chore: develop to master

config/config.yaml

@@ -5,7 +5,7 @@ units: "units.tsv"
 #hydra_local_path: "PATH_TO_REPO"
 
 output: "config/output_files.yaml"
-default_container: "docker://hydragenetics/common:1.8.1"
+default_container: "docker://hydragenetics/common:1.10.2"
 
 trimmer_software: "fastp_pe"
 
@@ -73,7 +73,7 @@ cnvkit_scatter:
 
 cnv_html_report:
   show_table: true
-  template_dir: config/reports/cnv_report_template
+  show_cytobands: true
 
 cnv_tsv_report:
   amp_cn_limit: 6.0
@@ -110,6 +110,7 @@ fgbio_group_reads_by_umi:
 
 filter_vcf:
   snv_soft_filter: "config/filters/config_soft_filter_uppsala_vep105.yaml"
+  snv_soft_filter_umi: "config/filters/config_soft_filter_umi_vep105.yaml"
   snv_hard_filter: "config/filters/config_hard_filter_uppsala_vep105.yaml"
   snv_hard_filter_umi: "config/filters/config_hard_filter_umi_vep105.yaml"
   snv_hard_filter_purecn: "config/filters/config_hard_filter_purecn.yaml"
@@ -126,7 +127,7 @@ fuseq_wes:
 
 fusioncatcher:
   container: "docker://hydragenetics/fusioncatcher:1.33"
-  extra: "--visualization-sam"
+  extra: ""
 
 gatk_calculate_contamination:
   container: "docker://hydragenetics/gatk4:4.1.9.0"
@@ -361,6 +362,10 @@ vep:
   mode: --offline --cache --refseq
   extra: " --assembly GRCh37 --check_existing --pick --sift b --polyphen b --ccds --uniprot --hgvs --symbol --numbers --domains --regulatory --canonical --protein --biotype --uniprot --tsl --appris --gene_phenotype --af --af_1kg --af_gnomad --max_af --pubmed --variant_class "
 
+vep_wo_pick:
+  mode: --offline --cache --refseq
+  extra: " --assembly GRCh37 --check_existing --sift b --polyphen b --ccds --uniprot --hgvs --symbol --numbers --domains --regulatory --canonical --protein --biotype --uniprot --tsl --appris --gene_phenotype --af --af_1kg --af_gnomad --max_af --pubmed --variant_class "
+
 vt_decompose:
   container: "docker://hydragenetics/vt:2015.11.10"
 

config/filters/config_hard_filter_germline_vep105.yaml

@@ -4,8 +4,8 @@ filters:
     expression: "(VEP:gnomAD_AF < 0.001)"
     soft_filter: "False"
   ad:
-    description: "Hard filter variants with few observations (AD lower than 50)"
-    expression: "(FORMAT:AD:1 < 50 or FORMAT:AD:0 < 50)"
+    description: "Hard filter variants with few observations (AD lower than 20)"
+    expression: "(FORMAT:AD:1 < 20 or FORMAT:AD:0 < 20)"
     soft_filter: "False"
   snp_type:
     description: "Hard filter variants that are not SNVs"

config/filters/config_hard_filter_germline_vep107.yaml

@@ -4,8 +4,8 @@ filters:
     expression: "(VEP:gnomADe_AF < 0.001)"
     soft_filter: "False"
   ad:
-    description: "Hard filter variants with few observations (AD lower than 50)"
-    expression: "(FORMAT:AD:1 < 50 or FORMAT:AD:0 < 50)"
+    description: "Hard filter variants with few observations (AD lower than 20)"
+    expression: "(FORMAT:AD:1 < 20 or FORMAT:AD:0 < 20)"
     soft_filter: "False"
   snp_type:
     description: "Hard filter variants that are not SNVs"

