REF: exchange poetry for hatch and refactor with ruff

Author: davidmeijer

.github/workflows/tests.yml

@@ -23,18 +23,15 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: "pip"
 
-      - name: install Poetry
+      - name: install package with dev dependencies
         run: |
           python -m pip install --upgrade pip
-          python -m pip install "poetry>=1.8.0,<2.0.0"
-
-      - name: install project (incl. dev group)
-        run: |
-          poetry install --with dev
+          pip install -e .[dev]
 
       - name: ruff lint
-        run: poetry run ruff check alembic bionexus
+        run: ruff check alembic src
 
       - name: ruff format check
-        run: poetry run ruff format --check alembic bionexus
+        run: ruff format --check alembic src

.gitignore

@@ -8,6 +8,7 @@ __pycache__/
 *.sql
 .env
 .vscode/
+.ruff_cache/
 
 # do not push /retromol_cache wherever it is
 # this is the default cache directory for retromol results if no directory is specified

README.md

@@ -15,30 +15,24 @@
     ```bash
     python -m venv .venv
     source .venv/bin/activate
-    pip install poetry
+    pip install -e .[dev]
     ```
 
     or using `conda`:
 
     ```bash
     conda create -n bionexus python=3.10
     conda activate bionexus
-    pip install poetry
+    pip install -e .[dev]
     ```
 
-4) Install deps:
-
-    ```bash
-    poetry install --all-extras
-    ```
-
-5) Create/upgrade schema:
+4) Create/upgrade schema:
 
     ```bash
     bionexus upgrade head
     ```
 
-6) Load data:
+5) Load data:
 
     * Load NPAtlas compound structures, their names and properties, and organism annotations:
 
@@ -48,28 +42,12 @@
 
     * Load MIBiG:
 
-        Make sure to have installed the `bio` extras:
-
-        ```bash
-        poetry install --extras bio
-        ```
-
-        Then run:
-
         ```bash
         bionexus load-mibig
         ```
 
     * (Optional) Compute compound fingerprints:
 
-        Make sure to have installed the `chem` extras:
-
-        ```bash
-        poetry install --extras chem
-        ```
-
-        Then run:
-
         ```bash
         bionexus compute-fp-morgan
         ```
@@ -82,14 +60,6 @@
 
     * (Optional) Parse compounds with RetroMol:
 
