[Bioc-devel] DEG data analysis

Gordon K Smyth smyth at wehi.EDU.AU
Sat Sep 10 02:46:21 CEST 2011

Dear Laura,

The edgeR package allows tests of any linear model hypothesis, including 
the ability to conduct F-statistic-like tests for differences between 
multiple groups.  See


and the last Case Study in the User's Guide.  Here is a quote from the 
introduction to the edgeR User's Guide (devel version):

"The package implements exact statistical methods for multigroup 
experiments developed by Robinson and Smyth [2007, 2008]. It also 
implements statistical methods based on generalized linear models, 
suitable for multifactor experiments of any complexity, developed by 
McCarthy et al. [2011]. Sometimes we refer to the former exact methods as 
classic edgeR, and the latter as glm edgeR. However the two sets of 
methods are complementary and can often be combined in the course of a 
data analysis. Most of the glm functions can be identied by the letters 
"glm" as part of the function name."

BTW, user questions like this are better send to the main Bioconductor 
mailing list, which is much more active than this list.  This mailing list 
is intended for package development issues.

Best wishes

Professor Gordon K Smyth,
Bioinformatics Division,
Walter and Eliza Hall Institute of Medical Research,
1G Royal Parade, Parkville, Vic 3052, Australia.
smyth at wehi.edu.au

> Date: Fri, 09 Sep 2011 10:06:35 +0200
> From: Pascual <Laura.Pascual at avignon.inra.fr>
> To: bioc-devel at r-project.org
> Subject: [Bioc-devel] DEG data analysis
> Hello,
> I have a set of DEG illumina data, coming from 12 different accessions
> with replicates of each samples. I have been taking a look at edgeR and
> DESeq to analyse the data, and extract differential expressed tags.
> However all analysis seem to be based in pair comparasions. Is there any
> packge to made comparesions between a greater number of groups? Do you
> know if anybody is planning to add this analysis in any existing package?
> Thanks
> Laura

The information in this email is confidential and intend...{{dropped:4}}

More information about the Bioc-devel mailing list