Ensembl · ahc87 · Dec 5, 2022 · Dec 5, 2022 · Dec 5, 2022
diff --git a/common/schemas/gene.graphql b/common/schemas/gene.graphql
@@ -8,7 +8,7 @@ type Gene {
   name: String
   so_term: String!
   transcripts: [Transcript!]!
-  transcripts_page(page: Int!, per_page: Int!): TranscriptsPage!
+  transcripts_page(page: Int!, per_page: Int!, filters: TranscriptFilter): TranscriptsPage!
   slice: Slice!
   external_references: [ExternalReference!]!
   alternative_symbols: [String!]!

diff --git a/common/schemas/query.graphql b/common/schemas/query.graphql
@@ -45,4 +45,9 @@ type Locus {
 input RegionNameInput  {
   genome_id: String!
   name: String!
-}
+}
+
+input TranscriptFilter {
+  biotype: [String!]
+  tsl: [String!]
+}
diff --git a/graphql_service/resolver/gene_model.py b/graphql_service/resolver/gene_model.py
@@ -218,14 +218,26 @@ async def resolve_gene_transcripts(gene: Dict, info: GraphQLResolveInfo) -> List
 
 @GENE_TYPE.field("transcripts_page")
 async def resolve_gene_transcripts_page(
-    gene: Dict, _: GraphQLResolveInfo, page: int, per_page: int
+    gene: Dict,
+    _: GraphQLResolveInfo,
+    page: int,
+    per_page: int,
+    filters=None,
 ):
     "This resolver passes required fields down to child resolvers"
 
+    if filters is None:
+        filters = {}
+    transcript_filter_queries = {
+        ".".join(["metadata", filter_name, "value"]): {"$in": filter_values}
+        for filter_name, filter_values in filters.items()
+    }
+
     return {
         "gene_primary_key": gene["gene_primary_key"],
         "page": page,
         "per_page": per_page,
+        "transcript_filter_queries": transcript_filter_queries,
     }
 
 
@@ -234,9 +246,11 @@ async def resolve_transcripts_page_transcripts(
     transcripts_page: Dict, info: GraphQLResolveInfo
 ) -> List[Dict]:
     "Load a page of transcripts"
+
     query = {
         "type": "Transcript",
         "gene_foreign_key": transcripts_page["gene_primary_key"],
+        **transcripts_page["transcript_filter_queries"],
     }
     page, per_page = transcripts_page["page"], transcripts_page["per_page"]
     collection = info.context["mongo_db"]
@@ -256,6 +270,7 @@ async def resolve_transcripts_page_metadata(
     query = {
         "type": "Transcript",
         "gene_foreign_key": transcripts_page["gene_primary_key"],
+        **transcripts_page["transcript_filter_queries"],
     }
     collection = info.context["mongo_db"]
     return {

diff --git a/graphql_service/resolver/tests/test_resolvers.py b/graphql_service/resolver/tests/test_resolvers.py
@@ -95,6 +95,7 @@ def fixture_transcript_data():
                     }
                 ],
                 "gene_foreign_key": "1_ENSG001.1",
+                "metadata": {"biotype": {"value": "protein_coding"}},
             },
             {
                 "genome_id": "1",
@@ -105,6 +106,7 @@ def fixture_transcript_data():
                 "gene": "ENSG001.1",
                 "product_generating_contexts": [],
                 "gene_foreign_key": "1_ENSG001.1",
+                "metadata": {"biotype": {"value": "nonsense_mediated_decay"}},
             },
             {
                 "genome_id": "1",
@@ -862,15 +864,36 @@ async def test_resolve_gene_transcripts_page():
         "unversioned_stable_id": "ENSG001",
         "gene_primary_key": "1_ENSG001.1",
     }
-    result = await model.resolve_gene_transcripts_page(gene, None, 1, 2)
-    assert result == {"gene_primary_key": "1_ENSG001.1", "page": 1, "per_page": 2}
+    transcript_filter = {
+        "biotype": ["protein_coding", "nonsense_mediated_decay"],
+        "tsl": ["tsl1", "tsl2", "tsl3"],
+    }
+    result = await model.resolve_gene_transcripts_page(
+        gene, None, 1, 2, transcript_filter
+    )
+    assert result == {
+        "gene_primary_key": "1_ENSG001.1",
+        "page": 1,
+        "per_page": 2,
+        "transcript_filter_queries": {
+            "metadata.biotype.value": {
+                "$in": ["protein_coding", "nonsense_mediated_decay"]
+            },
+            "metadata.tsl.value": {"$in": ["tsl1", "tsl2", "tsl3"]},
+        },
+    }
 
 
 @pytest.mark.asyncio
 async def test_resolve_transcripts_page_transcripts(transcript_data):
     info = create_info(transcript_data)
 
