build!: update ga4gh.vrs + gene/variation normalizers (#389)

close #305

* Update domain entity and entity class names
* Update tests to add `SequenceLocation.sequence`
* Update FastAPI configs to include response model and return Pydantic
models instead of dict

Pipfile

@@ -4,9 +4,9 @@ verify_ssl = true
 name = "pypi"
 
 [packages]
-"ga4gh.vrs" = "~=2.0.0a8"
-gene-normalizer = {version = "~=0.4.0", extras = ["etl"]}
-variation-normalizer = "~=0.9.1"
+"ga4gh.vrs" = "~=2.0.0a10"
+gene-normalizer = {version = "~=0.4.1", extras = ["etl"]}
+variation-normalizer = "~=0.10.0"
 disease-normalizer = {version = "~=0.5.0", extras = ["etl"]}
 thera-py = {version = "~=0.6.0", extras = ["etl"]}
 civicpy = "~=3.1"

pyproject.toml

@@ -23,9 +23,9 @@ requires-python = ">=3.10"
 description = "A search interface for cancer variant interpretations assembled by aggregating and harmonizing across multiple cancer variant interpretation knowledgebases."
 license = {file = "LICENSE"}
 dependencies = [
-    "ga4gh.vrs~=2.0.0a8",
-    "gene-normalizer[etl]~=0.4.0",
-    "variation-normalizer~=0.9.1",
+    "ga4gh.vrs~=2.0.0a10",
+    "gene-normalizer[etl]~=0.4.1",
+    "variation-normalizer~=0.10.0",
     "disease-normalizer[etl]~=0.5.0",
     "thera-py[etl]~=0.6.0",
     "civicpy~=3.1",

src/metakb/load_data.py

@@ -195,7 +195,7 @@ def _add_location(tx: ManagedTransaction, location_in: dict) -> None:
     loc = location_in.copy()
     loc_keys = [
         f"loc.{key}=${key}"
-        for key in ("id", "digest", "start", "end", "type")
+        for key in ("id", "digest", "start", "end", "sequence", "type")
         if loc.get(key) is not None  # start could be 0
     ]
     loc["sequence_reference"] = json.dumps(loc["sequenceReference"])

src/metakb/main.py

@@ -84,6 +84,8 @@ def custom_openapi() -> dict:
 @app.get(
     "/api/v2/search/studies",
     summary=search_studies_summary,
+    response_model=SearchStudiesService,
+    response_model_exclude_none=True,
     description=search_studies_descr,
 )
 async def get_studies(
@@ -94,7 +96,7 @@ async def get_studies(
     study_id: Annotated[str | None, Query(description=s_description)] = None,
     start: Annotated[int, Query(description=start_description)] = 0,
     limit: Annotated[int | None, Query(description=limit_description)] = None,
-) -> dict:
+) -> SearchStudiesService:
     """Get nested studies from queried concepts that match all conditions provided.
     For example, if `variation` and `therapy` are provided, will return all studies
     that have both the provided `variation` and `therapy`.
@@ -125,7 +127,7 @@ async def get_studies(
             service_meta_=ServiceMeta(),
             warnings=["`start` and `limit` params must both be nonnegative"],
         )
-    return resp.model_dump(exclude_none=True)
+    return resp
 
 
 _batch_descr = {
@@ -140,6 +142,8 @@ async def get_studies(
 @app.get(
     "/api/v2/batch_search/studies",
     summary=_batch_descr["summary"],
+    response_model=BatchSearchStudiesService,
+    response_model_exclude_none=True,
     description=_batch_descr["description"],
 )
 async def batch_get_studies(
@@ -149,7 +153,7 @@ async def batch_get_studies(
     ] = None,
     start: Annotated[int, Query(description=_batch_descr["arg_start"])] = 0,
     limit: Annotated[int | None, Query(description=_batch_descr["arg_limit"])] = None,
-) -> dict:
+) -> BatchSearchStudiesService:
     """Fetch all studies associated with `any` of the provided variations.
 
