#set working directory
setwd("/Users/lab/Documents/sequencingbulkdata/Plos_Genetics_2015/snps")

#read in a table containing genotype information
data <- read.table("3S_backcross_snps.txt", header = F, sep = "\t", as.is = T)
names(data) <- c("c", "p", "ref", "refct", "alt", "altct")

#calculate coverage and allele frequencies
data$cov <- data$refct + data$altct
data$fr <- (data$refct/data$cov)

#Remove non-segregating regions & apply a mild filter to data
split.data <- split(data, data$c)
split.data <- lapply(split.data, function(x) {
	x$use <- (as.vector(filter(x$fr > 0.2,rep(1/50,50))) >= 0.9)
	x$fr[x$use == F] <- 0
	x$filter <- as.vector(filter(x$fr,rep(1/10,10)))
	na.omit(x)
})
data <- do.call("rbind", split.data.2)

#print out snps present at >95% frequency on chromosome 7
data$p[data$c == 7 & d$filter >= .95]

#print out snps present at >95% frequency on chromosome 15
data$p[data$c == 15 & d$filter >= .95]