-    transcripts_page = {"gene_primary_key": "1_ENSG001.1", "page": 2, "per_page": 1}
+    transcripts_page = {
+        "gene_primary_key": "1_ENSG001.1",
+        "page": 2,
+        "per_page": 1,
+        "transcript_filter_queries": {},
+    }
     result = await model.resolve_transcripts_page_transcripts(transcripts_page, info)
     assert remove_ids(result) == [
         {
@@ -882,6 +905,41 @@ async def test_resolve_transcripts_page_transcripts(transcript_data):
             "symbol": "grape",
             "type": "Transcript",
             "unversioned_stable_id": "ENST002",
+            "metadata": {"biotype": {"value": "nonsense_mediated_decay"}},
+        }
+    ]
+
+
+@pytest.mark.asyncio
+async def test_resolve_transcripts_page_transcripts_filters(transcript_data):
+    info = create_info(transcript_data)
+
+    transcripts_page = {
+        "gene_primary_key": "1_ENSG001.1",
+        "page": 1,
+        "per_page": 2,
+        "transcript_filter_queries": {
+            "metadata.biotype.value": {"$in": ["protein_coding"]}
+        },
+    }
+    result = await model.resolve_transcripts_page_transcripts(transcripts_page, info)
+    assert remove_ids(result) == [
+        {
+            "gene": "ENSG001.1",
+            "gene_foreign_key": "1_ENSG001.1",
+            "genome_id": "1",
+            "metadata": {"biotype": {"value": "protein_coding"}},
+            "product_generating_contexts": [
+                {
+                    "product_foreign_key": "1_ENSP001.1",
+                    "product_id": "ENSP001.1",
+                    "product_type": "Protein",
+                }
+            ],
+            "stable_id": "ENST001.1",
+            "symbol": "kumquat",
+            "type": "Transcript",
+            "unversioned_stable_id": "ENST001",
         }
     ]
 
@@ -890,7 +948,12 @@ async def test_resolve_transcripts_page_transcripts(transcript_data):
 async def test_resolve_transcripts_page_transcripts_no_transcripts(transcript_data):
     info = create_info(transcript_data)
 
-    transcripts_page = {"gene_primary_key": "1_ENSG001.1", "page": 3, "per_page": 1}
+    transcripts_page = {
+        "gene_primary_key": "1_ENSG001.1",
+        "page": 3,
+        "per_page": 1,
+        "transcript_filter_queries": {},
+    }
     result = await model.resolve_transcripts_page_transcripts(transcripts_page, info)
     assert result == []
 
@@ -899,11 +962,32 @@ async def test_resolve_transcripts_page_transcripts_no_transcripts(transcript_da
 async def test_resolve_transcripts_page_metadata(transcript_data):
     info = create_info(transcript_data)
 
-    transcripts_page = {"gene_primary_key": "1_ENSG001.1", "page": 2, "per_page": 1}
+    transcripts_page = {
+        "gene_primary_key": "1_ENSG001.1",
+        "page": 2,
+        "per_page": 1,
+        "transcript_filter_queries": {},
+    }
     result = await model.resolve_transcripts_page_metadata(transcripts_page, info)
     assert result == {"page": 2, "per_page": 1, "total_count": 2}
 
 
+@pytest.mark.asyncio
+async def test_resolve_transcripts_page_metadata_filters(transcript_data):
+    info = create_info(transcript_data)
+
+    transcripts_page = {
+        "gene_primary_key": "1_ENSG001.1",
+        "page": 1,
+        "per_page": 1,
+        "transcript_filter_queries": {
+            "metadata.biotype.value": {"$in": ["protein_coding"]}
+        },
+    }
+    result = await model.resolve_transcripts_page_metadata(transcripts_page, info)
+    assert result == {"page": 1, "per_page": 1, "total_count": 1}
+
+
 def remove_ids(test_output):
     if isinstance(test_output, dict):
         del test_output["_id"]

diff --git a/graphql_service/tests/fixtures/human_brca2.py b/graphql_service/tests/fixtures/human_brca2.py
@@ -73,6 +73,7 @@ def build_transcripts():
         "so_term": "protein_coding",
         "genome_id": "homo_sapiens_GCA_000001405_28",
         "exons": build_exons(),
+        "metadata": {"biotype": {"value": "protein_coding"}},
         "slice": {
             "region_id": "homo_sapiens_GCA_000001405_28_13_chromosome",
             "location": {

diff --git a/graphql_service/tests/snapshots/snap_test_gene_retrieval.py b/graphql_service/tests/snapshots/snap_test_gene_retrieval.py
@@ -1,8 +1,5 @@
 # -*- coding: utf-8 -*-
 # snapshottest: v1 - https://goo.gl/zC4yUc
-
-"""Test data for gene retrieval tests"""
-
 from __future__ import unicode_literals
 
