Merge branch 'encode' into master (f41ded0c) · Commits · Chaos / chaos.juicer

AWS/scripts/check.sh

+2 −2

Changes for AWS/scripts/check.sh: 2 added lines, 2 removed lines.
Original line number	Diff line number	Diff line
		@@ -41,8 +41,8 @@ fi
		# no reads were lost
		total=1
		total2=0
		total=`ls -l ${outputdir}/merged_sort.txt \| awk '{print $5}'`
		total2=`ls -l ${outputdir}/merged_nodups.txt ${outputdir}/dups.txt ${outputdir}/opt_dups.txt \| awk '{sum = sum + $5}END{print sum}'`
		total=`ls -lgG ${outputdir}/merged_sort.txt \| awk '{print $3}'`
		total2=`ls -lgG ${outputdir}/merged_nodups.txt ${outputdir}/dups.txt ${outputdir}/opt_dups.txt \| awk '{sum = sum + $3}END{print sum}'`

		if [ -z $total ] \|\| [ -z $total2 ] \|\| [ $total -ne $total2 ]
		then

AWS/scripts/cleanup.sh

+2 −2

Changes for AWS/scripts/cleanup.sh: 2 added lines, 2 removed lines.
Original line number	Diff line number	Diff line
		@@ -25,8 +25,8 @@
		# Script to clean up big repetitive files and zip fastqs. Run after you are
		# sure the pipeline ran successfully. Run from top directory (HIC001 e.g.).
		# Juicer version 1.5
		total=`ls -l aligned/merged_sort.txt \| awk '{print $5}'`
		total2=`ls -l aligned/merged_nodups.txt aligned/dups.txt aligned/opt_dups.txt \| awk '{sum = sum + $5}END{print sum}'`
		total=`ls -lgG aligned/merged_sort.txt \| awk '{print $3}'`
		total2=`ls -lgG aligned/merged_nodups.txt aligned/dups.txt aligned/opt_dups.txt \| awk '{sum = sum + $3}END{print sum}'`
		if [ $total -eq $total2 ]
		then
		rm aligned/merged_sort.txt

AWS/scripts/juicer.sh

+3 −3

Changes for AWS/scripts/juicer.sh: 3 added lines, 3 removed lines.
Original line number	Diff line number	Diff line
		@@ -351,14 +351,14 @@ fi
		# If chunk size sent in, split. Otherwise check size before splitting
		if [ -z $splitme ]
		then
		fastqsize=`ls -lL ${fastqdir} \| awk '{sum+=$5}END{print sum}'`
		fastqsize=`ls -lgGL ${fastqdir} \| awk '{sum+=$3}END{print sum}'`
		if [ "$fastqsize" -gt "2592410750" ]
		then
		splitme=1
		fi
		fi

		testname=`ls -l ${fastqdir} \| awk 'NR==1{print $9}'`
		testname=`ls -lgG ${fastqdir} \| awk 'NR==1{print $7}'`
		if [ ${testname: -3} == ".gz" ]
		then
		read1=${splitdir}"/${read1str}.fastq.gz"
		@@ -500,7 +500,7 @@ SPLITMV
		## No need to re-split fastqs if they already exist
		echo -e "--- Using already created files in $splitdir\n"
		# unzipped files will have .fastq extension, softlinked gz
		testname=$(ls -l ${splitdir} \| awk '$9~/fastq$/\|\|$9~/gz$/{print $9; exit}')
		testname=$(ls -lgG ${splitdir} \| awk '$7~/fastq$/\|\|$7~/gz$/{print $7; exit}')
		if [ ${testname: -3} == ".gz" ]
		then
		read1=${splitdir}"/${read1str}.fastq.gz"

CPU/common/adjust_insert_size.awk

0 → 100755

+167 −0

Changes for CPU/common/adjust_insert_size.awk: 167 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		#!/usr/bin/awk -f

		# returns absolute value
		function abs(value)
		{
		return (value<0?-value:value);
		}
		BEGIN{
		while(getline<avgInsertFile>0) {
		insertsize=$7
		}
		saved="";
		OFS="\t";
		}
		{
		if ($(NF-1) ~ /^rt:/ && ($(NF-1) ~ /:0$/ \|\| $(NF-1) ~ /:1$/)) {
		# first appearance, process second one
		if (length(saved)==0) {
		saved=$0;
		saved_length=length($10);
		next;
		}
		else {
		split($NF, cb_str, ":");
		split(cb_str[3], cb, "_");
		strand1=cb[5];
		strand2=cb[6];

		for (i=12; i<=NF; i++) {
		if ($i ~ /^ip/) {
		split($i, ip, ":");
		}
		else if ($i ~ /^mp/) {
		split($i, mp, ":");
		}
		}

		is = insertsize - length($10) - saved_length;