config/filters/config_hard_filter_umi_vep105.yaml

@@ -5,45 +5,69 @@ filters:
     soft_filter: "False"
   artifacts:
     description: "Hard filter variants found in more than 3 normal samples"
-    expression: "((INFO:Artifact:0 > 3 and INFO:ArtifactNrSD:0 < 10) or (INFO:Artifact:1 > 3 and INFO:ArtifactNrSD:1 < 10))"
-    soft_filter: "False"
-  background:
-    description: "Hard filter position where background distribution overlaps variant (lower than 4 SD from median)"
-    expression: "(INFO:PositionNrSD < 0 and !exist[1-hotspot, INFO:Hotspot])"
+    expression: "((INFO:Artifact:0 > 2 and INFO:ArtifactNrSD:0 < 10) or (INFO:Artifact:0 > 2 and INFO:ArtifactNrSD:1 < 10))"
     soft_filter: "False"
   germline:
     description: "Hard filter germline"
     expression: "(VEP:gnomAD_AF > 0.005)"
     soft_filter: "False"
-  af_ad_snv1:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.003 and exist[SNV, VEP:VARIANT_CLASS])"
+  af_snv:
+    description: "Hard filter SNV variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.006 or FORMAT:AF:0 > 0.994) and exist[SNV, VEP:VARIANT_CLASS])"
+    soft_filter: "False"
+  ad_snv:
+    description: "Hard filter SNV variants with low ad"
+    expression: "((FORMAT:AD:1 < 15 or FORMAT:AD:0 < 15) and exist[SNV, VEP:VARIANT_CLASS])"
+    soft_filter: "False"
+  af_insertion:
+    description: "Hard filter Insertion variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.006 or FORMAT:AF:0 > 0.994) and exist[insertion, VEP:VARIANT_CLASS])"
+    soft_filter: "False"
+  ad_insertion:
+    description: "Hard filter Insertion variants with low ad"
+    expression: "((FORMAT:AD:1 < 15 or FORMAT:AD:0 < 15) and exist[insertion, VEP:VARIANT_CLASS])"
+    soft_filter: "False"
+  af_deletion:
+    description: "Hard filter Deletion variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.009 or FORMAT:AF:0 > 0.991) and exist[deletion, VEP:VARIANT_CLASS])"
+    soft_filter: "False"
+  ad_deletion:
+    description: "Hard filter Deletion variants with low ad"
+    expression: "((FORMAT:AD:1 < 20 or FORMAT:AD:0 < 20) and exist[deletion, VEP:VARIANT_CLASS])"
+    soft_filter: "False"
+  af_complex:
+    description: "Hard filter complex variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.009 or FORMAT:AF:0 > 0.991) and exist[indel, VEP:VARIANT_CLASS])"
+    soft_filter: "False"
+  ad_complex:
+    description: "Hard filter complex variants with low ad"
+    expression: "((FORMAT:AD:1 < 20 or FORMAT:AD:0 < 20) and exist[indel, VEP:VARIANT_CLASS])"
+    soft_filter: "False"
+  af_substitution:
+    description: "Hard filter substitution variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.006 or FORMAT:AF:0 > 0.994) and exist[substitution, VEP:VARIANT_CLASS])"
     soft_filter: "False"
-  af_ad_snv2:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.004 and FORMAT:AD:1 < 11 and exist[SNV, VEP:VARIANT_CLASS])"
+  ad_substitution:
+    description: "Hard filter substitution variants with low ad"
+    expression: "((FORMAT:AD:1 < 15 or FORMAT:AD:0 < 15) and exist[substitution, VEP:VARIANT_CLASS])"
     soft_filter: "False"
-  af_ad_snv3:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.005 and FORMAT:AD:1 < 9 and exist[SNV, VEP:VARIANT_CLASS])"
+  ald:
+    description: "Hard filter variants with skewed distribution between strands"
+    expression: "(FORMAT:ALD:0 < 3 or FORMAT:ALD:1 < 3)"
     soft_filter: "False"
-  af_ad_snv4:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.006 and FORMAT:AD:1 < 7 and exist[SNV, VEP:VARIANT_CLASS])"
+  sbf:
+    description: "Hard filter variants with skewed distribution between strands"
+    expression: "INFO:SBF < 0.01"
     soft_filter: "False"
-  af_ad_snv5:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AD:1 < 5 and exist[SNV, VEP:VARIANT_CLASS])"
+  pmean:
+    description: "Hard filter variants found only in start of reads"
+    expression: "INFO:PMEAN < 15.0"
     soft_filter: "False"
-  af_ad_indel1:
-    description: "Hard filter INDEL variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.005 and !exist[SNV, VEP:VARIANT_CLASS])"
+  callers:
+    description: "Hard filter variants only called by mutect2"
+    expression: "INFO:CALLERS:0 = gatk_mutect2"
     soft_filter: "False"
-  af_ad_indel2:
-    description: "Hard filter INDEL variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.008 and FORMAT:AD:1 < 14 and !exist[SNV, VEP:VARIANT_CLASS])"
+  qual:
+    description: "Hard filter variants with low calling quality"
+    expression: "INFO:QUAL:0 < 43.0"
     soft_filter: "False"
-  af_ad_indel3:
-    description: "Hard filter INDEL variants with low vaf and low ad"
-    expression: "(FORMAT:AD:1 < 5 and !exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter: "False"

