fixed a bug in indrops mode (fe318735) · Commits · github_fork / ZUMIs

fqfilter-inDrops.pl

+15 −6

Original line number	Diff line number	Diff line
		@@ -8,7 +8,7 @@ if(@ARGV != 13)
		{
		print
		"\n#####################################################################################
		Usage: perl $0 <cDNA-read.fq.gz> <cellbarcode1-Read.fq.gz> <librarybarcode-Read.fq.gz> <cellbarcode2-Read.fq.gz> <nBase_BC_threshold> <BC_Qual_threshold> <nBase_umi_threshold> <UMI_Qual_threshold> <UMI_range> <Threads> <StudyName> <Outdir> <pigz-executable> \n
		Usage: perl $0 <cDNA-read.fq.gz> <cellbarcode1-Read.fq.gz> <librarybarcode-Read.fq.gz> <cellbarcode2-Read.fq.gz> <nBase_BC_threshold> <BC_Qual_threshold> <nBase_umi_threshold> <UMI_Qual_threshold> <UMI_range> <Threads> <StudyName> <Outdir> <pigz-executable> <BC_range>\n
		Explanation of parameter:

		cDNA-Read.fq.gz - Input fastq file with cDNA reads.
		@@ -20,7 +20,8 @@ nBase_BC_threshold - Cell barcodes with number of bases under the base quality i
		BC_Qual_threshold - Minimum base quality required for the cell barcode to be accepted.(e.g. 20)
		nBase_umi_threshold - Molecular(UMI) barcodes with number of bases under the base quality is filtered out. (e.g. 1)
		UMI_Qual_threshold - Minimum base quality required for the molecule(umi) barcode to be accepted.(e.g. 20)
		UMI_range - Base range for UMI barcode in -f Barcode read (e.g. 1-6).
		UMI_range - Base range for UMI barcode (e.g. 1-6).
		BC_range - Base range for cell barcode (e.g. 1-22).

		Threads - Number of threads to use for zipping.
		Study - Study name.
		@@ -43,12 +44,20 @@ $bqualthreshold=$ARGV[5];
		$mnbases=$ARGV[6];
		$mqualthreshold=$ARGV[7];
		$mcrange=$ARGV[8];
		$bcrange=$ARGV[13];

		$threads=$ARGV[9];
		$study=$ARGV[10];
		$outdir=$ARGV[11];
		$pigz=$ARGV[12];

		@b = split("-",$bcrange);
		@m = split("-",$mcrange);
		$bs = $b[0] - 1;
		$ms = $m[0] - 1;
		$bl = $b[1]-$b[0]+1;
		$ml = $m[1]-$m[0]+1;

		$bcreadout = $outdir."/".$study.".barcodelist.filtered.sam";
		$bcreadoutfull = $outdir."/".$study.".barcoderead.filtered.fastq";
		$cdnareadout = $outdir."/".$study.".cdnaread.filtered.fastq";
		@@ -122,10 +131,10 @@ $total++;
		if(grep {$_ > 74} @quals){$offset=64;}else{$offset=33;}
		}

		$bseq = substr($seq,0,22);
		$mseq = substr($seq,22,6);
		$bqual = substr($qseq,0,22);
		$mqual = substr($qseq,22,6);
		$bseq = substr($seq,$bs,$bl);
		$mseq = substr($seq,$bl,$ml);
		$bqual = substr($qseq,$bs,$bl);
		$mqual = substr($qseq,$bl,$ml);

		@c = split(/\/\|\s/,$crid);
		@b1 = split(/\/\|\s/,$brid1);

zUMIs-filtering-inDrops.sh

+2 −1

Original line number	Diff line number	Diff line
		@@ -14,6 +14,7 @@ cq="${11}"
		t="${12}"
		d="${13}"
		pigz="${14}"
		xc="${15}"