 from snapshottest import Snapshot
@@ -12,35 +9,55 @@
 
 snapshots["test_gene_retrieval_by_id_camel_case 1"] = {
     "gene": {
+        "metadata": {
+            "biotype": {
+                "definition": "Transcipt that contains an open reading frame (ORF).",
+                "description": None,
+                "label": "Protein coding",
+                "value": "protein_coding",
+            },
+            "name": {
+                "accession_id": "HGNC:1101",
+                "source": {
+                    "description": "HUGO Genome Nomenclature Committee",
+                    "id": "HGNC",
+                    "name": "HGNC Symbol",
+                    "release": None,
+                    "url": "https://www.genenames.org",
+                },
+                "url": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:1101",
+                "value": "BRCA2 DNA repair associated",
+            },
+        },
         "name": "BRCA2 DNA repair associated [Source:HGNC Symbol;Acc:HGNC:1101]",
         "slice": {
             "location": {"end": 32400266, "start": 32315086},
             "region": {
-                "name": "13",
-                "length": 114364328,
-                "code": "chromosome",
-                "topology": "linear",
                 "assembly": {
-                    "id": "GRCh38.p13",
-                    "default": True,
-                    "name": "GRCh38",
                     "accession_id": "GCA_000001405.28",
                     "accessioning_body": "EGA",
+                    "default": True,
+                    "id": "GRCh38.p13",
+                    "name": "GRCh38",
                 },
+                "code": "chromosome",
+                "length": 114364328,
                 "metadata": {
                     "ontology_terms": [
                         {
                             "accession_id": "SO:0000340",
-                            "value": "chromosome",
-                            "url": "www.sequenceontology.org/browser/current_release/term/SO:0000340",
                             "source": {
+                                "description": "The Sequence Ontology is a set of terms and relationships used to describe the features and attributes of biological sequence. ",
                                 "name": "Sequence Ontology",
                                 "url": "www.sequenceontology.org",
-                                "description": "The Sequence Ontology is a set of terms and relationships used to describe the features and attributes of biological sequence. ",
                             },
+                            "url": "www.sequenceontology.org/browser/current_release/term/SO:0000340",
+                            "value": "chromosome",
                         }
                     ]
                 },
+                "name": "13",
+                "topology": "linear",
             },
             "strand": {"code": "forward"},
         },
@@ -53,37 +70,17 @@
         ],
         "unversioned_stable_id": "ENSG00000139618",
         "version": 15,
-        "metadata": {
-            "biotype": {
-                "label": "Protein coding",
-                "definition": "Transcipt that contains an open reading frame (ORF).",
-                "description": None,
-                "value": "protein_coding",
-            },
-            "name": {
-                "accession_id": "HGNC:1101",
-                "value": "BRCA2 DNA repair associated",
-                "url": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:1101",
-                "source": {
-                    "id": "HGNC",
-                    "name": "HGNC Symbol",
-                    "description": "HUGO Genome Nomenclature Committee",
-                    "url": "https://www.genenames.org",
-                    "release": None,
-                },
-            },
-        },
     }
 }
 
-expected_id_and_symbol = {
+snapshots["test_gene_retrieval_by_id_snake_case 1"] = {
     "stable_id": "ENSG00000139618.15",
     "symbol": "BRCA2",
 }
 
-snapshots["test_gene_retrieval_by_id_snake_case 1"] = expected_id_and_symbol
-
-snapshots["test_gene_retrieval_by_symbol 1"] = [expected_id_and_symbol]
+snapshots["test_gene_retrieval_by_symbol 1"] = [
+    {"stable_id": "ENSG00000139618.15", "symbol": "BRCA2"}
+]
 
 snapshots["test_transcript_pagination 1"] = {
     "gene": {
@@ -93,3 +90,12 @@
         }
     }
 }
+
+snapshots["test_transcript_pagination_filters 1"] = {
+    "gene": {
+        "transcripts_page": {
+            "page_metadata": {"page": 1, "per_page": 2, "total_count": 1},
+            "transcripts": [{"stable_id": "ENST00000380152.7"}],
+        }
+    }
+}
diff --git a/graphql_service/tests/test_gene_retrieval.py b/graphql_service/tests/test_gene_retrieval.py
@@ -167,3 +167,35 @@ async def test_transcript_pagination(snapshot):
     )
     assert success
     snapshot.assert_match(result["data"])
+
+
+@pytest.mark.asyncio
+async def test_transcript_pagination_filters(snapshot):
+    """
+    Run a query checking pagination with filters
+    """
+    query = """
+    {
+        gene(by_id:{
+          genome_id:"homo_sapiens_GCA_000001405_28",
+          stable_id: "ENSG00000139618.15"
+        }) {
+            transcripts_page(page: 1, per_page:2, filters: {biotype: ["protein_coding"]}) {
+                transcripts {
+                    stable_id
+                }
+                page_metadata {
+                    total_count
+                    page
+                    per_page
+                }
+            }
+        }
+    }
+    """
+    query_data = {"query": query}
+    (success, result) = await graphql(
+        executable_schema, query_data, context_value=add_loaders_to_context(context)
+    )
+    assert success
+    snapshot.assert_match(result["data"])