Mercurial > repos > kyost > atac_primer_tool
diff make_window_bed.R @ 0:fd3ea97a96bc draft
planemo upload commit 103cb51ec368438642504c3f98b76c363db478bb
author | kyost |
---|---|
date | Sat, 28 Apr 2018 15:07:26 -0400 |
parents | |
children | 72571a30f17b |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/make_window_bed.R Sat Apr 28 15:07:26 2018 -0400 @@ -0,0 +1,64 @@ +## Command to run tool: +# Rscript --vanilla make_window_bed.R qPCR_peaks.bed window_size output_file + +# Set up R error handling to go to stderr +options(show.error.messages=F, error=function(){cat(geterrmessage(),file=stderr());q("no",1,F)}) + +# Avoid crashing Galaxy with an UTF8 error on German LC settings +loc <- Sys.setlocale("LC_MESSAGES", "en_US.UTF-8") + +args <- commandArgs(TRUE) + +qPCR_bed <- args[1] +window_size <- strtoi(args[2]) +output_file <- args[3] + +qPCR_table <- read.delim(qPCR_bed, header=FALSE, stringsAsFactors=FALSE) + +make_windows_bed <- function(a, size) { #a is a bed file containing peaks of interest and coordinates + #generates bed file with overlapping windows spanning each peak of specified size + return_bed <- data.frame() + for (i in 1:nrow(a)) { + line <- data.frame(a[i,],stringsAsFactors=FALSE) + peak_name <- as.character(line[1,4]) + line <- rbind(line + , data.frame(V1=as.character(line[1,1]) + , V2=line[1,2] + , V3=line[1,2]+size + , V4=as.character(paste(as.character(line[1,4]) + , "_window1" + , sep = "") + ) + ) + ) + count <- as.numeric(line[1,2])+size + nline <- 2 + while (count < as.numeric(line[1,3])) { + line <- rbind(line + , data.frame(V1=as.character(line[nline,1]) + , V2=line[nline,2]+floor(size/4) + , V3=line[nline,2]+floor(size/4)+size + , V4=as.character(paste(as.character(line[1,4]) + , "_window" + , as.character(nline) + , sep = "") + ) + ) + ) + nline <- nline + 1 + count <- as.numeric(line[nline,3]) + } + return_bed <- rbind(return_bed,line) + } + return(return_bed) +} + +output <- make_windows_bed(qPCR_table, window_size) + + +write.table(output + , output_file + , sep = "\t" + , col.names = FALSE + , row.names = FALSE + , quote = FALSE)