Multiple testing correction with GOstats in R
2
1
Entering edit mode
9.7 years ago
YanO ▴ 140

I've carried out a GO analysis in R using GOstats, and have a list of p-values. However, as I understand it they have not been corrected for multiple testing, and I cannot see a way to do it in GOstats.

Did I miss something is there a way to do it in GOstats?

I understand why a multiple testing correction may not be appropriate, but all of the web-browser GO programs offer it, and I'd like to see what my results look like with it. I can't seem to find a consensus over whether GO p-values should be corrected or not.

Is there an alternative R package I should use that does offer correction, or is there a way to correct the p-values I have as an output of GOstats?

(I realise there has been many many posts on GO but none have given me exactly what I'm looking for.)

Thanks!

ontology R GO • 4.0k views
ADD COMMENT
4
Entering edit mode
9.7 years ago
raunakms ★ 1.1k

If you already have the p-values then you can simply use p.adjust command from the R base package

http://stat.ethz.ch/R-manual/R-patched/library/stats/html/p.adjust.html

ADD COMMENT
0
Entering edit mode

Very helpful, thanks! But what is my n here? The length of values that have p<0.05?

ADD REPLY
0
Entering edit mode
9.7 years ago
EagleEye 7.5k
This might be useful to you. Gene Set Clustering based on Functional annotation (GeneSCF)
ADD COMMENT

Login before adding your answer.

Traffic: 2736 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6