Merge pull request #516 from VariantEffect/release-2025.4.0

Release 2025.4.0

Author: jstone-dev

alembic/versions/019eb75ad9ae_rename_tax_id_to_code.py

@@ -5,24 +5,25 @@
 Create Date: 2025-08-20 16:21:15.872816
 
 """
+
 from alembic import op
 import sqlalchemy as sa
 
 
 # revision identifiers, used by Alembic.
-revision = '019eb75ad9ae'
-down_revision = '0b29eefbe1dd'
+revision = "019eb75ad9ae"
+down_revision = "0b29eefbe1dd"
 branch_labels = None
 depends_on = None
 
 
 def upgrade():
     # ### commands auto generated by Alembic - please adjust! ###
-    op.alter_column('taxonomies', 'tax_id', new_column_name='code', existing_type=sa.Integer(), existing_nullable=False)
+    op.alter_column("taxonomies", "tax_id", new_column_name="code", existing_type=sa.Integer(), existing_nullable=False)
     # ### end Alembic commands ###
 
 
 def downgrade():
     # ### commands auto generated by Alembic - please adjust! ###
-    op.alter_column('taxonomies', 'code', new_column_name='tax_id', existing_type=sa.Integer(), existing_nullable=False)
+    op.alter_column("taxonomies", "code", new_column_name="tax_id", existing_type=sa.Integer(), existing_nullable=False)
     # ### end Alembic commands ###

alembic/versions/0b29eefbe1dd_controlled_keyword_modification.py

@@ -5,28 +5,33 @@
 Create Date: 2025-08-07 15:45:43.241567
 
 """
+
 from alembic import op
 import sqlalchemy as sa
 
 
 # revision identifiers, used by Alembic.
-revision = '0b29eefbe1dd'
-down_revision = '2b7a977e7e98'
+revision = "0b29eefbe1dd"
+down_revision = "2b7a977e7e98"
 branch_labels = None
 depends_on = None
 
 
 def upgrade():
     # ### commands auto generated by Alembic - please adjust! ###
     # Rename existing columns
-    op.alter_column('controlled_keywords', 'value', new_column_name='label', existing_type=sa.String(), existing_nullable=False)
-    op.alter_column('controlled_keywords', 'vocabulary', new_column_name='system', existing_type=sa.String(), existing_nullable=True)
+    op.alter_column(
+        "controlled_keywords", "value", new_column_name="label", existing_type=sa.String(), existing_nullable=False
+    )
+    op.alter_column(
+        "controlled_keywords", "vocabulary", new_column_name="system", existing_type=sa.String(), existing_nullable=True
+    )
     # Add new columns
-    op.add_column('controlled_keywords', sa.Column('code', sa.String(), nullable=True))
-    op.add_column('controlled_keywords', sa.Column('version', sa.String(), nullable=True))
+    op.add_column("controlled_keywords", sa.Column("code", sa.String(), nullable=True))
+    op.add_column("controlled_keywords", sa.Column("version", sa.String(), nullable=True))
     # Drop and recreate the correct unique constraint
-    op.drop_constraint('ix_controlled_keywords_key_value', 'controlled_keywords', type_='unique')
-    op.create_unique_constraint('ix_controlled_keywords_key_label', 'controlled_keywords', ['key', 'label'])
+    op.drop_constraint("ix_controlled_keywords_key_value", "controlled_keywords", type_="unique")
+    op.create_unique_constraint("ix_controlled_keywords_key_label", "controlled_keywords", ["key", "label"])
     # ### end Alembic commands ###
 
     # TODO: Will modify this part when we get the final GO terms.
@@ -37,10 +42,14 @@ def upgrade():
 
 def downgrade():
     # ### commands auto generated by Alembic - please adjust! ###
-    op.alter_column('controlled_keywords', 'label', new_column_name='value', existing_type=sa.String(), existing_nullable=False)
-    op.alter_column('controlled_keywords', 'system', new_column_name='vocabulary', existing_type=sa.String(), existing_nullable=True)
-    op.drop_constraint('ix_controlled_keywords_key_label', 'controlled_keywords', type_='unique')
-    op.create_unique_constraint('ix_controlled_keywords_key_value', 'controlled_keywords', ['key', 'value'])
-    op.drop_column('controlled_keywords', 'version')
-    op.drop_column('controlled_keywords', 'code')
+    op.alter_column(
+        "controlled_keywords", "label", new_column_name="value", existing_type=sa.String(), existing_nullable=False
+    )
+    op.alter_column(
+        "controlled_keywords", "system", new_column_name="vocabulary", existing_type=sa.String(), existing_nullable=True
+    )
+    op.drop_constraint("ix_controlled_keywords_key_label", "controlled_keywords", type_="unique")
+    op.create_unique_constraint("ix_controlled_keywords_key_value", "controlled_keywords", ["key", "value"])
+    op.drop_column("controlled_keywords", "version")
+    op.drop_column("controlled_keywords", "code")
     # ### end Alembic commands ###

src/mavedb/lib/clingen/content_constructors.py

@@ -54,7 +54,9 @@ def construct_ldh_submission_entity(variant: Variant, mapped_variant: Optional[M
     return entity
 
