Add project toml and add uv to build

.github/workflows/build_and_publish.yml

@@ -6,34 +6,13 @@ on:
    - created
 
 jobs:
- build-n-publish:
-  name: Build and publish Python distribution to PyPI
-  runs-on: ubuntu-latest
-  permissions:
-    id-token: write
-  steps:
-   - name: Check out git repository
-     uses: actions/checkout@v4
-
-   - name: Set up Python 3.13
-     uses: actions/setup-python@v5
-     with:
-      python-version: 3.13
-
-   - name: Install build tools
-     run: >-
-        python -m
-        pip install
-        wheel
-        twine
-        --user
-
-   - name: Build a binary wheel and a source tarball
-     run: >-
-        python
-        setup.py
-        sdist
-        bdist_wheel
-
-   - name: Publish distribution 📦 to PyPI
-     uses: pypa/gh-action-pypi-publish@release/v1
+ pypi:
+    name: Build and publish to PyPI
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v3
+      - run: uv build
+      - run: uv publish --trusted-publishing always

.github/workflows/check_format.yml

@@ -0,0 +1,24 @@
+# Basic CI setup: Lint format with ruff
+name: Format-check
+
+on:
+  pull_request:
+    types: [ opened, synchronize, reopened, ready_for_review, labeled, unlabeled ]
+
+jobs:
+  lint-format:
+    name: Ruff includes and format
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Ruff check import sorting
+        uses: astral-sh/ruff-action@v1
+        with:
+          args: "check --select I ."
+
+      - name: Ruff format diff
+        uses: astral-sh/ruff-action@v1
+        with:
+          args: "format --diff ."
+

.github/workflows/lint.yml

@@ -0,0 +1,18 @@
+# Basic CI setup: Lint with ruff
+name: Lint
+
+on:
+  pull_request:
+    types: [ opened, synchronize, reopened, ready_for_review, labeled, unlabeled ]
+
+jobs:
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Ruff lint
+        uses: astral-sh/ruff-action@v1
+        with:
+          args: "check ."

.python-version

@@ -0,0 +1 @@
+3.13

CHANGELOG.md

@@ -14,6 +14,7 @@ Try to use the following format:
 - Released the constraint on Python 3.8 (collections, pkg_resources to importlib, tests) ([#142](https://github.com/Clinical-Genomics/genmod/pull/142))
 - Update annotation examples ([#144](https://github.com/Clinical-Genomics/genmod/pull/144))
 - Updated documentation with warning about compounds only being scored within the first family in the VCF ([#151](https://github.com/Clinical-Genomics/genmod/pull/151)) 
+- Use `uv` with `hatchling` to build and publish ([#104](https://github.com/Clinical-Genomics/genmod/issues/143))
 
 ## [3.9]
 - Fixed wrong models when chromosome X was named `chrX` and not `X` ([#135](https://github.com/Clinical-Genomics/genmod/pull/135))

Dockerfile

@@ -0,0 +1,14 @@
+###############################################
+# Dockerfile to build GeMod container image
+###############################################
+FROM ghcr.io/astral-sh/uv:python3.13-alpine
+
+RUN apk update & apk add build-base zlib-dev
+# Copy the project into the image
+ADD . /app
+
+# Sync the project into a new environment, using the frozen lockfile
+WORKDIR /app
+RUN uv sync --frozen
+
+ENTRYPOINT ["uv", "run", "genmod"]

Dockerfile.pytest

@@ -1,18 +1,9 @@
 # Dockerfile to run genmod pytest suite
-FROM python:3.13
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm
 
-RUN mkdir -p /genmod
+ADD . /app
 
-COPY requirements.txt /genmod/
+WORKDIR /app
+RUN uv sync --all-extras --dev
 
-RUN pip3 install -r /genmod/requirements.txt
-
-COPY . /genmod
-
-ENV PYTHONPATH=/genmod
-
-WORKDIR /genmod
-
-RUN pip3 install .
-
-ENTRYPOINT ["pytest"]
+ENTRYPOINT ["uv", "run", "pytest"]

MANIFEST.in

@@ -1,11 +1,9 @@
 include CHANGELOG.md
 include LICENSE.txt
 include README.md
-include requirements.txt
 
 recursive-include examples *.ped *.vcf *.gz *.tbi
 recursive-include genmod/annotations *.gz
 recursive-include genmod/configs *.ini
 recursive-exclude * __pycache__
 recursive-exclude * *.py[co]
-

README.md

@@ -27,7 +27,8 @@ or
 
 	git clone https://github.com/Clinical-Genomics/genmod.git
 	cd genmod
-	python setup.py install
+	uv install genmod
+	uv run genmod
 
