diff --git a/alignment/bam2tdf.sh b/alignment/bam2tdf.sh
index db7faefcdd1b5a3bd900a0759961730302503a9a..e6299d58137337fa2ded981c5239809c2ecf8e43 100644
--- a/alignment/bam2tdf.sh
+++ b/alignment/bam2tdf.sh
@@ -23,13 +23,15 @@ shift $(($OPTIND -1))
# Check for mandatory options
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
+
baseDir="`dirname \"$0\"`"
source /etc/profile.d/modules.sh
module load igvtools/2.3.71 samtools/1.6
-samtools index -@ $SLURM_CPUS_ON_NODE $bam
+samtools index -@ $NPROC $bam
igvtools count -z 5 $bam ${pair_id}.tdf ${index_path}/igv/human.genome
diff --git a/alignment/bamqc.sh b/alignment/bamqc.sh
index bfc8c54e77a13893ebcc8b2440bafac09ae821ac..466d01c0fe62ec2f08551756f1de351cc25b6347 100644
--- a/alignment/bamqc.sh
+++ b/alignment/bamqc.sh
@@ -40,28 +40,29 @@ samtools flagstat ${sbam} > ${pair_id}.flagstat.txt
fastqc -f bam ${sbam}
baseDir="`dirname \"$0\"`"
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
if [[ $dedup == 1 ]]
then
mv $sbam ori.bam
- samtools view -@ $SLURM_CPUS_ON_NODE -F 1024 -b -o ${sbam} ori.bam
+ samtools view -@ $NPROC -F 1024 -b -o ${sbam} ori.bam
fi
if [[ $nuctype == 'dna' ]]; then
module load bedtools/2.26.0 picard/2.10.3
if [[ -z $skiplc ]]
then
- samtools view -@ $SLURM_CPUS_ON_NODE -b -L ${bed} -o ${pair_id}.ontarget.bam ${sbam}
- samtools index -@ $SLURM_CPUS_ON_NODE ${pair_id}.ontarget.bam
+ samtools view -@ $NPROC -b -L ${bed} -o ${pair_id}.ontarget.bam ${sbam}
+ samtools index -@ $NPROC ${pair_id}.ontarget.bam
samtools flagstat ${pair_id}.ontarget.bam > ${pair_id}.ontarget.flagstat.txt
java -Xmx64g -jar $PICARD/picard.jar CollectAlignmentSummaryMetrics R=${index_path}/genome.fa I=${pair_id}.ontarget.bam OUTPUT=${pair_id}.alignmentsummarymetrics.txt
- java -Xmx64g -XX:ParallelGCThreads=$SLURM_CPUS_ON_NODE -jar $PICARD/picard.jar EstimateLibraryComplexity I=${sbam} OUTPUT=${pair_id}.libcomplex.txt
- samtools view -@ $SLURM_CPUS_ON_NODE -b -q 1 ${sbam} | bedtools coverage -sorted -hist -g ${index_path}/genomefile.txt -b stdin -a ${bed} > ${pair_id}.mapqualcov.txt
- samtools view -@ $SLURM_CPUS_ON_NODE ${sbam} | awk '{sum+=$5} END { print "Mean MAPQ =",sum/NR}' > ${pair_id}.meanmap.txt
+ java -Xmx64g -XX:ParallelGCThreads=$NPROC -jar $PICARD/picard.jar EstimateLibraryComplexity I=${sbam} OUTPUT=${pair_id}.libcomplex.txt
+ samtools view -@ $NPROC -b -q 1 ${sbam} | bedtools coverage -sorted -hist -g ${index_path}/genomefile.txt -b stdin -a ${bed} > ${pair_id}.mapqualcov.txt
+ samtools view -@ $NPROC ${sbam} | awk '{sum+=$5} END { print "Mean MAPQ =",sum/NR}' > ${pair_id}.meanmap.txt
fi
java -Xmx64g -jar $PICARD/picard.jar CollectInsertSizeMetrics INPUT=${sbam} HISTOGRAM_FILE=${pair_id}.hist.ps REFERENCE_SEQUENCE=${index_path}/genome.fa OUTPUT=${pair_id}.hist.txt
bedtools coverage -sorted -g ${index_path}/genomefile.txt -a ${bed} -b ${sbam} -hist > ${pair_id}.covhist.txt
diff --git a/alignment/dnaseqalign.sh b/alignment/dnaseqalign.sh
index cac762d61e7117fc2070f796d0e8adc4b85eadcb..184c787ba5e30d6a2983857fd7d84d26c78ebd95 100644
--- a/alignment/dnaseqalign.sh
+++ b/alignment/dnaseqalign.sh
@@ -33,9 +33,10 @@ if [[ -z $pair_id ]] || [[ -z $fq1 ]]; then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
if [[ -z $read_group ]]
@@ -61,7 +62,7 @@ else
file_opt="${fq1}"
fi
-bwa mem -M -t $SLURM_CPUS_ON_NODE -R "@RG\tID:${read_group}\tLB:tx\tPL:illumina\tPU:barcode\tSM:${read_group}" ${index_path}/genome.fa $file_opt > out.sam
+bwa mem -M -t $NPROC -R "@RG\tID:${read_group}\tLB:tx\tPL:illumina\tPU:barcode\tSM:${read_group}" ${index_path}/genome.fa $file_opt > out.sam
