ga4ghDigest key checks added

ga4gh · Sep 10, 2023 · c4d9d36 · c4d9d36
1 parent 706939d
commit c4d9d36
Show file tree

Hide file tree

Showing 8 changed files with 118 additions and 79 deletions.
diff --git a/.requirements.txt b/.requirements.txt
@@ -3,6 +3,6 @@ python-jsonschema-objects>=0.4.0
 jsonschema==3.2.0
 ipython
 pyyaml
-ga4gh.gks.metaschema==0.2.0rc6
+ga4gh.gks.metaschema==0.2.1
 sphinx ~= 4.5
 sphinx-rtd-theme ~= 1.2
diff --git a/schema/defs/vrs/SequenceReference.rst b/schema/defs/vrs/SequenceReference.rst
@@ -43,7 +43,7 @@ Some SequenceReference attributes are inherited from :ref:`ValueObject`.
        *  - refgetAccession
           - string
           - 1..1
-          - A `GA4GH RefGet <http://samtools.github.io/hts-specs/refget.html>` identifier for the referenced sequence, using the sha512t24u digest.
+          - A `GA4GH RefGet <http://samtools.github.io/hts-specs/refget.html>` identifier for the referenced sequence,  using the sha512t24u digest.
        *  - residueAlphabet
           - string
           - 0..1

diff --git a/schema/merged.json b/schema/merged.json
@@ -248,7 +248,7 @@
          "ga4ghDigest": {
             "keys": [
                "copies",
-               "subject",
+               "location",
                "type"
             ],
             "prefix": "CN"
@@ -328,7 +328,7 @@
          "ga4ghDigest": {
             "keys": [
                "copyChange",
-               "subject",
+               "location",
                "type"
             ],
             "prefix": "CX"
@@ -490,7 +490,7 @@
          "ga4ghDigest": {
             "keys": [
                "end",
-               "sequence",
+               "sequenceReference",
                "start",
                "type"
             ],
@@ -607,7 +607,7 @@
                "const": "SequenceReference"
             },
             "refgetAccession": {
-               "description": "A `GA4GH RefGet <http://samtools.github.io/hts-specs/refget.html>` identifier for the referenced sequence, using the sha512t24u digest.",
+               "description": "A `GA4GH RefGet <http://samtools.github.io/hts-specs/refget.html>` identifier for the referenced sequence,  using the sha512t24u digest.",
                "type": "string",
                "pattern": "SQ.[0-9A-Za-z_\\-]{32}"
             },
@@ -642,6 +642,13 @@
       },
       "ReferenceLengthExpression": {
          "maturity": "Alpha",
+         "ga4ghDigest": {
+            "keys": [
+               "length",
+               "repeatSubunitLength",
+               "type"
+            ]
+         },
          "description": "An expression of a length of a sequence from a repeating reference.",
          "type": "object",
          "properties": {
@@ -704,6 +711,12 @@
       },
       "LiteralSequenceExpression": {
          "maturity": "Alpha",
+         "ga4ghDigest": {
+            "keys": [
+               "sequence",
+               "type"
+            ]
+         },
          "description": "An explicit expression of a Sequence.",
          "type": "object",
          "properties": {
@@ -750,6 +763,12 @@
       },
       "GenotypeMember": {
          "privateTo": "Genotype",
+         "ga4ghDigest": {
+            "keys": [
+               "count",
+               "variation"
+            ]
+         },
          "description": "A class for expressing the count of a specific MolecularVariation present _in-trans_ at a genomic locus represented by a Genotype.",
          "type": "object",
          "properties": {

diff --git a/schema/merged.yaml b/schema/merged.yaml
@@ -181,7 +181,7 @@ $defs:
     ga4ghDigest:
       keys:
       - copies
-      - subject
+      - location
       - type
       prefix: CN
     type: object
@@ -240,7 +240,7 @@ $defs:
     ga4ghDigest:
       keys:
       - copyChange
-      - subject
+      - location
       - type
       prefix: CX
     type: object
@@ -374,7 +374,7 @@ $defs:
     ga4ghDigest:
       keys:
       - end
-      - sequence
+      - sequenceReference
       - start
       - type
       prefix: SL
@@ -466,7 +466,7 @@ $defs:
         const: SequenceReference
       refgetAccession:
         description: A `GA4GH RefGet <http://samtools.github.io/hts-specs/refget.html>`
-          identifier for the referenced sequence, using the sha512t24u digest.
+          identifier for the referenced sequence,  using the sha512t24u digest.
         type: string
         pattern: SQ.[0-9A-Za-z_\-]{32}
       residueAlphabet:
@@ -490,6 +490,11 @@ $defs:
       propertyName: type
   ReferenceLengthExpression:
     maturity: Alpha
+    ga4ghDigest:
+      keys:
+      - length
+      - repeatSubunitLength
+      - type
     description: An expression of a length of a sequence from a repeating reference.
     type: object
     properties:
@@ -538,6 +543,10 @@ $defs:
     additionalProperties: false
   LiteralSequenceExpression:
     maturity: Alpha
+    ga4ghDigest:
+      keys:
+      - sequence
+      - type
     description: An explicit expression of a Sequence.
     type: object
     properties:
@@ -577,6 +586,10 @@ $defs:
     additionalProperties: false
   GenotypeMember:
     privateTo: Genotype
+    ga4ghDigest:
+      keys:
+      - count
+      - variation
     description: A class for expressing the count of a specific MolecularVariation
       present _in-trans_ at a genomic locus represented by a Genotype.
     type: object

diff --git a/schema/vrs-source.yaml b/schema/vrs-source.yaml
@@ -53,9 +53,6 @@ $defs:
     heritableRequired:
       - type
 
