wip: removing GeneDescriptor and replacing GeneElement with Gene

cancervariants · Jul 17, 2024 · 9873ae7 · 9873ae7
1 parent d611a55
commit 9873ae7
Show file tree

Hide file tree

Showing 14 changed files with 259 additions and 278 deletions.
diff --git a/src/fusor/examples/alk.json b/src/fusor/examples/alk.json
@@ -38,10 +38,9 @@
       "type": "MultiplePossibleGenesElement"
     },
     {
-      "type": "GeneElement",
-      "gene_descriptor": {
+      "gene": {
         "id": "normalize.gene:ALK",
-        "type": "GeneDescriptor",
+        "type": "Gene",
         "label": "ALK",
         "gene_id": "hgnc:427"
       }

diff --git a/src/fusor/examples/bcr_abl1.json b/src/fusor/examples/bcr_abl1.json
@@ -1,111 +1,131 @@
 {
   "type": "CategoricalFusion",
-  "structural_elements": [
-    {
-      "type": "TranscriptSegmentElement",
-      "transcript": "refseq:NM_004327.3",
-      "gene_descriptor": {
-        "type": "GeneDescriptor",
-        "id": "normalize.gene:BCR",
-        "gene_id": "hgnc:1014",
-        "label": "BCR"
+  "structure": {
+    "type": "Adjacency",
+    "adjoinedSequences": [{
+      "type": "SequenceLocation",
+      "sequenceReference": {
+        "id": "GRCh38:chr22",
+        "type": "SequenceReference",
+        "refgetAccession": "SQ.7B7SHsmchAR0dFcDCuSFjJAo7tX87krQ",
+        "residueAlphabet": "na"
       },
-      "element_genomic_end": {
-        "id": "fusor.location_descriptor:NC_000022.11",
-        "type": "LocationDescriptor",
-        "label": "NC_000022.11",
-        "location": {
-          "type": "SequenceLocation",
-          "sequence_id": "refseq:NC_000022.11",
-          "interval": {
-            "type": "SequenceInterval",
-            "start": {
-              "type": "Number",
-              "value": 23253980
-            },
-            "end": {
-              "type": "Number",
-              "value": 23253981
+      "end": 23290413,
+      "extensions": [
+        {
+          "name": "NM_004327.4:e._14",
+          "description": "VICC exon representation of the aligned transcript boundary.",
+          "value": {
+            "exon_end": 14,
+            "exon_end_offset": 0,
+            "sequenceReference":{
+              "type": "SequenceReference",
+              "id": "NM_004327.4",
+              "refgetAccession": "SQ.kpytJsXw3BwLC3oBSjHQS1kwxs4WO3I3",
+              "residueAlphabet": "na"
             }
           }
-        }
-      },
-      "exon_end": 2,
-      "exon_end_offset": 182
-    },
-    {
-      "type": "LinkerSequenceElement",
-      "linker_sequence": {
-        "id": "sequence:ACTAAAGCG",
-        "type": "SequenceDescriptor",
-        "sequence": "ACTAAAGCG",
-        "residue_type": "SO:0000348"
-      }
-    },
-    {
-      "type": "TranscriptSegmentElement",
-      "transcript": "refseq:NM_005157.5",
-      "exon_start": 2,
-      "exon_start_offset": -173,
-      "gene_descriptor": {
-        "id": "normalize.gene:ABL1",
-        "type": "GeneDescriptor",
-        "label": "ABL1",
-        "gene_id": "hgnc:76"
-      },
-      "element_genomic_start": {
-        "id": "fusor.location_descriptor:NC_000009.12",
-        "type": "LocationDescriptor",
-        "label": "NC_000009.12",
-        "location": {
-          "type": "SequenceLocation",
-          "sequence_id": "refseq:NC_000009.12",
-          "interval": {
-            "type": "SequenceInterval",
-            "start": {
-              "type": "Number",
-              "value": 130854064
+        },
+        {
+          "name": "NM_004327.4:c._2782",
+          "description": "Transcript SequenceLocation of the aligned transcript boundary.",
+          "value": {
+            "type": "SequenceLocation",
+            "sequenceReference": {
+              "id": "NM_004327.4",
+              "type": "SequenceReference",
+              "refgetAccession": "SQ.kpytJsXw3BwLC3oBSjHQS1kwxs4WO3I3",
+              "residueAlphabet": "na"
             },
-            "end": {
-              "type": "Number",
-              "value": 130854065
-            }
+            "end": 3234
+          }
+        },
+        {
+          "name": "gene",
+          "description": "The gene concept (BCR) associated with this fusion partner.",
+          "value": {
+            "code": "hgnc:1014",
+            "system": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/",
+            "label": "BCR"
           }
         }
-      }
+      ]},
+      {
+        "type": "SequenceLocation",
+        "sequenceReference": {
+          "id": "GRCh38:chr9",
+          "type": "SequenceReference",
+          "refgetAccession": "SQ.KEO-4XBcm1cxeo_DIQ8_ofqGUkp4iZhI",
+          "residueAlphabet": "na"
+        },
+        "start": 130854064,
+        "extensions": [
+          {
+            "name": "NM_005157.6:e.2_",
+            "description": "VICC exon representation of the aligned transcript boundary.",
+            "value": {
+              "exon_start": 2,
+              "exon_start_offset": 0,
+              "sequenceReference":{
+                "id": "NM_005157.6",
+                "type": "SequenceReference",
+                "refgetAccession": "SQ.w8Qg3x-PQ2akJrJQeGEN-_eBUMo1H1CL",
+                "residueAlphabet": "na"
+              }
+            }
+          },
+          {
+            "name": "NM_005157.6:c.80_",
+            "description": "Transcript SequenceLocation of the aligned transcript boundary.",
+            "value": {
+              "type": "SequenceLocation",
+              "sequenceReference": {
+                "id": "NM_005157.6",
+                "type": "SequenceReference",
+                "refgetAccession": "SQ.w8Qg3x-PQ2akJrJQeGEN-_eBUMo1H1CL",
+                "residueAlphabet": "na"
+              },
+              "end": 273
+            }
+          },
+          {
+            "name": "gene",
+            "description": "The gene concept (ABL1) associated with this fusion partner.",
+            "value": {
+              "code": "hgnc:76",
+              "system": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/",
+              "label": "ABL1"
+            }
+          }
+        ]
+      }],
+    "linker": {
+      "type": "LiteralSequenceExpression",
+      "sequence": "CCCGTC"
     }
-  ],
-  "r_frame_preserved": true,
-  "critical_functional_domains": [
+  },
+  "readingFramePreserved": true,
+  "criticalFunctionalDomains": [
     {
       "type": "FunctionalDomain",
       "status": "preserved",
-      "associated_gene": {
-        "id": "normalize.gene:hgnc%3A76",
-        "type": "GeneDescriptor",
-        "label": "ABL1",
-        "gene_id": "hgnc:76"
+      "gene": {
+        "code": "hgnc:76",
+        "system": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/",
+        "label": "ABL1"
       },
-      "_id": "interpro:IPR000980",
+      "id": "interpro:IPR000980",
       "label": "SH2 domain",
-      "sequence_location": {
-        "id": "fusor.location_descriptor:NP_005148.2",
-        "type": "LocationDescriptor",
-        "location": {
-          "type": "SequenceLocation",
-          "sequence_id": "refseq:NP_005148.2",
-          "interval": {
-            "type": "SequenceInterval",
-            "start": {
-              "type": "Number",
-              "value": 127
-            },
-            "end": {
-              "type": "Number",
-              "value": 202
-            }
-          }
-        }
+      "sequenceLocation": {
+        "type": "SequenceLocation",
+        "sequenceReference": {
+          "id": "GRCh38:chr22",
+          "type": "SequenceReference",
+          "refgetAccession": "SQ.7B7SHsmchAR0dFcDCuSFjJAo7tX87krQ",
+          "residueAlphabet": "na"
+        },
+        "start": 127,
+        "end": 202
       }
     }
   ]