if [[ $umi == 'umi' ]] && [[ -f "${index_path}/genome.fa.alt" ]]
then
@@ -77,6 +78,6 @@ else
fi
which samtools
-samtools sort -n --threads $SLURM_CPUS_ON_NODE -o output.dups.bam output.unsort.bam
+samtools sort -n --threads $NPROC -o output.dups.bam output.unsort.bam
java -Djava.io.tmpdir=./ -Xmx4g -jar $PICARD/picard.jar FixMateInformation ASSUME_SORTED=TRUE SORT_ORDER=coordinate ADD_MATE_CIGAR=TRUE I=output.dups.bam O=${pair_id}.bam
samtools index ${pair_id}.bam
diff --git a/alignment/hisat_genotype.sh b/alignment/hisat_genotype.sh
index 7e0655ecd393c73483cb63201d266c3c554b687c..4ee37c672dea6910e9f0a8e9b8516e55ed4d35b6 100644
--- a/alignment/hisat_genotype.sh
+++ b/alignment/hisat_genotype.sh
@@ -29,9 +29,10 @@ if [[ -z $pair_id ]]; then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
source /etc/profile.d/modules.sh
diff --git a/alignment/indexbams.sh b/alignment/indexbams.sh
index 38238fb1b337c8051e225e9e0f410ccd3fe2bd8a..2af125dd027eac1ad1ae2cefd1f776e0a9bc17a5 100644
--- a/alignment/indexbams.sh
+++ b/alignment/indexbams.sh
@@ -18,14 +18,16 @@ shift $(($OPTIND -1))
# Check for mandatory options
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
+
baseDir="`dirname \"$0\"`"
source /etc/profile.d/modules.sh
module load samtools/1.6
for i in *.bam; do
- samtools index -@ $SLURM_CPUS_ON_NODE ${i}
+ samtools index -@ $NPROC ${i}
done
diff --git a/alignment/markdups.sh b/alignment/markdups.sh
index 91bcc0a0693d36175d27cde1020742c788fb93e7..ca36c409a959dcdb49a100f271125aeb698d2792 100644
--- a/alignment/markdups.sh
+++ b/alignment/markdups.sh
@@ -28,10 +28,12 @@ if [[ -z $pair_id ]] || [[ -z $sbam ]]; then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
+
if [[ -z $index_path ]]
then
index_path="/project/shared/bicf_workflow_ref/human/grch38_cloud/dnaref"
@@ -46,39 +48,39 @@ module load picard/2.10.3
if [ $algo == 'sambamba' ]
then
module load speedseq/20160506
- sambamba markdup -t $SLURM_CPUS_ON_NODE ${sbam} ${pair_id}.dedup.bam
+ sambamba markdup -t $NPROC ${sbam} ${pair_id}.dedup.bam
touch ${pair_id}.dedup.stat.txt
elif [ $algo == 'samtools' ]
then
module load samtools/gcc/1.8
- samtools markdup -s --output-fmt BAM -@ $SLURM_CPUS_ON_NODE sort.bam ${pair_id}.dedup.bam
+ samtools markdup -s --output-fmt BAM -@ $NPROC sort.bam ${pair_id}.dedup.bam
touch ${pair_id}.dedup.stat.txt
elif [ $algo == 'picard' ]
then
- java -XX:ParallelGCThreads=$SLURM_CPUS_ON_NODE -Djava.io.tmpdir=./ -Xmx16g -jar $PICARD/picard.jar MarkDuplicates I=${sbam} O=${pair_id}.dedup.bam M=${pair_id}.dedup.stat.txt
+ java -XX:ParallelGCThreads=$NPROC -Djava.io.tmpdir=./ -Xmx16g -jar $PICARD/picard.jar MarkDuplicates I=${sbam} O=${pair_id}.dedup.bam M=${pair_id}.dedup.stat.txt
elif [ $algo == 'picard_umi' ]
then
- java -XX:ParallelGCThreads=$SLURM_CPUS_ON_NODE -Djava.io.tmpdir=./ -Xmx16g -jar $PICARD/picard.jar MarkDuplicates BARCODE_TAG=RX I=${sbam} O=${pair_id}.dedup.bam M=${pair_id}.dedup.stat.txt
+ java -XX:ParallelGCThreads=$NPROC -Djava.io.tmpdir=./ -Xmx16g -jar $PICARD/picard.jar MarkDuplicates BARCODE_TAG=RX I=${sbam} O=${pair_id}.dedup.bam M=${pair_id}.dedup.stat.txt
elif [ $algo == 'fgbio_umi' ]
then
module load fgbio bwakit/0.7.15 bwa/intel/0.7.17 samtools/gcc/1.8
- samtools index -@ $SLURM_CPUS_ON_NODE ${sbam}
+ samtools index -@ $NPROC ${sbam}
fgbio --tmp-dir ./ GroupReadsByUmi -s identity -i ${sbam} -o ${pair_id}.group.bam --family-size-histogram ${pair_id}.umihist.txt -e 0 -m 0
fgbio --tmp-dir ./ CallMolecularConsensusReads -i ${pair_id}.group.bam -p consensus -M 1 -o ${pair_id}.consensus.bam -S ':none:'
samtools index ${pair_id}.consensus.bam
