From 903f1fd2a1d30788728f3ac200d7a50a92c53aff Mon Sep 17 00:00:00 2001 From: "naumenko.sa" Date: Tue, 10 Sep 2024 15:39:04 -0400 Subject: [PATCH] test --- cram2bam.sh | 2 ++ cre.vep.sh | 51 --------------------------------------------------- 2 files changed, 2 insertions(+), 51 deletions(-) delete mode 100755 cre.vep.sh diff --git a/cram2bam.sh b/cram2bam.sh index 7201351..0d570b1 100644 --- a/cram2bam.sh +++ b/cram2bam.sh @@ -5,6 +5,8 @@ #PBS -d . #PBS -l vmem=20g,mem=20g +# test + module load java cramtools bam -I $cram -O $bam -b -R $ref diff --git a/cre.vep.sh b/cre.vep.sh deleted file mode 100755 index 03c3148..0000000 --- a/cre.vep.sh +++ /dev/null @@ -1,51 +0,0 @@ -#/bin/bash - -# gemini.vcf2vep annotates vcf with vep before loading to gemini database -# based on bcbio.log -# uses hgvs notation and no --pick = all effects for a gene -# 10h walltime is not enough for genomes or big multisample vcfs - -#PBS -l walltime=23:00:00,nodes=1:ppn=1 -#PBS -joe . -#PBS -d . -#PBS -l vmem=30g,mem=30g - -if [ -z $vcf ] -then - vcf=$1 -fi - -if [ -z $threads ] -then - threads=5 -fi - -. /hpf/largeprojects/ccmbio/naumenko/tools/bcbio_1.1.5/.profile115 - -bname=`basename $vcf .vcf.gz` - -#find reference -reference=`readlink -f $(which bcbio_nextgen.py) | sed s/"anaconda\/bin\/bcbio_nextgen.py"/"genomes\/Hsapiens\/GRCh37"/` -vep_reference=`readlink -f $(which vep) | sed s/"\/vep"//` - -echo "Threads:" $threads - -#unset PERL5LIB && vep --vcf -o stdout \ -# -i $vcf --fork $threads --species homo_sapiens --no_stats --cache --offline --dir ${reference}/vep --symbol --numbers --biotype --total_length \ -# --canonical --gene_phenotype --ccds --uniprot --domains --regulatory --protein --tsl --appris --af --max_af --af_1kg --af_esp --af_gnomad --pubmed --variant_class \ -# --allele_number \ -# --fasta ${reference}/seq/GRCh37.fa.gz \ -# --plugin LoF,human_ancestor_fa:${reference}/variation/human_ancestor.fa.gz,loftee_path:$vep_reference \ -# --plugin MaxEntScan,/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/anaconda/share/maxentscan-0_2004.04.21-1 \ -# --plugin SpliceRegion --sift b --polyphen b --hgvs --shift_hgvs 1 --merged \ -# | sed '/^#/! s/;;/;/g' | bgzip -c > $bname.vepeffects.vcf.gz - -unset PERL5LIB && vep --vcf -o stdout \ - -i $vcf --fork $threads --species homo_sapiens --no_stats --cache --offline --dir ${reference}/vep --symbol --numbers --biotype --total_length \ - --canonical --gene_phenotype --ccds --uniprot --domains --regulatory --protein --tsl --appris --af --max_af --af_1kg --af_esp --af_gnomad --pubmed --variant_class \ - --allele_number \ - --fasta ${reference}/seq/GRCh37.fa.gz \ - --plugin LoF,human_ancestor_fa:${reference}/human_ancestor.fa.gz,loftee_path:$vep_reference \ - --plugin MaxEntScan,/hpf/largeprojects/ccmbio/naumenko/tools/bcbio_1.1.5/anaconda/share/maxentscan-0_2004.04.21-1 \ - --plugin SpliceRegion --sift b --polyphen b --hgvsg --hgvs --shift_hgvs 1 --merged \ - | sed '/^#/! s/;;/;/g' | bgzip -c > $bname.vepeffects.vcf.gz