[BioC] Differentially Expressed Genes using Limma

[James W. MacDonald]

Hi Marcos,

Marcos Pinho wrote:
>   Dear List,
> I have been trying to use limma to identify differentially expressed genes
> but have been finding some difilcuties in creating a basic model.matrix. and
> establishing a contrast. I usually have two different types of RNA in
> triplicates, a reference an an experimental and wish to see genes
> differentially expressed between the them. Following the limma manual my
> model.matrix would be:
> 
> design <- model.matrix (~ -1 + factor (c (0,0,0,1,1,1)))
> 
> Could it be done this way???

Yes, but you could use a simpler parameterization.

> 
> In such case, what would be the best way to fit a contrast between my
> reference and experimental???

If you use the treatment contrasts parameterization, the second 
coefficient will be the difference between the two sample types, so you 
don't need a contrasts matrix.

design <- model.matrix(~ factor(rep(1:2, each = 3)))
fit <- lmFit(<data>, design)
fit2 <- eBayes(fit)
topTable(fit2, coef = 2)


> 
> Any help would be greatly appreciated!
> 
> best regards,
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor

-- 
James W. MacDonald, M.S.
Biostatistician
Douglas Lab
University of Michigan
Department of Human Genetics
5912 Buhl
1241 E. Catherine St.
Ann Arbor MI 48109-5618
734-615-7826