Merge pull request #362 from VariantEffect/release-2024.4.2

Release 2024.4.2

alembic/manual_migrations/migrate_non_api_like_constants.py

@@ -0,0 +1,40 @@
+import sqlalchemy as sa
+from sqlalchemy.orm import Session, configure_mappers
+
+from mavedb.models import *
+from mavedb.models.enums.target_category import TargetCategory
+from mavedb.models.target_gene import TargetGene
+
+from mavedb.db.session import SessionLocal
+
+configure_mappers()
+
+def api_like_target_gene_category(category: str):
+    if category == "Protein coding":
+        return TargetCategory.protein_coding
+    elif category == "Other noncoding":
+        return TargetCategory.other_noncoding
+    elif category == "Regulatory":
+        return TargetCategory.regulatory
+    else:
+        raise ValueError()
+
+
+def do_migration(db: Session):
+    target_genes = db.scalars(sa.select(TargetGene)).all()
+
+    for target in target_genes:
+        target.category = api_like_target_gene_category(target.category)
+        db.add(target)
+
+    db.commit()
+
+
+if __name__ == "__main__":
+    db = SessionLocal()
+    db.current_user = None  # type: ignore
+
+    do_migration(db)
+
+    db.commit()
+    db.close()

alembic/manual_migrations/refresh_published_tmp_urns.py

@@ -0,0 +1,33 @@
+import sqlalchemy as sa
+from sqlalchemy.orm import Session, configure_mappers
+
+from mavedb.models import *
+
+from mavedb.lib.score_sets import refresh_variant_urns
+
+from mavedb.models.score_set import ScoreSet
+from mavedb.models.variant import Variant
+
+from mavedb.db.session import SessionLocal
+
+configure_mappers()
+
+
+def do_migration(db: Session):
+    published_score_sets_with_associated_tmp_variants: sa.ScalarResult[str]
+    published_score_sets_with_associated_tmp_variants = db.execute(
+        sa.select(sa.distinct(ScoreSet.urn)).join(Variant).where(ScoreSet.published_date.is_not(None), Variant.urn.like("%tmp:%"))
+    ).scalars()
+
+    for score_set_urn in published_score_sets_with_associated_tmp_variants:
+        refresh_variant_urns(db, db.execute(sa.select(ScoreSet).where(ScoreSet.urn == score_set_urn)).scalar_one())
+
+
+if __name__ == "__main__":
+    db = SessionLocal()
+    db.current_user = None  # type: ignore
+
+    do_migration(db)
+
+    db.commit()
+    db.close()

alembic/versions/03c7124c33e1_target_category_enum.py

@@ -0,0 +1,54 @@
+"""Target category enum
+
+Revision ID: 03c7124c33e1
+Revises: 2b6f40ea2fb6
+Create Date: 2024-11-01 11:27:03.609116
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "03c7124c33e1"
+down_revision = "2b6f40ea2fb6"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.alter_column(
+        "target_genes",
+        "category",
+        type_=sa.Enum(
+            "protein_coding",
+            "other_noncoding",
+            "regulatory",
+            name="targetcategory",
+            native_enum=False,
+            create_constraint=True,
+            length=32,
+        ),
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.alter_column(
+        "target_genes",
+        "category",
+        type_=sa.String(),
+        existing_type=sa.Enum(
+            "protein_coding",
+            "other_noncoding",
+            "regulatory",
+            name="targetcategory",
+            native_enum=False,
+            create_constraint=True,
+            length=32,
+        ),
+    )
+    # ### end Alembic commands ###

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"
@@ -26,7 +26,7 @@ python = "^3.9"
 
 fqfa = "~1.3.0"
 pyhumps = "~3.8.0"
-pyyaml = "~5.1"
+pyyaml = "~6.0.1"
 IDUtils = "~1.2.0"
 mavehgvs = "~0.6.0"
 eutils = "~0.6.0"
@@ -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/experiments.py

@@ -99,7 +99,7 @@ def search_experiments(
             )
         )
 
-    items: list[Experiment] = query.order_by(Experiment.title).all()
+    items: list[Experiment] = query.order_by(Experiment.urn, Experiment.title).all()
     if not items:
         items = []
 

src/mavedb/lib/score_sets.py

@@ -617,6 +617,21 @@ def create_variants(db, score_set: ScoreSet, variants_data: list[VariantData], b
     return len(score_set.variants)
 
 
+def refresh_variant_urns(db: Session, score_set: ScoreSet):
+    variants = db.execute(select(Variant).where(Variant.score_set_id == score_set.id)).scalars()
+
+    for variant in variants:
+        if not variant.urn:
+            raise ValueError("All variants should have an associated URN.")
+
+        variant_number = variant.urn.split("#")[1]
+        refreshed_urn = f"{score_set.urn}#{variant_number}"
+        variant.urn = refreshed_urn
+        db.add(variant)
+
+    db.commit()
+
+
 def bulk_create_urns(n, score_set, reset_counter=False) -> list[str]:
     start_value = 0 if reset_counter else score_set.num_variants
     parent_urn = score_set.urn

src/mavedb/lib/target_genes.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/validation/constants/target.py

@@ -1,2 +1 @@
-valid_categories = ["Protein coding", "Regulatory", "Other noncoding"]
 valid_sequence_types = ["infer", "dna", "protein"]

src/mavedb/lib/validation/target.py

@@ -1,31 +1,10 @@
 from fqfa import infer_sequence_type
 from fqfa.validator import amino_acids_validator, dna_bases_validator
 
-from mavedb.lib.validation.constants.target import valid_categories, valid_sequence_types
+from mavedb.lib.validation.constants.target import valid_sequence_types
 from mavedb.lib.validation.exceptions import ValidationError
 
 
-def validate_target_category(category: str):
-    """
-    If the target category provided does not fall within a pre-defined list of valid categories.
-
-    Parameters
-    __________
-    category: str
-        The target category to be validated.
-
-    Raises
-    ______
-    ValidationError
-        If the target category provided is not valid.
-    """
-    if category not in valid_categories:
-        raise ValidationError(
-            "{} is not a valid target category. Valid categories are "
-            "Protein coding, Regulatory, and Other noncoding".format(category)
-        )
-
-
 def validate_sequence_category(sequence_type: str):
     """
     If the sequence type provided does not fall within a pre-defined list of valid sequence types.

src/mavedb/models/enums/target_category.py

@@ -0,0 +1,7 @@
+from enum import Enum
+
+
+class TargetCategory(str, Enum):
+    protein_coding = "protein_coding"
+    regulatory = "regulatory"
+    other_noncoding = "other_noncoding"

src/mavedb/models/license.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/mapped_variant.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)