samtools fastq -1 ${pair_id}.consensus.R1.fastq -2 ${pair_id}.consensus.R2.fastq ${pair_id}.consensus.bam
gzip ${pair_id}.consensus.R1.fastq
gzip ${pair_id}.consensus.R2.fastq
- bwa mem -M -C -t $SLURM_CPUS_ON_NODE -R "@RG\tID:${pair_id}\tLB:tx\tPL:illumina\tPU:barcode\tSM:${pair_id}" ${index_path}/genome.fa ${pair_id}.consensus.R1.fastq.gz ${pair_id}.consensus.R2.fastq.gz > out.sam
+ bwa mem -M -C -t $NPROC -R "@RG\tID:${pair_id}\tLB:tx\tPL:illumina\tPU:barcode\tSM:${pair_id}" ${index_path}/genome.fa ${pair_id}.consensus.R1.fastq.gz ${pair_id}.consensus.R2.fastq.gz > out.sam
if [[ ${index_path}/genome.fa.alt ]]
then
k8 ${testexe}/bwa-postalt.js -p tmphla ${index_path}/genome.fa.alt out.sam | samtools view -1 - > ${pair_id}.consensus.bam
else
samtools view -1 out.sam > ${pair_id}.consensus.bam
fi
- samtools sort --threads $SLURM_CPUS_ON_NODE -o ${pair_id}.dedup.bam ${pair_id}.consensus.bam
+ samtools sort --threads $NPROC -o ${pair_id}.dedup.bam ${pair_id}.consensus.bam
else
cp ${sbam} ${pair_id}.dedup.bam
fi
module load samtools/gcc/1.8
-samtools index -@ $SLURM_CPUS_ON_NODE ${pair_id}.dedup.bam
+samtools index -@ $NPROC ${pair_id}.dedup.bam
diff --git a/alignment/rnaseqalign.sh b/alignment/rnaseqalign.sh
index d044bda3ea5646968bb06609ec54eb3296816f61..a46a1f75af784aa1d6ef7df386b087e98fe5d39f 100644
--- a/alignment/rnaseqalign.sh
+++ b/alignment/rnaseqalign.sh
@@ -36,9 +36,10 @@ fi
source /etc/profile.d/modules.sh
module load samtools/1.6 picard/2.10.3
baseDir="`dirname \"$0\"`"
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
diff $fq1 $fq2 > difffile
@@ -59,17 +60,17 @@ else
module load hisat2/2.1.0-intel
if [ -s difffile ]
then
- hisat2 -p $SLURM_CPUS_ON_NODE --rg-id ${pair_id} --rg LB:tx --rg PL:illumina --rg PU:barcode --rg SM:${pair_id} --no-unal --dta -x ${index_path}/genome -1 $fq1 -2 $fq2 -S out.sam --summary-file ${pair_id}.alignerout.txt
+ hisat2 -p $NPROC --rg-id ${pair_id} --rg LB:tx --rg PL:illumina --rg PU:barcode --rg SM:${pair_id} --no-unal --dta -x ${index_path}/genome -1 $fq1 -2 $fq2 -S out.sam --summary-file ${pair_id}.alignerout.txt
else
- hisat2 -p $SLURM_CPUS_ON_NODE --rg-id ${pair_id} --rg LB:tx --rg PL:illumina --rg PU:barcode --rg SM:${pair_id} --no-unal --dta -x ${index_path}/genome -U $fq1 -S out.sam --summary-file ${pair_id}.alignerout.txt
+ hisat2 -p $NPROC --rg-id ${pair_id} --rg LB:tx --rg PL:illumina --rg PU:barcode --rg SM:${pair_id} --no-unal --dta -x ${index_path}/genome -U $fq1 -S out.sam --summary-file ${pair_id}.alignerout.txt
fi
if [[ $umi == 1 ]]
then
python ${baseDir}/add_umi_sam.py -s out.sam -o output.bam
else
- samtools view -1 --threads $SLURM_CPUS_ON_NODE -o output.bam out.sam
+ samtools view -1 --threads $NPROC -o output.bam out.sam
fi
- samtools sort -@ $SLURM_CPUS_ON_NODE -O BAM -o ${pair_id}.bam output.bam
+ samtools sort -@ $NPROC -O BAM -o ${pair_id}.bam output.bam
fi
-samtools index -@ $SLURM_CPUS_ON_NODE ${pair_id}.bam
+samtools index -@ $NPROC ${pair_id}.bam
diff --git a/alignment/starfusion.sh b/alignment/starfusion.sh
index 81a58775d29d860f623557b5eb1c9321f423cf9e..a9f984c59e288df27ea45277fb2c4848449564c5 100644
--- a/alignment/starfusion.sh
+++ b/alignment/starfusion.sh
@@ -31,9 +31,10 @@ if [[ -z $pair_id ]] || [[ -z $fq1 ]]; then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
baseDir="`dirname \"$0\"`"
@@ -50,7 +51,7 @@ then
fi
export TMP_HOME=$tmphome
refgeno=${index_path}/CTAT_lib_trinity1.6
- trinity /usr/local/src/STAR-Fusion/STAR-Fusion --min_sum_frags 3 --CPU $SLURM_CPUS_ON_NODE --genome_lib_dir ${refgeno} --left_fq ${fq1} --right_fq ${fq2} --examine_coding_effect --output_dir ${pair_id}_star_fusion
