update CAF to support joint FAF

ga4gh · Oct 27, 2023 · 0ecbf46 · 0ecbf46
1 parent 4050031
commit 0ecbf46
Show file tree

Hide file tree

Showing 2 changed files with 92 additions and 45 deletions.
diff --git a/schema/cohortAlleleFreq.json b/schema/cohortAlleleFreq.json
@@ -3,6 +3,29 @@
    "title": "Cohort Allele Frequency",
    "type": "object",
    "definitions": {
+      "GrpMaxFAF95": {
+         "type": "object",
+         "properties": {
+            "frequency": {
+               "type": "number"
+            },
+            "confidenceInterval": {
+               "type": "number",
+               "const": 0.95,
+               "default": 0.95
+            },
+            "groupId": {
+               "type": "string",
+               "description": "The genetic ancestry group from which the max frequency was calculated."
+            }
+         },
+         "required": [
+            "frequency",
+            "confidenceInterval",
+            "groupId"
+         ],
+         "additionalProperties": false
+      },
       "Allele": {
          "description": "The state of a molecule at a Location.",
          "type": "object",
@@ -318,27 +341,19 @@
       "ancillaryResults": {
          "type": "object",
          "properties": {
-            "popMaxFAF95": {
-               "type": "object",
-               "properties": {
-                  "frequency": {
-                     "type": "number"
-                  },
-                  "confidenceInterval": {
-                     "type": "number",
-                     "const": 0.95,
-                     "default": 0.95
+            "grpMaxFAF95": {
+               "$ref": "#/$defs/GrpMaxFAF95"
+            },
+            "jointGrpMaxFAF95": {
+               "description": "The Group Max Filtering Allele Frequency (95% confidence interval) calculated jointly from genome and exome data.",
+               "oneOf": [
+                  {
+                     "$ref": "#/$defs/GrpMaxFAF95"
                   },
-                  "popFreqId": {
-                     "type": "string"
+                  {
+                     "type": null
                   }
-               },
-               "required": [
-                  "frequency",
-                  "confidenceInterval",
-                  "popFreqId"
-               ],
-               "additionalProperties": false
+               ]
             },
             "homozygotes": {
                "type": "integer"
@@ -350,22 +365,43 @@
          "additionalProperties": false
       },
       "qualityMeasures": {
-         "meanDepth": {
-            "type": "number"
-         },
-         "qcFilters": {
-            "type": "array",
-            "items": {
-               "type": "string"
+         "type": "object",
+         "properties": {
+            "meanDepth": {
+               "type": "number"
+            },
+            "qcFilters": {
+               "type": "array",
+               "items": {
+                  "type": "string"
+               }
+            },
+            "monoallelic": {
+               "description": "All samples are homozygous alternate for the variant.",
+               "type": "boolean"
+            },
+            "lowComplexityRegion": {
+               "description": "This flag indicates the variant is found in a low complexity region. These regions were identified  with the symmetric DUST algorithm at a score threshold of 30.",
+               "type": "boolean"
+            },
+            "lowConfidenceLossOfFunctionError": {
+               "description": "Low confidence in predicted Loss of Function (pLoF), where variant is determined by LOFTEE  to be unlikely loss of function for a transcript.",
+               "type": "boolean"
+            },
+            "lossOfFunctionWarning": {
+               "description": "A warning provided by LOFTEE to use caution when interpreting the transcript or variant.",
+               "type": "boolean"
+            },
+            "noncodingTranscriptError": {
+               "description": "Marked in a putative loss of function category by VEP (essential splice, stop-gained, or frameshift)  but appears on a non-protein-coding transcript.",
+               "type": "boolean"
+            },
+            "heterozygousSkewedAlleleCount": {
+               "description": "The count of individuals called as heterozygous for this variant with a skewed allele balance, indicating some of these individuals may be miscalled homozygous alternative allele.",
+               "type": "integer"
             }
          },
-         "lowComplexityRegion": {
-            "type": "boolean"
-         },
-         "heterozygousSkewedAlleleCount": {
-            "description": "The count of individuals called as heterozygous for this variant with a skewed allele balance, indicating some of these individuals may be miscalled homozygous alternative allele.",
-            "type": "integer"
-         }
+         "additionalProperties": false
       },
       "subcohortFrequency": {
          "type": "array",

diff --git a/schema/cohortAlleleFreq.yaml b/schema/cohortAlleleFreq.yaml
@@ -2,6 +2,21 @@ $schema: http://json-schema.org/draft-07/schema
 title: Cohort Allele Frequency
 type: object
 definitions:
+  GrpMaxFAF95:
+    type: object
+    properties:
+      frequency:
+        type: number
+      confidenceInterval:
+        type: number
+        const: 0.95
+        default: 0.95
+      groupId:
+        type: string
+        description: >-
+          The genetic ancestry group from which the max frequency was calculated.
+    required: [ frequency, confidenceInterval, groupId ]
+    additionalProperties: false
   Allele:
     description: The state of a molecule at a Location.
     type: object
@@ -240,18 +255,14 @@ properties:
     type: object
     properties:
       grpMaxFAF95:
-        type: object
-        properties:
-          frequency:
-            type: number
-          confidenceInterval:
-            type: number
-            const: 0.95
-            default: 0.95
-          popFreqId:
-            type: string
-        required: [frequency, confidenceInterval, popFreqId]
-        additionalProperties: false
+        $ref: '#/$defs/GrpMaxFAF95'
+      jointGrpMaxFAF95:
+        description: >-
+          The Group Max Filtering Allele Frequency (95% confidence interval) calculated jointly
+          from genome and exome data.
+        oneOf:
+          - $ref: '#/$defs/GrpMaxFAF95'
+          - type: null
       homozygotes:
         type: integer
       hemizygotes: