work in progress for new annotations

uab-cgds-worthey · Dec 10, 2024 · 3e23ed5 · 3e23ed5
1 parent 969453a
commit 3e23ed5
Show file tree

Hide file tree

Showing 5 changed files with 155 additions and 28 deletions.
diff --git a/backend/src/core/annotation_task.py b/backend/src/core/annotation_task.py
@@ -100,6 +100,7 @@ def extract(self, incomming_json):
                 ))
             jq_result = next(jq_results, None)
             while jq_result is not None:
+                print(jq_result)
                 result_keys = list(jq_result.keys())
 
                 if 'transcript' in self.annotation_unit.dataset:

diff --git a/backend/tests/unit/core/test_annotation_task.py b/backend/tests/unit/core/test_annotation_task.py
@@ -47,6 +47,13 @@ def test_extraction_forge_gene_linkout_dataset(forge_annotation_task_gene):
     assert extracted_annotations[0]['value'] == 'https://www.ncbi.nlm.nih.gov/gene?Db=gene&Cmd=DetailsSearch&Term=45614'
 
 
+def test_extraction_forge_hgvs_variant_without_transcript_version(hgvs_without_transcript_version_annotation_task):
+    """Verifies the jq query used to forge create the transcript without a version dataset for a variant"""
+    forge_annotation = hgvs_without_transcript_version_annotation_task.annotate()
+    actual_extractions = hgvs_without_transcript_version_annotation_task.extract(forge_annotation)
+    assert(actual_extractions, "NM_170707:c.745C>T")
+
+
 def test_annotation_extraction_for_transcript_id_dataset(http_annotation_transcript_id, transcript_annotation_response):
     """Verifying genomic unit extraction for a transcript using the the transcript ID dataset"""
     actual_extractions = http_annotation_transcript_id.extract(transcript_annotation_response)
@@ -249,6 +256,20 @@ def fixture_transcript_id_dataset():
         "attribute": ".[].transcript_consequences[] | { transcript_id: .transcript_id }",
     }
 
+@pytest.fixture(name="hgvs_without_transcript_version_annotation_task")
+def fixture_hgvs_without_transcript_version(hgvs_variant_genomic_unit):
+    annotation_unit = AnnotationUnit(hgvs_variant_genomic_unit, {
+        "data_set": "hgvs_variant_without_transcript_version",
+        "data_source": "Rosalution",
+        "annotation_source_type": "forge",
+        "genomic_unit_type": "hgvs_variant",
+        "base_string": "{hgvs_variant}",
+        "attribute": ".hgvs_variant_without_transcript_version | split(\":\") as $transcript_split | $transcript_split[0] | split(\".\")[0] | . + \":\" + $transcript_split[1] | {\"hgvs_variant_without_transcript_version\": .}",
+        "versioning_type": "rosalution"
+    })
+    task = ForgeAnnotationTask(annotation_unit)
+    return task
+
 
 @pytest.fixture(name="hgvs_variant_annotation_unit")
 def fixture_hgvs_variant_annotation_unit(hgvs_variant_genomic_unit, transcript_id_dataset):

