ci: add Ruff config, pre-commit hooks, and GitHub Actions lint workflow

- Add Ruff config (E/F/I rules, per-file ignores for __init__.py)
- Add .pre-commit-config.yaml with ruff lint + format hooks
- Add .github/workflows/lint.yml triggering on PRs
- Auto-fix 63 violations (unsorted imports, unused imports, f-strings)
Note: ruff-format is excluded from pre-commit and CI — this repo uses pyink. F722/F821 ignored: false positives from jaxtyping annotations.

Author: korbonits

.github/workflows/lint.yml

@@ -0,0 +1,16 @@
+name: Lint
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v5
+      - run: uv python install 3.10
+      - run: uv pip install ruff
+      - run: uv run ruff check .

.pre-commit-config.yaml

@@ -0,0 +1,6 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.2
+    hooks:
+      - id: ruff
+        args: [--fix]

hatch_build.py

@@ -16,9 +16,11 @@
 
 import os
 from typing import Any
-from grpc_tools import protoc
-from hatchling.builders.hooks.plugin.interface import BuildHookInterface  # pylint: disable=g-importing-member
 
+from grpc_tools import protoc
+from hatchling.builders.hooks.plugin.interface import (
+  BuildHookInterface,  # pylint: disable=g-importing-member
+)
 
 _ROOT_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'src')
 

pyproject.toml

@@ -134,3 +134,16 @@ unstable = true
 pyink-indentation = 2
 pyink-use-majority-quotes = true
 exclude = 'src/alphagenome/protos'
+
+[tool.ruff]
+line-length = 80
+indent-width = 2
+extend-exclude = ["*.ipynb"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I"]
+# F722/F821: false positives from jaxtyping annotations
+ignore = ["E501", "E402", "E731", "E722", "E741", "E721", "E701", "F841", "F403", "F405", "F722", "F821"]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401"]

scripts/process_gtf.py

@@ -16,16 +16,13 @@
 
 import os
 import tempfile
-from urllib import parse
-from urllib import request
+from urllib import parse, request
 
-from absl import app
-from absl import flags
-from absl import logging
-from alphagenome.data import transcript as transcript_utils
 import pandas as pd
 import pyranges
+from absl import app, flags, logging
 
+from alphagenome.data import transcript as transcript_utils
 
 _GTF_PATH = flags.DEFINE_string(
     'gtf_path', None, 'Path to GTF file.', required=True

scripts/process_gtf_test.py

@@ -12,14 +12,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from absl.testing import absltest
-from absl.testing import parameterized
 import numpy as np
 import pandas as pd
+from absl.testing import absltest, parameterized
 
 from . import process_gtf
 
-
 _EXAMPLE_GTF = r"""
 chr1	FOO	gene	12100	21316	.	+	.	gene_id "GENE00000000001.1";
 chr1	FOO	transcript	12100	18244	.	+	.	gene_id "GENE00000000001.1"; transcript_id "TRANS00000000001.2";

src/alphagenome/colab_utils_test.py

@@ -17,8 +17,8 @@
 from unittest import mock
 
 from absl.testing import absltest
-from alphagenome import colab_utils
 
+from alphagenome import colab_utils
 
 _TEST_SECRET_KEY = '_TEST_ALPHAGENOME_API_KEY'
 

src/alphagenome/data/fold_intervals.py

@@ -16,10 +16,10 @@
 
 import enum
 
-from alphagenome.models import dna_client
 import immutabledict
 import pandas as pd
 
+from alphagenome.models import dna_client
 
 _DEFAULT_EXAMPLE_REGIONS = immutabledict.immutabledict({
     dna_client.Organism.HOMO_SAPIENS: (

src/alphagenome/data/fold_intervals_test.py

@@ -12,12 +12,11 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from absl.testing import absltest
-from absl.testing import parameterized
-from alphagenome.data import fold_intervals
-from alphagenome.models import dna_client
 import pandas as pd
+from absl.testing import absltest, parameterized
 
+from alphagenome.data import fold_intervals
+from alphagenome.models import dna_client
 
 _dummy_intervals = pd.DataFrame({
     'chromosome': ['chr' + str(i) for i in range(8)],

src/alphagenome/data/gene_annotation.py

@@ -14,13 +14,14 @@
 
 """Utilities for working with gene annotations (e.g., GTFs)."""
 
-from collections.abc import Sequence
 import enum
+from collections.abc import Sequence
 
-from alphagenome.data import genome
 import numpy as np
 import pandas as pd
 
+from alphagenome.data import genome
+
 
 @enum.unique
 class TranscriptType(enum.Enum):