+ trinity /usr/local/src/STAR-Fusion/STAR-Fusion --min_sum_frags 3 --CPU $NPROC --genome_lib_dir ${refgeno} --left_fq ${fq1} --right_fq ${fq2} --examine_coding_effect --output_dir ${pair_id}_star_fusion
cp ${pair_id}_star_fusion/star-fusion.fusion_predictions.abridged.coding_effect.tsv ${pair_id}.starfusion.txt
else
module add star/2.5.2b
diff --git a/genect_rnaseq/geneabundance.sh b/genect_rnaseq/geneabundance.sh
index 39aad284f18c21a6c93f1e7c08ac479e893d1c74..5ad0e357a6330121875588edcc7bab863f98e561 100644
--- a/genect_rnaseq/geneabundance.sh
+++ b/genect_rnaseq/geneabundance.sh
@@ -29,20 +29,21 @@ if [[ -z $pair_id ]] || [[ -z $sbam ]]
then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
-if [[ $SLURM_CPUS_ON_NODE > 64 ]]
+if [[ $NPROC > 64 ]]
then
- SLURM_CPUS_ON_NODE=64
+ NPROC=64
fi
source /etc/profile.d/modules.sh
module load subread/1.6.1
export PATH=/project/shared/bicf_workflow_ref/seqprg/bin:$PATH
-featureCounts -s $stranded -M --fraction -J --ignoreDup -T $SLURM_CPUS_ON_NODE -p -g gene_name -a ${gtf} -o ${pair_id}.cts ${sbam}
+featureCounts -s $stranded -M --fraction -J --ignoreDup -T $NPROC -p -g gene_name -a ${gtf} -o ${pair_id}.cts ${sbam}
mkdir ${pair_id}_stringtie
cd ${pair_id}_stringtie
-stringtie ../${sbam} -p $SLURM_CPUS_ON_NODE -G ${gtf} -B -e -o denovo.gtf -A ../${pair_id}.fpkm.txt
+stringtie ../${sbam} -p $NPROC -G ${gtf} -B -e -o denovo.gtf -A ../${pair_id}.fpkm.txt
diff --git a/genect_rnaseq/statanal.sh b/genect_rnaseq/statanal.sh
index ad5cab388e0f1edbe81cb8af30c4515dc6b6d14a..9cba1e37976c079754bd830ebf1b38acf12dec03 100644
--- a/genect_rnaseq/statanal.sh
+++ b/genect_rnaseq/statanal.sh
@@ -20,9 +20,10 @@ shift $(($OPTIND -1))
baseDir="`dirname \"$0\"`"
# Check for mandatory options
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
source /etc/profile.d/modules.sh
diff --git a/variants/cnvkit.sh b/variants/cnvkit.sh
index 23a40e557b0971b737e0173456425824515fff13..a728ad9cc23a8ad0d5015a0d2da36d82b2e6e7c5 100755
--- a/variants/cnvkit.sh
+++ b/variants/cnvkit.sh
@@ -35,9 +35,10 @@ if [[ -z $pair_id ]] || [[ -z $sbam ]]
then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
if [[ -z $paneldir ]]
then
diff --git a/variants/gatkrunner.sh b/variants/gatkrunner.sh
index 41436e5685ac938f62ec9a4698973a3b1b99f708..d3dd05f3990d9984bce5d86554010b415c873c39 100755
--- a/variants/gatkrunner.sh
+++ b/variants/gatkrunner.sh
@@ -30,9 +30,10 @@ then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
if [[ -a "${index_path}/dbSnp.gatk4.vcf.gz" ]]
then
@@ -59,7 +60,7 @@ fi
source /etc/profile.d/modules.sh
module load gatk/4.1.2.0 samtools/gcc/1.8
which samtools
-/cm/shared/apps/samtools/gcc/1.8/bin/samtools index -@ $SLURM_CPUS_ON_NODE ${sbam}
+/cm/shared/apps/samtools/gcc/1.8/bin/samtools index -@ $NPROC ${sbam}
if [[ $algo == 'gatkbam_rna' ]]
then
@@ -67,21 +68,21 @@ then
java -Xmx4g -jar $PICARD/picard.jar CleanSam INPUT=${sbam} OUTPUT=${pair_id}.clean.bam
java -Xmx4g -jar $PICARD/picard.jar ReorderSam I=${pair_id}.clean.bam O=${pair_id}.sort.bam R=${reffa} CREATE_INDEX=TRUE
java -Xmx4g -jar $PICARD/picard.jar AddOrReplaceReadGroups INPUT=${pair_id}.clean.bam O=${pair_id}.rg_added_sorted.bam SO=coordinate RGID=${pair_id} RGLB=tx RGPL=illumina RGPU=barcode RGSM=${pair_id}
- samtools index -@ $SLURM_CPUS_ON_NODE ${pair_id}.rg_added_sorted.bam
+ samtools index -@ $NPROC ${pair_id}.rg_added_sorted.bam
gatk SplitNCigarReads -R ${reffa} -I ${pair_id}.rg_added_sorted.bam -O ${pair_id}.split.bam
gatk --java-options "-Xmx32g" BaseRecalibrator -I ${pair_id}.split.bam --known-sites ${index_path}/dbSnp.gatk4.vcf.gz -R ${reffa} -O ${pair_id}.recal_data.table --use-original-qualities
