How to meta analyze p values of different observations

Question

I am trying to meta analyze p values from different studies. I have data frame

DF1
p-value1   p-value2   pvalue3   m
0.1          0.2        0.3     a
0.2          0.3        0.4     b
0.3          0.4        0.5     c
0.4          0.4        0.5     a 
0.6          0.7        0.9     b
0.6          0.7        0.3     c

I am trying to get fourth column of meta analyzed p-values1 to p-value3. I tried to use metap package

p<–rbind(DF1$p-value1,DF1$p-value2,DF1$p-value3)
pv–split (p,p$m)
library(metap)
for (i in 1:length(pv))
{pvalue <- sumlog(pv[[i]]$pvalue)}

But it results in one p value. Thank you for any help.

Answer 1

You can try

apply(DF1[,1:3], 1, sumlog)