AWFisher_pvalue: AWFisher

In Caleb-Huo/AWFisher: An R package for fast computing for adaptively weighted fisher's method

AWFisher

Description

R package for fast computing for adaptively weighted fisher's method

Usage

AWFisher_pvalue(p.values)

Arguments

p.values

Input G by K p-value matrix. Each row represent a gene and each column represent a study. Note that K has to be >=2 and <=100.

Details

fast computing for adaptively weighted fisher's method

Value

A list consisting of AWFisher pvalues and AWweight.

pvalues	AWFisher pvalues.
weights	G by K binary weight matrix W. $W_gk = 1$ represents for gene $g$, study $k$ contributes to the meta-analysis result. $W_gk = 0$ otherwise.

Author(s)

Zhiguang Huo

Examples

K <- 40
G <- 10000
p.values = matrix(rbeta(K*G, 1,1), ncol=K)
res = AWFisher_pvalue(p.values)
hist(res$pvalues, breaks=40)
table(rowSums(res$weights))
pvalues=res$pvalues[order(res$pvalues)]
plot(-log10((1:NROW(pvalues))/(1+NROW(pvalues))), 
 -log10(pvalues),xlab='theoretical quantile', ylab='observed quantile')
lines(c(0,100), c(0,100), col=2)

Caleb-Huo/AWFisher documentation built on June 16, 2022, 5:48 p.m.