Question: Executing Permutation Test with Hypergeometric P Value
0
gravatar for melodyo
2.7 years ago by
melodyo0
melodyo0 wrote:

Hi All,

I'm new to these forums, but hoping you can help me with a question.

I am using phyper in R to compute p values that assess the significance of overlapping gene sets, though from whole exome sequencing results, not gene expression data.

1-phyper((#overlaps-1), disease list size, (total # genes-disease list size), PPI list size) example: 1-phyper((9-1), 353, 20000-353, 182)

where my PPI list size is the # of genes in my own dataset and disease list size is the number of genes in the gene set of interest.

I have performed a Bonferroni Correction to correct for multiple comparisons/tests, but feel like the proper way to assess significance is using a permutation test. I am wondering whether folks have good recommendations of R packages or scripts that will perform this kind of test WITHOUT gene expression data, and in general feedback about how to perform the permutation test. I have little statistical knowledge and little experience using R.

Thanks for any help you can give me!

ADD COMMENTlink modified 2.7 years ago by WouterDeCoster37k • written 2.7 years ago by melodyo0
1

If you need to correct for multiple testing and find Bonferroni too conservative, the standard alternative is to control the false discovery rate, typically using the Benjamini-Hochberg procedure (available among others in the p.adjust function in R). See here.

ADD REPLYlink written 2.7 years ago by Jean-Karim Heriche18k
Please log in to add an answer.

Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 2.3.0
Traffic: 2329 users visited in the last hour