ReCapSeg_restart.R

library(data.table)
# set directory to where file is located
setwd("/Users/jakeconway/Downloads")

# name of file
file.name <- "PR_VanAllen_Haq_Melanoma_Capture_All_Pairs.aggregated_case_sample.seg"

# let the following do the rest
data <- fread(file.name)
data <- data[order(data$Chromosome, data$Start), ]
data$Chromosome <- as.character(data$Chromosome)
markers <- fread("whole_exome_agilent_1.1_refseq_plus_3_boosters.Homo_sapiens_assembly19.targets.markers.txt")
names(markers) <- c("Target", "Chromosome", "Start")
markers$Chromosome <- as.character(markers$Chromosome)

chrs <- unique(data$Chromosome)
df <- data.frame()
for(chr in chrs) {
  temp.data <- data[which(data$Chromosome == chr), ]
  
  temp.markers <- markers[which(markers$Chromosome == chr), ]
  temp.markers <- temp.markers[order(temp.markers$Start, decreasing = FALSE), ]$Start
  closest <- c()
  for(i in temp.data$Start) {
    closest <- c(closest, temp.markers[which(abs(temp.markers-i) == min(abs(temp.markers-i)))])
  }
  temp.data$Start <- closest
  df <- rbind(df, temp.data)
}

df <- df[order(df$Sample, df$Chromosome, df$Start), ]

# rewrite the file using new Start positions
write.table(df, file.name, quote = F, sep = "\t", row.names = F)