diff --git a/etc/fixtures/initial-seed/annotations-config.json b/etc/fixtures/initial-seed/annotations-config.json
@@ -1,24 +1,37 @@
 [
+  {
+      "data_set": "hgvs_variant_without_transcript_version",
+      "data_source": "Rosalution",
+      "annotation_source_type": "forge",
+      "genomic_unit_type": "hgvs_variant",
+      "base_string": "{hgvs_variant}",
+      "attribute": ".hgvs_variant_without_transcript_version | split(\":\") as $transcript_split | $transcript_split[0] | split(\".\")[0] | . + \":\" + $transcript_split[1] | {\"hgvs_variant_without_transcript_version\": .}",
+      "versioning_type": "rosalution"
+  },
   {
     "data_set": "transcript_id",
     "data_source": "Ensembl",
     "genomic_unit_type": "hgvs_variant",
     "transcript": true,
     "annotation_source_type": "http",
-    "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;refseq=1;",
+    "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;refseq=1;",
     "attribute": ".[].transcript_consequences[] | { transcript_id: .transcript_id }",
+    "dependencies": ["hgvs_variant_without_transcript_version"],
     "versioning_type": "rest",
     "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
     "version_attribute": ".releases[]"
-   },
+  },
   {
-    "data_set": "HPO_NCBI_GENE_ID",
-    "data_source": "HPO",
-    "genomic_unit_type": "gene",
+    "data_set": "ensembl_vep_vcf_string",
+    "data_source": "Ensembl",
+    "genomic_unit_type": "hgvs_variant",
     "annotation_source_type": "http",
-    "url": "https://ontology.jax.org/api/network/search/GENE?q={gene}&page=0&limit=10",
-    "attribute": "{ \"HPO_NCBI_GENE_ID\": .results[] | select( .name == \"{gene}\") | .id }",
-    "versioning_type": "date" 
+    "url": "https://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;refseq=1;vcf_string=1;",
+    "attribute": ".[] | .vcf_string",
+    "versioning_type": "rest",
+    "dependencies": ["hgvs_variant_without_transcript_version"],
+    "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
+    "version_attribute": ".releases[]"
   },
   {
     "data_set": "Ensembl Gene Id",
@@ -48,8 +61,9 @@
     "genomic_unit_type": "hgvs_variant",
     "annotation_source_type": "http",
     "attribute": ".[] | select(.colocated_variants != null) | .colocated_variants[] | select(.var_synonyms != null) | .var_synonyms | select( .ClinVar != null ) | select(.ClinVar != []) | .ClinVar[] | select(contains(\"VCV\")) | sub(\"VCV0+\"; \"\") | {\"ClinVar_Variantion_Id\": . } ",
-    "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;clinvar=1;",
-    "versioning_type": "rosalution"
+    "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;clinvar=1;",
+    "versioning_type": "rosalution",
+    "dependencies": ["hgvs_variant_without_transcript_version"]
   },
   {
     "data_set": "OMIM_gene_search_url",
@@ -214,6 +228,25 @@
     "dependencies": ["Ensembl Gene Id"],
     "versioning_type": "rosalution"
   },
+  {
+    "data_set": "gnomAD_variant_url",
+    "data_source": "Rosalution",
+    "genomic_unit_type": "gene",
+    "annotation_source_type": "forge",
+    "base_string": "https://gnomad.broadinstitute.org/gene/{ensembl_vep_vcf_string}?dataset=gnomad_r4",
+    "attribute": "{ \"gnomAD_variant_url\": .gnomAD_variant_url }",
+    "dependencies": ["Ensembl Gene Id"],
+    "versioning_type": "rosalution"
+  },
+  {
+    "data_set": "HPO_NCBI_GENE_ID",
+    "data_source": "HPO",
+    "genomic_unit_type": "gene",
+    "annotation_source_type": "http",
+    "url": "https://ontology.jax.org/api/network/search/GENE?q={gene}&page=0&limit=10",
+    "attribute": "{ \"HPO_NCBI_GENE_ID\": .results[] | select( .name == \"{gene}\") | .id }",
+    "versioning_type": "date"
+  },
   {
     "data_set": "OMIM",
     "data_source": "HPO",
@@ -384,9 +417,10 @@
      "genomic_unit_type": "hgvs_variant",
      "transcript": true,
      "annotation_source_type": "http",
-     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;refseq=1;",
+     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;refseq=1;",
      "attribute": ".[].transcript_consequences[] | { polyphen_prediction: .polyphen_prediction, transcript_id: .transcript_id }",
      "versioning_type": "rest",
+     "dependencies": ["hgvs_variant_without_transcript_version"],
      "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
      "version_attribute": ".releases[]"
    },
@@ -396,9 +430,10 @@
      "genomic_unit_type": "hgvs_variant",
      "transcript": true,
      "annotation_source_type": "http",
-     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;refseq=1;",
+     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;refseq=1;",
      "attribute": ".[].transcript_consequences[] | { polyphen_score: .polyphen_score, transcript_id: .transcript_id }",
      "versioning_type": "rest",
+     "dependencies": ["hgvs_variant_without_transcript_version"],
      "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
      "version_attribute": ".releases[]"
    },
@@ -408,9 +443,10 @@
      "genomic_unit_type": "hgvs_variant",
      "transcript": true,
      "annotation_source_type": "http",
-     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;refseq=1;",
+     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;refseq=1;",
      "attribute": ".[].transcript_consequences[] | { sift_prediction: .sift_prediction, transcript_id: .transcript_id }",
      "versioning_type": "rest",
