Mercurial > repos > greg > ideas_preprocessor
changeset 12:ab0f306504a3 draft
Uploaded
author | greg |
---|---|
date | Wed, 24 Jan 2018 13:47:23 -0500 |
parents | 26eb979cf8d9 |
children | 4d542da396a7 |
files | ideas_preprocessor.R |
diffstat | 1 files changed, 33 insertions(+), 26 deletions(-) [+] |
line wrap: on
line diff
--- a/ideas_preprocessor.R Wed Jan 24 13:47:16 2018 -0500 +++ b/ideas_preprocessor.R Wed Jan 24 13:47:23 2018 -0500 @@ -4,11 +4,10 @@ suppressPackageStartupMessages(library("optparse")) option_list <- list( - make_option(c("--bed_input"), action="store", dest="bed_input", defaul=NULL, help="Chromosome windows positions file"), + make_option(c("--chrom_bed_input"), action="store", dest="chrom_bed_input", defaul=NULL, help="Chromosome windows positions file"), make_option(c("--exclude_input"), action="store", dest="exclude_input", defaul=NULL, help="File(s) containing regions to exclude"), make_option(c("--bychr"), action="store_true", dest="bychr", defaul=FALSE, help="Separate files by chromosome"), make_option(c("--chrom_len_file"), action="store", dest="chrom_len_file", default=NULL, help="Chromosome lengths file"), - make_option(c("--ideas_input_config"), action="store", dest="ideas_input_config", help="Preprocessing output config file"), make_option(c("--ideaspre_input_config"), action="store", dest="ideaspre_input_config", help="Preprocessing input config file"), make_option(c("--output"), action="store", dest="output", help="Primary output dataset"), make_option(c("--output_files_path"), action="store", dest="output_files_path", help="Primary output dataset extra files path"), @@ -44,25 +43,28 @@ # "cell type name" "epigenetic factor name" "file path" "file name" "datatype" ideaspre_input_config = as.matrix(read.table(opt$ideaspre_input_config)); # Process data to windows mean. -for (i in 1:dim(ideaspre_input_config)[1]) { - file_path = ideaspre_input_config[i, 3] - file_name = ideaspre_input_config[i, 4] - datatype = ideaspre_input_config[i, 5] - if (datatype == "bam") { - cmd = paste("samtools index", file_path); - system(cmd); - bigwig_file_name = paste(file_name, "bw", sep="."); - cmd = paste("bamCoverage --bam", file_path, "-o", bigwig_file_name, "--binSize", opt$window_size); +# TODO: implement scenario where user did not select chrom_bed_input. +if (!is.null(opt$chrom_bed_input)) { + for (i in 1:dim(ideaspre_input_config)[1]) { + file_path = ideaspre_input_config[i, 3] + file_name = ideaspre_input_config[i, 4] + datatype = ideaspre_input_config[i, 5] + if (datatype == "bam") { + cmd = paste("samtools index", file_path); + system(cmd); + bigwig_file_name = paste(file_name, "bw", sep="."); + cmd = paste("bamCoverage --bam", file_path, "-o", bigwig_file_name, "--binSize", opt$window_size); + system(cmd); + } else { + bigwig_file_name = file_path; + } + bed_file_name = paste(file_name, "bed", sep="."); + bed_file_path = paste("tmp", bed_file_name, sep="/"); + cmd = paste("bigWigAverageOverBed", bigwig_file_name, opt$chrom_bed_input, "stdout | cut -f5 >", bed_file_path); system(cmd); - } else { - bigwig_file_name = file_path; + cmd = paste("gzip -f", bed_file_path); + system(cmd); } - bed_file_name = paste(file_name, "bed", sep="."); - bed_file_path = paste("tmp", bed_file_name, sep="/"); - cmd = paste("bigWigAverageOverBed", bigwig_file_name, opt$bed_input, "stdout | cut -f5 >", bed_file_path); - system(cmd); - cmd = paste("gzip -f", bed_file_path); - system(cmd); } # Create file1.txt. @@ -73,12 +75,13 @@ # Create file2.txt. cmd = paste("ls", tmp_gzipped_files, "> file2.txt", sep=" "); system(cmd); -# Create the ideas_input_config with the format required by IDEAS. -cmd = paste("paste -d' ' file1.txt file2.txt >", opt$ideas_input_config, sep=" "); +# Create IDEAS_input_config.txt with the format required by IDEAS. +ideas_input_config = "IDEAS_input_config.txt" +cmd = paste("paste -d' ' file1.txt file2.txt >", ideas_input_config, sep=" " ); system(cmd); -# Move the ideas_input_config to the output directory. -to_path = paste(opt$output_files_path, opt$ideas_input_config, sep="/"); -file.rename(opt$ideas_input_config, to_path); +# Move IDEAS_input_config.txt to the output directory. +to_path = paste(opt$output_files_path, ideas_input_config, sep="/"); +file.rename(ideas_input_config, to_path); # Move the compressed bed files in the tmp # directory to the output tmp directory. tmp_files = list.files(path=tmp_dir); @@ -87,8 +90,12 @@ to_path = paste(output_tmp_dir, tmp_files[i], sep="/"); file.rename(from_path, to_path); } -if (!is.null(opt$chromosome_windows)) { - # Move the chromosome_windows to the output directory. +if (!is.null(opt$chrom_bed_input) && !is.null(opt$chromosome_windows)) { + # Renane opt$chrom_bed_input to be chromosomes.bed + # and make a copy of it in the output directory. + to_path = paste(opt$output_files_path, "chromosomes.bed", sep="/"); + file.copy(opt$chromosome_windows, to_path); + # Move chromosome_windows.txt to the output directory. to_path = paste(opt$output_files_path, opt$chromosome_windows, sep="/"); file.rename(opt$chromosome_windows, to_path); }