Merge pull request #254 from aidenlab/master (2bb48d64) · Commits · Chaos / chaos.juicer

AWS/scripts/dups.awk

+15 −0

Changes for AWS/scripts/dups.awk: 15 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		@@ -50,8 +50,14 @@ function optcheck(tile1,tile2,x1,x2,y1,y2) {
		# Executed once, before beginning the file read
		BEGIN {
		i=0;
		if (length(nowobble)==0) {
		wobble1=4;
		wobble2=4;
		}
		else {
		wobble1=0;
		wobble2=0;
		}
		# names of output files
		# the variable "name" can be set via the -v flag
		dupname=name"dups.txt";
		@@ -95,6 +101,10 @@ $1 != p1 \|\| $2 != p2 \|\| $4 != p4 \|\| $5 != p5 \|\| $6 != p6 \|\| $8 != p8 \|\| abs($3-p
		}
		else dups[k]++; #places a 1 at dups[k]
		}
		if (abs(pos1[j]-pos1[k])>wobble1) {
		#print "test", pos1[j], pos1[k]
		break
		}
		}
		}
		}
		@@ -173,6 +183,11 @@ END {
		dups[k]++;
		}
		}
		if (abs(pos1[j]-pos1[k])>wobble1) {
		#print "test", pos1[j], pos1[k]
		break

		}
		}
		}
		}

AWS/scripts/juicer.sh

+15 −8

Changes for AWS/scripts/juicer.sh: 15 added lines, 8 removed lines.
Original line number	Diff line number	Diff line
		@@ -100,11 +100,12 @@ genomeID="hg19"
		shortreadend=0
		# description, default empty
		about=""
		nofrag=0

		nofrag=1
		# use wobble for dedupping by default (not just exact matches)
		justexact=0

		## Read arguments
		usageHelp="Usage: ${0##*/} [-g genomeID] [-d topDir] [-q queue] [-l long queue] [-s site]\n [-a about] [-R end] [-S stage] [-p chrom.sizes path]\n [-y restriction site file] [-z reference genome file]\n [-C chunk size] [-D Juicer scripts directory]\n [-Q queue time limit] [-L long queue time limit] [-b ligation] [-t threads]\n [-r] [-h] [-x]"
		usageHelp="Usage: ${0##*/} [-g genomeID] [-d topDir] [-q queue] [-l long queue] [-s site]\n [-a about] [-R end] [-S stage] [-p chrom.sizes path]\n [-y restriction site file] [-z reference genome file]\n [-C chunk size] [-D Juicer scripts directory]\n [-Q queue time limit] [-L long queue time limit] [-b ligation] [-t threads]\n [-r] [-h] [-f] [-j]"
		genomeHelp="* [genomeID] must be defined in the script, e.g. \"hg19\" or \"mm10\" (default \n \"$genomeID\"); alternatively, it can be defined using the -z command"
		dirHelp="* [topDir] is the top level directory (default\n \"$topDir\")\n [topDir]/fastq must contain the fastq files\n [topDir]/splits will be created to contain the temporary split files\n [topDir]/aligned will be created for the final alignment"
		queueHelp="* [queue] is the queue for running alignments (default \"$queue\")"
		@@ -113,7 +114,7 @@ siteHelp="* [site] must be defined in the script, e.g. \"HindIII\" or \"MboI\"
		aboutHelp="* [about]: enter description of experiment, enclosed in single quotes"
		shortHelp="* -r: use the short read version of the aligner, bwa aln\n (default: long read, bwa mem)"
		shortHelp2="* [end]: use the short read aligner on read end, must be one of 1 or 2 "
		stageHelp="* [stage]: must be one of \"merge\", \"dedup\", \"final\", \"postproc\", or \"early\".\n -Use \"merge\" when alignment has finished but the merged_sort file has not\n yet been created.\n -Use \"dedup\" when the files have been merged into merged_sort but\n merged_nodups has not yet been created.\n -Use \"final\" when the reads have been deduped into merged_nodups but the\n final stats and hic files have not yet been created.\n -Use \"postproc\" when the hic files have been created and only\n postprocessing feature annotation remains to be completed.\n -Use \"early\" for an early exit, before the final creation of the stats and\n hic files"
		stageHelp="* [stage]: must be one of \"merge\", \"dedup\", \"final\", \"postproc\", or \"early\".\n -Use \"merge\" when alignment has finished but the merged_sort file has not\n yet been created.\n -Use \"dedup\" when the files have been merged into merged_sort but\n merged_nodups has not yet been created.\n -Use \"final\" when the reads have been deduped into merged_nodups but the\n final stats and hic files have not yet been created.\n -Use \"postproc\" when the hic files have been created and only\n postprocessing feature annotation remains to be completed.\n -Use \"early\" for an early exit, before the final creation of the stats and\n hic files. Can also use -e flag to exit early"
		pathHelp="* [chrom.sizes path]: enter path for chrom.sizes file"
		siteFileHelp="* [restriction site file]: enter path for restriction site file (locations of\n restriction sites in genome; can be generated with the script\n misc/generate_site_positions.py)"
		chunkHelp="* [chunk size]: number of lines in split files, must be multiple of 4\n (default ${splitsize}, which equals $(awk -v ss=${splitsize} 'BEGIN{print ss/4000000}') million reads)"
		@@ -123,7 +124,9 @@ queueTimeHelp="* [queue time limit]: time limit for queue, i.e. -W 12:00 is 12 h
		longQueueTimeHelp="* [long queue time limit]: time limit for long queue, i.e. -W 168:00 is one week\n (default ${long_queue_time})"
		ligationHelp="* [ligation junction]: use this string when counting ligation junctions"
		threadsHelp="* [threads]: number of threads when running BWA alignment"
		excludeHelp="* -x: exclude fragment-delimited maps from hic file creation"
		justHelp="* -j: just exact duplicates excluded at dedupping step"
		excludeHelp="* -f: include fragment-delimited maps in hic file creation"
		earlyexitHelp="* -e: Use for an early exit, before the final creation of the hic files"
		helpHelp="* -h: print this help and exit"