+     "dependencies": ["hgvs_variant_without_transcript_version"],
      "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
      "version_attribute": ".releases[]"
    },
@@ -420,9 +456,11 @@
      "genomic_unit_type": "hgvs_variant",
      "transcript": true,
      "annotation_source_type": "http",
-     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;refseq=1;",
+     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;refseq=1;",
      "attribute": ".[].transcript_consequences[] | { sift_score: .sift_score, transcript_id: .transcript_id }",
      "versioning_type": "rest",
+     "dependencies": ["hgvs_variant_without_transcript_version"],
+
      "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
      "version_attribute": ".releases[]"
    },
@@ -432,8 +470,9 @@
      "genomic_unit_type": "hgvs_variant",
      "transcript": true,
      "annotation_source_type": "http",
-     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;refseq=1;",
+     "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;refseq=1;",
      "attribute": ".[].transcript_consequences[] | { consequence_terms: .consequence_terms, transcript_id: .transcript_id }",
+     "dependencies": ["hgvs_variant_without_transcript_version"],
      "versioning_type": "rest",
      "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
      "version_attribute": ".releases[]"
@@ -443,9 +482,9 @@
     "data_source": "Ensembl",
     "genomic_unit_type": "hgvs_variant",
     "annotation_source_type": "http",
-    "url": "https://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;CADD=1;refseq=1;",
+    "url": "https://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;CADD=1;refseq=1;",
     "attribute": ".[].transcript_consequences[] | select( .transcript_id | contains(\"{transcript}\") ) | { CADD: .cadd_phred }",
-    "dependencies": ["transcript"],
+    "dependencies": ["transcript","hgvs_variant_without_transcript_version"],
     "versioning_type": "rest",
     "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
     "version_attribute": ".releases[]"
@@ -456,9 +495,10 @@
     "genomic_unit_type": "hgvs_variant",
     "transcript": true,
     "annotation_source_type": "http",
-    "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant}?content-type=application/json;refseq=1;",
+    "url": "http://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;refseq=1;",
     "attribute": ".[].transcript_consequences[] | { impact: .impact, transcript_id: .transcript_id }",
     "versioning_type": "rest",
+    "dependencies": ["hgvs_variant_without_transcript_version"],
     "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
     "version_attribute": ".releases[]"
   },
@@ -538,6 +578,18 @@
     "version_url": "https://www.alliancegenome.org/api/releaseInfo",
     "version_attribute": ".releaseVersion"
   },
+  {
+    "data_set": "C-Elegens_Worm_Base_url",
+    "data_source": "Alliance Genome",
+    "annotation_source_type": "http",
+    "genomic_unit_type": "gene",
+    "url": "https://www.alliancegenome.org/api/gene/{C-Elegens Gene Identifier}",
+    "attribute": "{ \"C-Elegens_Worm_Base_url\": .modCrossRefCompleteUrl }",
+    "dependencies": ["C-Elegens Gene Identifier"],
+    "versioning_type": "rest",
+    "version_url": "https://www.alliancegenome.org/api/releaseInfo",
+    "version_attribute": ".releaseVersion"
+  },
   {
     "data_set": "C-Elegens_Alliance_Genome_url",
     "data_source": "Rosalution",
@@ -549,15 +601,15 @@
     "versioning_type": "rosalution"
   },
   {
-    "data_set": "C-Elegens_Worm_Base_url",
-    "data_source": "Alliance Genome",
+    "data_set": "opencravat_search_variant_vcf_string",
+    "data_source": "Ensembl",
+    "genomic_unit_type": "hgvs_variant",
     "annotation_source_type": "http",
-    "genomic_unit_type": "gene",
-    "url": "https://www.alliancegenome.org/api/gene/{C-Elegens Gene Identifier}",
-    "attribute": "{ \"C-Elegens_Worm_Base_url\": .modCrossRefCompleteUrl }",
-    "dependencies": ["C-Elegens Gene Identifier"],
+    "url": "https://rest.ensembl.org/vep/human/hgvs/{hgvs_variant_without_transcript_version}?content-type=application/json;CADD=1;refseq=1;vcf_string=1;",
+    "attribute": ".[] | .vcf_string | split(\"-\") | \"chrom=chr\" + .[0] + \"&pos=\" + .[1] + \"&ref_base=\" + .[2] + \"&alt_base=\" + .[3] ",
     "versioning_type": "rest",
-    "version_url": "https://www.alliancegenome.org/api/releaseInfo",
-    "version_attribute": ".releaseVersion"
+    "dependencies": ["hgvs_variant_without_transcript_version"],
+    "version_url": "https://rest.ensembl.org/info/data/?content-type=application/json",
+    "version_attribute": ".releases[]"
   }
 ]
diff --git a/etc/fixtures/initial-seed/genomic-units.json b/etc/fixtures/initial-seed/genomic-units.json
@@ -465,6 +465,24 @@
             "value": "https://www.ncbi.nlm.nih.gov/clinvar/variation/581244"
           }
         ]
+      },
+      {
+        "ensembl_vep_vcf_string": [
+          {
+            "data_source": "Rosalution",
+            "version": "rosalution-manifest-00",
+            "value": "X-151404916-G-T"
+          }
+        ]
+      },
+      {
+        "gnomAD_variant_url": [
+          {
+            "data_source": "Rosalution",
+            "version": "rosalution-manifest-00",
+            "value": "https://gnomad.broadinstitute.org/gene/X-151404916-G-T?dataset=gnomad_r4"
+          }
+        ]
       }
     ]
   },

