Mercurial > repos > greg > ideas_preprocessor

changeset 3:e97851e8951b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Tue, 23 Jan 2018 10:48:38 -0500
parents 248b5f72fc02
children f577a83e86c4
files ideas_preprocessor.R
diffstat 1 files changed, 59 insertions(+), 25 deletions(-) [+]
line wrap: on
line diff
--- a/ideas_preprocessor.R	Tue Jan 23 10:48:31 2018 -0500
+++ b/ideas_preprocessor.R	Tue Jan 23 10:48:38 2018 -0500
@@ -4,17 +4,19 @@
 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("--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("--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"),
-            make_option(c("--prep_input_config"), action="store", dest="prep_input_config", help="Preprocessing input config file"),
-            make_option(c("--reads_per_bp"), action="store", dest="reads_per_bp", type="integer", help="Calculate the signal in each genomic window"),
-            make_option(c("--restrict_to_chroms"), action="store", dest="restrict_to_chroms", default=NULL, help="Restrict processing to specified chromosomes"),
-            make_option(c("--standardize_datasets"), action="store_true", dest="standardize_datasets", default=FALSE, help="Standardize all datasets"),
-            make_option(c("--window_size"), action="store", dest="window_size", type="integer", default=NULL, help="Window size in base pairs")
+        make_option(c("--bed_input"), action="store", dest="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("--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"),
+        make_option(c("--prep_input_config"), action="store", dest="prep_input_config", help="Preprocessing input config file"),
+        make_option(c("--prep_output_config"), action="store", dest="prep_output_config", help="Preprocessing output config file"),
+        make_option(c("--reads_per_bp"), action="store", dest="reads_per_bp", type="integer", help="Calculate the signal in each genomic window"),
+        make_option(c("--restrict_to_chroms"), action="store", dest="restrict_to_chroms", default=NULL, help="Restrict processing to specified chromosomes"),
+        make_option(c("--standardize_datasets"), action="store_true", dest="standardize_datasets", default=FALSE, help="Standardize all datasets"),
+        make_option(c("--windows_positions_by_chroms_config"), action="store", dest="windows_positions_by_chroms_config", default=NULL, help="Windows positions by chroms config file"),
+        make_option(c("--window_size"), action="store", dest="window_size", type="integer", default=NULL, help="Window size in base pairs")
 )
 
 parser <- OptionParser(usage="%prog [options] file", option_list=option_list)
@@ -22,21 +24,21 @@
 opt <- args$options
 
 create_primary_html = function(output, output_files_path) {
-    tmp_files = list.files(path=output_files_path);
+    files = list.files(path=output_files_path, pattern="\\.txt");
     s <- paste('<html><head></head><body>', sep="\n");
     s <- paste(s, '<h3>Contents of directory required by IDEAS</h3>\n', sep="");
     s <- paste(s, '<ul>\n', sep="");
-    s <- paste(s, '<li><a href="prep_output_config.txt">', prep_output_config.txt, '</a></li>\n', sep="");
-    for (i in 1:length(tmp_files)) {
-        s <- paste(s, '<li><a href="', 'tmp/', tmp_files[i], '">', tmp_files[i], '</a></li>\n', sep="");
+    for (i in 1:length(files)) {
+        s <- paste(s, '<li><a href="', files[i], '">', files[i], '</a></li>\n', sep="");
     }
+    s <- paste(s, '<li><a href="tmp">tmp</a></li>\n', sep="");
     s <- paste(s, '</ul>\n</body>\n</html>', sep="");
     cat(s, file=output);
 }
 
-# Create the directories that will contain all of the output files.
-dir.create(opt$output_files_path, showWarnings=FALSE);
-dir.create(paste(opt$output_files_path, "tmp", sep="/"), showWarnings=FALSE);
+tmp_dir = "tmp";
+output_tmp_dir = paste(opt$output_files_path, tmp_dir, sep="/");
+dir.create(output_tmp_dir, showWarnings=FALSE);
 
 # Read the prep_input_config text file which has this format:
 # "cell type name" "epigenetic factor name" "file path" "file name" "datatype"
@@ -47,16 +49,48 @@
     file_name = prep_input_config_matrix[i, 4]
     datatype = prep_input_config_matrix[i, 5]
     if (datatype == "bam") {
-        system(paste("samtools index", file_path));
-        bw = paste(file_name, "bw", sep=".");
-        system(paste("bamCoverage --bam", file_path, "-o", bw, "--binSize", opt$window_size));
+        cmd = paste("samtools index", file_path);
+        system(cmd);
+        bigwig_file_name = paste(file_name, "bw", sep=".");
+        cmd = paste("bamCoverage --bam", file_path, "-o", bigwig_file_name, "--binSize", opt$window_size);
+        system(cmd);
     } else {
-        bw = file_path;
+        bigwig_file_name = file_path;
     }
-    bd = paste(output_files_path, "tmp", file_name, ".bed", sep="/");
-    system(paste("bigWigAverageOverBed", bw, opt$bed_input, "stdout | cut -f5 >", bd));
-    system(paste("gzip -f", bd));
+    bed_file_name = paste(file_name, "bed", sep=".");
+    bed_file_path = paste("tmp", bed_file_name, sep="/");
+    cmd = paste("bigWigAverageOverBed", bigwig_file_name, opt$bed_input, "stdout | cut -f5 >", bed_file_path);
+    system(cmd);
+    cmd = paste("gzip -f", bed_file_path);
+    system(cmd);
 }
 
+# Create file1.txt.
+cmd = paste("cut -d' '", opt$prep_input_config, "-f1,2 > file1.txt", sep=" ");
+system(cmd);
+# Compress the bed files in the tmp directory.
+tmp_gzipped_files = paste(tmp_dir, "*.bed.gz", sep="/");
+# Create file2.txt.
+cmd = paste("ls", tmp_gzipped_files, "> file2.txt", sep=" ");
+system(cmd);
+# Create the prep_output_config with the format required by IDEAS.
+cmd = paste("paste -d' ' file1.txt file2.txt >", opt$prep_output_config, sep=" ");
+system(cmd);
+# Move the prep_output_config to the output directory.
+to_path = paste(opt$output_files_path, opt$prep_output_config, sep="/");
+file.rename(opt$prep_output_config, to_path);
+# Move the compressed bed files in the tmp
+# directory to the output tmp directory.
+tmp_files = list.files(path=tmp_dir);
+for (i in 1:length(tmp_files)) {
+    from_path = paste(tmp_dir, tmp_files[i], sep="/");
+    to_path = paste(output_tmp_dir, tmp_files[i], sep="/");
+    file.rename(from_path, to_path);
+}
+if (!is.null(opt$windows_positions_by_chroms_config)) {
+    # Move the windows_positions_by_chroms_config to the output directory.
+    to_path = paste(opt$output_files_path, opt$windows_positions_by_chroms_config, sep="/");
+    file.rename(opt$windows_positions_by_chroms_config, to_path);
+}
 # Create the primary HTML dataset.
 create_primary_html(opt$output, opt$output_files_path);