library(data.table)

# Number of resistant clones in the experiment
n_clones = 3

## Load variants file for first resistant clone and add a sample label column
clone_1 = read.table('data/variants_1.vcf', header=F, sep='\t') 
clone_1$sample = “resistant_1”

## Repeat for variants for each resistant clone

## Combine all clones into single, tall data.table
all_variants = as.data.table(rbind(clone_1, clone_2, clone_3))

## Count recurrent mutations: filter REJECT calls, group by coordinate, 
##  and count samples for each coordinate
## VCF column headers: V1: chr, V2: start, V3: end, V4: ref allele, V5: alt allele, V7: KEEP/REJECT
grouped = all_variants[V7 != "REJECT", 
                  list(alt=V5[1], n_samples=length(unique(sample))), 
                  by=list(chr=V1, start=V2, end=V2, ref=V4)]

## Remove any mutations not occurring in all clones, and write to file
filtered = grouped[n_samples == n_clones, list(chr, start, end, ref, alt)]
write.table(filtered, file=”data/filtered_recurrent_variants.txt”, 
	        row.names=F, quote=F)