Merge branch 'release-2024.4.2' into estelle/excludeMetaAnalysisExperiment

Author: EstelleDa

alembic/versions/2b6f40ea2fb6_add_score_range_column.py

@@ -1,7 +1,7 @@
 """Add score range column
 
 Revision ID: 2b6f40ea2fb6
-Revises: 1d4933b4b6f7
+Revises: 1cee01c42909
 Create Date: 2024-09-09 12:25:33.180077
 
 """

alembic/versions/68a0ec57694e_add_active_column_to_licenses.py

@@ -0,0 +1,29 @@
+"""Add active column to licenses
+
+Revision ID: 68a0ec57694e
+Revises: 03c7124c33e1
+Create Date: 2024-10-22 15:36:41.868909
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "68a0ec57694e"
+down_revision = "03c7124c33e1"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column("licenses", sa.Column("active", sa.Boolean(), nullable=False, server_default=sa.true()))
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("licenses", "active")
+    # ### end Alembic commands ###

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "mavedb"
-version = "2024.4.1"
+version = "2024.4.2"
 description = "API for MaveDB, the database of Multiplexed Assays of Variant Effect."
 license = "AGPL-3.0-only"
 readme = "README.md"
@@ -99,6 +99,7 @@ mypy_path = "mypy_stubs"
 addopts = "-v -rP --import-mode=importlib --disable-socket --allow-hosts localhost,::1,127.0.0.1"
 asyncio_mode = 'strict'
 testpaths = "tests/"
+pythonpath = "."
 norecursedirs = "tests/helpers/"
 # Uncomment the following lines to include application log output in Pytest logs.
 # log_cli = true

src/mavedb/__init__.py

@@ -6,6 +6,6 @@
 logger = module_logging.getLogger(__name__)
 
 __project__ = "mavedb-api"
-__version__ = "2024.4.1"
+__version__ = "2024.4.2"
 
 logger.info(f"MaveDB {__version__}")

src/mavedb/lib/script_environment.py

@@ -0,0 +1,56 @@
+import logging
+from typing import Optional
+
+from sqlalchemy import func, or_
+from sqlalchemy.orm import Session
+
+from mavedb.lib.logging.context import logging_context, save_to_logging_context
+from mavedb.models.contributor import Contributor
+from mavedb.models.score_set import ScoreSet
+from mavedb.models.target_gene import TargetGene
+from mavedb.models.user import User
+from mavedb.view_models.search import TextSearch
+
+logger = logging.getLogger(__name__)
+
+
+def search_target_genes(
+    db: Session,
+    owner_or_contributor: Optional[User],
+    search: TextSearch,
+    limit: Optional[int],
+) -> list[TargetGene]:
+    save_to_logging_context({"target_gene_search_criteria": search.dict()})
+
+    query = db.query(TargetGene)
+
+    if search.text and len(search.text.strip()) > 0:
+        lower_search_text = search.text.strip().lower()
+        query = query.filter(func.lower(TargetGene.name).contains(lower_search_text))
+    if owner_or_contributor is not None:
+        query = query.filter(
+            TargetGene.score_set.has(
+                or_(
+                    ScoreSet.created_by_id == owner_or_contributor.id,
+                    ScoreSet.contributors.any(
+                        Contributor.orcid_id == owner_or_contributor.username
+                    ),
+                )
+            )
+        )
+
+    query = query.order_by(TargetGene.name)
+    if limit is not None:
+        query = query.limit(limit)
+
+    target_genes = query.all()
+    if not target_genes:
+        target_genes = []
+
+    save_to_logging_context({"matching_resources": len(target_genes)})
+    logger.debug(
+        msg=f"Target gene search yielded {len(target_genes)} matching resources.",
+        extra=logging_context(),
+    )
+
+    return target_genes

src/mavedb/lib/target_genes.py

@@ -1,6 +1,6 @@
 from datetime import date
 
-from sqlalchemy import Column, Date, Integer, String
+from sqlalchemy import Boolean, Column, Date, Integer, String
 
 from mavedb.db.base import Base
 
@@ -16,3 +16,4 @@ class License(Base):
     version = Column(String, nullable=True, unique=False)
     creation_date = Column(Date, nullable=False, default=date.today)
     modification_date = Column(Date, nullable=False, default=date.today, onupdate=date.today)
+    active = Column(Boolean, nullable=False)

src/mavedb/models/license.py

@@ -14,8 +14,8 @@ class MappedVariant(Base):
 
     id = Column(Integer, primary_key=True)
 
