Merge pull request #267 from alliance-genome/variation_cleanup

Tweaks to variant model
alliance-genome · Oct 9, 2024 · 41b2abd · 41b2abd
2 parents 157f4ab + 4a9f6b3
commit 41b2abd
Showing 4 changed files with 34 additions and 82 deletions.
diff --git a/generated/jsonschema/allianceModel.schema.json b/generated/jsonschema/allianceModel.schema.json
@@ -8892,10 +8892,6 @@
                     "description": "A high-level grouping for the relationship type. This is analogous to category for nodes. In RDF, this corresponds to rdf:predicate and in Neo4j this corresponds to the relationship type.",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"
@@ -8977,8 +8973,8 @@
                     "description": "The sequence of DNA base pairs removed from the reference sequence by the variant.",
                     "type": "string"
                 },
-                "dna_mutation_type": {
-                    "description": "The type of DNA mutation, for example, insertion, deletion, substitution, or indel.",
+                "dna_mutation_type_curie": {
+                    "description": "Curie of SOTerm describing the type of DNA mutation, for example, insertion, deletion, substitution, or indel.",
                     "type": "string"
                 },
                 "end": {
@@ -8992,8 +8988,8 @@
                     },
                     "type": "array"
                 },
-                "gene_localization_type": {
-                    "description": "The type of gene localization, for example, intronic, intergenic, or intragenic.",
+                "gene_localization_type_curie": {
+                    "description": "Curie of SOTerm describing the type of gene localization, for example, intronic, intergenic, or intragenic.",
                     "type": "string"
                 },
                 "inserted_sequence": {
@@ -9033,10 +9029,6 @@
                     "description": "Name of VocabularyTerm representing relation of an Association",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"
@@ -9156,10 +9148,6 @@
                     "description": "A high-level grouping for the relationship type. This is analogous to category for nodes. In RDF, this corresponds to rdf:predicate and in Neo4j this corresponds to the relationship type.",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"
@@ -9279,10 +9267,6 @@
                     "description": "Name of VocabularyTerm representing relation of an Association",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"
@@ -9391,10 +9375,6 @@
                     "description": "A high-level grouping for the relationship type. This is analogous to category for nodes. In RDF, this corresponds to rdf:predicate and in Neo4j this corresponds to the relationship type.",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"
@@ -9504,10 +9484,6 @@
                     "description": "Name of VocabularyTerm representing relation of an Association",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"
@@ -21980,10 +21956,6 @@
                     "description": "A high-level grouping for the relationship type. This is analogous to category for nodes. In RDF, this corresponds to rdf:predicate and in Neo4j this corresponds to the relationship type.",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "single_reference": {
                     "$ref": "#/$defs/Reference",
                     "description": "holds between an object and a single reference"
@@ -22067,8 +22039,8 @@
                     "description": "The sequence of DNA base pairs removed from the reference sequence by the variant.",
                     "type": "string"
                 },
-                "dna_mutation_type": {
-                    "description": "The type of DNA mutation, for example, insertion, deletion, substitution, or indel.",
+                "dna_mutation_type_curie": {
+                    "description": "Curie of SOTerm describing the type of DNA mutation, for example, insertion, deletion, substitution, or indel.",
                     "type": "string"
                 },
                 "end": {
@@ -22082,8 +22054,8 @@
                     },
                     "type": "array"
                 },
-                "gene_localization_type": {
-                    "description": "The type of gene localization, for example, intronic, intergenic, or intragenic.",
+                "gene_localization_type_curie": {
+                    "description": "Curie of SOTerm describing the type of gene localization, for example, intronic, intergenic, or intragenic.",
                     "type": "string"
                 },
                 "inserted_sequence": {
@@ -22127,10 +22099,6 @@
                     "description": "Name of VocabularyTerm representing relation of an Association",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"
@@ -22249,10 +22217,6 @@
                     "description": "A high-level grouping for the relationship type. This is analogous to category for nodes. In RDF, this corresponds to rdf:predicate and in Neo4j this corresponds to the relationship type.",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "single_reference": {
                     "$ref": "#/$defs/Reference",
                     "description": "holds between an object and a single reference"
@@ -22378,10 +22342,6 @@
                     "description": "Name of VocabularyTerm representing relation of an Association",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"
@@ -22489,10 +22449,6 @@
                     "description": "A high-level grouping for the relationship type. This is analogous to category for nodes. In RDF, this corresponds to rdf:predicate and in Neo4j this corresponds to the relationship type.",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "single_reference": {
                     "$ref": "#/$defs/Reference",
                     "description": "holds between an object and a single reference"
@@ -22608,10 +22564,6 @@
                     "description": "Name of VocabularyTerm representing relation of an Association",
                     "type": "string"
                 },
-                "sequence_of_reference_accession_number": {
-                    "description": "The accession number that describes the assembly and assembly component (chromosome or scaffold) of the reference sequence.",
-                    "type": "string"
-                },
                 "start": {
                     "description": "The start of the feature in positive 1-based integer coordinates relative to the reference landmark.",
                     "type": "integer"

diff --git a/model/schema/variantDTO.yaml b/model/schema/variantDTO.yaml
@@ -55,7 +55,6 @@ classes:
       - variant_sequence
       - consequence_curie
       - curated_consequence_curie
-      - sequence_of_reference_accession_number
 