diff --git a/src/fusor/examples/ewsr1.json b/src/fusor/examples/ewsr1.json
@@ -2,9 +2,8 @@
   "type": "AssayedFusion",
   "structural_elements": [
     {
-      "type": "GeneElement",
-      "gene_descriptor": {
-        "type": "GeneDescriptor",
+      "gene": {
+        "type": "Gene",
         "id": "normalize.gene:EWSR1",
         "label": "EWSR1",
         "gene_id": "hgnc:3508"

diff --git a/src/fusor/examples/ewsr1_elements_only.json b/src/fusor/examples/ewsr1_elements_only.json
@@ -2,9 +2,8 @@
   "type": "AssayedFusion",
   "structural_elements": [
     {
-      "type": "GeneElement",
-      "gene_descriptor": {
-        "type": "GeneDescriptor",
+      "gene": {
+        "type": "Gene",
         "id": "normalize.gene:EWSR1",
         "label": "EWSR1",
         "gene_id": "hgnc:3508"

diff --git a/src/fusor/examples/ewsr1_no_assay.json b/src/fusor/examples/ewsr1_no_assay.json
@@ -2,9 +2,8 @@
   "type": "AssayedFusion",
   "structural_elements": [
     {
-      "type": "GeneElement",
-      "gene_descriptor": {
-        "type": "GeneDescriptor",
+      "gene": {
+        "type": "Gene",
         "id": "normalize.gene:EWSR1",
         "label": "EWSR1",
         "gene_id": "hgnc:3508"

diff --git a/src/fusor/examples/ewsr1_no_causative_event.json b/src/fusor/examples/ewsr1_no_causative_event.json
@@ -2,9 +2,8 @@
   "type": "AssayedFusion",
   "structural_elements": [
     {
-      "type": "GeneElement",
-      "gene_descriptor": {
-        "type": "GeneDescriptor",
+      "gene": {
+        "type": "Gene",
         "id": "normalize.gene:EWSR1",
         "label": "EWSR1",
         "gene_id": "hgnc:3508"

diff --git a/src/fusor/examples/igh_myc.json b/src/fusor/examples/igh_myc.json
@@ -13,9 +13,8 @@
   },
   "structural_elements": [
     {
-      "type": "GeneElement",
-      "gene_descriptor": {
-        "type": "GeneDescriptor",
+      "gene": {
+        "type": "Gene",
         "label": "MYC",
         "gene_id": "hgnc:7553",
         "id": "normalize.gene:MYC"