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
  issues: 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 pandas pyarrow
          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
          # Install the package in development mode
          pip install -e .

      - name: Lint with flake8
        run: |
          # stop the build if there are Python syntax errors or undefined names
          flake8 onsite/ tests/ --count --select=E9,F63,F7,F82 --show-source --statistics --exclude=__pycache__,.git,build,dist,__init__.py
          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
          flake8 onsite/ tests/ --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics --exclude=__pycache__,.git,build,dist,__init__.py

      - 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/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1.mzML \
            -id data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1_comet_perc.idparquet \
            -out test_ascore_output.idparquet \
            --fragment-mass-tolerance 0.05 \
            --fragment-mass-unit Da \
            --threads 1

          # Verify output directory was created
          if [ -d test_ascore_output.idparquet ]; then
            echo "AScore output created successfully"
            ls -lh test_ascore_output.idparquet/
          else
            echo "Warning: AScore output not created"
          fi

      - name: Test PhosphoRS with real data
        run: |
          # Test PhosphoRS algorithm with real data
          python -m onsite.phosphors.cli \
            -in data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1.mzML \
            -id data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1_comet_perc.idparquet \
            -out test_phosphors_output.idparquet \
            --fragment-mass-tolerance 0.05 \
            --fragment-mass-unit Da \
            --threads 1 \
            --add-decoys

          # Verify output file was created
          if [ -d test_phosphors_output.idparquet ]; then
            echo "PhosphoRS output created successfully"
            ls -lh test_phosphors_output.idparquet/
          else
            echo "Warning: PhosphoRS output not created"
          fi

      - name: Test LucXor with real data
        run: |
          # Test LucXor algorithm with real data
          python -m onsite.lucxor.cli \
            -in data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1.mzML \
            -id data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1_comet_perc.idparquet \
            -out test_lucxor_output.idparquet \
            --fragment-method HCD \
            --fragment-mass-tolerance 0.5 \
            --fragment-mass-unit Da \
            --threads 1 \
            --min-num-psms-model 5

          # Verify output file was created
          if [ -d test_lucxor_output.idparquet ]; then
            echo "LucXor output created successfully"
            ls -lh test_lucxor_output.idparquet/
          else
            echo "Warning: LucXor output not created"
          fi

      - name: Test unified CLI with real data
        run: |
          # Test unified onsite CLI command
          onsite ascore \
            -in data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1.mzML \
            -id data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1_comet_perc.idparquet \
            -out test_unified_ascore.idparquet \
            --fragment-mass-tolerance 0.05 \
            --fragment-mass-unit Da \
            --threads 1 \
            --add-decoys

          onsite phosphors \
            -in data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1.mzML \
            -id data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1_comet_perc.idparquet \
            -out test_unified_phosphors.idparquet \
            --fragment-mass-tolerance 0.05 \
            --fragment-mass-unit Da \
            --threads 1 \
            --add-decoys

          onsite lucxor \
            -in data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1.mzML \
            -id data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1_comet_perc.idparquet \
            -out test_unified_lucxor.idparquet \
            --fragment-method HCD \
            --fragment-mass-tolerance 0.5 \
            --threads 1 \
            --min-num-psms-model 5

      - name: Verify reference result files exist
        run: |
          # Verify that reference result files exist for comparison
          echo "Checking reference result files..."
          ls -lh data/SF_200217_pPeptideLibrary_pool1_HCDnlETcaD_OT_rep1_comet_perc.idparquet || echo "Input idparquet directory 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()
        continue-on-error: true
        uses: actions/github-script@v7
        with:
          github-token: ${{ secrets.GITHUB_TOKEN }}
          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_*.idparquet/
            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