   VariantGenomicLocationAssociationDTO:
     is_a: VariantLocationAssociationDTO
@@ -68,8 +67,8 @@ classes:
       - inserted_sequence
       - deleted_sequence
       - padded_base
-      - dna_mutation_type
-      - gene_localization_type
+      - dna_mutation_type_curie
+      - gene_localization_type_curie
 
   VariantTranscriptLocationAssociationDTO:
     is_a: VariantLocationAssociationDTO
@@ -180,6 +179,22 @@ slots:
     domain: VariantLocationAssociationDTO
     range: string
 
+  dna_mutation_type_curie:
+    description: >-
+      Curie of SOTerm describing the type of DNA mutation, for example, insertion, deletion, substitution, or indel.
+    range: SOTerm
+    examples:
+      - value: SO:1000027 # G_to_T_transversion
+    notes: >-
+      This is a ZFIN specific field.
+
+  gene_localization_type_curie:
+    description: >-
+      Curie of SOTerm describing the type of gene localization, for example, intronic, intergenic, or intragenic.
+    range: string
+    examples:
+      - value: SO:0000147 # exon
+
   source_general_consequence_dtos:
     domain: VariantDTO
     range: VariantSourceGeneralConsequenceSlotAnnotationDTO

diff --git a/model/schema/variation.yaml b/model/schema/variation.yaml
@@ -82,7 +82,6 @@ classes:
       - variant_sequence
       - consequence
       - curated_consequence
-      - sequence_of_reference_accession_number # Should this point to a chromosome object instead of a string? Will this be redundant with genomic location association of the subject?
 
   VariantGenomicLocationAssociation:
     is_a: VariantLocationAssociation
@@ -257,19 +256,19 @@ slots:
     exact_mappings:
       - SO:0001889
 
-  dna_mutation_type: # Should the range of this be an object (SOTerm / OntologyTerm) rather than just a curie?
+  dna_mutation_type:
     description: >-
       The type of DNA mutation, for example, insertion, deletion, substitution, or indel.
-    range: uriorcurie
+    range: SOTerm
     examples:
       - value: SO:1000027 # G_to_T_transversion
     notes: >-
       This is a ZFIN specific field.
 
-  gene_localization_type: # Should the range of this be an object (SOTerm / OntologyTerm) rather than just a curie?
+  gene_localization_type:
     description: >-
       The type of gene localization, for example, intronic, intergenic, or intragenic.
-    range: uriorcurie
+    range: SOTerm
     examples:
       - value: SO:0000147 # exon
 
@@ -380,18 +379,6 @@ slots:
     required: true
     multivalued: false
 
-  sequence_of_reference_accession_number:
-    description: >-
-      The accession number that describes the assembly and assembly component
-      (chromosome or scaffold) of the reference sequence.
-    notes: >-
-      With redefined Location Associations to AssemblyComponent, Transcript or
-      Protein, is this redundant?
-    required: false
-    multivalued: false
-    domain: VariantLocationAssociation
-    range: string
-
   consequence:
     description: >-
       SOTerm (child of SO:0001576 - transcript_variant) that describes the

diff --git a/test/data/variant_association_ingest_test.json b/test/data/variant_association_ingest_test.json
@@ -12,7 +12,6 @@
       "end": 30341645,
       "reference_sequence": "C",
       "variant_sequence": "T",
-      "sequence_of_reference_accession_number": "NC_007118.7",
       "internal": false,
       "obsolete": false,
       "date_created": "2015-04-09T10:15:30+00:00",
@@ -25,8 +24,8 @@
       "inserted_sequence": "AT",
       "deleted_sequence": "GCGC",
       "padded_base": "A",
-      "dna_mutation_type": "SO:001231",
-      "gene_localization_type": "SO:121313"
+      "dna_mutation_type_curie": "SO:001231",
+      "gene_localization_type_curie": "SO:121313"
     }
   ],
  "variant_transcript_location_association_ingest_set": [
@@ -82,7 +81,6 @@
       "end": 30341645,
       "reference_sequence": "C",
       "variant_sequence": "T",
-      "sequence_of_reference_accession_number": "NC_007118.7",
       "internal": false,
       "obsolete": false,
       "date_created": "2015-04-09T10:15:30+00:00",
@@ -95,8 +93,8 @@
       "inserted_sequence": "AT",
       "deleted_sequence": "GCGC",
       "padded_base": "A",
-      "dna_mutation_type": "SO:001231",
-      "gene_localization_type": "SO:121313"
+      "dna_mutation_type_curie": "SO:001231",
+      "gene_localization_type_curie": "SO:121313"
     }
   ],
  "source_variant_transcript_location_association_ingest_set": [