config/filters/config_soft_filter_umi_vep105.yaml

@@ -6,55 +6,86 @@ filters:
     soft_filter: "True"
   artifacts:
     description: "Hard filter variants found in more than 3 normal samples"
-    expression: "((INFO:Artifact:0 > 3 and INFO:ArtifactNrSD:0 < 10) or (INFO:Artifact:1 > 3 and INFO:ArtifactNrSD:1 < 10))"
-    soft_filter_flag: "Artifact_gt_3"
-    soft_filter: "True"
-  background:
-    description: "Hard filter position where background distribution overlaps variant (lower than 4 SD from median)"
-    expression: "(INFO:PositionNrSD < 0 and !exist[1-hotspot, INFO:Hotspot])"
+    expression: "((INFO:Artifact:0 > 2 and INFO:ArtifactNrSD:0 < 10) or (INFO:Artifact:0 > 2 and INFO:ArtifactNrSD:1 < 10))"
+    soft_filter_flag: "Artifact_gt_2"
     soft_filter: "True"
   germline:
     description: "Hard filter germline"
     expression: "(VEP:gnomAD_AF > 0.005)"
     soft_filter_flag: "germline"
     soft_filter: "True"
-  af_ad_snv1:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.003 and exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter_flag: "af_ad_snv1"
-    soft_filter: "True"
-  af_ad_snv2:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.004 and FORMAT:AD:1 < 11 and exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter_flag: "af_ad_snv2"
-    soft_filter: "True"
-  af_ad_snv3:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.005 and FORMAT:AD:1 < 9 and exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter_flag: "af_ad_snv3"
-    soft_filter: "True"
-  af_ad_snv4:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.006 and FORMAT:AD:1 < 7 and exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter_flag: "af_ad_snv4"
-    soft_filter: "True"
-  af_ad_snv5:
-    description: "Hard filter SNV variants with low vaf and low ad"
-    expression: "(FORMAT:AD:1 < 5 and exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter_flag: "af_ad_snv5"
-    soft_filter: "True"
-  af_ad_indel1:
-    description: "Hard filter INDEL variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.005 and !exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter_flag: "af_ad_indel1"
-    soft_filter: "True"
-  af_ad_indel2:
-    description: "Hard filter INDEL variants with low vaf and low ad"
-    expression: "(FORMAT:AF:0 < 0.008 and FORMAT:AD:1 < 14 and !exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter_flag: "af_ad_indel2"
-    soft_filter: "True"
-  af_ad_indel3:
-    description: "Hard filter INDEL variants with low vaf and low ad"
-    expression: "(FORMAT:AD:1 < 5 and !exist[SNV, VEP:VARIANT_CLASS])"
-    soft_filter_flag: "af_ad_indel3"
-    soft_filter: "True"
+  af_snv:
+    description: "Hard filter SNV variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.006 or FORMAT:AF:0 > 0.994) and exist[SNV, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "af_snv"
+    soft_filter: "True"
+  ad_snv:
+    description: "Hard filter SNV variants with low ad"
+    expression: "((FORMAT:AD:1 < 15 or FORMAT:AD:0 < 15) and exist[SNV, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "ad_snv"
+    soft_filter: "True"
+  af_insertion:
+    description: "Hard filter Insertion variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.006 or FORMAT:AF:0 > 0.994) and exist[insertion, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "af_insertion"
+    soft_filter: "True"
+  ad_insertion:
+    description: "Hard filter Insertion variants with low ad"
+    expression: "((FORMAT:AD:1 < 15 or FORMAT:AD:0 < 15) and exist[insertion, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "ad_insertion"
+    soft_filter: "True"
+  af_deletion:
+    description: "Hard filter Deletion variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.009 or FORMAT:AF:0 > 0.991) and exist[deletion, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "af_deletion"
+    soft_filter: "True"
+  ad_deletion:
+    description: "Hard filter Deletion variants with low ad"
+    expression: "((FORMAT:AD:1 < 20 or FORMAT:AD:0 < 20) and exist[deletion, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "ad_deletion"
+    soft_filter: "True"
+  af_complex:
+    description: "Hard filter complex variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.009 or FORMAT:AF:0 > 0.991) and exist[indel, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "af_complex"
+    soft_filter: "True"
+  ad_complex:
+    description: "Hard filter complex variants with low ad"
+    expression: "((FORMAT:AD:1 < 20 or FORMAT:AD:0 < 20) and exist[indel, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "ad_complex"
+    soft_filter: "True"
+  af_substitution:
+    description: "Hard filter substitution variants with low vaf"
+    expression: "((FORMAT:AF:0 < 0.006 or FORMAT:AF:0 > 0.994) and exist[substitution, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "af_substitution"
+    soft_filter: "True"
+  ad_substitution:
+    description: "Hard filter substitution variants with low ad"
+    expression: "((FORMAT:AD:1 < 15 or FORMAT:AD:0 < 15) and exist[substitution, VEP:VARIANT_CLASS])"
+    soft_filter_flag: "ad_substitution"
+    soft_filter: "True"
+  ald:
+    description: "Hard filter variants with skewed distribution between strands"
+    expression: "(FORMAT:ALD:0 < 3 or FORMAT:ALD:1 < 3)"
+    soft_filter_flag: "ald_skewed"
+    soft_filter: "True"
+  sbf:
+    description: "Hard filter variants with skewed distribution between strands"
+    expression: "INFO:SBF < 0.01"
+    soft_filter_flag: "sbf_strand_bias"
+    soft_filter: "True"
+  pmean:
+    description: "Hard filter variants found only in start of reads"
+    expression: "INFO:PMEAN < 15.0"
+    soft_filter_flag: "start_of_read"
+    soft_filter: "True"
+  callers:
+    description: "Hard filter variants only called by mutect2"
+    expression: "INFO:CALLERS:0 = gatk_mutect2"
+    soft_filter_flag: "only_mutect2"
+    soft_filter: "True"
+  qual:
+    description: "Hard filter variants with low calling quality"
+    expression: "INFO:QUAL:0 < 43.0"
+    soft_filter_flag: "calling_qual"
+    soft_filter: "True"