py-gbcms 2.0.0__tar.gz

py_gbcms-2.0.0/.gitbook.yaml

@@ -0,0 +1,8 @@
+root: ./docs/
+
+structure:
+  readme: README.md
+  summary: SUMMARY.md
+
+redirects:
+  previous/page: new-folder/page.md

py_gbcms-2.0.0/.github/workflows/release.yml

@@ -0,0 +1,130 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - '[0-9]+.[0-9]+.[0-9]+'  # Matches 1.0.0, 2.3.4, etc. (semantic versioning)
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'Version to release (e.g., 1.0.0)'
+        required: false
+
+env:
+  PYTHON_VERSION: '3.11'
+  REGISTRY: ghcr.io
+
+jobs:
+  release:
+    name: Build, Test, and Release
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write  # Required for PyPI Trusted Publisher OIDC
+      contents: read   # Required for checkout and metadata
+      packages: write  # Required for Docker registry access
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0  # Full history for proper version detection
+
+    - name: Set up Python ${{ env.PYTHON_VERSION }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ env.PYTHON_VERSION }}
+
+    - name: Install uv
+      run: pip install uv
+
+    - name: Setup and test package
+      run: |
+        # Create virtual environment and install package in development mode
+        uv venv .venv
+        source .venv/bin/activate
+
+        # Install the package with all dependencies
+        uv pip install -e ".[dev]"
+
+        # Run tests to ensure everything works
+        uv run pytest -v
+
+        # Verify package can be imported
+        uv run python -c "import gbcms; print(f'gbcms version: {gbcms.__version__}')"
+
+    - name: Build Python package
+      run: |
+        source .venv/bin/activate
+        uv pip install build
+        python -m build --sdist --wheel --outdir dist/
+
+    - name: Verify package
+      run: |
+        source .venv/bin/activate
+        uv pip install twine
+        twine check dist/*
+
+    - name: Publish to PyPI
+      if: startsWith(github.ref, 'refs/tags/')
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        skip-existing: true
+        verbose: true
+        print-hash: true
+
+    - name: Log in to GitHub Container Registry
+      uses: docker/login-action@v3
+      with:
+        registry: ${{ env.REGISTRY }}
+        username: ${{ github.actor }}
+        password: ${{ secrets.RS_PAT }}
+
+    - name: Extract metadata for Docker
+      id: meta
+      uses: docker/metadata-action@v5
+      with:
+        images: ${{ env.REGISTRY }}/${{ github.repository }}
+        tags: |
+          type=ref,event=tag
+          type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
+
+    - name: Build and push Docker image
+      uses: docker/build-push-action@v5
+      with:
+        context: .
+        push: true
+        tags: ${{ steps.meta.outputs.tags }}
+        labels: ${{ steps.meta.outputs.labels }}
+        cache-from: type=gha
+        cache-to: type=gha,mode=max
+
+    - name: Generate release notes
+      if: startsWith(github.ref, 'refs/tags/')
+      run: |
+        echo "## 🚀 gbcms v${{ github.ref_name }}" >> release_notes.md
+        echo "" >> release_notes.md
+        echo "### Changes" >> release_notes.md
+        echo "- Published to PyPI" >> release_notes.md
+        echo "- Published Docker image to GitHub Container Registry" >> release_notes.md
+        echo "" >> release_notes.md
+        echo "### Installation" >> release_notes.md
+        echo "\`\`\`bash" >> release_notes.md
+        echo "# PyPI" >> release_notes.md
+        echo "pip install gbcms==${{ github.ref_name }}" >> release_notes.md
+        echo "" >> release_notes.md
+        echo "# Docker" >> release_notes.md
+        echo "docker pull ghcr.io/${{ github.repository }}:${{ github.ref_name }}" >> release_notes.md
+        echo "\`\`\`" >> release_notes.md
+        echo "" >> release_notes.md
+        echo "### Usage" >> release_notes.md
+        echo "\`\`\`bash" >> release_notes.md
+        echo "gbcms count run --fasta reference.fa --bam sample:sample.bam --vcf variants.vcf --output counts.txt" >> release_notes.md
+        echo "\`\`\`" >> release_notes.md
+
+    - name: Show release summary
+      run: |
+        echo "✅ Release completed successfully!"
+        echo "📦 PyPI package: https://pypi.org/project/gbcms/${{ github.ref_name }}/"
+        echo "🐳 Docker image: ${{ env.REGISTRY }}/${{ github.repository }}:${{ github.ref_name }}"
+        echo "📋 Package contents:"
+        ls -la dist/ || echo "No dist directory found"