-  # TODO: Draft recomposition of Allele as "AlleleMember" plus seq requirement
-  # TODO: Explore "typed entity"
-
   Variation:
     inherits: Ga4ghIdentifiableObject
     description: >-
@@ -186,61 +183,13 @@ $defs:
           into an `Allele` when computing GA4GH identifiers.
     required: [ "members" ]
 
-  # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
-  # UtilityVariation
-
-#  Text:
-#    ga4ghPrefix: VT
-#    inherits: UtilityVariation
-#    description: >-
-#      A free-text definition of variation.
-#    type: object
-#    properties:
-#      type:
-#        type: string
-#        const: "Text"
-#        default: "Text"
-#        description: MUST be "Text"
-#      definition:
-#        type: string
-#        description: >-
-#          A textual representation of variation not representable by
-#          other subclasses of Variation.
-#    required: [ "definition" ]
-#
-#  VariationSet:
-#    ga4ghPrefix: VS
-#    inherits: UtilityVariation
-#    description: >-
-#      An unconstrained set of Variation members.
-#    type: object
-#    properties:
-#      type:
-#        type: string
-#        const: "VariationSet"
-#        default: "VariationSet"
-#        description: MUST be "VariationSet"
-#      members:
-#        type: array
-#        ordered: false
-#        uniqueItems: true
-#        items:
-#          oneOf:
-#            - $refCurie: gks.core:IRI
-#            - $ref: "#/$defs/Variation"
-#        description: >-
-#          List of Variation objects or identifiers. Attribute is
-#          required, but MAY be empty.
-#    required: [ "members" ]
-
-
   # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
   # SystemicVariation
 
   CopyNumber:
     ga4ghDigest:
       keys:
-        - subject
+        - location
     inherits: SystemicVariation
     description: >-
       A measure of the copies of a :ref:`Location` within a system (e.g. genome, cell, etc.)
@@ -299,7 +248,8 @@ $defs:
           MUST be "CopyNumberChange"
       copyChange:
         type: string
-        enum: [ "efo:0030069", "efo:0020073", "efo:0030068", "efo:0030067", "efo:0030064", "efo:0030070", "efo:0030071", "efo:0030072" ]
+        enum: [ "efo:0030069", "efo:0020073", "efo:0030068", "efo:0030067", "efo:0030064", "efo:0030070",
+                "efo:0030071", "efo:0030072" ]
         description: >-
           MUST be one of "efo:0030069" (complete genomic loss), "efo:0020073" (high-level loss),
           "efo:0030068" (low-level loss), "efo:0030067" (loss), "efo:0030064" (regional base ploidy),
@@ -402,7 +352,7 @@ $defs:
       keys:
         - start
         - end
-        - sequence
+        - sequenceReference
       prefix: SL
     inherits: Location
     description: >-
@@ -445,15 +395,18 @@ $defs:
     inherits: ValueObject
     ga4ghDigest:
       assigned: true # This special property indicates that the `digest` field follows an alternate convention
-                     # and is expected to have the value assigned following that convention.
+                     # and is expected to have the value assigned following that convention. For SequenceReference,
+                     # it is expected the digest will be the refget accession value without the `SQ.` prefix.
     type: object
     description: A sequence of nucleic or amino acid character codes.
     properties:
       type:
         type: string
         const: SequenceReference
       refgetAccession:
-        description: A `GA4GH RefGet <http://samtools.github.io/hts-specs/refget.html>` identifier for the referenced sequence, using the sha512t24u digest.
+        description: >-
+          A `GA4GH RefGet <http://samtools.github.io/hts-specs/refget.html>` identifier for the referenced sequence, 
+          using the sha512t24u digest.
         type: string
         pattern: 'SQ.[0-9A-Za-z_\-]{32}'
       residueAlphabet:
@@ -468,7 +421,6 @@ $defs:
       - refgetAccession
       - type
 
-      #TODO: add VRSATILE
       #TODO: implementation guidance: digest property is RefGet TRUNC512
 
   # =============================================================================
@@ -481,6 +433,9 @@ $defs:
 
   SequenceExpression:
     inherits: ValueObject
+    ga4ghDigest:
+      keys:
+        - type
     description: >-
       An expression describing a :ref:`Sequence`.
     oneOf:
@@ -502,6 +457,10 @@ $defs:
   ReferenceLengthExpression:
     maturity: Alpha
     inherits: SequenceExpression
+    ga4ghDigest:
+      keys:
+        - length
+        - repeatSubunitLength
     description: >-
       An expression of a length of a sequence from a repeating reference.
     type: object
@@ -531,6 +490,9 @@ $defs:
   LiteralSequenceExpression:
     maturity: Alpha
     inherits: SequenceExpression
+    ga4ghDigest:
+      keys:
+        - sequence
     description: >-
       An explicit expression of a Sequence.
     type: object
@@ -669,6 +631,10 @@ $defs:
   GenotypeMember:
     privateTo: Genotype
     inherits: ValueObject
+    ga4ghDigest:
+      keys:
+        - count
+        - variation
     description: >-
       A class for expressing the count of a specific :ref:`MolecularVariation` present
       _in-trans_ at a genomic locus represented by a :ref:`Genotype`.