Use new layers/gene info format in mapped target metadata

alembic/versions/dcf8572d3a17_add_mapped_hgnc_name_to_targets.py

@@ -0,0 +1,29 @@
+"""add mapped hgnc name to targets
+
+Revision ID: dcf8572d3a17
+Revises: b22b450d409c
+Create Date: 2025-12-12 17:32:40.147429
+
+"""
+
+import sqlalchemy as sa
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "dcf8572d3a17"
+down_revision = "b22b450d409c"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column("target_genes", sa.Column("mapped_hgnc_name", sa.String(), nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("target_genes", "mapped_hgnc_name")
+    # ### end Alembic commands ###

src/mavedb/lib/mapping.py

@@ -13,11 +13,19 @@
 class VRSMap:
     url: str
 
+    class GeneInfo(TypedDict):
+        hgnc_symbol: str
+        selection_method: str
+
+    class TargetAnnotation(TypedDict):
+        gene_info: "VRSMap.GeneInfo"
+        layers: dict[str, dict[str, dict[str, dict[str, Union[str, list[str]]]]]]
+
     class ScoreSetMappingResults(TypedDict):
         metadata: Optional[dict[str, str]]
         dcd_mapping_version: str
         mapped_date_utc: date
-        reference_sequences: Optional[dict[str, dict[str, dict[str, dict[str, Union[str, list[str]]]]]]]
+        reference_sequences: Optional[dict[str, "VRSMap.TargetAnnotation"]]
         mapped_scores: Optional[list[dict]]
         error_message: Optional[str]
 

src/mavedb/models/target_gene.py

@@ -47,6 +47,7 @@ class TargetGene(Base):
 
     pre_mapped_metadata: Mapped[JSONB] = Column("pre_mapped_metadata", JSONB, nullable=True)
     post_mapped_metadata: Mapped[JSONB] = Column("post_mapped_metadata", JSONB, nullable=True)
+    mapped_hgnc_name = Column(String, nullable=True)
     uniprot_id_from_mapped_metadata = Column(String, nullable=True)
 
     creation_date = Column(Date, nullable=False, default=date.today)

src/mavedb/scripts/populate_mapped_variants.py

@@ -1,8 +1,8 @@
 import logging
-import click
 from datetime import date
-from typing import Sequence, Optional
+from typing import Optional, Sequence, Union
 
+import click
 from sqlalchemy import cast, select
 from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.orm import Session
@@ -12,10 +12,9 @@
 from mavedb.lib.logging.context import format_raised_exception_info_as_dict
 from mavedb.lib.mapping import ANNOTATION_LAYERS
 from mavedb.models.enums.mapping_state import MappingState
-from mavedb.models.score_set import ScoreSet
 from mavedb.models.mapped_variant import MappedVariant
+from mavedb.models.score_set import ScoreSet
 from mavedb.models.variant import Variant
-
 from mavedb.scripts.environment import script_environment, with_database_session
 
 logger = logging.getLogger(__name__)
@@ -111,18 +110,24 @@ def populate_mapped_variant_data(db: Session, urns: Sequence[Optional[str]], all
                         )
                     # allow for multiple annotation layers
                     pre_mapped_metadata = {}
-                    post_mapped_metadata = {}
+                    post_mapped_metadata: dict[str, Union[Optional[str], dict[str, dict[str, str | list[str]]]]] = {}
                     excluded_pre_mapped_keys = {"sequence"}
-                    for annotation_layer in reference_metadata[target_gene_identifier]:
-                        layer_premapped = reference_metadata[target_gene_identifier][annotation_layer].get(
+
+                    gene_info = reference_metadata[target_gene_identifier].get("gene_info")
+                    if gene_info:
+                        target_gene.mapped_hgnc_name = gene_info.get("hgnc_symbol")
+                        post_mapped_metadata["hgnc_name_selection_method"] = gene_info.get("selection_method")
+
+                    for annotation_layer in reference_metadata[target_gene_identifier]["layers"]:
+                        layer_premapped = reference_metadata[target_gene_identifier]["layers"][annotation_layer].get(
                             "computed_reference_sequence"
                         )
                         if layer_premapped:
                             pre_mapped_metadata[ANNOTATION_LAYERS[annotation_layer]] = {
                                 k: layer_premapped[k]
                                 for k in set(list(layer_premapped.keys())) - excluded_pre_mapped_keys
                             }
-                        layer_postmapped = reference_metadata[target_gene_identifier][annotation_layer].get(
+                        layer_postmapped = reference_metadata[target_gene_identifier]["layers"][annotation_layer].get(
                             "mapped_reference_sequence"
                         )
                         if layer_postmapped:

src/mavedb/view_models/target_gene.py

@@ -60,6 +60,7 @@ class SavedTargetGene(TargetGeneBase):
     target_sequence: Optional[SavedTargetSequence] = None
     target_accession: Optional[SavedTargetAccession] = None
     external_identifiers: Sequence[external_gene_identifier_offset.SavedExternalGeneIdentifierOffset]
+    mapped_hgnc_name: Optional[str] = None
     uniprot_id_from_mapped_metadata: Optional[str] = None
 
