modified: cre.vep.seqr.sh

naumenko-sa · Aug 10, 2018 · 50c6f47 · 50c6f47
1 parent 7180a96
commit 50c6f47
Showing 1 changed file with 6 additions and 13 deletions.
diff --git a/cre.vep.seqr.sh b/cre.vep.seqr.sh
@@ -1,18 +1,11 @@
 #/bin/bash
 
-# gemini.vcf2vep - annotate vcf with vep before loading to gemini database
-# based on  bcbio.log
-# uses hgvs notation and no --pick - all effects for a gene
-# 10h is not enough for genomes or big multisample vcfs
-
-#PBS -l walltime=23:00:00,nodes=1:ppn=16
+#PBS -l walltime=23:00:00,nodes=1:ppn=5
 #PBS -joe .
 #PBS -d .
 #PBS -l vmem=10g,mem=10g
 
-module load perl/5.20.1
-vcf='/hpf/largeprojects/ccmbio/teja/SEQR_test/661d.vcf'
-
+#module load perl/5.20.1
 
 reference=`which gatk-launch | sed s/"bin\/gatk-launch"/"\/genomes\/Hsapiens\/GRCh37"/`
 echo ${reference}
@@ -26,8 +19,8 @@ unset PERL5LIB && export PATH=/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/ana
     --fields Allele,Consequence,IMPACT,SYMBOL,Gene,Feature_type,Feature,BIOTYPE,EXON,INTRON,HGVSc,HGVSp,cDNA_position,CDS_position,Protein_position,Amino_acids,Codons,Existing_variation,ALLELE_NUM,DISTANCE,STRAND,FLAGS,VARIANT_CLASS,SYMBOL_SOURCE,HGNC_ID,CANONICAL,TSL,APPRIS,CCDS,ENSP,SWISSPROT,TREMBL,UNIPARC,REFSEQ_MATCH,SOURCE,GIVEN_REF,USED_REF,BAM_EDIT,GENE_PHENO,SIFT,PolyPhen,DOMAINS,HGVS_OFFSET,AF,AFR_AF,AMR_AF,EAS_AF,EUR_AF,SAS_AF,AA_AF,EA_AF,gnomAD_AF,gnomAD_AFR_AF,gnomAD_AMR_AF,gnomAD_ASJ_AF,gnomAD_EAS_AF,gnomAD_FIN_AF,gnomAD_NFE_AF,gnomAD_OTH_AF,gnomAD_SAS_AF,MAX_AF,MAX_AF_POPS,CLIN_SIG,SOMATIC,PHENO,PUBMED,MOTIF_NAME,MOTIF_POS,HIGH_INF_POS,MOTIF_SCORE_CHANGE,LoF,LoF_filter,LoF_flags,LoF_info,Polyphen2_HVAR_pred,CADD_phred,SIFT_pred,FATHMM_pred,MutationTaster_pred,MetaSVM_pred \
     --fasta /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa.gz \
     --plugin LoF,human_ancestor_fa:/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/variation/human_ancestor.fa.gz,\
-    loftee_path:/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/anaconda/share/ensembl-vep-91.2-0 \
- --plugin dbNSFP,/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/variation/dbNSFP.txt.gz,Polyphen2_HVAR_pred,CADD_phred,SIFT_pred,FATHMM_pred,MutationTaster_pred,MetaSVM_pred \
+             loftee_path:/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/anaconda/share/ensembl-vep-91.2-0 \
+    --plugin dbNSFP,/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/variation/dbNSFP.txt.gz,Polyphen2_HVAR_pred,CADD_phred,SIFT_pred,FATHMM_pred,MutationTaster_pred,MetaSVM_pred \
     --plugin MaxEntScan,/hpf/largeprkjects/ccmbio/naumenko/tools/bcbio/anaconda/share/maxentscan-0_2004.04.21-0 \
-    --plugin SpliceRegion --sift b --polyphen b --hgvs --shift_hgvs 1 --merged \
-    | sed '/^#/! s/;;/;/g'  >/hpf/largeprojects/ccmbio/teja/SEQR_test/661d.vep.vcf
+    --plugin SpliceRegion --sift b --polyphen b --hgvs --shift_hgvs 1 --merged | \
+     sed '/^#/! s/;;/;/g'  > `echo $vcf | sed s/vcf.gz/seqr.vcf.gz/`