[BioC] quick question about romer results

[Iain Gallagher]

Hello list.

I have a quick question about the 'romer' function used for GSEA in the limma suite.

With guidance (much appreciated!) from Di Wu I have run some data through the algorithm and the results look appropriate for my dataset.

The question I have is to do with the p-values returned. I run romer with 9999 rotations (a method suitable for 'permutation' in linear models) and get back ~3200 sig genesets. This is from an examination of ~ 17000 probes across 2 groups (3 adult arrays and 9 fetal arrays - affy data). 

If a set is significant I get back a p value of 0.0001 - nothing more & nothing less. If a set is not sig I get a p value of 1. 

I understand that the MINIMUM p value is 1/(nrot+1) so all my significant sets are at the minimum p value. 

I would have expected a range of p values however. Could someone with a more statistical background shed some light on this? Perhaps my groups are very different (would make some sense I suppose).

Thanks again in advance for any help.

iain

> sessionInfo()
R version 2.12.0 (2010-10-15)
Platform: x86_64-pc-linux-gnu (64-bit)

locale:
 [1] LC_CTYPE=en_GB.utf8       LC_NUMERIC=C             
 [3] LC_TIME=en_GB.utf8        LC_COLLATE=en_GB.utf8    
 [5] LC_MONETARY=C             LC_MESSAGES=en_GB.utf8   
 [7] LC_PAPER=en_GB.utf8       LC_NAME=C                
 [9] LC_ADDRESS=C              LC_TELEPHONE=C           
[11] LC_MEASUREMENT=en_GB.utf8 LC_IDENTIFICATION=C      

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

other attached packages:
 [1] hgu133plus2.db_2.4.5 org.Hs.eg.db_2.4.6   RSQLite_0.9-3       
 [4] DBI_0.2-5            AnnotationDbi_1.12.0 genefilter_1.32.0   
 [7] hgu133plus2cdf_2.7.0 affy_1.28.0          Biobase_2.10.0      
[10] RColorBrewer_1.0-2   limma_3.6.6         

loaded via a namespace (and not attached):
[1] affyio_1.18.0         annotate_1.28.0       preprocessCore_1.12.0
[4] splines_2.12.0        survival_2.36-2       tools_2.12.0         
[7] xtable_1.5-6         
>