py_gbcms-2.0.0/.github/workflows/test.yml

@@ -0,0 +1,150 @@
+name: Tests
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main, develop ]
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        python-version: ['3.11', '3.12']
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install system dependencies (Ubuntu)
+        if: runner.os == 'Linux'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y \
+            build-essential \
+            zlib1g-dev \
+            libbz2-dev \
+            liblzma-dev \
+            libcurl4-openssl-dev \
+            libssl-dev \
+            libncurses5-dev \
+            libncursesw5-dev \
+            libsqlite3-dev \
+            libgdbm-dev \
+            libreadline-dev \
+            libxml2-dev \
+            libxslt1-dev \
+            gfortran \
+            libopenblas-dev \
+            liblapack-dev \
+            git \
+            autoconf \
+            samtools
+
+      - name: Install system dependencies (macOS)
+        if: runner.os == 'macOS'
+        run: |
+          brew install htslib samtools autoconf automake
+
+      - name: Install uv
+        run: |
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+
+      - name: Install package and test basic functionality
+        run: |
+          # Install without fast dependencies on Ubuntu due to htslib issues
+          if [ "$RUNNER_OS" = "Linux" ]; then
+            uv pip install --system -e ".[dev]"
+          else
+            uv pip install --system -e ".[dev,all]"
+          fi
+          gbcms --help
+
+      - name: Run tests with coverage
+        run: |
+          pytest --cov=gbcms --cov-report=xml --cov-report=term-missing -v
+
+      - name: Upload coverage to Codecov
+        if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.11'
+        uses: codecov/codecov-action@v4
+        with:
+          file: ./coverage.xml
+          flags: unittests
+          name: codecov-umbrella
+          fail_ci_if_error: false
+
+      - name: Run integration tests (Ubuntu only)
+        if: matrix.os == 'Linux'
+        run: |
+          chmod +x scripts/test_vcf_workflow.sh scripts/test_maf_workflow.sh scripts/test_docker.sh
+          # Skip integration tests that require cyvcf2 on Ubuntu
+          echo "⚠️  Skipping integration tests on Ubuntu due to htslib dependency issues"
+          # bash scripts/test_docker.sh  # Only run Docker test
+
+  lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install uv
+        run: |
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+
+      - name: Install dependencies
+        run: |
+          uv pip install --system  scipy-stubs
+          uv pip install --system -e ".[dev]"
+
+      - name: Run black
+        run: |
+          black --check src/ tests/
+
+      - name: Run ruff
+        run: |
+          ruff check src/ tests/
+
+      - name: Run mypy
+        run: |
+          mypy src/
+
+  docker-test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: false
+          tags: gbcms:test
+          cache-from: type=gha,scope=test
+          cache-to: type=gha,mode=max,scope=test
+
+      - name: Verify Docker build success
+        run: |
+          # Check that the image was built successfully
+          docker images gbcms:test --format "table {{.Repository}}\t{{.Tag}}\t{{.Size}}"
+          echo "✅ Docker image gbcms:test built successfully"
+

py_gbcms-2.0.0/.gitignore

@@ -0,0 +1,65 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+venv/
+env/
+ENV/
+.venv
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+coverage.xml
+*.cover
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Project specific
+data/
+test_data/
+*.bam
+*.bam.bai
+*.fa
+*.fa.fai
+*.vcf
+*.maf
+output/
+results/
+
+# Logs
+*.log
+
+# Temporary files
+tmp/
+temp/

py_gbcms-2.0.0/.pre-commit-config.yaml

@@ -0,0 +1,31 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+      - id: check-json
+      - id: check-toml
+      - id: check-merge-conflict
+      - id: debug-statements
+
+  - repo: https://github.com/psf/black
+    rev: 23.12.1
+    hooks:
+      - id: black
+        language_version: python3.11
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.1.9
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.8.0
+    hooks:
+      - id: mypy
+        additional_dependencies: [types-all]
+        args: [--ignore-missing-imports]