-        Make sure to have installed the `retromol` extras:
-
-        ```bash
-        poetry install --extras retromol
-        ```
-
-        Then run:
-
         ```bash
         bionexus parse-compounds
         ```

alembic/env.py

@@ -1,13 +1,14 @@
 """Alembic migration environment configuration file."""
 
 from __future__ import annotations
+
+import os
 from logging.config import fileConfig
 from pathlib import Path
-import os
 
 from sqlalchemy import engine_from_config, pool
-from alembic import context
 
+from alembic import context
 from bionexus.db import models as bnx_models
 
 # Make sure we import local repo version, not installed package
@@ -65,9 +66,7 @@ def run_migrations_online() -> None:
     """
     Run migrations in 'online' mode.
     """
-    connectable = engine_from_config(
-        {"sqlalchemy.url": get_url()}, prefix="sqlalchemy.", poolclass=pool.NullPool
-    )
+    connectable = engine_from_config({"sqlalchemy.url": get_url()}, prefix="sqlalchemy.", poolclass=pool.NullPool)
     with connectable.connect() as connection:
         context.configure(
             connection=connection,

alembic/versions/0001_init.py

@@ -1,7 +1,8 @@
-from alembic import op
 import sqlalchemy as sa
-from sqlalchemy.dialects.postgresql import ARRAY, BIT
 from pgvector.sqlalchemy import Vector
+from sqlalchemy.dialects.postgresql import ARRAY, BIT
+
+from alembic import op
 
 revision = "0001_init"
 down_revision = None
@@ -10,9 +11,7 @@
 
 
 def upgrade():
-    op.execute(
-        "CREATE EXTENSION IF NOT EXISTS vector;"
-    )  # pgvector for fp_morgan_b2048_r2_vec
+    op.execute("CREATE EXTENSION IF NOT EXISTS vector;")  # pgvector for fp_morgan_b2048_r2_vec
 
     op.create_table(
         "compound",
@@ -87,9 +86,7 @@ def upgrade():
         "compound_record",
         ["compound_id", "source", "ext_id"],
     )
-    op.create_index(
-        "ix_compound_record_compound_id", "compound_record", ["compound_id"]
-    )
+    op.create_index("ix_compound_record_compound_id", "compound_record", ["compound_id"])
     # speed lookups by accession
     op.create_index(
         "ix_compound_record_source_ext",
@@ -136,18 +133,14 @@ def upgrade():
 def downgrade():
     # drop in reverse order
     # drop triggers/functions first (otherwise DROP TABLE will drop dependent objs, but be explicit)
-    op.execute(
-        "DROP TRIGGER IF EXISTS compound_record_set_timestamp ON public.compound_record;"
-    )
+    op.execute("DROP TRIGGER IF EXISTS compound_record_set_timestamp ON public.compound_record;")
     op.execute("DROP FUNCTION IF EXISTS public.set_timestamp_compound_record;")
     op.execute("DROP TRIGGER IF EXISTS compound_set_timestamp ON public.compound;")
     op.execute("DROP FUNCTION IF EXISTS public.set_timestamp_compound;")
 
     op.drop_index("ix_compound_record_source_ext", table_name="compound_record")
     op.drop_index("ix_compound_record_compound_id", table_name="compound_record")
-    op.drop_constraint(
-        "uq_compound_record_compound_source_ext", "compound_record", type_="unique"
-    )
+    op.drop_constraint("uq_compound_record_compound_source_ext", "compound_record", type_="unique")
     op.drop_table("compound_record")
 
     op.drop_constraint("uq_compound_inchikey", "compound", type_="unique")

alembic/versions/0002_rev.py

@@ -4,9 +4,10 @@
 Create Date: 2025-10-10 21:56:15.797293
 """
 
-from alembic import op
 import sqlalchemy as sa
 
+from alembic import op
+
 revision = "0002_rev"
 down_revision = "0001_init"
 branch_labels = None
@@ -21,9 +22,7 @@ def upgrade():
         sa.Column("ext_id", sa.String(128), nullable=False),
         sa.Column("gbk_text", sa.Text, nullable=False),  # full GenBank as TEXT
         sa.Column("size_bytes", sa.Integer, nullable=True),  # raw size on ingest
-        sa.Column(
-            "sha256", sa.String(64), nullable=True
-        ),  # content checksum for dedup/integrity
+        sa.Column("sha256", sa.String(64), nullable=True),  # content checksum for dedup/integrity
         sa.Column(
             "created_at",
             sa.DateTime(timezone=True),
@@ -72,9 +71,7 @@ def upgrade():
 
 def downgrade():
     # drop trigger and its function first
-    op.execute(
-        "DROP TRIGGER IF EXISTS genbank_region_set_timestamp ON public.genbank_region;"
-    )
+    op.execute("DROP TRIGGER IF EXISTS genbank_region_set_timestamp ON public.genbank_region;")
     op.execute("DROP FUNCTION IF EXISTS public.set_timestamp_genbank_region;")
 
     # drop optional partial unique index (if created)

alembic/versions/0003_rev.py

@@ -4,10 +4,11 @@
 Create Date: 2025-10-11 10:32:00.000000
 """
 
-from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects.postgresql import JSONB
 
+from alembic import op
+
 revision = "0003_rev"
 down_revision = "0002_rev"
 branch_labels = None
@@ -72,12 +73,8 @@ def upgrade():
 
     # helpful indexes for common lookups
     op.create_index("ix_annotation_compound_id", "annotation", ["compound_id"])
-    op.create_index(
-        "ix_annotation_genbank_region_id", "annotation", ["genbank_region_id"]
-    )
-    op.create_index(
-        "ix_annotation_scheme_key_value", "annotation", ["scheme", "key", "value"]
-    )
+    op.create_index("ix_annotation_genbank_region_id", "annotation", ["genbank_region_id"])
+    op.create_index("ix_annotation_scheme_key_value", "annotation", ["scheme", "key", "value"])
 
     # JSON metadata indexing (existence/path queries)
     op.execute("""
@@ -115,9 +112,7 @@ def downgrade():
     op.drop_index("ix_annotation_scheme_key_value", table_name="annotation")
     op.drop_index("ix_annotation_genbank_region_id", table_name="annotation")
     op.drop_index("ix_annotation_compound_id", table_name="annotation")
-    op.drop_constraint(
-        "uq_annotation_target_scheme_key_value", "annotation", type_="unique"
-    )
+    op.drop_constraint("uq_annotation_target_scheme_key_value", "annotation", type_="unique")
 
     # drop table
     op.drop_table("annotation")

alembic/versions/0004_rev.py

@@ -4,10 +4,11 @@
 Create Date: 2025-10-14 12:25:00.000000
 """
 
-from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects.postgresql import BIT, JSONB
 
+from alembic import op
+
 revision = "0004_rev"
 down_revision = "0003_rev"
 branch_labels = None
@@ -23,9 +24,7 @@ def upgrade():
     op.create_table(
         "ruleset",
         sa.Column("id", sa.BigInteger, primary_key=True),
-        sa.Column(
-            "version", sa.Integer, nullable=False, unique=True
-        ),  # auto-assign by trigger
+        sa.Column("version", sa.Integer, nullable=False, unique=True),  # auto-assign by trigger
         # store rules as text (YAML) for both monomers and reaction rules, also store sha256 for integrity
         sa.Column("matching_rules_yaml", sa.Text, nullable=False),
         sa.Column("matching_rules_sha256", sa.String(64), nullable=False, unique=True),
@@ -206,9 +205,7 @@ def upgrade():
 
 def downgrade():
     # drop child triggers/indexes/tables first
-    op.execute(
-        "DROP TRIGGER IF EXISTS retromol_compound_set_timestamp ON public.retromol_compound;"
-    )
+    op.execute("DROP TRIGGER IF EXISTS retromol_compound_set_timestamp ON public.retromol_compound;")
     op.execute("DROP FUNCTION IF EXISTS public.set_timestamp_retromol_compound;")
     op.drop_index("ix_retromol_compound_ruleset_id", table_name="retromol_compound")
     op.drop_index("ix_retromol_compound_compound_id", table_name="retromol_compound")