gatk --java-options "-Xmx32g" ApplyBQSR -I ${pair_id}.split.bam -R ${reffa} -O ${pair_id}.final.bam --use-original-qualities -bqsr ${pair_id}.recal_data.table
- /cm/shared/apps/samtools/gcc/1.8/bin/samtools index -@ $SLURM_CPUS_ON_NODE ${pair_id}.final.bam
+ /cm/shared/apps/samtools/gcc/1.8/bin/samtools index -@ $NPROC ${pair_id}.final.bam
elif [[ $algo == 'gatkbam' ]]
then
gatk --java-options "-Xmx32g" BaseRecalibrator -I ${sbam} --known-sites ${index_path}/dbSnp.gatk4.vcf.gz -R ${reffa} -O ${pair_id}.recal_data.table --use-original-qualities
gatk --java-options "-Xmx32g" ApplyBQSR -I ${sbam} -R ${reffa} -O ${pair_id}.final.bam --use-original-qualities -bqsr ${pair_id}.recal_data.table
- /cm/shared/apps/samtools/gcc/1.8/bin/samtools index -@ $SLURM_CPUS_ON_NODE ${pair_id}.final.bam
+ /cm/shared/apps/samtools/gcc/1.8/bin/samtools index -@ $NPROC ${pair_id}.final.bam
elif [[ $algo == 'abra2' ]]
then
module load abra2/2.18
mkdir tmpdir
- java -Xmx16G -jar /cm/shared/apps/abra2/lib/abra2.jar --in ${sbam} --in-vcf /archive/PHG/PHG_Clinical/phg_workflow/analysis/awesomeproject/GoldIndels.vcf --out ${pair_id}.final.bam --ref ${reffa} --threads $SLURM_CPUS_ON_NODE --tmpdir tmpdir
- samtools index -@ $SLURM_CPUS_ON_NODE ${pair_id}.final.bam
+ java -Xmx16G -jar /cm/shared/apps/abra2/lib/abra2.jar --in ${sbam} --in-vcf /archive/PHG/PHG_Clinical/phg_workflow/analysis/awesomeproject/GoldIndels.vcf --out ${pair_id}.final.bam --ref ${reffa} --threads $NPROC --tmpdir tmpdir
+ samtools index -@ $NPROC ${pair_id}.final.bam
fi
diff --git a/variants/germline_vc.sh b/variants/germline_vc.sh
index 018f765406f4ba2e7fe5653f805807794452a7df..b8699b0272243106981dc2093a514fd64a7b8b9e 100755
--- a/variants/germline_vc.sh
+++ b/variants/germline_vc.sh
@@ -30,9 +30,10 @@ shift $(($OPTIND -1))
if [[ -z $pair_id ]] || [[ -z $index_path ]]; then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
if [[ -s "${index_path}/dbSnp.vcf.gz" ]]
then
@@ -70,13 +71,13 @@ module load python/2.7.x-anaconda picard/2.10.3 samtools/gcc/1.8 bcftools/gcc/1.
for i in *.bam; do
if [[ ! -f ${i}.bai ]]
then
- samtools index -@ $SLURM_CPUS_ON_NODE $i
+ samtools index -@ $NPROC $i
fi
done
if [[ $algo == 'mpileup' ]]
then
- threads=`expr $SLURM_CPUS_ON_NODE - 10`
+ threads=`expr $NPROC - 10`
bcftools mpileup --threads $threads -a 'INFO/AD,INFO/ADF,INFO/ADR,FORMAT/DP,FORMAT/SP,FORMAT/AD,FORMAT/ADF,FORMAT/ADR' -Ou -A -d 1000000 -C50 -f ${reffa} *.bam | bcftools call -A --threads 10 -vmO z -o ${pair_id}.vcf.gz
vcf-annotate -n --fill-type ${pair_id}.vcf.gz | bcftools norm -c s -f ${reffa} -w 10 -O v -o sam.vcf
java -jar $PICARD/picard.jar SortVcf I=sam.vcf O=${pair_id}.sam.vcf R=${reffa} CREATE_INDEX=TRUE
@@ -88,13 +89,13 @@ then
for i in *.bam; do
bamlist="$bamlist --bam ${PWD}/${i}"
done
- cut -f 1 ${index_path}/genomefile.5M.txt | parallel --delay 2 -j $SLURM_CPUS_ON_NODE "freebayes -f ${index_path}/genome.fa --min-mapping-quality 0 --min-base-quality 20 --min-coverage 10 --min-alternate-fraction 0.01 -C 3 --use-best-n-alleles 3 -r {} ${bamlist} > fb.{}.vcf"
+ cut -f 1 ${index_path}/genomefile.5M.txt | parallel --delay 2 -j $NPROC "freebayes -f ${index_path}/genome.fa --min-mapping-quality 0 --min-base-quality 20 --min-coverage 10 --min-alternate-fraction 0.01 -C 3 --use-best-n-alleles 3 -r {} ${bamlist} > fb.{}.vcf"
vcf-concat fb.*.vcf | vcf-sort | vcf-annotate -n --fill-type | bcftools norm -c s -f ${reffa} -w 10 -O z -o ${pair_id}.freebayes.vcf.gz -
elif [[ $algo == 'platypus' ]]
then
module load platypus/gcc/0.8.1