diff --git a/frontend/src/models/analyses.js b/frontend/src/models/analyses.js
@@ -321,7 +321,7 @@ const annotationRenderingTemporary = [
       'type': 'icon-linkout-dataset',
       'props': {
         'imageFilename': 'gnomad-logo.png',
-        'altText': 'Genome Aggregation Database (gnomAD) from Broad Institute',
+        'altText': 'Genome Aggregation Database (gnomAD) for variants from Broad Institute',
       },
     }],
     'rows': [
@@ -368,7 +368,14 @@ const annotationRenderingTemporary = [
     'class': '',
     'header': 'variant',
     'anchor': 'Variant',
-    'header_datasets': [],
+    'header_datasets': [{
+      'dataset': 'gnomAD_variant_url',
+      'type': 'icon-linkout-dataset',
+      'props': {
+        'imageFilename': 'gnomad-logo.png',
+        'altText': 'Genome Aggregation Database (gnomAD) for genes from Broad Institute',
+      },
+    }],
     'rows': [
       {
         'class': '',
@@ -401,6 +408,34 @@ const annotationRenderingTemporary = [
               'cutoff': 1,
             },
           },
+          {
+            'dataset': 'REVEL',
+            'type': 'score-dataset',
+            'props': {
+              'label': 'REVEL',
+              'minimum': 0,
+              'maximum': 1,
+              'bounds': {
+                'lowerBound': 0.5,
+                'upperBound': 0.79,
+              },
+              'cutoff': 1,
+            },
+          },
+          {
+            'dataset': 'AlphaMissense',
+            'type': 'score-dataset',
+            'props': {
+              'label': 'REVEL',
+              'minimum': 0,
+              'maximum': 1,
+              'bounds': {
+                'lowerBound': 0.34,
+                'upperBound': 0.564,
+              },
+              'cutoff': 1,
+            },
+          },
           // {
           //   'dataset': 'Phylop100',
           //   'type': 'score-dataset',