CCGC
Ann Arbor MI 48109
734-647-5623