bamlist=`join_by , *.bam`
- Platypus.py callVariants --minMapQual=0 --minReads=3 --mergeClusteredVariants=1 --nCPU=$SLURM_CPUS_ON_NODE --bamFiles=${bamlist} --refFile=${reffa} --output=platypus.vcf
+ Platypus.py callVariants --minMapQual=0 --minReads=3 --mergeClusteredVariants=1 --nCPU=$NPROC --bamFiles=${bamlist} --refFile=${reffa} --output=platypus.vcf
vcf-sort platypus.vcf |vcf-annotate -n --fill-type -n |bgzip > platypus.vcf.gz
tabix platypus.vcf.gz
bcftools norm -c s -f ${reffa} -w 10 -O z -o ${pair_id}.platypus.vcf.gz platypus.vcf.gz
@@ -143,8 +144,8 @@ then
gvcflist="$gvcflist --bam ${i}"
done
configManta.py $gvcflist --referenceFasta ${reffa} $mode --runDir manta
- manta/runWorkflow.py -m local -j $SLURM_CPUS_ON_NODE
+ manta/runWorkflow.py -m local -j $NPROC
configureStrelkaGermlineWorkflow.py $gvcflist --referenceFasta ${reffa} $mode --indelCandidates manta/results/variants/candidateSmallIndels.vcf.gz --runDir strelka
- strelka/runWorkflow.py -m local -j $SLURM_CPUS_ON_NODE
+ strelka/runWorkflow.py -m local -j $NPROC
bcftools norm -c s -f ${reffa} -w 10 -O z -o ${pair_id}.strelka2.vcf.gz strelka/results/variants/variants.vcf.gz
fi
diff --git a/variants/itdseek.sh b/variants/itdseek.sh
index 0ea6ac83510bc896c371ce12edf884a78b48cf37..3af0ea721cdd5485f5a5cc8718cc04a300ec90c9 100755
--- a/variants/itdseek.sh
+++ b/variants/itdseek.sh
@@ -31,9 +31,10 @@ baseDir="`dirname \"$0\"`"
if [[ -z $pair_id ]] || [[ -z $index_path ]]; then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
if [[ -z $snpeffgeno ]]
then
@@ -56,7 +57,7 @@ source /etc/profile.d/modules.sh
module load samtools/gcc/1.8 snpeff/4.3q vcftools/0.1.14 htslib/gcc/1.8 bcftools/gcc/1.8 bedtools/2.26.0
stexe=`which samtools`
-samtools view -@ $SLURM_CPUS_ON_NODE -L ${itdbed} ${sbam} | /project/shared/bicf_workflow_ref/seqprg/itdseek-1.2/itdseek.pl --refseq ${reffa} --samtools ${stexe} --bam ${sbam} | vcf-sort | bedtools intersect -header -b ${itdbed} -a stdin | bgzip > ${pair_id}.itdseek.vcf.gz
+samtools view -@ $NPROC -L ${itdbed} ${sbam} | /project/shared/bicf_workflow_ref/seqprg/itdseek-1.2/itdseek.pl --refseq ${reffa} --samtools ${stexe} --bam ${sbam} | vcf-sort | bedtools intersect -header -b ${itdbed} -a stdin | bgzip > ${pair_id}.itdseek.vcf.gz
tabix ${pair_id}.itdseek.vcf.gz
bcftools norm --fasta-ref $reffa -c w -m - -Ov ${pair_id}.itdseek.vcf.gz | java -Xmx30g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config $snpeffgeno - |bgzip > ${pair_id}.itdseek_tandemdup.vcf.gz
diff --git a/variants/pindel.sh b/variants/pindel.sh
index 294d7cd57175d1792a23be3bdc6eabd7bb524275..ebbd3fe316bf36bf42c4aa6ecb3795ea397d9dcb 100755
--- a/variants/pindel.sh
+++ b/variants/pindel.sh
@@ -29,9 +29,10 @@ baseDir="`dirname \"$0\"`"
if [[ -z $pair_id ]] || [[ -z $index_path ]]; then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
if [[ -a "${index_path}/genome.fa" ]]
@@ -59,7 +60,7 @@ for i in *.bam; do
echo -e "${i}\t400\t${sname}" >> ${pair_id}.pindel.config
done
-pindel -T $SLURM_CPUS_ON_NODE -f ${reffa} -i ${pair_id}.pindel.config -o ${pair_id}.pindel_out --RP
+pindel -T $NPROC -f ${reffa} -i ${pair_id}.pindel.config -o ${pair_id}.pindel_out --RP
pindel2vcf -P ${pair_id}.pindel_out -r ${reffa} -R HG38 -d ${genomefiledate} -v pindel.vcf
cat pindel.vcf | java -jar $SNPEFF_HOME/SnpSift.jar filter "( GEN[*].AD[1] >= 10 )" | bgzip > pindel.vcf.gz
tabix pindel.vcf.gz
diff --git a/variants/somatic_vc.sh b/variants/somatic_vc.sh
index d21321a0852fe3b9d0535fdc41273ea58aa67b85..159351e4fb5f53c3b0f2966cbde1614954870320 100755
--- a/variants/somatic_vc.sh
+++ b/variants/somatic_vc.sh
