Add VEP + LOFTEE (+ GERP + HGNC) to VAT [VS-1520] [VS-1765] [VS-1767]

.dockstore.yml

@@ -240,6 +240,7 @@ workflows:
          branches:
              - master
              - ah_var_store
+             - vs_1520_loftee
          tags:
              - /.*/
    - name: GvsCreateVATFilesFromBigQuery
@@ -343,7 +344,7 @@ workflows:
          branches:
              - master
              - ah_var_store
-             - vs_1739_cmrg_learnings
+             - vs_1520_loftee
          tags:
              - /.*/
    - name: GvsIngestTieout

scripts/variantstore/scripts/variant_annotation_table/schema/variant_transcript_schema.json

@@ -431,6 +431,48 @@
     "type": "String",
     "mode": "Nullable"
   },
+  {
+    "description": "HGNC (HUGO Gene Nomenclature Committee) Symbol",
+    "name": "hgnc_symbol",
+    "type": "String",
+    "mode": "Nullable"
+  },
+  {
+    "description": "HGNC_ID (HUGO Gene Nomenclature Committee) Identifier",
+    "name": "hgnc_id",
+    "type": "Integer",
+    "mode": "Nullable"
+  },
+  {
+    "description": "LOFTEE Loss-of-function annotation (HC = High Confidence; LC = Low Confidence)",
+    "name": "LoF",
+    "type": "String",
+    "mode": "Nullable"
+  },
+  {
+    "description": "LOFTEE Reason for LoF not being HC",
+    "name": "LoF_filter",
+    "type": "String",
+    "mode": "Repeated"
+  },
+  {
+    "description": "LOFTEE Possible warning flags for LoF",
+    "name": "LoF_flags",
+    "type": "String",
+    "mode": "Repeated"
+  },
+  {
+    "description": "LOFTEE Info used for LoF annotation",
+    "name": "LoF_info",
+    "type": "String",
+    "mode": "Repeated"
+  },
+  {
+    "description": "GERP (Genomic Evolutionary Rate Profiling) Scores",
+    "name": "GERP",
+    "type": "Float",
+    "mode": "Repeated"
+  },
   {
     "description": "gnomAD: 'Total' frequency",
     "name": "gnomad_all_af",

scripts/variantstore/scripts/variant_annotation_table/schema/vat_schema.json

@@ -431,6 +431,48 @@
     "type": "String",
     "mode": "Nullable"
   },
+  {
+    "description": "HGNC (HUGO Gene Nomenclature Committee) Symbol",
+    "name": "hgnc_symbol",
+    "type": "String",
+    "mode": "Nullable"
+  },
+  {
+    "description": "HGNC_ID (HUGO Gene Nomenclature Committee) Identifier",
+    "name": "hgnc_id",
+    "type": "Integer",
+    "mode": "Nullable"
+  },
+  {
+    "description": "LOFTEE Loss-of-function annotation (HC = High Confidence; LC = Low Confidence)",
+    "name": "LoF",
+    "type": "String",
+    "mode": "Nullable"
+  },
+  {
+    "description": "LOFTEE Reason for LoF not being HC",
+    "name": "LoF_filter",
+    "type": "String",
+    "mode": "Repeated"
+  },
+  {
+    "description": "LOFTEE Possible warning flags for LoF",
+    "name": "LoF_flags",
+    "type": "String",
+    "mode": "Repeated"
+  },
+  {
+    "description": "LOFTEE Info used for LoF annotation",
+    "name": "LoF_info",
+    "type": "String",
+    "mode": "Repeated"
+  },
+  {
+    "description": "GERP (Genomic Evolutionary Rate Profiling) Scores",
+    "name": "GERP",
+    "type": "Float",
+    "mode": "Repeated"
+  },
   {
     "description": "gnomAD: 'Total' frequency",
     "name": "gnomad_all_af",

scripts/variantstore/scripts/variant_annotation_table/schema/vep_loftee_115_cooked.json

@@ -0,0 +1,137 @@
+[
+  {
+    "name": "vid",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Uploaded_variation",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Location",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Allele",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Gene",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Feature",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Feature_type",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Consequence",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "cDNA_position",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "CDS_position",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Protein_position",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Amino_acids",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Codons",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Existing_variation",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "IMPACT",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "DISTANCE",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "STRAND",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "FLAGS",
+    "type": "STRING",
+    "mode": "REPEATED"
+  },
+  {
+    "name": "HGNC_SYMBOL",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "SYMBOL_SOURCE",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "HGNC_ID",
+    "type": "INTEGER",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "SOURCE",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "LoF",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "LoF_filter",
+    "type": "STRING",
+    "mode": "REPEATED"
+  },
+  {
+    "name": "LoF_flags",
+    "type": "STRING",
+    "mode": "REPEATED"
+  },
+  {
+    "name": "LoF_info",
+    "type": "STRING",
+    "mode": "REPEATED"
+  },
+  {
+    "name": "GERP",
+    "type": "FLOAT",
+    "mode": "REPEATED"
+  }
+]

scripts/variantstore/scripts/variant_annotation_table/schema/vep_loftee_115_raw.json

@@ -0,0 +1,132 @@
+[
+  {
+    "name": "Uploaded_variation",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Location",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Allele",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Gene",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Feature",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Feature_type",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Consequence",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "cDNA_position",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "CDS_position",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Protein_position",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Amino_acids",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Codons",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "Existing_variation",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "IMPACT",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "DISTANCE",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "STRAND",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "FLAGS",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "SYMBOL",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "SYMBOL_SOURCE",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "HGNC_ID",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "SOURCE",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "LoF",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "LoF_filter",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "LoF_flags",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "LoF_info",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  },
+  {
+    "name": "GERP",
+    "type": "STRING",
+    "mode": "NULLABLE"
+  }
+]