		split($(NF-1), rt, ":");
		if (rt[3]==0) {
		cigar1=$6;
		split(saved, prev);
		cigar2=prev[6];
		pos1=ip[3];
		pos2=mp[3];
		}
		else {
		cigar2=$6;
		split(saved, prev);
		cigar1=prev[6];
		pos1=mp[3];
		pos2=ip[3];
		}
		cigloc1=0;
		cigloc2=0;
		newpos1=pos1;
		newpos2=pos2;
		if (strand1==0) {
		if (cigar1 ~ /[0-9]+S$/) {
		where = match(cigar1,/[0-9]+S$/);
		cigloc1 = cigloc1 + (substr(cigar1,where,RLENGTH-1) + 0);
		}
		else if (cigar1 ~ /[0-9]+H$/) {
		where = match(cigar1,/[0-9]+H$/);
		cigloc1 = cigloc1 + (substr(cigar1,where,RLENGTH-1) + 0);
		}
		}
		else if (strand1==16) {
		if (cigar1 ~ /^[0-9]+S/) {
		where = match(cigar1,/^[0-9]+S/);
		cigloc1 = cigloc1 + (substr(cigar1,where,RLENGTH-1) + 0);
		}
		else if (cigar1 ~ /^[0-9]+H/) {
		where = match(cigar1,/^[0-9]+H/);
		cigloc1 = cigloc1 + (substr(cigar1,where,RLENGTH-1) + 0);
		}
		}
		if (strand2==0) {
		if (cigar2 ~ /[0-9]+S$/) {
		where = match(cigar2,/[0-9]+S$/);
		cigloc2 = cigloc2 + (substr(cigar2,where,RLENGTH-1) + 0);
		}
		else if (cigar2 ~ /[0-9]+H$/) {
		where = match(cigar2,/[0-9]+H$/);
		cigloc2 = cigloc2 + (substr(cigar2,where,RLENGTH-1) + 0);
		}
		}
		else if (strand2==16) {
		if (cigar2 ~ /^[0-9]+S/) {
		where = match(cigar2,/^[0-9]+S/);
		cigloc2 = cigloc2 + (substr(cigar2,where,RLENGTH-1) + 0);
		}
		else if (cigar2 ~ /^[0-9]+H/) {
		where = match(cigar2,/^[0-9]+H/);
		cigloc2 = cigloc2 + (substr(cigar1,where,RLENGTH-1) + 0);
		}
		}
		if (cigloc1==0 && cigloc2==0) {
		if (strand1==0) {
		newpos1 += int(is/2);
		}
		else if (strand1==16) {
		newpos1 -= int(is/2);
		}
		if (strand2 ==0) {
		newpos2 += int(is/2);
		}
		else if (strand2 == 16) {
		newpos2 -= int(is/2);
		}
		}
		else if (cigloc1>0&&cigloc2==0) {
		if (strand2==0) {
		newpos2 = newpos2 + int(is) + cigloc1;
		}
		else if (strand2==16) {
		newpos2 = newpos2 - int(is) - cigloc1;
		}
		}
		else if (cigloc1==0&&cigloc2>0) {
		if (strand1==0) {
		newpos1 = newpos1 + int(is) + cigloc2;
		}
		else if (strand1==16) {
		newpos1 = newpos1 - int(is) - cigloc2;
		}
		}

		if (rt[3]==0) {
		p1 = newpos1;
		p2 = newpos2;
		}
		else {
		p1 = newpos2;
		p2 = newpos1;
		}
		for (i=12; i<=NF; i++) {
		if ($i ~ /^ip/) {
		$i = "ip:i:"p1;
		}
		else if ($i ~ /^mp/) {
		$i = "mp:i:"p2;
		}
		}

		str=prev[1];
		for (j=2; j<=length(prev); j++) {
		if (prev[j] ~ /^ip/) {
		prev[j] = "ip:i:"p2;
		}
		else if (prev[j] ~ /^mp/) {
		prev[j] = "mp:i:"p1;
		}
		str=str"\t"prev[j];
		}

		print str;
		print;
		saved="";
		}
		}
		# otherwise, not adjusting the insert size, just print (also header, collisions, etc)
		else {
		print;
		}
		}

CPU/common/check.sh

+3 −15

Changes for CPU/common/check.sh: 3 added lines, 15 removed lines.
Original line number	Diff line number	Diff line
		@@ -25,11 +25,11 @@
		#
		# Sanity check once pipeline is complete to be sure number of lines adds up, deduping
		# proceeded appropriately, and that files were created
		# Juicer version 1.5
		# Juicer version 2.0

		# Start by checking the statistics to see if they add up
		res1=`cat ${splitdir}/normres*`
		check1=`cat ${splitdir}/normres* \| awk '{s2+=$2; s3+=$3; s4+=$4; s5+=$5; s6+=$6}END{if (s2 != s3+s4+s5+s6){print 0}else{print 1}}'`
		check1=`cat ${splitdir}/normres* \| awk '{s2+=$2; s3+=$3; s4+=$4; s5+=$5; s6+=$6; s7+=$7}END{if (s2 != s3+s4+s5+s6+s7){print 0}else{print 1}}'`
		if [ $check1 -eq 0 ] \|\| [ -z "$res1" ]
		then
		echo "***! Error! The statistics do not add up. Alignment likely failed to complete on one or more files. Run relaunch_prep.sh"
		@@ -37,19 +37,7 @@ then
		exit 1
		fi

		# Check the sizes of merged_sort versus the dups/no dups files to be sure
		# no reads were lost
		total=1
		total2=0
		total=`ls -l ${outputdir}/merged_sort.txt \| awk '{print $5}'`
		total2=`ls -l ${outputdir}/merged_nodups.txt ${outputdir}/dups.txt ${outputdir}/opt_dups.txt \| awk '{sum = sum + $5}END{print sum}'`

		if [ -z $total ] \|\| [ -z $total2 ] \|\| [ $total -ne $total2 ]
		then
		echo "***! Error! The sorted file and dups/no dups files do not add up, or were empty. Merge or dedupping likely failed, restart pipeline with -S merge or -S dedup"
		echo "Dups don't add up. Check ${outputdir} for results"
		exit 1
		fi
		# could add flagstat check here

		wctotal=`cat ${splitdir}/*_linecount.txt \| awk '{sum+=$1}END{print sum/4}'`
		check2=`cat ${splitdir}/normres* \| awk '{s2+=$2;}END{print s2}'`

Admin message