[BioC] limma decideTests

Jenny Drnevich drnevich at uiuc.edu
Tue Jan 3 18:33:23 CET 2006

Hi Laurens,

See ?topTable - this may give you what you want, but only for one 
coefficient/contrast at a time. Also, see ?write.fit - this will give you 
all the p-values (adjusted if you want)  written out to a file that can be 
opened in Excel; you can also use the results option in write.fit to attach 
your -1, 0, and 1s from decideTests.

Alternatively, if you want an object in R that has both the adjusted 
p-values and the -1, 0, and 1s, I've been using this code, which I pulled 
from write.fit:

p.value <- as.matrix(fit2$p.value)
for (j in 1:ncol(p.value)) p.value[, j] <- p.adjust(p.value[,
         j], method = "fdr")
tab <- list()
tab$Genes <- fit2$genes
tab$p.value <- p.value
tab$Res <- unclass(results)
tab <- data.frame(tab, check.names = FALSE)


At 09:52 AM 1/3/2006, Laurens Pauwels wrote:
>Happy New Year everyone!
>I used decideTests in limma to correct for multiple testing
>across probes and contrasts. I was wondering if there is a way
>to obtain adjusted p values rather than 1,0,-1 scores.
>Laurens Pauwels
>DEPARTMENT OF PLANT SYSTEMS BIOLOGY           Fax:32 (0)9 3313809
>GHENT UNIVERSITY/VIB,    Technology Park 927, B-9000 Gent, Belgium
>Vlaams Interuniversitair Instituut voor Biotechnologie         VIB
>mailto:lapau at psb.ugent.be                  http://www.psb.ugent.be
>Bioconductor mailing list
>Bioconductor at stat.math.ethz.ch

Jenny Drnevich, Ph.D.

Functional Genomics Bioinformatics Specialist
W.M. Keck Center for Comparative and Functional Genomics
Roy J. Carver Biotechnology Center
University of Illinois, Urbana-Champaign

330 ERML
1201 W. Gregory Dr.
Urbana, IL 61801

ph: 217-244-7355
fax: 217-265-5066
e-mail: drnevich at uiuc.edu

More information about the Bioconductor mailing list