 
 ## Usage

genmod/annotate_models/__init__.py

@@ -1,7 +1 @@
 from __future__ import absolute_import
-
-from .make_haploblocks import get_haploblocks
-from .genetic_models import check_genetic_models
-from .model_score import get_model_score
-from .fix_variant import make_print_version
-from .variant_annotator import VariantAnnotator

genmod/annotate_models/fix_variant.py

@@ -1,90 +1,76 @@
-from . import get_model_score
+from .model_score import get_model_score
+
 
 def make_print_version(variant, families):
     """
     Get the variants ready for printing
-    
+
     This function collects the annotations added and merge them in the INFO
     dict.
-    
+
     Arguments:
         variant (dict): A variant dictionary
-    
+
     """
-
-    variant_id = variant['variant_id']
-    vcf_info = variant['INFO'].split(';')
-
-    feature_list = variant.get('annotation', set())
-
+
+    variant_id = variant["variant_id"]
+    vcf_info = variant["INFO"].split(";")
+
     # variant[compounds] is a dictionary with family id as keys and a set of compounds as values
-    compounds = variant.get('compounds', dict())
+    compounds = variant.get("compounds", dict())
     # Here we store the compound strings that should be added to the variant:
     family_compound_strings = []
 
-    genetic_models = variant.get('inheritance_models', {})
+    genetic_models = variant.get("inheritance_models", {})
 
     # We need to check if compounds have already been annotated.
-    if 'Compounds' not in variant['info_dict']:
-
+    if "Compounds" not in variant["info_dict"]:
         for family_id in compounds:
-            if (genetic_models[family_id].get('AR_comp') or genetic_models[family_id].get('AR_comp_dn')):
-                compound_string = ''
+            if genetic_models[family_id].get("AR_comp") or genetic_models[family_id].get(
+                "AR_comp_dn"
+            ):
+                compound_string = ""
                 compound_set = compounds[family_id]
-                #We do not want reference to itself as a compound:
+                # We do not want reference to itself as a compound:
                 compound_set.discard(variant_id)
                 # If there are any compounds for the family:
                 if compounds[family_id]:
-                    compound_string = '|'.join(compound_set)
-                    family_compound_strings.append(':'.join([family_id, compound_string]))
-                
+                    compound_string = "|".join(compound_set)
+                    family_compound_strings.append(":".join([family_id, compound_string]))
+
                 if len(family_compound_strings) > 0:
-                    vcf_info.append('Compounds=' + ','.join(family_compound_strings))
-    
+                    vcf_info.append("Compounds=" + ",".join(family_compound_strings))
+
     # Check if any genetic models are followed
-    if 'GeneticModels' not in variant['info_dict']:
+    if "GeneticModels" not in variant["info_dict"]:
         # Here we store the compound strings that should be added to the variant:
         family_model_strings = []
         model_scores = {}
         for family_id in genetic_models:
-            model_string = ''
+            model_string = ""
             model_list = []
             for model in genetic_models[family_id]:
                 if genetic_models[family_id][model]:
                     model_list.append(model)
-                model_string = '|'.join(model_list)
+                model_string = "|".join(model_list)
             if len(model_list) > 0:
-                family_model_strings.append(':'.join(
-                                            [family_id, model_string]))
-
+                family_model_strings.append(":".join([family_id, model_string]))
+
                 model_scores[family_id] = str(
-                    get_model_score(families[family_id].individuals, variant))
-
+                    get_model_score(families[family_id].individuals, variant)
+                )
+
         if len(family_model_strings) > 0:
-            vcf_info.append(
-                        'GeneticModels={0}'.format( 
-                        ','.join(family_model_strings)))
+            vcf_info.append("GeneticModels={0}".format(",".join(family_model_strings)))
 
             model_score_list = []
             for family_id in model_scores:
                 if model_scores[family_id]:
                     if float(model_scores[family_id]) > 0:
-                        model_score_list.append(
-                            ':'.join(
-                                        [
-                                            family_id, 
-                                            model_scores[family_id]
-                                        ]
-                                    )
-                                )
+                        model_score_list.append(":".join([family_id, model_scores[family_id]]))
             if len(model_score_list) > 0:
-                vcf_info.append(
-                            'ModelScore=' +  
-                            ','.join(model_score_list)
-                            )
-
-
-
-    variant['INFO'] = ';'.join(vcf_info)
+                vcf_info.append("ModelScore=" + ",".join(model_score_list))
+
+    variant["INFO"] = ";".join(vcf_info)
 
     return variant