fixed issue when VEP and gnomad have conflicting annotations

cre.annotation.strip.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
 bname=`basename $1 .vcf.gz`
-vt rminfo -t CSQ,af_adj_exac_afr,af_adj_exac_amr,af_adj_exac_eas,af_adj_exac_fin,af_adj_exac_nfe,af_adj_exac_oth,af_adj_exac_sas,af_exac_all,ac_exac_all,an_exac_all,ac_adj_exac_afr,an_adj_exac_afr,ac_adj_exac_amr,an_adj_exac_amr,ac_adj_exac_eas,an_adj_exac_eas,ac_adj_exac_fin,an_adj_exac_fin,ac_adj_exac_nfe,an_adj_exac_nfe,ac_adj_exac_oth,an_adj_exac_oth,ac_adj_exac_sas,an_adj_exac_sas,common_pathogenic,max_aaf_all,num_exac_Het,num_exac_Hom,rs_ids,af_1kg_amr,af_1kg_eas,af_1kg_sas,af_1kg_afr,af_1kg_eur,af_1kg_all,fitcons,encode_consensus_gm12878,encode_consensus_h1hesc,encode_consensus_helas3,encode_consensus_hepg2,encode_consensus_huvec,encode_consensus_k562,dgv,hapmap1,hapmap2,gnomAD_AF,gnomAD_AFR_AF,gnomAD_AMR_AF,gnomAD_ASJ_AF,gnomAD_EAS_AF,gnomAD_FIN_AF,gnomAD_NFE_AF,gnomAD_OTH_AF,gnomad_ac_es,gnomad_hom_es,gnomad_af_es,gnomad_an_es,gnomad_ac_gs,gnomad_hom_gs,gnomad_af_gs,gnomad_an_gs,gnomad_ac,gnomad_af_popmax,gnomad_an,gnomad_af,clinvar_pathogenic,clinvar_sig,CADD_phred,phyloP20way_mammalian,phastCons20way_mammalian,Vest3_score,Revel_score,Gerp_score \
+vt rminfo -t CSQ,af_adj_exac_afr,af_adj_exac_amr,af_adj_exac_eas,af_adj_exac_fin,af_adj_exac_nfe,af_adj_exac_oth,af_adj_exac_sas,af_exac_all,ac_exac_all,an_exac_all,ac_adj_exac_afr,an_adj_exac_afr,ac_adj_exac_amr,an_adj_exac_amr,ac_adj_exac_eas,an_adj_exac_eas,ac_adj_exac_fin,an_adj_exac_fin,ac_adj_exac_nfe,an_adj_exac_nfe,ac_adj_exac_oth,an_adj_exac_oth,ac_adj_exac_sas,an_adj_exac_sas,common_pathogenic,max_aaf_all,num_exac_Het,num_exac_Hom,rs_ids,af_1kg_amr,af_1kg_eas,af_1kg_sas,af_1kg_afr,af_1kg_eur,af_1kg_all,fitcons,encode_consensus_gm12878,encode_consensus_h1hesc,encode_consensus_helas3,encode_consensus_hepg2,encode_consensus_huvec,encode_consensus_k562,dgv,hapmap1,hapmap2,gnomAD_AF,gnomAD_AFR_AF,gnomAD_AMR_AF,gnomAD_ASJ_AF,gnomAD_EAS_AF,gnomAD_FIN_AF,gnomAD_NFE_AF,gnomAD_OTH_AF,gnomad_ac_es,gnomad_hom_es,gnomad_af_es,gnomad_an_es,gnomad_ac_gs,gnomad_hom_gs,gnomad_af_gs,gnomad_an_gs,gnomad_ac,gnomad_af_popmax,gnomad_an,gnomad_af,clinvar_pathogenic,clinvar_sig,CADD_phred,phyloP20way_mammalian,phastCons20way_mammalian,Vest3_score,Revel_score,Gerp_score,vcfanno_gnomad_ac_es,vcfanno_gnomad_hom_es,vcfanno_gnomad_af_es,vcfanno_gnomad_an_es,vcfanno_gnomad_ac_gs,vcfanno_gnomad_hom_gs,vcfanno_gnomad_af_gs,vcfanno_gnomad_an_gs,vcfanno_gnomad_ac,vcfanno_gnomad_af_popmax,vcfanno_gnomad_an,vcfanno_gnomad_af \
 	     $1 -o $bname.no_anno.vcf.gz
 tabix $bname.no_anno.vcf.gz

cre.gemini.variant_impacts.vcf2db.sh

@@ -65,7 +65,7 @@ then
 	i.spliceregion"
 fi
 
-sQuery=$sQuery" from variants v,variant_impacts i where "$severity_filter"v.gnomad_af_popmax <= "$max_af" and \
+sQuery=$sQuery" from variants v,variant_impacts i where "$severity_filter"v.vcfanno_gnomad_af_popmax <= "$max_af" and \
 		v.variant_id=i.variant_id and \
 		(v.dp>="$depth_threshold" or v.dp='' or v.dp is null)"
 