     _record_type_factory = record_type_validator()(set_record_type)

src/mavedb/worker/jobs.py

@@ -453,21 +453,27 @@ async def map_variants_for_score_set(
                                 f"Target gene {target_gene_identifier} not found in database for score set {score_set.urn}."
                             )
                         # allow for multiple annotation layers
-                        pre_mapped_metadata = {}
-                        post_mapped_metadata = {}
+                        pre_mapped_metadata: dict[str, Any] = {}
+                        post_mapped_metadata: dict[str, Any] = {}
                         excluded_pre_mapped_keys = {"sequence"}
-                        for annotation_layer in reference_metadata[target_gene_identifier]:
-                            layer_premapped = reference_metadata[target_gene_identifier][annotation_layer].get(
-                                "computed_reference_sequence"
-                            )
+
+                        gene_info = reference_metadata[target_gene_identifier].get("gene_info")
+                        if gene_info:
+                            target_gene.mapped_hgnc_name = gene_info.get("hgnc_symbol")
+                            post_mapped_metadata["hgnc_name_selection_method"] = gene_info.get("selection_method")
+
+                        for annotation_layer in reference_metadata[target_gene_identifier]["layers"]:
+                            layer_premapped = reference_metadata[target_gene_identifier]["layers"][
+                                annotation_layer
+                            ].get("computed_reference_sequence")
                             if layer_premapped:
                                 pre_mapped_metadata[ANNOTATION_LAYERS[annotation_layer]] = {
                                     k: layer_premapped[k]
                                     for k in set(list(layer_premapped.keys())) - excluded_pre_mapped_keys
                                 }
-                            layer_postmapped = reference_metadata[target_gene_identifier][annotation_layer].get(
-                                "mapped_reference_sequence"
-                            )
+                            layer_postmapped = reference_metadata[target_gene_identifier]["layers"][
+                                annotation_layer
+                            ].get("mapped_reference_sequence")
                             if layer_postmapped:
                                 post_mapped_metadata[ANNOTATION_LAYERS[annotation_layer]] = layer_postmapped
                         target_gene.pre_mapped_metadata = cast(pre_mapped_metadata, JSONB)

tests/conftest.py

@@ -1,7 +1,7 @@
 import logging  # noqa: F401
+import sys
 from datetime import datetime
 from unittest import mock
-import sys
 
 import email_validator
 import pytest
@@ -11,35 +11,33 @@
 from sqlalchemy.pool import NullPool
 
 from mavedb.db.base import Base
+from mavedb.models import *  # noqa: F403
+from mavedb.models.experiment import Experiment
 from mavedb.models.experiment_set import ExperimentSet
-from mavedb.models.score_set_publication_identifier import ScoreSetPublicationIdentifierAssociation
-from mavedb.models.user import User, UserRole, Role
 from mavedb.models.license import License
-from mavedb.models.taxonomy import Taxonomy
-from mavedb.models.publication_identifier import PublicationIdentifier
-from mavedb.models.experiment import Experiment
-from mavedb.models.variant import Variant
 from mavedb.models.mapped_variant import MappedVariant
+from mavedb.models.publication_identifier import PublicationIdentifier
 from mavedb.models.score_set import ScoreSet
-
-from mavedb.models import *  # noqa: F403
-
+from mavedb.models.score_set_publication_identifier import ScoreSetPublicationIdentifierAssociation
+from mavedb.models.taxonomy import Taxonomy
+from mavedb.models.user import Role, User, UserRole
+from mavedb.models.variant import Variant
 from tests.helpers.constants import (
     ADMIN_USER,
     EXTRA_USER,
-    TEST_LICENSE,
+    TEST_BRNICH_SCORE_CALIBRATION,
     TEST_INACTIVE_LICENSE,
+    TEST_LICENSE,
+    TEST_PATHOGENICITY_SCORE_CALIBRATION,
+    TEST_PUBMED_IDENTIFIER,
     TEST_SAVED_TAXONOMY,
     TEST_USER,
-    VALID_VARIANT_URN,
-    VALID_SCORE_SET_URN,
-    VALID_EXPERIMENT_URN,
-    VALID_EXPERIMENT_SET_URN,
-    TEST_PUBMED_IDENTIFIER,
     TEST_VALID_POST_MAPPED_VRS_ALLELE_VRS2_X,
     TEST_VALID_PRE_MAPPED_VRS_ALLELE_VRS2_X,
-    TEST_BRNICH_SCORE_CALIBRATION,
-    TEST_PATHOGENICITY_SCORE_CALIBRATION,
+    VALID_EXPERIMENT_SET_URN,
+    VALID_EXPERIMENT_URN,
+    VALID_SCORE_SET_URN,
+    VALID_VARIANT_URN,
 )
 
 sys.path.append(".")
@@ -56,7 +54,7 @@
 assert pytest_postgresql.factories
 
 # Allow the @test domain name through our email validator.
-email_validator.SPECIAL_USE_DOMAIN_NAMES.remove("test")
+email_validator.TEST_ENVIRONMENT = True
 
