Merge pull request #103 from MannLabs/development

Release 1.5.4

.github/workflows/release_new.yml

@@ -0,0 +1,160 @@
+on:
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:
+
+
+name: Release on GitHub
+
+jobs:
+  Version_Bumped:
+    runs-on: ubuntu-latest
+    outputs:
+      version: ${{ steps.master_version_bumped.outputs.version }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - uses: conda-incubator/setup-miniconda@v3
+        with:
+          auto-update-conda: true
+          python-version: ${{ matrix.python-version }}
+      - name: Master version bumped
+        id: master_version_bumped
+        shell: bash -l {0}
+        run: |
+          cd misc
+          . ./check_version.sh
+          echo "version=$current_version" >> $GITHUB_OUTPUT
+   
+  Create_Draft_On_GitHub:
+    runs-on: ubuntu-latest
+    needs: Version_Bumped
+    outputs:
+      upload_url: ${{ steps.draft_release.outputs.upload_url }}
+    steps:
+      - name: Draft Release
+        id: draft_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: v${{ needs.Version_Bumped.outputs.version }}
+          release_name: v${{ needs.Version_Bumped.outputs.version }}
+          draft: true
+          prerelease: false
+
+  Create_MacOS_Installer:
+    needs: [Create_Draft_On_GitHub, Version_Bumped]
+    env:
+        ARCH: x64
+        EAGER_IMPORT: true
+    runs-on: macos-latest-xlarge
+    steps:
+    - name : Checkout code
+      uses: actions/checkout@v4
+
+    - name: Setup Node.js
+      uses: actions/setup-node@v4
+
+    - name: Install conda
+      uses: conda-incubator/setup-miniconda@v3
+      with:
+        miniconda-version: "latest"
+        continue-on-error: true
+        auto-update-conda: true
+        activate-environment: alpha
+        python-version: "3.11"
+
+    - name: Check arm64
+      shell: bash -el {0}
+      run: |
+        python -c "import platform; print(platform.machine())"
+
+    - name: Build GUI
+      run: |
+        release/macos/build_gui_macos.sh
+
+    - name: Build backend
+      shell: bash -l {0}
+      run: |
+        release/macos/build_backend_macos.sh
+
+    - name: Build package
+      shell: bash -l {0}
+      run: |
+        release/macos/build_pkg_macos.sh
+
+    - name: List output files
+      run: |
+        ls dist
+
+    - name: Upload a Release Asset
+      uses: actions/upload-release-asset@v1
+      env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      with:
+          upload_url: ${{ needs.Create_Draft_On_GitHub.outputs.upload_url }}
+          asset_path: dist/alphadia-${{ needs.Version_Bumped.outputs.version }}-darwin-${{ env.ARCH }}.pkg
+          asset_name: alphadia-${{ needs.Version_Bumped.outputs.version }}-darwin-${{ env.ARCH }}.pkg
+          asset_content_type: application/zip
+
+  #Create_Windows_Installer:
+  #  needs: [Create_Draft_On_GitHub, Version_Bumped]
+  #  env:
+  #      ARCH: x64
+  #  runs-on: windows-latest
+  #  steps:
+  #  - name : Checkout code
+  #    uses: actions/checkout@v4
+
+  #  - name: Setup Node.js
+  #    uses: actions/setup-node@v4
+
+  #  - name: Install conda
+  #    uses: conda-incubator/setup-miniconda@v3
+  #    with:
+  #      miniconda-version: "latest"
+  #      continue-on-error: true
+  #      auto-update-conda: true
+  #      activate-environment: alpha
+  #      python-version: "3.11"
+
+  #  - name: Check if Innosetup is installed
+  #    shell: powershell
+  #    run: |
+  #      if (-not (Test-Path "C:\Program Files (x86)\Inno Setup 6\ISCC.exe")) {
+  #        Write-Host "Inno Setup is not installed"
+  #        exit 1
+  #      }
+  #      else {
+  #        Write-Host "Inno Setup is installed"
+  #      }
+
+  #  - name: Build GUI
+  #    shell: powershell
+  #    run: |
+  #      release/windows/build_gui.ps1
+
+  #  - name: Build Backend
+  #    shell: powershell
+  #    run: |
+  #      release/windows/build_backend.ps1
+
+  #  - name: Build Installer
+  #    shell: powershell
+  #    run: |
+  #      release/windows/build_installer.ps1
+
+  #  - name: List output files
+  #    run: |
+  #      ls dist
+
+  #  - name: Upload a Release Asset
+  #    uses: actions/upload-release-asset@v1
+  #    env:
+  #        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+  #    with:
+  #        upload_url: ${{ needs.Create_Draft_On_GitHub.outputs.upload_url }}
+  #        asset_path: dist/alphadia-${{ needs.Version_Bumped.outputs.version }}-win-x64.exe
+  #        asset_name: alphadia-${{ needs.Version_Bumped.outputs.version }}-win-x64.exe
+  #        asset_content_type: application/zip

alphadia/__init__.py

@@ -2,7 +2,7 @@
 
 
 __project__ = "alphadia"
-__version__ = "1.5.3"
+__version__ = "1.5.4"
 __license__ = "Apache"
 __description__ = "An open-source Python package of the AlphaPept ecosystem"
 __author__ = "Mann Labs"
@@ -13,7 +13,7 @@
     "software",
     "AlphaPept ecosystem",
 ]
-__python_version__ = ">=3.8,<=3.12"
+__python_version__ = ">=3.8"
 __classifiers__ = [
     "Development Status :: 1 - Planning",
     # "Development Status :: 2 - Pre-Alpha",