		printHelpAndExit() {
		@@ -146,12 +149,14 @@ printHelpAndExit() {
		echo -e "$longQueueTimeHelp"
		echo -e "$ligationHelp"
		echo -e "$threadsHelp"
		echo -e "$justHelp"
		echo -e "$earlyexitHelp"
		echo "$excludeHelp"
		echo "$helpHelp"
		exit "$1"
		}

		while getopts "d:g:R:a:hrq:s:p:l:y:z:S:C:D:Q:L:b:t:x" opt; do
		while getopts "d:g:R:a:hrq:s:p:l:y:z:S:C:D:Q:L:b:t:fje" opt; do
		case $opt in
		g) genomeID=$OPTARG ;;
		h) printHelpAndExit 0;;
		@@ -170,9 +175,11 @@ while getopts "d:g:R:a:hrq:s:p:l:y:z:S:C:D:Q:L:b:t:x" opt; do
		D) juiceDir=$OPTARG ;;
		Q) queue_time=$OPTARG ;;
		L) long_queue_time=$OPTARG ;;
		x) nofrag=1 ;;
		f) nofrag=0 ;;
		b) ligation=$OPTARG ;;
		t) threads=$OPTARG ;;
		j) justexact=1 ;;
		e) earlyexit=1 ;;
		[?]) printHelpAndExit 1;;
		esac
		done
		@@ -821,7 +828,7 @@ then
		${waitstring}
		#BSUB -J "${groupname}_osplit"
		bkill -J ${groupname}_clean1
		awk -v queue=$long_queue -v outfile=${debugdir}/dedup-${groupname}.out -v juicedir=${juiceDir} -v dir=$outputdir -v queuetime=$long_queue_time -v groupname=$groupname -f ${juiceDir}/scripts/split_rmdups.awk $outputdir/merged_sort.txt
		awk -v queue=$long_queue -v outfile=${debugdir}/dedup-${groupname}.out -v juicedir=${juiceDir} -v dir=$outputdir -v queuetime=$long_queue_time -v groupname=$groupname -v justexact=$justexact -f ${juiceDir}/scripts/split_rmdups.awk $outputdir/merged_sort.txt
		KILLCLNUP