py_gbcms-2.0.0/CONTRIBUTING.md

@@ -0,0 +1,154 @@
+# Contributing to GetBaseCounts
+
+Thank you for your interest in contributing to GetBaseCounts! This document provides guidelines and instructions for contributing.
+
+## Development Setup
+
+1. **Clone the repository**
+   ```bash
+   git clone https://github.com/msk-access/py-gbcms.git
+   cd py-gbcms
+   ```
+
+2. **Install uv** (if not already installed)
+   ```bash
+   curl -LsSf https://astral.sh/uv/install.sh | sh
+   ```
+
+3. **Install development dependencies**
+   ```bash
+   uv pip install -e ".[dev]"
+   ```
+
+4. **Install pre-commit hooks**
+   ```bash
+   pre-commit install
+   ```
+
+## Development Workflow
+
+### Running Tests
+
+```bash
+# Run all tests
+pytest
+
+# Run with coverage
+pytest --cov=gbcms --cov-report=html
+
+# Run specific test file
+pytest tests/test_counter.py
+
+# Run with verbose output
+pytest -v
+```
+
+### Code Quality
+
+```bash
+# Format code
+black src/ tests/
+
+# Lint code
+ruff check src/ tests/
+
+# Fix linting issues automatically
+ruff check --fix src/ tests/
+
+# Type checking
+mypy src/
+```
+
+### Building and Testing Docker
+
+```bash
+# Build Docker image
+docker build -t gbcms:latest .
+
+# Run tests in Docker
+docker build -f Dockerfile.test -t gbcms:test .
+docker run --rm gbcms:test
+```
+
+## Code Style
+
+- Follow PEP 8 style guidelines
+- Use type hints for all function signatures
+- Write docstrings for all public functions and classes
+- Keep functions focused and single-purpose
+- Maximum line length: 100 characters
+
+## Testing Guidelines
+
+- Write tests for all new features
+- Maintain or improve code coverage
+- Use descriptive test names
+- Use fixtures for common test setup
+- Test edge cases and error conditions
+
+## Pull Request Process
+
+1. **Create a feature branch**
+   ```bash
+   git checkout -b feature/your-feature-name
+   ```
+
+2. **Make your changes**
+   - Write code following the style guidelines
+   - Add tests for new functionality
+   - Update documentation as needed
+
+3. **Run tests and linters**
+   ```bash
+   make test
+   make lint
+   ```
+
+4. **Commit your changes**
+   ```bash
+   git add .
+   git commit -m "Description of your changes"
+   ```
+
+5. **Push to your fork**
+   ```bash
+   git push origin feature/your-feature-name
+   ```
+
+6. **Create a Pull Request**
+   - Provide a clear description of the changes
+   - Reference any related issues
+   - Ensure all CI checks pass
+
+## Reporting Issues
+
+When reporting issues, please include:
+
+- Python version
+- Operating system
+- Steps to reproduce
+- Expected behavior
+- Actual behavior
+- Error messages or logs
+
+## Feature Requests
+
+We welcome feature requests! Please:
+
+- Check if the feature already exists
+- Provide a clear use case
+- Describe the expected behavior
+- Consider submitting a PR if you can implement it
+
+## Code of Conduct
+
+- Be respectful and inclusive
+- Welcome newcomers
+- Focus on constructive feedback
+- Help others learn and grow
+
+## Questions?
+
+Feel free to open an issue for questions or reach out to the maintainers.
+
+Thank you for contributing!

py_gbcms-2.0.0/Dockerfile

@@ -0,0 +1,55 @@
+# syntax=docker/dockerfile:1
+FROM python:3.11-slim
+
+# Install OS-level build dependencies commonly needed for cyvcf2, pysam, numpy, etc.
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    zlib1g-dev \
+    libbz2-dev \
+    liblzma-dev \
+    libcurl4-openssl-dev \
+    libssl-dev \
+    libncurses5-dev \
+    libncursesw5-dev \
+    libsqlite3-dev \
+    libgdbm-dev \
+    libreadline-dev \
+    libffi-dev \
+    libxml2-dev \
+    libxslt1-dev \
+    gfortran \
+    libopenblas-dev \
+    liblapack-dev \
+    git \
+    autoconf \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install uv (optional helper) — you can remove if you prefer pip directly
+RUN pip install --no-cache-dir uv
+
+WORKDIR /app
+
+# Copy only the files needed for installation first to leverage Docker cache
+COPY pyproject.toml pyproject.lock* README.md LICENSE* /app/
+COPY src/ /app/src/
+
+# Create a virtualenv, activate it and install the package with extras
+RUN uv venv .venv && \
+    /bin/bash -lc "source .venv/bin/activate && uv pip install --no-cache-dir '.[all]'" 
+
+# Ensure the venv bin is first in PATH
+ENV PATH="/app/.venv/bin:${PATH}"
+
+# Working directory for running
+WORKDIR /data
+
+# Entrypoint/command defaults
+ENTRYPOINT ["gbcms"]
+CMD ["--help"]
+
+LABEL maintainer="MSK-ACCESS <access@mskcc.org>"
+LABEL description="Python implementation of GetBaseCountsMultiSample (gbcms) for calculating base counts in BAM files"
+LABEL org.opencontainers.image.source="https://github.com/msk-access/py-gbcms"
+LABEL org.opencontainers.image.documentation="https://github.com/msk-access/py-gbcms/blob/main/README.md"
+LABEL org.opencontainers.image.licenses="AGPL-3.0"
+LABEL org.opencontainers.image.base.image="python:3.11-slim"

py_gbcms-2.0.0/Dockerfile.test

@@ -0,0 +1,39 @@
+# Dockerfile for testing py-gbcms
+FROM ubuntu:22.04
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    gcc \
+    g++ \
+    make \
+    zlib1g-dev \
+    libbz2-dev \
+    liblzma-dev \
+    libcurl4-openssl-dev \
+    libssl-dev \
+    libhts-dev \
+    samtools \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install uv
+RUN pip install --no-cache-dir uv
+
+# Set working directory
+WORKDIR /app
+
+# Copy project files
+COPY pyproject.toml README.md LICENSE ./
+COPY src/ ./src/
+COPY tests/ ./tests/
+
+# Install package with dev and all dependencies
+# This includes cyvcf2 and all dev tools
+RUN uv pip install --system --no-cache ".[dev,all]"
+
+# Verify installation
+RUN gbcms version
+
+# Run tests by default
+CMD ["pytest", "-v", "--cov=gbcms", "--cov-report=term-missing"]