Merge branch 'release-2024.4.2' into estelle/excludeMetaAnalysisExperiment

Author: EstelleDa

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/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 ###

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/target_gene.py

@@ -1,11 +1,12 @@
 from datetime import date
 from typing import TYPE_CHECKING
 
-from sqlalchemy import Column, Date, ForeignKey, Integer, String
+from sqlalchemy import Column, Date, Enum, ForeignKey, Integer, String
 from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.orm import Mapped, backref, relationship
 
 from mavedb.db.base import Base
+from mavedb.models.enums.target_category import TargetCategory
 from mavedb.models.score_set import ScoreSet
 from mavedb.models.target_accession import TargetAccession
 from mavedb.models.target_sequence import TargetSequence
@@ -24,7 +25,10 @@ class TargetGene(Base):
     id = Column(Integer, primary_key=True)
 
     name = Column(String, nullable=False)
-    category = Column(String, nullable=False)
+    category = Column(
+        Enum(TargetCategory, create_constraint=True, length=32, native_enum=False, validate_strings=True),
+        nullable=False,
+    )
 
     score_set_id = Column("scoreset_id", Integer, ForeignKey("scoresets.id"), index=True, nullable=False)
     score_set: Mapped[ScoreSet] = relationship(back_populates="target_genes", single_parent=True, uselist=True)

src/mavedb/routers/score_sets.py

@@ -334,6 +334,10 @@ async def create_score_set(
                 msg="Failed to create score set; The requested experiment does not exist.", extra=logging_context()
             )
             raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Unknown experiment")
+        # Not allow add score set in meta-analysis experiments.
+        if any(s.meta_analyzes_score_sets for s in experiment.score_sets):
+            raise HTTPException(status_code=status.HTTP_403_FORBIDDEN,
+                                detail="Score sets may not be added to a meta-analysis experiment.")
 
         save_to_logging_context({"experiment": experiment.urn})
         assert_permission(user_data, experiment, Action.ADD_SCORE_SET)
@@ -386,7 +390,7 @@ async def create_score_set(
             )
 
     if len(meta_analyzes_score_sets) > 0:
-        # If any existing score set is a meta-analysis for score sets in the same collection of exepriment sets, use its
+        # If any existing score set is a meta-analysis for score sets in the same collection of experiment sets, use its
         # experiment as the parent of our new meta-analysis. Otherwise, create a new experiment.
         meta_analyzes_experiment_sets = list(
             set(

src/mavedb/view_models/target_gene.py

@@ -4,7 +4,7 @@
 from pydantic import root_validator
 from pydantic.utils import GetterDict
 
-from mavedb.lib.validation import target
+from mavedb.models.enums.target_category import TargetCategory
 from mavedb.view_models import external_gene_identifier_offset
 from mavedb.view_models.base.base import BaseModel, validator
 from mavedb.view_models.target_accession import SavedTargetAccession, TargetAccession, TargetAccessionCreate
@@ -40,18 +40,15 @@ class TargetGeneBase(BaseModel):
     """Base class for target gene view models."""
 
     name: str
-    category: str
+    category: TargetCategory
     external_identifiers: Sequence[external_gene_identifier_offset.ExternalGeneIdentifierOffsetBase]
 
     class Config:
         getter_dict: ExternalIdentifiersGetter
 
 
 class TargetGeneModify(TargetGeneBase):
-    @validator("category")
-    def validate_category(cls, v):
-        target.validate_target_category(v)
-        return v
+    pass
 
 
 class TargetGeneCreate(TargetGeneModify):

tests/helpers/constants.py

@@ -301,7 +301,7 @@
     "target_genes": [
         {
             "name": "TEST1",
-            "category": "Protein coding",
+            "category": "protein_coding",
             "external_identifiers": [],
             "target_sequence": {
                 "sequence_type": "dna",
@@ -327,7 +327,7 @@
     "targetGenes": [
         {
             "name": "TEST1",
-            "category": "Protein coding",
+            "category": "protein_coding",
             "externalIdentifiers": [],
             "targetSequence": {
                 "sequenceType": "dna",
@@ -369,7 +369,7 @@
     "targetGenes": [
         {
             "name": "TEST1",
-            "category": "Protein coding",
+            "category": "protein_coding",
             "externalIdentifiers": [],
             "id": 1,
             "targetSequence": {
@@ -413,7 +413,7 @@
     "targetGenes": [
         {
             "name": "TEST2",
-            "category": "Protein coding",
+            "category": "protein_coding",
             "externalIdentifiers": [],
             "targetAccession": {"accession": VALID_ACCESSION, "assembly": "GRCh37", "gene": VALID_GENE},
         }
@@ -428,7 +428,7 @@
     "target_genes": [
         {
             "name": "TEST2",
-            "category": "Protein coding",
+            "category": "protein_coding",
             "external_identifiers": [],
             "target_accession": {"accession": VALID_ACCESSION, "assembly": "GRCh37", "gene": VALID_GENE},
         }
@@ -457,7 +457,7 @@
     "targetGenes": [
         {
             "name": "TEST2",
-            "category": "Protein coding",
+            "category": "protein_coding",
             "externalIdentifiers": [],
             "targetAccession": {"accession": VALID_ACCESSION, "assembly": "GRCh37", "gene": VALID_GENE},
         }

tests/routers/test_score_set.py

@@ -174,6 +174,17 @@ def test_cannot_create_score_set_without_email(client, setup_router_db):
     assert response_data["detail"] in "There must be an email address associated with your account to use this feature."
 
 
+def test_cannot_create_score_set_with_invalid_target_gene_category(client, setup_router_db):
+    experiment = create_experiment(client)
+    score_set_post_payload = deepcopy(TEST_MINIMAL_SEQ_SCORESET)
+    score_set_post_payload["experimentUrn"] = experiment["urn"]
+    score_set_post_payload["targetGenes"][0]["category"] = "some_invalid_target_category"
+    response = client.post("/api/v1/score-sets/", json=score_set_post_payload)
+    assert response.status_code == 422
+    response_data = response.json()
+    assert "value is not a valid enumeration member;" in response_data["detail"][0]["msg"]
+
+
 def test_get_own_private_score_set(client, setup_router_db):
     experiment = create_experiment(client)
     score_set = create_seq_score_set(client, experiment["urn"])