[BioC] Problem with limma's topTable lfc filter when more than 1 contrast is in output

[Vladimir Zhurov]

> ...

Dear Bioconductors,

I am having the following problem which can be due to a misunderstanding,
or an actual problem with topTable function in limma package.

As far as I understand lfc and p filters should work together in filtering
topTable results. Am I correct in this regard?

If it is an intended situation then the problem is the following: when more
than one contrasts is reported lfc filter does not affect the output. Which
is shown in the sample R session below.

I would appreciate you help.

Regards.

Vladimir.


$ uname -a
Linux 2.6.32-37-generic #81-Ubuntu SMP Fri Dec 2 20:32:42 UTC 2011
x86_64 GNU/Linux

Sample R session:

R version 2.14.1 (2011-12-22)
Copyright (C) 2011 The R Foundation for Statistical Computing
ISBN 3-900051-07-0
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

  Natural language support but running in an English locale

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> # load data
> library("ALLMLL")
Loading required package: affy
Loading required package: Biobase

Welcome to Bioconductor

  Vignettes contain introductory material. To view, type
  'browseVignettes()'. To cite Bioconductor, see
  'citation("Biobase")' and for packages 'citation("pkgname")'.

> data("MLL.A")
> # calculate RMA measures for the first 6 arrays
> eset<-rma(MLL.A[,1:6])
Loading required package: AnnotationDbi

Background correcting
Normalizing
Calculating Expression
> # load and proceed with limma. lets have 3 groups of 2 arrays
> library("limma")
> design <- model.matrix(~ 0+factor(c(1,1,2,2,3,3)))
> colnames(design)<-c("G1", "G2", "G3")
> # lets make all pair-wise comparisons
> contrast.matrix <- makeContrasts(G1-G2, G1-G3, G2-G3, levels=design)
> fit<-lmFit(eset, design)
> fit.c<-contrasts.fit(fit, contrast.matrix)
> fit.eb<-eBayes(fit.c)
> # create topTable's with different filters and check dimensions
> # lets output data for all comparisons and adjust lfc
> tt.1<-topTable(fit.eb, number=Inf, p=0.05, adjust.method="none")
> dim(tt.1)
[1] 1482    8
> tt.2<-topTable(fit.eb, number=Inf, p=0.05, adjust.method="none", lfc=2)
> dim(tt.2)
[1] 1482    8
> tt.3<-topTable(fit.eb, number=Inf, p=0.05, adjust.method="none", lfc=10)
> dim(tt.3)
[1] 1482    8
> # we have 3 identical tables with no effect of lfc filter
> # lets output data for all comparisons and adjust lfc
> # p value will be at 1 and have no effect
> tt.1p<-topTable(fit.eb, number=Inf, adjust.method="none")
> dim(tt.1p)
[1] 22283     8
> tt.2p<-topTable(fit.eb, number=Inf, adjust.method="none", lfc=2)
> dim(tt.2p)
[1] 22283     8
> tt.3p<-topTable(fit.eb, number=Inf, adjust.method="none", lfc=10)
> dim(tt.3p)
[1] 22283     8
> # we have 3 identical tables with no effect of lfc filter
> # lets output data for just the 1st comparison and adjust lfc
> tt.1c<-topTable(fit.eb, number=Inf, p=0.05, adjust.method="none", coef=1)
> dim(tt.1c)
[1] 806   7
> tt.2c<-topTable(fit.eb, number=Inf, p=0.05, adjust.method="none", lfc=2,
+ coef=1)
> dim(tt.2c)
[1] 26  7
> tt.3c<-topTable(fit.eb, number=Inf, p=0.05, adjust.method="none", lfc=10,
+ coef=1)
> dim(tt.3c)
[1] 0 0
> # now lfc filter works
>
> traceback()
No traceback available
> warnings()
NULL
> sessionInfo()
R version 2.14.1 (2011-12-22)
Platform: x86_64-pc-linux-gnu (64-bit)

locale:
 [1] LC_CTYPE=en_CA.UTF-8       LC_NUMERIC=C
 [3] LC_TIME=en_CA.UTF-8        LC_COLLATE=en_CA.UTF-8
 [5] LC_MONETARY=en_CA.UTF-8    LC_MESSAGES=en_CA.UTF-8
 [7] LC_PAPER=C                 LC_NAME=C
 [9] LC_ADDRESS=C               LC_TELEPHONE=C
[11] LC_MEASUREMENT=en_CA.UTF-8 LC_IDENTIFICATION=C

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base

other attached packages:
[1] limma_3.10.1          hgu133acdf_2.9.1      AnnotationDbi_1.16.11
[4] ALLMLL_1.2.11         affy_1.32.0           Biobase_2.14.0

loaded via a namespace (and not attached):
[1] affyio_1.22.0         BiocInstaller_1.2.1   DBI_0.2-5
[4] IRanges_1.12.5        preprocessCore_1.16.0 RSQLite_0.11.1
[7] tools_2.14.1          zlibbioc_1.0.0