     :param variations: variations to match against
@@ -166,4 +170,4 @@ async def batch_get_studies(
             warnings=["`start` and `limit` params must both be nonnegative"],
         )
 
-    return response.model_dump(exclude_none=True)
+    return response

src/metakb/schemas/annotation.py

@@ -4,7 +4,7 @@
 from enum import Enum
 from typing import Literal
 
-from ga4gh.core.entity_models import IRI, Coding, _DomainEntity, _Entity
+from ga4gh.core.entity_models import IRI, Coding, DomainEntity, Entity
 from pydantic import Field, StrictInt, StrictStr, constr, field_validator
 
 
@@ -24,7 +24,7 @@ class Direction(str, Enum):
     NONE = "none"
 
 
-class Document(_DomainEntity):
+class Document(DomainEntity):
     """a representation of a physical or digital document"""
 
     type: Literal["Document"] = "Document"
@@ -42,7 +42,7 @@ class Document(_DomainEntity):
     )
 
 
-class Method(_Entity):
+class Method(Entity):
     """A set of instructions that specify how to achieve some objective (e.g.
     experimental protocols, curation guidelines, rule sets, etc.)
     """
@@ -57,7 +57,7 @@ class Method(_Entity):
     )
 
 
-class Agent(_Entity):
+class Agent(Entity):
     """An autonomous actor (person, organization, or computational agent) that bears
     some form of responsibility for an activity taking place, for the existence of an
     entity, or for another agent's activity.
@@ -68,7 +68,7 @@ class Agent(_Entity):
     subtype: AgentSubtype | None = None
 
 
-class Contribution(_Entity):
+class Contribution(Entity):
     """The sum of all actions taken by a single agent in contributing to the creation,
     modification, assessment, or deprecation of a particular entity (e.g. a Statement,
     EvidenceLine, DataItem, Publication, etc.)
@@ -99,7 +99,7 @@ def date_format(cls, v: str | None) -> str | None:
         return v
 
 
-class _InformationEntity(_Entity):
+class _InformationEntity(Entity):
     """InformationEntities are abstract (non-physical) entities that are about something
     (i.e. they carry information about things in the real world).
     """

src/metakb/schemas/categorical_variation.py

@@ -7,7 +7,7 @@
 from enum import Enum
 from typing import Literal
 
-from ga4gh.core.entity_models import IRI, _DomainEntity
+from ga4gh.core.entity_models import IRI, DomainEntity
 from ga4gh.vrs import models
 from pydantic import Field, RootModel, StrictStr
 
@@ -28,7 +28,7 @@ class LocationMatchCharacteristic(str, Enum):
     SUPERINTERVAL = "superinterval"
 
 
-class _CategoricalVariationBase(_DomainEntity):
+class _CategoricalVariationBase(DomainEntity):
     """Base class for Categorical Variation"""
 
     members: list[models.Variation | IRI] | None = Field(

tests/conftest.py

@@ -188,6 +188,7 @@ def civic_mpid33(civic_vid33):
                     },
                     "start": 55191821,
                     "end": 55191822,
+                    "sequence": "T",
                 },
                 "state": {"type": "LiteralSequenceExpression", "sequence": "G"},
             }
@@ -362,6 +363,7 @@ def civic_vid12():
             },
             "start": 599,
             "end": 600,
+            "sequence": "V",
         },
         "state": {"sequence": "E", "type": "LiteralSequenceExpression"},
         "expressions": [
@@ -396,6 +398,7 @@ def braf_v600e_genomic():
             },
             "start": 140753335,
             "end": 140753336,
+            "sequence": "A",
         },
         "state": {"type": "LiteralSequenceExpression", "sequence": "T"},
     }
@@ -1737,6 +1740,7 @@ def moa_vid66():
                     },
                     "start": 133748282,
                     "end": 133748283,
+                    "sequence": "C",
                 },
                 "state": {"type": "LiteralSequenceExpression", "sequence": "T"},
             }

tests/unit/database/test_database.py

@@ -384,6 +384,7 @@ def test_location_rules(
         "sequence_reference",
         "start",
         "end",
+        "sequence",
         "type",
     }
     assert json.loads(loc["sequence_reference"]) == {