feat(/IPVC-2695): Updates needed to retain HGNC on transcript (#45)

src/alembic/versions/77076df4224c_add_tx_hgnc_index.py

@@ -0,0 +1,30 @@
+"""hgnc test
+
+Revision ID: 77076df4224c
+Revises: 19561fe444c8
+Create Date: 2024-08-26 17:08:13.160259
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '77076df4224c'
+down_revision: Union[str, None] = '19561fe444c8'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_index(op.f('ix_uta_transcript_hgnc'), 'transcript', ['hgnc'], unique=False, schema='uta')
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_uta_transcript_hgnc'), table_name='transcript', schema='uta')
+    # ### end Alembic commands ###

src/alembic/versions/f85dd97bd9f5_set_gene_id_and_primary_and_foreign_keys.py

@@ -171,16 +171,8 @@ def upgrade() -> None:
     """)
     # ### end of updates to existing views ###
 
-    # ### drop hgnc from transcript ###
-    op.drop_column('transcript', 'hgnc', schema='uta')
-    # ### end Alembic commands ###
-
 
 def downgrade() -> None:
-    # ### updates to views to add hgnc to transcript ###
-    op.add_column('transcript', sa.Column('hgnc', sa.Text(), nullable=True), schema='uta')
-    # ### end of updates to transcript ###
-
     # ### commands to downgrade views before adding hgnc to transcript ###
     op.execute("DROP VIEW IF EXISTS tx_similarity_v CASCADE;")
     op.execute("DROP MATERIALIZED VIEW IF EXISTS tx_def_summary_mv CASCADE;")

src/uta/models.py

@@ -129,12 +129,13 @@ class Transcript(Base):
     origin_id = sa.Column(
         sa.Integer, sa.ForeignKey("origin.origin_id", onupdate="CASCADE", ondelete="CASCADE"), nullable=False, index=True)
     gene_id = sa.Column(sa.Text, sa.ForeignKey("gene.gene_id"), nullable=False, index=True)
+    hgnc = sa.Column(sa.Text, nullable=True, index=True)
     cds_start_i = sa.Column(sa.Integer)
     cds_end_i = sa.Column(sa.Integer)
     cds_md5 = sa.Column(sa.Text, index=True)
     added = sa.Column(
         sa.DateTime, default=datetime.datetime.now(), nullable=False)
-    codon_table = sa.Column(sa.Integer, nullable=False, server_default='1')  # 1 = standard, 2 = mitochondrial
+    codon_table = sa.Column(sa.Text, nullable=True, server_default='1')  # 1 = standard, 2 = mitochondrial
 
     # relationships:
     origin = sao.relationship("Origin", backref="transcripts")

tests/test_uta_loading.py

@@ -214,7 +214,7 @@ def test_load_txinfo(self):
                 'gene_id': '140606',
                 'cds_start_i': 63,
                 'cds_end_i': 501,
-                'codon_table': 1,
+                'codon_table': '1',
             },
         )
 
@@ -232,7 +232,7 @@ def test_load_txinfo(self):
                 'gene_id': '4514',
                 'cds_start_i': 0,
                 'cds_end_i': 784,
-                'codon_table': 2,
+                'codon_table': '2',
             },
         )