cre.gemini2txt.vcf2db.sh

@@ -45,10 +45,10 @@ sQuery="select \
         exon as Exon,\
         domains as Protein_domains,\
         rs_ids as rsIDs,\
-        gnomad_af as Gnomad_af,\
-        gnomad_af_popmax as Gnomad_af_popmax,\
-        gnomad_ac as Gnomad_ac,\
-        gnomad_hom as Gnomad_hom,\
+        vcfanno_gnomad_af as Gnomad_af,\
+        vcfanno_gnomad_af_popmax as Gnomad_af_popmax,\
+        vcfanno_gnomad_ac as Gnomad_ac,\
+        vcfanno_gnomad_hom as Gnomad_hom,\
         sift_score as Sift_score,\
         polyphen_score as Polyphen_score,\
         cadd_phred as Cadd_score,\
@@ -90,7 +90,7 @@ sQuery=$sQuery"hgvsc as Nucleotide_change_ensembl,\
         old_multiallelic as Old_multiallelic
 		from variants \
         where \
-	        (dp >= "$depth_threshold" or dp = '' or dp is null) "$severity_filter" and gnomad_af_popmax <= "$max_af
+	        (dp >= "$depth_threshold" or dp = '' or dp is null) "$severity_filter" and vcfanno_gnomad_af_popmax <= "$max_af
 
 s_gt_filter=''
 if [ -n "$denovo" ] && [ "$denovo" == 1 ]

cre.vcf2cre.sh

@@ -25,7 +25,7 @@
 ##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
 # gunzip -c 331606_S1.flt.nochr.vcf.gz | grep -v "^#"  | grep PASS | sed s/":DPI:"/":DP:"awk -F ':' '{print $0"\tDP="$9}' | awk -F "\t" '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$11";"$8"\t"$9"\t"$10}' >> 331606.vcf
 
-. /hpf/largeprojects/ccmbio/naumenko/tools/bcbio_1.1.5/.test_profile
+. /hpf/largeprojects/ccmbio/naumenko/tools/bcbio_1.1.5/.profile115
 
 bname=`basename $original_vcf .vcf.gz`
 

cre.vcfanno.conf

@@ -1,43 +1,44 @@
+# using prefix vcfanno to discriminate data from vcfanno and vep
 [[annotation]]
 file="variation/gnomad_exome.vcf.gz"
 fields=["AC","nhomalt","AF_popmax","AN"]
-names=["gnomad_ac_es","gnomad_hom_es","gnomad_af_es","gnomad_an_es"]
+names=["vcfanno_gnomad_ac_es","vcfanno_gnomad_hom_es","vcfanno_gnomad_af_es","vcfanno_gnomad_an_es"]
 ops=["first","first","first","first"]
 
 [[annotation]]
 file="variation/gnomad_genome.vcf.gz"
 fields=["AC", "nhomalt","AF_popmax","AN"]
-names=["gnomad_ac_gs", "gnomad_hom_gs","gnomad_af_gs","gnomad_an_gs"]
+names=["vcfanno_gnomad_ac_gs", "vcfanno_gnomad_hom_gs","vcfanno_gnomad_af_gs","vcfanno_gnomad_an_gs"]
 ops=["self","self","self","self"]
 
 [[postannotation]]
-fields=["gnomad_ac_es","gnomad_ac_gs"]
+fields=["vcfanno_gnomad_ac_es","vcfanno_gnomad_ac_gs"]
 op="sum"
-name="gnomad_ac"
+name="vcfanno_gnomad_ac"
 type="Integer"
 
 [[postannotation]]
-fields=["gnomad_hom_es","gnomad_hom_gs"]
+fields=["vcfanno_gnomad_hom_es","vcfanno_gnomad_hom_gs"]
 op="sum"
-name="gnomad_hom"
+name="vcfanno_gnomad_hom"
 type="Integer"
 
 [[postannotation]]
-fields=["gnomad_af_es","gnomad_af_gs"]
+fields=["vcfanno_gnomad_af_es","vcfanno_gnomad_af_gs"]
 op="max"
-name="gnomad_af_popmax"
+name="vcfanno_gnomad_af_popmax"
 type="Float"
 
 [[postannotation]]
-fields=["gnomad_an_es","gnomad_an_gs"]
+fields=["vcfanno_gnomad_an_es","vcfanno_gnomad_an_gs"]
 op="sum"
-name="gnomad_an"
+name="vcfanno_gnomad_an"
 type="Integer"
 
 [[postannotation]]
-fields=["gnomad_ac","gnomad_an"]
+fields=["vcfanno_gnomad_ac","vcfanno_gnomad_an"]
 op="div2"
-name="gnomad_af"
+name="vcfanno_gnomad_af"
 type="Float"
 
 [[annotation]]