		# if it dies, cleanup and write to relaunch script

AWS/scripts/split_rmdups.awk

+11 −3

Changes for AWS/scripts/split_rmdups.awk: 11 added lines, 3 removed lines.
Original line number	Diff line number	Diff line
		@@ -26,7 +26,6 @@
		# Dedup script that submits deduping jobs after splitting at known
		# non-duplicates
		# Juicer version 1.5

		BEGIN{
		tot=0;
		name=0;
		@@ -36,7 +35,13 @@ BEGIN{
		if (tot >= 1000000) {
		if (p1 != $1 \|\| p2 != $2 \|\| p4 != $4 \|\| p5 != $5 \|\| p8 != $8) {
		sname=sprintf("%s_msplit%04d_", groupname, name);
		if (justexact) {
		sysstring = sprintf("bsub -W %s -o %s -q %s -J %s <<- EOF\nawk -v nowobble=1 -f %s/scripts/dups.awk -v name=%s/%s %s/split%04d;\nEOF\n", queuetime, outfile, queue, sname, juicedir, dir, sname, dir, name, dir, name);
		}
		else {
		sysstring = sprintf("bsub -W %s -o %s -q %s -J %s <<- EOF\nawk -f %s/scripts/dups.awk -v name=%s/%s %s/split%04d;\nEOF\n", queuetime, outfile, queue, sname, juicedir, dir, sname, dir, name, dir, name);
		}

		system(sysstring);
		if (name==0) {
		waitstring=sprintf("done(%s)", sname);
		@@ -55,7 +60,12 @@ BEGIN{
		}
		END {
		sname=sprintf("%s_msplit%04d_", groupname, name);
		if (justexact) {
		sysstring = sprintf("bsub -W %s -o %s -q %s -J %s <<-EOF\nawk -v nowobble=1 -f %s/scripts/dups.awk -v name=%s/%s %s/split%04d;\nEOF\n", queuetime, outfile, queue, sname, juicedir, dir, sname, dir, name, dir, name);
		}
		else {
		sysstring = sprintf("bsub -W %s -o %s -q %s -J %s <<-EOF\nawk -f %s/scripts/dups.awk -v name=%s/%s %s/split%04d;\nEOF\n", queuetime, outfile, queue, sname, juicedir, dir, sname, dir, name, dir, name);
		}
		system(sysstring);
		if (name==0) {
		waitstring=sprintf("done(%s)", sname);
		@@ -67,6 +77,4 @@ END {
		system(sysstring);
		sysstring = sprintf("bsub -W %s -o %s -q %s -J %s_rmsplit -w \"done(%s_catsplit)\" <<- EOF\n rm %s/_msplit_optdups.txt; rm %s/_msplit_dups.txt; rm %s/_msplit_merged_nodups.txt; rm %s/split*;\nEOF",queuetime, outfile, queue, groupname, groupname, dir, dir, dir, dir);
		system(sysstring);


		}

CPU/juicer.sh

+1 −0

Changes for CPU/juicer.sh: 1 added line, 0 removed lines.
Original line number	Diff line number	Diff line
		@@ -613,6 +613,7 @@ then
		fi
		fi


		if [ -n "$deduponly" ]
		then
		exit 0

README.md

+1 −1

Changes for README.md: 1 added line, 1 removed line.
Original line number	Diff line number	Diff line
		@@ -4,7 +4,7 @@ Juicer is a platform for analyzing kilobase resolution Hi-C data. In this
		distribution, we include the pipeline for generating Hi-C maps from fastq raw
		data files and command line tools for feature annotation on the Hi-C maps.

		Juicer is currently in its beta release, Juicer version 1.5.
		Juicer is currently in its beta release, Juicer version 1.6.
		For general questions, please use
		[the Google Group](https://groups.google.com/forum/#!forum/3d-genomics).

Admin message