@@ -45,10 +45,10 @@ if [[ -z $normal ]] || [[ -z $tumor ]] || [[ -z $algo ]]; then
echo $normal $tumor $algo
usage
fi
-
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
#pair_id=${tid}_${nid}
if [[ -z $mtumor ]]
@@ -104,7 +104,7 @@ fi
if [ $algo == 'virmid' ]
then
module load virmid/1.2 samtools/gcc/1.8 vcftools/0.1.14
- virmid -R ${reffa} -D ${tumor} -N ${normal} -s ${cosmic} -t $SLURM_CPUS_ON_NODE -M 2000 -c1 10 -c2 10
+ virmid -R ${reffa} -D ${tumor} -N ${normal} -s ${cosmic} -t $NPROC -M 2000 -c1 10 -c2 10
perl $baseDir/addgt_virmid.pl ${tumor}.virmid.som.passed.vcf
perl $baseDir/addgt_virmid.pl ${tumor}.virmid.loh.passed.vcf
module rm java/oracle/jdk1.7.0_51
@@ -114,7 +114,7 @@ elif [ $algo == 'mutect2' ]
then
gatk4_dbsnp=${index_path}/clinseq_prj/dbSnp.gatk4.vcf.gz
module load gatk/4.1.4.0 picard/2.10.3 snpeff/4.3q samtools/gcc/1.8 vcftools/0.1.14
- java -XX:ParallelGCThreads=$SLURM_CPUS_ON_NODE -Djava.io.tmpdir=./ -Xmx16g -jar $PICARD/picard.jar CollectSequencingArtifactMetrics I=${tumor} O=artifact_metrics.txt R=${reffa}
+ java -XX:ParallelGCThreads=$NPROC -Djava.io.tmpdir=./ -Xmx16g -jar $PICARD/picard.jar CollectSequencingArtifactMetrics I=${tumor} O=artifact_metrics.txt R=${reffa}
gatk --java-options "-Xmx20g" Mutect2 $ponopt -R ${reffa} -I ${tumor} -tumor ${tid} -I ${normal} -normal ${nid} --output ${tid}.mutect.vcf
gatk --java-options "-Xmx20g" FilterMutectCalls -R ${reffa} -V ${tid}.mutect.vcf -O ${tid}.mutect.filt.vcf
vcf-sort ${tid}.mutect.filt.vcf | vcf-annotate -n --fill-type | java -jar $SNPEFF_HOME/SnpSift.jar filter -p '(GEN[*].DP >= 10)' | bgzip > ${pair_id}.mutect.vcf.gz
diff --git a/variants/svcalling.sh b/variants/svcalling.sh
index eedc0c9b8f13289abe96c7c3dac3a9f3495024f9..d193da7c81973b6e5b754f246774e97e88a002ef 100755
--- a/variants/svcalling.sh
+++ b/variants/svcalling.sh
@@ -36,9 +36,10 @@ baseDir="`dirname \"$0\"`"
if [[ -z $pair_id ]] || [[ -z $index_path ]]; then
usage
fi
-if [[ -z $SLURM_CPUS_ON_NODE ]]
+NPROC=$SLURM_CPUS_ON_NODE
+if [[ -z $NPROC ]]
then
- SLURM_CPUS_ON_NODE=1
+ NPROC=`nproc`
fi
if [[ -a "${index_path}/genome.fa" ]]
@@ -99,9 +100,9 @@ if [[ $method == 'svaba' ]]
then
if [[ -n ${normal} ]]
then
- /project/shared/bicf_workflow_ref/seqprg/svaba/bin/svaba run -p $SLURM_CPUS_ON_NODE -G ${reffa} -t ${sbam} -n ${normal} -a ${pair_id}
+ /project/shared/bicf_workflow_ref/seqprg/svaba/bin/svaba run -p $NPROC -G ${reffa} -t ${sbam} -n ${normal} -a ${pair_id}
else
- /project/shared/bicf_workflow_ref/seqprg/svaba/bin/svaba run -p $SLURM_CPUS_ON_NODE -G ${reffa} -t ${sbam} -a ${pair_id}
+ /project/shared/bicf_workflow_ref/seqprg/svaba/bin/svaba run -p $NPROC -G ${reffa} -t ${sbam} -a ${pair_id}
fi
java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config ${snpeffgeno} ${pair_id}.svaba.unfiltered.somatic.sv.vcf | bgzip > ${pair_id}.svaba.vcf.gz
fi
@@ -109,20 +110,20 @@ fi
if [[ $method == 'lumpy' ]]
then
#MAKE FILES FOR LUMPY
- samtools sort -@ $SLURM_CPUS_ON_NODE -n -o namesort.bam ${sbam}
+ samtools sort -@ $NPROC -n -o namesort.bam ${sbam}
samtools view -h namesort.bam | samblaster -M -a --excludeDups --addMateTags --maxSplitCount 2 --minNonOverlap 20 -d discordants.sam -s splitters.sam > temp.sam
gawk '{ if ($0~"^@") { print; next } else { $10="*"; $11="*"; print } }' OFS="\t" splitters.sam | samtools view -S -b - | samtools sort -o splitters.bam -
gawk '{ if ($0~"^@") { print; next } else { $10="*"; $11="*"; print } }' OFS="\t" discordants.sam | samtools view -S -b - | samtools sort -o discordants.bam -
#RUN LUMPY
if [[ -n ${normal} ]]
then
- samtools sort -@ $SLURM_CPUS_ON_NODE -n -o namesort.bam ${normal}
