[BioC] Analisys with MAS5 and affyPLM

[Pedro Botías]

Hi friends,
I would like to carry out a similar analysis of data to which carries out
affylmGUI, but with standard sign data with MAS5, and to carry out a
statistical eBayes to the carried out contrast the same as in affylmGUI.
Serious this correct?
I have tried to carry out it but I find that the data that I obtain are not
correct or distance much of the analysis that I have carried out with GCRMA
in affylmGUI.
These are my chips:
pData(eset)
                       sample
mtl1-diam.CEL        1
mtl1-diam2.CEL      2
mtl1.2.CEL             3
mtl1.CEL                4
wt-diam2.CEL         5
wt-diam3.CEL         6
wt2.CEL                 7
wt3.CEL                 8

I have two you reply of each condition. And I want to carry out the
following contrasts:
 mtl1 vs wt
 mtl1.diam vs mtl1
 wt.diam vs wt

This is the script that I have used for the analysis, noticing limma user's
guide.

>eset<-call.exprs(data,"mas5")
>strain =
c("mtl1.diam","mtl1.diam","mtl1","mtl1","wt","wt","wt.diam","wt.diam")
>design = model.matrix(~factor(strain))
>colnames(design) = c("mtl1.diam","mtl1","wt","wt.diam")
>fit<-lmFit(eset,design)
>contrast.matrix<-makeContrasts(mtl1-wt,mtl1.diam-mtl1,wt.diam-wt,
levels=design)
>fit2<-contrasts.fit(fit,contrast.matrix)
>fit2<-eBayes(fit2)
>results<-decideTests(fit2)

Not you if there is something in the design of the analysis that I make bad.
I thank all their help.
Thank you

*********************************
Pedro Botías Talamantes
Unidad de Genómica
Parque Científico de Madrid-UCM
Facultad CC Biológicas- Planta sótano
Universidad Complutense de Madrid
28040 Madrid
Tel: 91 3945036
FAX 91 3944883
e-mail: pbotias at bio.ucm.es
Web: http://www.ucm.es/info/gyp/genomica/