python-app.yml

# This workflow will install Python dependencies, run tests and lint with a single version of Python
# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python

name: Python application

on:
  push:
    branches: [ "main" ]
  pull_request:
    branches: [ "main" ]

permissions:
  contents: read
  pull-requests: write

jobs:
  build:

    runs-on: ubuntu-latest

    steps:
    - uses: actions/checkout@v4
    - name: Set up Python 3.11
      uses: actions/setup-python@v6
      with:
        python-version: "3.11"
    
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        pip install flake8 pytest pytest-cov click
        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
        # Install the package in development mode
        pip install -e .
    
    - name: Install 7-Zip
      run: sudo apt-get update && sudo apt-get install -y p7zip-full

    - name: Extract test data files
      run: |
        # Extract compressed mzML file from zip archives
        cd data
        if [ -f 1.zip ]; then
          echo "Extracting 1.mzML from split zip archives..."
          ls -lh 1.*
          7z x 1.zip
          ls -lh 1.mzML
          echo "Extraction complete"
        else
          echo "Warning: 1.zip not found in data directory"
          ls -la
        fi
        cd ..
    
    - name: Verify test data files
      run: |
        # Verify that required test data files exist
        if [ ! -f data/1_consensus_fdr_filter_pep.idXML ]; then
          echo "Error: idXML file not found"
          exit 1
        fi
        if [ ! -f data/1.mzML ]; then
          echo "Error: mzML file not found"
          exit 1
        fi
        echo "Test data files verified:"
        ls -lh data/1_consensus_fdr_filter_pep.idXML
        ls -lh data/1.mzML
    
    - name: Lint with flake8
      run: |
        # stop the build if there are Python syntax errors or undefined names
        flake8 onsite/ --count --select=E9,F63,F7,F82 --show-source --statistics --exclude=__pycache__,.git,build,dist
        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
        flake8 onsite/ --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics --exclude=__pycache__,.git,build,dist
    
    - name: Test package imports
      run: |
        # Test that the package and all modules can be imported
        python -c "import onsite; print('onsite package imported successfully')"
        python -c "from onsite import AScore; print('AScore imported successfully')"
        python -c "from onsite import calculate_phospho_localization_compomics_style; print('PhosphoRS imported successfully')"
        python -c "from onsite.lucxor import cli; print('LucXor CLI imported successfully')"
    
    - name: Test CLI commands availability
      run: |
        # Test that CLI commands are available
        onsite --help
        ascore --help || python -m onsite.ascore.cli --help
        phosphors --help || python -m onsite.phosphors.cli --help
        lucxor --help || python -m onsite.lucxor.cli --help
    
    - name: Run unit tests with coverage
      run: |
        # Run all unit tests with pytest and generate coverage report
        pytest tests/ -v --tb=short --color=yes --cov=onsite --cov-report=xml --cov-report=term
    
    - name: Test AScore with real data
      run: |
        # Test AScore algorithm with real data
        python -m onsite.ascore.cli \
          -in data/1.mzML \
          -id data/1_consensus_fdr_filter_pep.idXML \
          -out test_ascore_output.idXML \
          --fragment-mass-tolerance 0.05 \
          --fragment-mass-unit Da \
          --threads 1 \
          --add-decoys
        
        # Verify output file was created
        if [ -f test_ascore_output.idXML ]; then
          echo "AScore output file created successfully"
          ls -lh test_ascore_output.idXML
        else
          echo "Warning: AScore output file not created (may be expected if no phosphorylated peptides)"
        fi
    
    - name: Test PhosphoRS with real data
      run: |
        # Test PhosphoRS algorithm with real data
        python -m onsite.phosphors.cli \
          -in data/1.mzML \
          -id data/1_consensus_fdr_filter_pep.idXML \
          -out test_phosphors_output.idXML \
          --fragment-mass-tolerance 0.05 \
          --fragment-mass-unit Da \
          --threads 1 \
          --add-decoys
        
        # Verify output file was created
        if [ -f test_phosphors_output.idXML ]; then
          echo "PhosphoRS output file created successfully"
          ls -lh test_phosphors_output.idXML
        else
          echo "Warning: PhosphoRS output file not created (may be expected if no phosphorylated peptides)"
        fi
    
    - name: Test LucXor with real data
      run: |
        # Test LucXor algorithm with real data
        python -m onsite.lucxor.cli \
          -in data/1.mzML \
          -id data/1_consensus_fdr_filter_pep.idXML \
          -out test_lucxor_output.idXML \
          --fragment-method HCD \
          --fragment-mass-tolerance 0.5 \
          --fragment-error-units Da \
          --threads 1 \
          --min-num-psms-model 50
        