+ samtools sort -@ $NPROC -n -o namesort.bam ${normal}
samtools view -h namesort.bam | samblaster -M -a --excludeDups --addMateTags --maxSplitCount 2 --minNonOverlap 20 -d discordants.sam -s splitters.sam > temp.sam
gawk '{ if ($0~"^@") { print; next } else { $10="*"; $11="*"; print } }' OFS="\t" splitters.sam | samtools view -S -b - | samtools sort -o normal.splitters.bam -
gawk '{ if ($0~"^@") { print; next } else { $10="*"; $11="*"; print } }' OFS="\t" discordants.sam | samtools view -S -b - | samtools sort -o normal.discordants.bam -
- speedseq sv -t $SLURM_CPUS_ON_NODE -o lumpy -R ${reffa} -B ${normal},${sbam} -D normal.discordants.bam,discordants.bam -S normal.splitters.bam,splitters.bam -x ${index_path}/exclude_alt.bed
+ speedseq sv -t $NPROC -o lumpy -R ${reffa} -B ${normal},${sbam} -D normal.discordants.bam,discordants.bam -S normal.splitters.bam,splitters.bam -x ${index_path}/exclude_alt.bed
else
- speedseq sv -t $SLURM_CPUS_ON_NODE -o lumpy -R ${reffa} -B ${sbam} -D discordants.bam -S splitters.bam -x ${index_path}/exclude_alt.bed
+ speedseq sv -t $NPROC -o lumpy -R ${reffa} -B ${sbam} -D discordants.bam -S splitters.bam -x ${index_path}/exclude_alt.bed
fi
java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config ${snpeffgeno} lumpy.sv.vcf.gz | java -jar $SNPEFF_HOME/SnpSift.jar filter " ( GEN[*].DV >= 20 )" | bgzip > ${pair_id}.lumpy.vcf.gz
fi
@@ -134,9 +135,9 @@ then
for i in *.bam; do
sname=`echo "$i" |cut -f 1 -d '.'`
echo -e "${i}\t400\t${sname}" >> ${pair_id}.pindel.config
- samtools index -@ $SLURM_CPUS_ON_NODE $i
+ samtools index -@ $NPROC $i
done
- pindel -T $SLURM_CPUS_ON_NODE -f ${reffa} -i ${pair_id}.pindel.config -o ${pair_id}.pindel_out --RP
+ pindel -T $NPROC -f ${reffa} -i ${pair_id}.pindel.config -o ${pair_id}.pindel_out --RP
pindel2vcf -P ${pair_id}.pindel_out -r ${reffa} -R HG38 -d ${genomefiledate} -v pindel.vcf
cat pindel.vcf | java -jar $SNPEFF_HOME/SnpSift.jar filter "( GEN[*].AD[1] >= 10 )" | bgzip > pindel.vcf.gz
tabix pindel.vcf.gz
@@ -149,7 +150,7 @@ fi
if [[ $method == 'itdseek' ]]
then
stexe=`which samtools`
- samtools view -@ $SLURM_CPUS_ON_NODE -L ${bed} ${sbam} | /project/shared/bicf_workflow_ref/seqprg/itdseek-1.2/itdseek.pl --refseq ${reffa} --samtools ${stexe} --bam ${sbam} | vcf-sort | bedtools intersect -header -b ${bed} -a stdin | bgzip > ${pair_id}.itdseek.vcf.gz
+ samtools view -@ $NPROC -L ${bed} ${sbam} | /project/shared/bicf_workflow_ref/seqprg/itdseek-1.2/itdseek.pl --refseq ${reffa} --samtools ${stexe} --bam ${sbam} | vcf-sort | bedtools intersect -header -b ${bed} -a stdin | bgzip > ${pair_id}.itdseek.vcf.gz
tabix ${pair_id}.itdseek.vcf.gz
bcftools norm --fasta-ref $reffa -m - -Ov ${pair_id}.itdseek.vcf.gz | java -Xmx30g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config ${snpeffgeno} - |bgzip > ${pair_id}.itdseek_tandemdup.vcf.gz
diff --git a/variants/union.sh b/variants/union.sh
index 6c2edeefa94f7bfe8fa4e69a4d41f77dfc76926a..5dd626ce70070000a2e75e83380b5288a1aa110d 100755
--- a/variants/union.sh
+++ b/variants/union.sh
@@ -41,7 +41,7 @@ for i in ${dir}/*.vcf.gz; do
if [[ $i == $HS ]]
then
bcftools norm -m - -O z -o hotspot.norm.vcf.gz $i
- java -jar /cm/shared/apps/snpeff/4.3q/SnpSift.jar filter "(GEN[*].AD[1] > 3)" hotspot.norm.vcf.gz |bgzip > hotspot.lowfilt.vcf.gz
+ java -jar $SNPEFF_HOME/SnpSift.jar filter "(GEN[*].AD[1] > 3)" hotspot.norm.vcf.gz |bgzip > hotspot.lowfilt.vcf.gz
bedtools multiinter -i $list1 |cut -f 1,2,3 |bedtools intersect -header -v -a hotspot.lowfilt.vcf.gz -b stdin |bgzip > nooverlap.hotspot.vcf.gz
list2="$list2 nooverlap.hotspot.vcf.gz"
fi