diff --git a/alignment/filter_genefusions.pl b/alignment/filter_genefusions.pl
index c7097db2ec82487ef53d66b3e82647673b1ee592..e110246e2270565037e2d2ba4000e16c91c1bd1f 100755
--- a/alignment/filter_genefusions.pl
+++ b/alignment/filter_genefusions.pl
@@ -15,14 +15,14 @@ while (my $line = <ENT>) {
}
}
-open OM, "</project/shared/bicf_workflow_ref/human/GRCh38/clinseq_prj/utswv2_known_genefusions.txt" or die $!;
+open OM, "</project/shared/bicf_workflow_ref/human/GRCh38/clinseq_prj/known_genefusions.txt" or die $!;
while (my $line = <OM>) {
chomp($line);
$known{$line} = 1;
}
close OM;
-open OM, "</project/shared/bicf_workflow_ref/human/GRCh38/clinseq_prj/panel1410.genelist.txt" or die $!;
+open OM, "</project/shared/bicf_workflow_ref/human/GRCh38/clinseq_prj/panelgenes.txt" or die $!;
while (my $line = <OM>) {
chomp($line);
$keep{$line} = 1;
diff --git a/alignment/starfusion.sh b/alignment/starfusion.sh
index cc0d8dfda4ef497503d6853906da14eef945f845..fdde560708ff4bde1d8eb2776fed1eea624f3fba 100644
--- a/alignment/starfusion.sh
+++ b/alignment/starfusion.sh
@@ -51,7 +51,6 @@ then
export TMP_HOME=$tmphome
index_path=${refgeno}/CTAT_lib_trinity1.6
trinity /usr/local/src/STAR-Fusion/STAR-Fusion --min_sum_frags 3 --CPU $SLURM_CPUS_ON_NODE --genome_lib_dir ${index_path} --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.tsv ${pair_id}.starfusion.txt
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/variants/filter_cnvkit.pl b/variants/filter_cnvkit.pl
index e86ee768a88b5633cddc4ee05653e490b030df12..7bd4bbf73f26c15ed570dea7dfb8d0baef83df74 100755
--- a/variants/filter_cnvkit.pl
+++ b/variants/filter_cnvkit.pl
@@ -2,7 +2,7 @@
#parse_cnvkit_table.pl
my $refdir = '/project/shared/bicf_workflow_ref/human/GRCh38/';
-open OM, "<$refdir\/clinseq_prj/panel1410.genelist.txt" or die $!;
+open OM, "<$refdir\/clinseq_prj/panelgenes.txt" or die $!;
while (my $line = <OM>) {
chomp($line);
$keep{$line} = 1;
diff --git a/variants/germline_vc.sh b/variants/germline_vc.sh
index 62006d27ea31845de401c8be6195adba62412a0b..4550ad90a63dcfd6f67f020bd48744418a8356a8 100755
--- a/variants/germline_vc.sh
+++ b/variants/germline_vc.sh
@@ -56,6 +56,12 @@ else
echo "Missing Fasta File: ${index_path}/genome.fa"
usage
fi
+if [[ -z $pon ]]
+then
+ ponopt='';
+else
+ ponopt="--pon $pon"
+fi
source /etc/profile.d/modules.sh
module load python/2.7.x-anaconda picard/2.10.3 samtools/gcc/1.8 bcftools/gcc/1.8 bedtools/2.26.0 snpeff/4.3q vcftools/0.1.14 parallel
@@ -118,8 +124,8 @@ then
prefix="${i%.bam}"
echo ${prefix}
java -XX:ParallelGCThreads=$SLURM_CPUS_ON_NODE -Djava.io.tmpdir=./ -Xmx16g -jar $PICARD/picard.jar CollectSequencingArtifactMetrics I=${i} O=artifact_metrics.txt R=${reffa}