 
-def construct_ldh_submission(variant_content: list[tuple[str, Variant, Optional[MappedVariant]]]) -> list[LdhSubmission]:
+def construct_ldh_submission(
+    variant_content: list[tuple[str, Variant, Optional[MappedVariant]]],
+) -> list[LdhSubmission]:
     content_submission: list[LdhSubmission] = []
     for hgvs, variant, mapped_variant in variant_content:
         subject = construct_ldh_submission_subject(hgvs)

src/mavedb/lib/target_genes.py

@@ -32,9 +32,7 @@ def search_target_genes(
             TargetGene.score_set.has(
                 or_(
                     ScoreSet.created_by_id == owner_or_contributor.id,
-                    ScoreSet.contributors.any(
-                        Contributor.orcid_id == owner_or_contributor.username
-                    ),
+                    ScoreSet.contributors.any(Contributor.orcid_id == owner_or_contributor.username),
                 )
             )
         )

src/mavedb/lib/validation/dataframe/column.py

@@ -73,38 +73,49 @@ def validate_variant_formatting(column: pd.Series, prefixes: list[str], targets:
 
     # if there is more than one target, we expect variants to be fully qualified
     if fully_qualified:
-        invalid_fully_qualified = [f"{len(str(v).split(':'))} invalid fully qualified found from row {idx}"
-                                   for idx, v in enumerate(variants) if len(str(v).split(":")) != 2]
+        invalid_fully_qualified = [
+            f"{len(str(v).split(':'))} invalid fully qualified found from row {idx}"
+            for idx, v in enumerate(variants)
+            if len(str(v).split(":")) != 2
+        ]
         if invalid_fully_qualified:
             raise ValidationError(
                 f"variant column '{column.name}' has {len(invalid_fully_qualified)} unqualified variants.",
-                triggers=invalid_fully_qualified
+                triggers=invalid_fully_qualified,
             )
 
-        inconsistent_prefixes = [f"row {idx}: '{v}' uses inconsistent prefix '{str(v).split(':')[1][:2]}'"
-                                 for idx, v in enumerate(variants)
-                                 if len(set(str(v).split(":")[1][:2] for v in variants)) > 1]
+        inconsistent_prefixes = [
+            f"row {idx}: '{v}' uses inconsistent prefix '{str(v).split(':')[1][:2]}'"
+            for idx, v in enumerate(variants)
+            if len(set(str(v).split(":")[1][:2] for v in variants)) > 1
+        ]
         if inconsistent_prefixes:
             raise ValidationError(
                 f"variant column '{column.name}' has {len(inconsistent_prefixes)} inconsistent variant prefixes.",
-                triggers=inconsistent_prefixes
+                triggers=inconsistent_prefixes,
             )
 
-        invalid_prefixes = [f"row {idx}: '{v}' uses invalid prefix '{str(v).split(':')[1][:2]}'"
-                            for idx, v in enumerate(variants) if str(v).split(":")[1][:2] not in prefixes]
+        invalid_prefixes = [
+            f"row {idx}: '{v}' uses invalid prefix '{str(v).split(':')[1][:2]}'"
+            for idx, v in enumerate(variants)
+            if str(v).split(":")[1][:2] not in prefixes
+        ]
         if invalid_prefixes:
             raise ValidationError(
                 f"variant column '{column.name}' has {len(invalid_prefixes)} invalid variant prefixes.",
-                triggers=invalid_prefixes
+                triggers=invalid_prefixes,
             )
 
-        invalid_accessions = [f"accession identifier {str(v).split(':')[0]} from row {idx}, variant {v} not found"
-                              for idx, v in enumerate(variants) if str(v).split(":")[0] not in targets]
+        invalid_accessions = [
+            f"accession identifier {str(v).split(':')[0]} from row {idx}, variant {v} not found"
+            for idx, v in enumerate(variants)
+            if str(v).split(":")[0] not in targets
+        ]
         if invalid_accessions:
             raise ValidationError(
                 f"variant column '{column.name}' has invalid accession identifiers; "
                 f"{len(invalid_accessions)} accession identifiers present in the score file were not added as targets.",
-                triggers=invalid_accessions
+                triggers=invalid_accessions,
             )
 
     else:

src/mavedb/lib/validation/dataframe/variant.py

@@ -217,7 +217,7 @@ def _validate_allelic_variation(variant: Variant) -> bool:
             If the variant is not a valid HGVS string (for reasons of transcript/variant inconsistency).
         """
 
