[BioC] limma and makeContrasts

[Gordon Smyth]

At 11:38 PM 20/01/2004, Stephen Henderson wrote:
>Hi
>I've been using the limma and eBayes function for looking at a set of
>affymetrix chips with 8 or so different groups within. Following the
>instructions on page 11=12 of the PDF guide, this works fine I think.
>
>My question regards different ways to specify the contrasts. If I wish to
>compare composite groups, e.g.
>
>(group1,group2) vs (group3,group4) and others

What about

makeContrasts((group1+group2)/2-(group3+group4)/2,levels=design)

?

Gordon


>is there a syntax to specify this within the makeContrasts function?, and
>where can I read about this?, or alternatively is there a better step at
>which I can achieve this (without changing my class vector repeatedly that
>is)?
>
>Stephen