		# MAKING THE HEADER
		echo '#!/bin/bash' >$o/$sn.prep.sh
		@@ -24,6 +25,6 @@ echo '#SBATCH --cpus-per-task='$t >>$o/$sn.prep.sh
		echo '#SBATCH --workdir='$o >>$o/$sn.prep.sh
		echo '#SBATCH --mem=1000' >>$o/$sn.prep.sh

		echo "srun perl $d/fqfilter-inDrops.pl $f1 $f2 $f3 $f4 $cq $cbq $mq $mbq $xm $t $sn $o $pigz" >>$o/$sn.prep.sh
		echo "srun perl $d/fqfilter-inDrops.pl $f1 $f2 $f3 $f4 $cq $cbq $mq $mbq $xm $t $sn $o $pigz $xc" >>$o/$sn.prep.sh

		sbatch $o/$sn.prep.sh > $o/$sn.preparejobid.txt

zUMIs-master.sh

+3 −3

Original line number	Diff line number	Diff line
		@@ -40,7 +40,7 @@ Make sure you have 3-4 times more disk space to your input fastq files.
		-a <GTF annotation> : Path to GTF file. Required.
		-c <XC baserange> : Base range for cell/sample barcode in -f Barcode read(e.g. 1-6). Required.
		For STRT-seq give this as 1-n where n is your first cell barcode(-f) length.
		For InDrops give this as 1-n where n is the total length of cell barcode(e.g. 1-22).
		For InDrops give this as 1-n where n is the total length of cell barcode (8bp BC part1 + 6bp library barcode + 8bp BC part2) (e.g. 1-22).
		-m <XM baserange> : Base range for UMI barcode in -f Barcode read(e.g. 7-16). Required.
		For STRT-seq/InDrops give this as 1-n where n is your UMI length.
		-l <readlength> : Read length of -r cDNA reads (e.g. 50). Required.
		@@ -357,7 +357,7 @@ if [[ "$isslurm" == "yes" ]] ; then
		if [[ "$isstrt" == "yes" ]] ; then
		bash $zumisdir/zUMIs-filtering-strt.sh $cdnaread $bcread $sname $outdir $xmrange $cbasequal $mbasequal $molbcbase $cellbcbase $threads $zumisdir $bcread2 $BaseTrim $pigzexc
		elif [[ "$isindrops" == "yes" ]] ; then
		bash $zumisdir/zUMIs-filtering-inDrops.sh $cdnaread $bcread $libread $bcread2 $sname $outdir $xmrange $cbasequal $mbasequal $molbcbase $cellbcbase $threads $zumisdir $pigzexc
		bash $zumisdir/zUMIs-filtering-inDrops.sh $cdnaread $bcread $libread $bcread2 $sname $outdir $xmrange $cbasequal $mbasequal $molbcbase $cellbcbase $threads $zumisdir $pigzexc $xcrange
		else
		bash $zumisdir/zUMIs-filtering.sh $bcread $cdnaread $sname $outdir $xcrange $xmrange $cbasequal $mbasequal $molbcbase $cellbcbase $threads $zumisdir $pigzexc $pbcfastq $pbcrange
		fi

zUMIs-noslurm.sh

+1 −1

Original line number	Diff line number	Diff line
		@@ -93,7 +93,7 @@ re='^[0-9]+$'
		if [[ "$isstrt" == "yes" ]] ; then
		perl $zumisdir/fqfilter-strt.pl $f1 $f2 $f3 $cq $cbq $mq $mbq $xm $bt $t $sn $o $pigzexc
		elif [[ "$isindrops" == "yes" ]] ; then
		perl $zumisdir/fqfilter-inDrops.pl $f1 $f2 $libread $f3 $cq $cbq $mq $mbq $xm $t $sn $o $pigzexc
		perl $zumisdir/fqfilter-inDrops.pl $f1 $f2 $libread $f3 $cq $cbq $mq $mbq $xm $t $sn $o $pigzexc $xc
		else
		perl $zumisdir/fqfilter.pl $f2 $f1 $pbcfastq $cq $cbq $mq $mbq $xc $pbcrange $xm $t $sn $o $pigzexc
		fi

Admin message