-        for variant_sub_string in variant.components(): # type: ignore
+        for variant_sub_string in variant.components():  # type: ignore
             validator.validate(parser.parse(variant_sub_string), strict=False)
 
         return True

src/mavedb/lib/validation/keywords.py

@@ -1,16 +1,17 @@
-import re
 from typing import Optional
 
 from mavedb.lib.validation.exceptions import ValidationError
 from mavedb.lib.validation.utilities import is_null
 
 
 def validate_code(key: str, label: str, code: Optional[str]):
-    if key.lower() == "phenotypic assay mechanism" and label.lower() != "other":
-        # The Gene Ontology accession is a unique seven digit identifier prefixed by GO:.
-        # e.g. GO:0005739, GO:1904659, or GO:0016597.
-        if code is None or not re.match(r"^GO:\d{7}$", code):
-            raise ValidationError("Invalid Gene Ontology accession.")
+    # TODO(#511) Re-enable the Gene Ontology code requirement.
+    pass
+    # if key.lower() == "phenotypic assay mechanism" and label.lower() != "other":
+    #     # The Gene Ontology accession is a unique seven digit identifier prefixed by GO:.
+    #     # e.g. GO:0005739, GO:1904659, or GO:0016597.
+    #     if code is None or not re.match(r"^GO:\d{7}$", code):
+    #         raise ValidationError("Invalid Gene Ontology accession.")
 
 
 # TODO: label will not be Optional when we confirm the final controlled keyword list.

src/mavedb/routers/experiment_sets.py

@@ -52,13 +52,9 @@ def fetch_experiment_set(
 
     # Filter experiment sub-resources to only those experiments readable by the requesting user.
     item.experiments[:] = [exp for exp in item.experiments if has_permission(user_data, exp, Action.READ).permitted]
-    enriched_experiments = [
-        enrich_experiment_with_num_score_sets(exp, user_data)
-        for exp in item.experiments
-    ]
-    enriched_item = experiment_set.ExperimentSet.model_validate(item).copy(update={
-        "experiments": enriched_experiments,
-        "num_experiments": len(enriched_experiments)
-    })
+    enriched_experiments = [enrich_experiment_with_num_score_sets(exp, user_data) for exp in item.experiments]
+    enriched_item = experiment_set.ExperimentSet.model_validate(item).copy(
+        update={"experiments": enriched_experiments, "num_experiments": len(enriched_experiments)}
+    )
 
     return enriched_item

src/mavedb/routers/experiments.py

@@ -89,10 +89,7 @@ def search_experiments(search: ExperimentsSearch, db: Session = Depends(deps.get
     Search experiments.
     """
     items = _search_experiments(db, None, search)
-    return [
-        enrich_experiment_with_num_score_sets(exp, None)
-        for exp in items
-    ]
+    return [enrich_experiment_with_num_score_sets(exp, None) for exp in items]
 
 
 @router.post(
@@ -109,10 +106,7 @@ def search_my_experiments(
     Search experiments created by the current user..
     """
     items = _search_experiments(db, user_data.user, search)
-    return [
-            enrich_experiment_with_num_score_sets(exp, user_data)
-            for exp in items
-        ]
+    return [enrich_experiment_with_num_score_sets(exp, user_data) for exp in items]
 
 
 @router.get(
@@ -176,11 +170,7 @@ def get_experiment_score_sets(
     )
 
     filter_superseded_score_set_tails = [
-        find_superseded_score_set_tail(
-            score_set,
-            Action.READ,
-            user_data
-        ) for score_set in score_set_result
+        find_superseded_score_set_tail(score_set, Action.READ, user_data) for score_set in score_set_result
     ]
     filtered_score_sets = [score_set for score_set in filter_superseded_score_set_tails if score_set is not None]
     if not filtered_score_sets:

src/mavedb/routers/score_sets.py

@@ -1465,10 +1465,7 @@ async def get_clinical_controls_for_score_set(
         select(ClinicalControl)
         .join(ClinicalControl.mapped_variants)
         .join(MappedVariant.variant)
-        .options(
-            contains_eager(ClinicalControl.mapped_variants)
-            .contains_eager(MappedVariant.variant)
-        )
+        .options(contains_eager(ClinicalControl.mapped_variants).contains_eager(MappedVariant.variant))
         .filter(MappedVariant.current.is_(True))
         .filter(Variant.score_set_id == item.id)
     )