Question: How to calculate q-values in this case
0
gravatar for xsh6528
4.2 years ago by
xsh65280
China
xsh65280 wrote:

I have data for gene mutations (binary values) and gene expression level (continuous values) for several patients. (Theseare shown in two tables in the first row of the pic.)


To decide whether a gene mutation truly affects function.
I need to combine it with its expression level.

So I divided people into two groups based on gene mutation.
Then do a test on their gene expression levels.

This test result in a P-value.

My question is, what is the right way to convert P-values to q-values in this case, in

Should I pool all P-values across groups or within a group together to calculate individual q-values?

 

It is actually the method used in 'Emerging landscape of oncogenic signatures across human cancers', which I intend to imitate.

http://www.nature.com/ng/journal/v45/n10/full/ng.2762.html

see Method-Testing for concordant mRNA and copy number changes.

hypothesis-testing • 2.2k views
ADD COMMENTlink modified 4.2 years ago • written 4.2 years ago by xsh65280

Is this homework?

ADD REPLYlink written 4.2 years ago by h.mon28k

It is the method used in Emerging landscape of oncogenic signatures across human cancers.

http://www.nature.com/ng/journal/v45/n10/full/ng.2762.html

see Method-Testing for concordant mRNA and copy number changes.

I want to figure out their way of preprocessing data, so that I can imitate in my research.

ADD REPLYlink modified 16 days ago by RamRS25k • written 4.2 years ago by xsh65280
p.adjust(p, method = p.adjust.methods, n = length(p))
ADD REPLYlink modified 16 days ago by RamRS25k • written 4.2 years ago by apelin20470
1

p.adjust doesn't produce Q values, which are related to adjusted p-values but not actually the same. There happens to be a separate qvalue Bioconductor package for this purpose though (it's even written by John Storey, who came up with q-values).

ADD REPLYlink written 4.2 years ago by Devon Ryan93k

But let's say this wasn't a homework question and one was interested in correcting for multiple tests, would p.adjust work? It seems to implement a variety of methods

p.adjust.methods
# c("holm", "hochberg", "hommel", "bonferroni", "BH", "BY",
#   "fdr", "none")
ADD REPLYlink written 4.2 years ago by apelin20470

Sure, p.adjust() (I use the BH method myself) is the standard function unless one really wants/needs q-values.

ADD REPLYlink written 4.2 years ago by Devon Ryan93k
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: 2258 users visited in the last hour