- gatk --java-options "-Xmx20g -Djava.io.tmpdir=./" Mutect2 $ponopt -R ${reffa} -A FisherStrand -A QualByDepth -A StrandArtifact -A DepthPerAlleleBySample --enable_strand_artifact_filter -I ${i} --output ${prefix}.mutect.vcf
- gatk --java-options "-Xmx20g -Djava.io.tmpdir=./" FilterMutectCalls -V ${prefix}.mutect.vcf -O ${prefix}.mutect.filt.vcf
+ gatk --java-options "-Xmx20g" Mutect2 $ponopt -R ${reffa} --enable-all-annotations -I ${i} --output ${prefix}.mutect.vcf
+ gatk --java-options "-Xmx20g" FilterMutectCalls -V ${prefix}.mutect.vcf -O ${prefix}.mutect.filt.vcf
vcf-sort ${prefix}.mutect.filt.vcf | vcf-annotate -n --fill-type | java -jar $SNPEFF_HOME/SnpSift.jar filter -p '(GEN[*].DP >= 10)' | bgzip > ${prefix}.mutect.vcf.gz
done
elif [[ $algo == 'strelka2' ]]
diff --git a/variants/somatic_vc.sh b/variants/somatic_vc.sh
index e6d6c9007e78448440267f1b90b702a26063f9ea..0d336ef121fe0d04b5fddff7d7e4eb5fad86062b 100755
--- a/variants/somatic_vc.sh
+++ b/variants/somatic_vc.sh
@@ -114,8 +114,8 @@ then
gatk4_dbsnp=${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}
- gatk --java-options "-Xmx20g -Djava.io.tmpdir=./" Mutect2 $ponopt -R ${reffa} -A FisherStrand -A QualByDepth -A StrandArtifact -A DepthPerAlleleBySample --enable_strand_artifact_filter -I ${tumor} -tumor ${tid} -I ${normal} -normal ${nid} --output ${tid}.mutect.vcf
- gatk --java-options "-Xmx20g -Djava.io.tmpdir=./" FilterMutectCalls -V ${tid}.mutect.vcf -O ${tid}.mutect.filt.vcf
+ gatk --java-options "-Xmx20g" Mutect2 $ponopt -R ${reffa} --enable-all-annotations -I ${tumor} -tumor ${tid} -I ${normal} -normal ${nid} --output ${tid}.mutect.vcf
+ gatk --java-options "-Xmx20g" FilterMutectCalls -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
elif [ $algo == 'varscan' ]
then
diff --git a/variants/svcalling.sh b/variants/svcalling.sh
index 881eefde49010df1ee7c2c0a9ec911628e7977cc..bbd1eaad0f279b0c9fe19d08fd686329944fcea8 100755
--- a/variants/svcalling.sh
+++ b/variants/svcalling.sh
@@ -11,7 +11,7 @@ usage() {
exit 1
}
OPTIND=1 # Reset OPTIND
-while getopts :r:p:b:i:n:a:h opt
+while getopts :r:p:b:i:x:y:n:l:a:h opt
do
case $opt in
r) index_path=$OPTARG;;
@@ -20,6 +20,9 @@ do
i) tumor=$OPTARG;;
n) normal=$OPTARG;;
a) method=$OPTARG;;
+ x) tid=$OPTARG;;
+ y) nid=$OPTARG;;
+ l) bed=$OPTARG;;
h) usage;;
esac
done
@@ -49,17 +52,17 @@ else
fi
source /etc/profile.d/modules.sh
-module load samtools/1.6 bedtools/2.26.0 snpeff/4.3q vcftools/0.1.14
-mkdir temp
+module load htslib/gcc/1.8 samtools/gcc/1.8 bcftools/gcc/1.8 bedtools/2.26.0 snpeff/4.3q vcftools/0.1.14
if [[ $method == 'delly' ]]
then
- module load delly2/v0.7.7-multi samtools/1.6 snpeff/4.3q
+ mkdir temp
+ module load delly2/v0.7.7-multi
if [[ -n ${normal} ]]
then
#RUN DELLY
- echo -e "${normal}\tcontrol"> samples.tsv
- echo -e "${tumor}\ttumor" >> samples.tsv
+ echo -e "${nid}\tcontrol"> samples.tsv
+ echo -e "${tid}\ttumor" >> samples.tsv