        # Verify output file was created
        if [ -f test_lucxor_output.idXML ]; then
          echo "LucXor output file created successfully"
          ls -lh test_lucxor_output.idXML
        else
          echo "Warning: LucXor output file not created (may be expected if no phosphorylated peptides)"
        fi
    
    - name: Test unified CLI with real data
      run: |
        # Test unified onsite CLI command
        onsite ascore \
          -in data/1.mzML \
          -id data/1_consensus_fdr_filter_pep.idXML \
          -out test_unified_ascore.idXML \
          --fragment-mass-tolerance 0.05 \
          --fragment-mass-unit Da \
          --threads 1 \
          --add-decoys
        
        onsite phosphors \
          -in data/1.mzML \
          -id data/1_consensus_fdr_filter_pep.idXML \
          -out test_unified_phosphors.idXML \
          --fragment-mass-tolerance 0.05 \
          --fragment-mass-unit Da \
          --threads 1 \
          --add-decoys
        
        onsite lucxor \
          -in data/1.mzML \
          -id data/1_consensus_fdr_filter_pep.idXML \
          -out test_unified_lucxor.idXML \
          --fragment-method HCD \
          --fragment-mass-tolerance 0.5 \
          --threads 1 \
          --min-num-psms-model 50
    
    - name: Verify reference result files exist
      run: |
        # Verify that reference result files exist for comparison
        echo "Checking reference result files..."
        ls -lh data/1_lucxor_result.idXML || echo "Warning: LucXor reference file not found"
        ls -lh data/1_ascore_result.idXML || echo "Warning: AScore reference file not found"
        ls -lh data/1_phosphors_result.idXML || echo "Warning: PhosphoRS reference file not found"
    
    - name: Run algorithm comparison tests
      id: algorithm_comparison
      run: |
        set -o pipefail
        # Run algorithm comparison tests to compare new results with reference results
        # Tests compare at different thresholds:
        # - LucXor: local_flr < 0.01, 0.05, 0.1 (with q-value < 0.01)
        # - AScore: AScore >= 3, 15, 20 (with q-value < 0.01)
        # - PhosphoRS: site probability > 75%, 90%, 99% (with q-value < 0.01)
        pytest tests/test_algorithm_comparison.py -v -s --tb=short --color=no 2>&1 | tee algorithm_comparison_results.txt
    
    - name: Post algorithm comparison results to PR
      if: github.event_name == 'pull_request' && always()
      uses: actions/github-script@v7
      with:
        script: |
          const fs = require('fs');
          const resultsFile = 'algorithm_comparison_results.txt';
          
          if (!fs.existsSync(resultsFile)) {
            console.log('Results file not found, skipping comment');
            return;
          }
          
          let results = fs.readFileSync(resultsFile, 'utf8');
          
          // Truncate if too long (GitHub comments have a limit)
          const maxLength = 65000;
          if (results.length > maxLength) {
            results = results.substring(0, maxLength) + '\n\n... (truncated)';
          }
          
          const body = [
            '## Algorithm Comparison Test Results',
            '',
            '<details>',
            '<summary>Click to expand test results</summary>',
            '',
            '```',
            results,
            '```',
            '',
            '</details>'
          ].join('\n');
          
          // Find and update existing comment or create new one
          const { data: comments } = await github.rest.issues.listComments({
            owner: context.repo.owner,
            repo: context.repo.repo,
            issue_number: context.issue.number,
          });
          
          const botComment = comments.find(comment => 
            comment.user.login === 'github-actions[bot]' && 
            comment.body.includes('## Algorithm Comparison Test Results')
          );
          
          if (botComment) {
            await github.rest.issues.updateComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              comment_id: botComment.id,
              body: body
            });
          } else {
            await github.rest.issues.createComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              issue_number: context.issue.number,
              body: body
            });
          }
    
    - name: Upload test outputs as artifacts
      if: always()
      uses: actions/upload-artifact@v4
      with:
        name: test-outputs
        path: |
          test_*.idXML
          algorithm_comparison_results.txt
        retention-days: 7
    
    - name: Upload coverage to artifacts
      if: always()
      uses: actions/upload-artifact@v4
      with:
        name: coverage-report
        path: coverage.xml
        retention-days: 7