-    pre_mapped = Column(JSONB, nullable=True)
-    post_mapped = Column(JSONB, nullable=True)
+    pre_mapped = Column(JSONB(none_as_null=True), nullable=True)
+    post_mapped = Column(JSONB(none_as_null=True), nullable=True)
     vrs_version = Column(String, nullable=True)
     error_message = Column(String, nullable=True)
     modification_date = Column(Date, nullable=False, default=date.today, onupdate=date.today)

src/mavedb/models/mapped_variant.py

@@ -23,6 +23,19 @@ def list_licenses(
     return items
 
 
+@router.get("/active", status_code=200, response_model=List[license.ShortLicense], responses={404: {}})
+def list_active_licenses(
+    *,
+    db: Session = Depends(deps.get_db),
+) -> Any:
+    """
+    List active licenses.
+    """
+
+    items = db.query(License).where(License.active.is_(True)).order_by(License.short_name).all()
+    return items
+
+
 @router.get("/{item_id}", status_code=200, response_model=license.License, responses={404: {}})
 def fetch_license(
     *,

src/mavedb/routers/licenses.py

@@ -348,6 +348,11 @@ async def create_score_set(
     if not license_:
         logger.info(msg="Failed to create score set; The requested license does not exist.", extra=logging_context())
         raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Unknown license")
+    elif not license_.active:
+        logger.info(
+            msg="Failed to create score set; The requested license is no longer active.", extra=logging_context()
+        )
+        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid license")
 
     save_to_logging_context({"requested_superseded_score_set": item_create.superseded_score_set_urn})
     if item_create.superseded_score_set_urn is not None:
@@ -651,7 +656,9 @@ async def upload_score_set_variant_data(
     return item
 
 
-@router.put("/score-sets/{urn}", response_model=score_set.ScoreSet, responses={422: {}})
+@router.put(
+    "/score-sets/{urn}", response_model=score_set.ScoreSet, responses={422: {}}, response_model_exclude_none=True
+)
 async def update_score_set(
     *,
     urn: str,
@@ -673,68 +680,73 @@ async def update_score_set(
 
     assert_permission(user_data, item, Action.UPDATE)
 
-    # Editing unpublished score set
-    if item.private is True:
-        license_ = None
-
-        if item_update.license_id is not None:
-            save_to_logging_context({"license": item_update.license_id})
-            license_ = db.query(License).filter(License.id == item_update.license_id).one_or_none()
+    for var, value in vars(item_update).items():
+        if var not in [
+            "contributors",
+            "score_ranges",
+            "doi_identifiers",
+            "experiment_urn",
+            "license_id",
+            "secondary_publication_identifiers",
+            "primary_publication_identifiers",
+            "target_genes",
+        ]:
+            setattr(item, var, value) if value else None
+
+    if item_update.license_id is not None:
+        save_to_logging_context({"license": item_update.license_id})
+        license_ = db.query(License).filter(License.id == item_update.license_id).one_or_none()
+
+        if not license_:
+            logger.info(
+                msg="Failed to update score set; The requested license does not exist.", extra=logging_context()
+            )
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Unknown license")
 
-            if not license_:
-                logger.info(
-                    msg="Failed to update score set; The requested license does not exist.", extra=logging_context()
-                )
-                raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Unknown license")
+            # Allow in-active licenses to be retained on update if they already exist on the item.
+        elif not license_.active and item.licence_id != item_update.license_id:
+            logger.info(
+                msg="Failed to update score set license; The requested license is no longer active.",
+                extra=logging_context(),
+            )
+            raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid license")
 