delly2 call -t BND -o delly_translocations.bcf -q 30 -g ${reffa} ${sbam} ${normal}
delly2 call -t DUP -o delly_duplications.bcf -q 30 -g ${reffa} ${sbam} ${normal}
delly2 call -t INV -o delly_inversions.bcf -q 30 -g ${reffa} ${sbam} ${normal}
@@ -86,7 +89,17 @@ then
#MERGE DELLY AND MAKE BED
bcftools concat -a -O v delly_dup.bcf delly_inv.bcf delly_tra.bcf delly_del.bcf delly_ins.bcf| vcf-sort -t temp > delly.vcf
bgzip delly.vcf
- java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config GRCh38.86 delly.vcf | java -jar $SNPEFF_HOME/SnpSift.jar filter " ( GEN[*].AD[1] >= 20 )" | bgzip > ${pair_id}.sv.vcf.gz
+ java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config GRCh38.86 delly.vcf | bgzip > ${pair_id}.delly.vcf.gz
+fi
+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}
+ else
+ /project/shared/bicf_workflow_ref/seqprg/svaba/bin/svaba run -p $SLURM_CPUS_ON_NODE -G ${reffa} -t ${sbam} -a ${pair_id}
+ fi
+ java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config GRCh38.86 ${pair_id}.svaba.unfiltered.somatic.sv.vcf | bgzip > ${pair_id}.svaba.vcf.gz
fi
if [[ $method == 'lumpy' ]]
@@ -107,5 +120,33 @@ then
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
fi
- java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config GRCh38.86 lumpy.sv.vcf.gz | java -jar $SNPEFF_HOME/SnpSift.jar filter " ( GEN[*].DV >= 20 )" | bgzip > ${pair_id}.sv.vcf.gz
+ java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config GRCh38.86 lumpy.sv.vcf.gz | java -jar $SNPEFF_HOME/SnpSift.jar filter " ( GEN[*].DV >= 20 )" | bgzip > ${pair_id}.lumpy.vcf.gz
+fi
+if [[ $method == 'pindel' ]]
+then
+ module load pindel/0.2.5-intel
+ genomefiledate=`find ${reffa} -maxdepth 0 -printf "%TY%Tm%Td\n"`
+ touch ${pair_id}.pindel.config
+ for i in *.bam; do
+ sname=`echo "$i" |cut -f 1 -d '.'`
+ echo -e "${i}\t400\t${sname}" >> ${pair_id}.pindel.config
+ samtools index -@ $SLURM_CPUS_ON_NODE $i
+ done
+ pindel -T $SLURM_CPUS_ON_NODE -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
+ bash $baseDir/norm_annot.sh -r ${index_path} -p pindel -v pindel.vcf.gz
+ perl $baseDir/parse_pindel.pl ${pair_id} pindel.norm.vcf.gz
+ java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config GRCh38.86 ${pair_id}.indel.vcf |bgzip > ${pair_id}.pindel_indel.vcf.gz
+ java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config GRCh38.86 ${pair_id}.dup.vcf | bedtools intersect -header -b ${bed} -a stdin | bgzip > ${pair_id}.pindel_tandemdup.vcf.gz
+ java -Xmx10g -jar $SNPEFF_HOME/snpEff.jar -no-intergenic -lof -c $SNPEFF_HOME/snpEff.config GRCh38.86 ${pair_id}.sv.vcf | bgzip > ${pair_id}.pindel_sv.vcf.gz
+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
+
+ 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 GRCh38.86 - |bgzip > ${pair_id}.itdseek_tandemdup.vcf.gz
fi