 
 @pytest.fixture()

tests/helpers/constants.py

@@ -1189,27 +1189,38 @@
     }
 }
 
+
+TEST_GENE_INFO = {
+    "hgnc_symbol": VALID_GENE,
+    "selection_method": "tx_selection",
+}
+
+
+TEST_GENOMIC_LAYER = {
+    "computed_reference_sequence": {
+        "sequence_type": "dna",
+        "sequence_id": "ga4gh:SQ.ref_test",
+        "sequence": "ACGTTT",
+    },
+    "mapped_reference_sequence": {
+        "sequence_type": "dna",
+        "sequence_id": "ga4gh:SQ.map_test",
+        "sequence_accessions": [VALID_CHR_ACCESSION],
+    },
+}
+
+TEST_CODING_LAYER = {
+    "mapped_reference_sequence": {
+        "sequence_accessions": [VALID_NT_ACCESSION],
+    },
+}
+
 TEST_SEQ_SCORESET_VARIANT_MAPPING_SCAFFOLD = {
     "metadata": {},
     "reference_sequences": {
         "TEST1": {
-            "g": {
-                "computed_reference_sequence": {
-                    "sequence_type": "dna",
-                    "sequence_id": "ga4gh:SQ.ref_test",
-                    "sequence": "ACGTTT",
-                },
-                "mapped_reference_sequence": {
-                    "sequence_type": "dna",
-                    "sequence_id": "ga4gh:SQ.map_test",
-                    "sequence_accessions": [VALID_CHR_ACCESSION],
-                },
-            },
-            "c": {
-                "mapped_reference_sequence": {
-                    "sequence_accessions": [VALID_NT_ACCESSION],
-                },
-            },
+            "gene_info": TEST_GENE_INFO,
+            "layers": {"g": TEST_GENOMIC_LAYER, "c": TEST_CODING_LAYER},
         }
     },
     "mapped_scores": [],
@@ -1222,23 +1233,8 @@
     "metadata": {},
     "reference_sequences": {
         "TEST2": {
-            "g": {
-                "computed_reference_sequence": {
-                    "sequence_type": "dna",
-                    "sequence_id": "ga4gh:SQ.ref_test",
-                    "sequence": "ACGTTT",
-                },
-                "mapped_reference_sequence": {
-                    "sequence_type": "dna",
-                    "sequence_id": "ga4gh:SQ.map_test",
-                    "sequence_accessions": [VALID_CHR_ACCESSION],
-                },
-            },
-            "c": {
-                "mapped_reference_sequence": {
-                    "sequence_accessions": [VALID_NT_ACCESSION],
-                },
-            },
+            "gene_info": TEST_GENE_INFO,
+            "layers": {"g": TEST_GENOMIC_LAYER, "c": TEST_CODING_LAYER},
         }
     },
     "mapped_scores": [],
@@ -1251,42 +1247,12 @@
     "metadata": {},
     "reference_sequences": {
         "TEST3": {
-            "g": {
-                "computed_reference_sequence": {
-                    "sequence_type": "dna",
-                    "sequence_id": "ga4gh:SQ.ref_test3",
-                    "sequence": "ACGTTT",
-                },
-                "mapped_reference_sequence": {
-                    "sequence_type": "dna",
-                    "sequence_id": "ga4gh:SQ.map_test",
-                    "sequence_accessions": [VALID_CHR_ACCESSION],
-                },
-            },
-            "c": {
-                "mapped_reference_sequence": {
-                    "sequence_accessions": [VALID_NT_ACCESSION],
-                },
-            },
+            "gene_info": TEST_GENE_INFO,
+            "layers": {"g": TEST_GENOMIC_LAYER, "c": TEST_CODING_LAYER},
         },
         "TEST4": {
-            "g": {
-                "computed_reference_sequence": {
-                    "sequence_type": "dna",
-                    "sequence_id": "ga4gh:SQ.ref_test4",
-                    "sequence": "TAATGCC",
-                },
-                "mapped_reference_sequence": {
-                    "sequence_type": "dna",
-                    "sequence_id": "ga4gh:SQ.map_test",
-                    "sequence_accessions": [VALID_CHR_ACCESSION],
-                },
-            },
-            "c": {
-                "mapped_reference_sequence": {
-                    "sequence_accessions": [VALID_NT_ACCESSION],
-                },
-            },
+            "gene_info": TEST_GENE_INFO,
+            "layers": {"g": TEST_GENOMIC_LAYER, "c": TEST_CODING_LAYER},
         },
     },
     "mapped_scores": [],