-            item.license = license_
+        item.license = license_
 
-        for var, value in vars(item_update).items():
-            if var not in [
-                "contributors",
-                "score_ranges",
-                "doi_identifiers",
-                "experiment_urn",
-                "license_id",
-                "secondary_publication_identifiers",
-                "primary_publication_identifiers",
-                "target_genes",
-            ]:
-                setattr(item, var, value) if value else None
-
-        try:
-            item.contributors = [
-                await find_or_create_contributor(db, contributor.orcid_id)
-                for contributor in item_update.contributors or []
-            ]
-        except NonexistentOrcidUserError as e:
-            logger.error(msg="Could not find ORCID user with the provided user ID.", extra=logging_context())
-            raise pydantic.ValidationError(
-                [pydantic.error_wrappers.ErrorWrapper(ValidationError(str(e)), loc="contributors")],
-                model=score_set.ScoreSetUpdate,
-            )
+    item.doi_identifiers = [
+        await find_or_create_doi_identifier(db, identifier.identifier)
+        for identifier in item_update.doi_identifiers or []
+    ]
+    primary_publication_identifiers = [
+        await find_or_create_publication_identifier(db, identifier.identifier, identifier.db_name)
+        for identifier in item_update.primary_publication_identifiers or []
+    ]
+    publication_identifiers = [
+        await find_or_create_publication_identifier(db, identifier.identifier, identifier.db_name)
+        for identifier in item_update.secondary_publication_identifiers or []
+    ] + primary_publication_identifiers
 
-        item.doi_identifiers = [
-            await find_or_create_doi_identifier(db, identifier.identifier)
-            for identifier in item_update.doi_identifiers or []
-        ]
-        primary_publication_identifiers = [
-            await find_or_create_publication_identifier(db, identifier.identifier, identifier.db_name)
-            for identifier in item_update.primary_publication_identifiers or []
-        ]
-        publication_identifiers = [
-            await find_or_create_publication_identifier(db, identifier.identifier, identifier.db_name)
-            for identifier in item_update.secondary_publication_identifiers or []
-        ] + primary_publication_identifiers
+    # create a temporary `primary` attribute on each of our publications that indicates
+    # to our association proxy whether it is a primary publication or not
+    primary_identifiers = [p.identifier for p in primary_publication_identifiers]
+    for publication in publication_identifiers:
+        setattr(publication, "primary", publication.identifier in primary_identifiers)
 
-        # create a temporary `primary` attribute on each of our publications that indicates
-        # to our association proxy whether it is a primary publication or not
-        primary_identifiers = [pub.identifier for pub in primary_publication_identifiers]
-        for publication in publication_identifiers:
-            setattr(publication, "primary", publication.identifier in primary_identifiers)
+    item.publication_identifiers = publication_identifiers
 
-        item.publication_identifiers = publication_identifiers
+    try:
+        item.contributors = [
+            await find_or_create_contributor(db, contributor.orcid_id) for contributor in item_update.contributors or []
+        ]
+    except NonexistentOrcidUserError as e:
+        logger.error(msg="Could not find ORCID user with the provided user ID.", extra=logging_context())
+        raise pydantic.ValidationError(
+            [pydantic.error_wrappers.ErrorWrapper(ValidationError(str(e)), loc="contributors")],
+            model=score_set.ScoreSetUpdate,
+        )
 
+    # Score set has not been published and attributes affecting scores may still be edited.
+    if item.private:
         if item_update.score_ranges:
             item.score_ranges = item_update.score_ranges.dict()
         else:
@@ -889,35 +901,8 @@ async def update_score_set(
             if job is not None:
                 save_to_logging_context({"worker_job_id": job.job_id})
             logger.info(msg="Enqueud variant creation job.", extra=logging_context())
-
-        for var, value in vars(item_update).items():
-            if var not in [
-                "score_ranges",
-                "contributors",
-                "doi_identifiers",
-                "experiment_urn",
-                "primary_publication_identifiers",
-                "secondary_publication_identifiers",
-                "target_genes",
-            ]:
-                setattr(item, var, value) if value else None
-
-    # Editing published score set
     else:
-        for var, value in vars(item_update).items():
-            if var in ["title", "method_text", "abstract_text", "short_description"]:
-                setattr(item, var, value) if value else None
-        try:
-            item.contributors = [
-                await find_or_create_contributor(db, contributor.orcid_id)
-                for contributor in item_update.contributors or []
-            ]
-        except NonexistentOrcidUserError as e:
-            logger.error(msg="Could not find ORCID user with the provided user ID.", extra=logging_context())
-            raise pydantic.ValidationError(
-                [pydantic.error_wrappers.ErrorWrapper(ValidationError(str(e)), loc="contributors")],
-                model=score_set.ScoreSetUpdate,
-            )
+        logger.debug(msg="Skipped score range and target gene update. Score set is published.", extra=logging_context())
 
     db.add(item)
     db.commit()