alphadia/cli.py

@@ -300,7 +300,12 @@ def parse_fasta(args: argparse.Namespace, config: dict) -> list:
 
 def run(*args, **kwargs):
     # parse command line arguments
-    args = parser.parse_args()
+    args, unknown = parser.parse_known_args()
+
+    if unknown:
+        print(f"Unknown arguments: {unknown}")
+        parser.print_help()
+        return
 
     if args.version:
         print(f"{alphadia.__version__}")
@@ -310,7 +315,11 @@ def run(*args, **kwargs):
 
     output_directory = parse_output_directory(args, config)
     if output_directory is None:
-        raise ValueError("No output directory specified.")
+        # print help message if no output directory specified
+        parser.print_help()
+
+        print("No output directory specified.")
+        return
 
     reporting.init_logging(output_directory)
     raw_path_list = parse_raw_path_list(args, config)

alphadia/constants/default.yaml

@@ -0,0 +1,185 @@
+# configuration for the extraction plan
+version: 1
+
+general:
+  thread_count: 10
+  # maximum number of threads or processes to use per raw file
+  reuse_calibration: false
+  reuse_quant: false
+  astral_ms1: false
+  log_level: 'INFO'
+  wsl: false
+  mmap_detector_events: false
+  use_gpu: true
+
+library_loading:
+  rt_heuristic: 180
+  # if retention times are reported in absolute units, the rt_heuristic defines rt is interpreted as minutes or seconds
+
+library_prediction:
+  predict: False
+  enzyme: trypsin
+  fixed_modifications: 'Carbamidomethyl@C'
+  variable_modifications: 'Oxidation@M;Acetyl@Protein N-term'
+  max_var_mod_num: 2
+  missed_cleavages: 1
+  precursor_len:
+    - 7
+    - 35
+  precursor_charge:
+    - 2
+    - 4
+  precursor_mz:
+    - 400
+    - 1200
+  fragment_mz:
+    - 200
+    - 2000
+  nce: 25.0
+  instrument: QE
+  save_hdf: True
+
+search:
+  channel_filter: '0'
+  exclude_shared_ions: True
+  compete_for_fragments: True
+
+  target_num_candidates: 2
+  target_ms1_tolerance: 15
+  target_ms2_tolerance: 15
+  target_mobility_tolerance: 0.04
+  target_rt_tolerance: 60
+
+  quant_window: 3
+
+search_advanced:
+  top_k_fragments: 12
+
+calibration:
+  min_epochs: 3
+  max_epochs: 20
+  batch_size: 8000
+  recalibration_target: 200
+  final_full_calibration: False
+  norm_rt_mode: 'linear'
+
+search_initial:
+  initial_num_candidates: 1
+  initial_ms1_tolerance: 30
+  initial_ms2_tolerance: 30
+  initial_mobility_tolerance: 0.08
+  initial_rt_tolerance: 240
+
+selection_config:
+  peak_len_rt: 10.
+  sigma_scale_rt: 0.5
+  peak_len_mobility: 0.01
+  sigma_scale_mobility: 1.
+
+  top_k_precursors: 3
+  kernel_size: 30
+
+  f_mobility: 1.0
+  f_rt: 0.99
+  center_fraction: 0.5
+  min_size_mobility: 8
+  min_size_rt: 3
+  max_size_mobility: 50
+  max_size_rt: 15
+
+  group_channels: False
+  use_weighted_score: True
+
+  join_close_candidates: True
+  join_close_candidates_scan_threshold: 0.01
+  join_close_candidates_cycle_threshold: 0.6
+
+scoring_config:
+  score_grouped: false
+  top_k_isotopes: 3
+  reference_channel: -1
+  precursor_mz_tolerance: 10
+  fragment_mz_tolerance: 15
+
+multiplexing:
+  multiplexed_quant: False
+  target_channels: '4,8'
+  decoy_channel: 12
+  reference_channel: 0
+  competetive_scoring: True
+
+fdr:
+  fdr: 0.01
+  group_level: 'proteins'
+  competetive_scoring: true
+  keep_decoys: false
+  channel_wise_fdr: false
+  inference_strategy: "heuristic"
+
+search_output:
+  peptide_level_lfq: false
+  precursor_level_lfq: false
+  min_k_fragments: 12
+  min_correlation: 0.9
+  num_samples_quadratic: 50
+  min_nonnan: 3
+  normalize_lfq: True
+
+# configuration for the optimization manager
+# initial parameters, will nbe optimized
+optimization_manager:
+  fwhm_rt: 5
+  fwhm_mobility: 0.01
+  score_cutoff: 0
+
+# configuration for the calibration manager
+# the config has to start with the calibration keyword and consists of a list of calibration groups.
+# each group consists of datapoints which have multiple properties.
+# This can be for example precursors (mz, rt ...), fragments (mz, ...), quadrupole (transfer_efficiency)
+calibration_manager:
+  - name: fragment
+    estimators: 
+      - name: mz
+        model: LOESSRegression
+        model_args:
+          n_kernels: 2
+        input_columns: 
+          - mz_library
+        target_columns:
+          - mz_observed
+        output_columns:
+          - mz_calibrated
+        transform_deviation: 1e6
+  - name: precursor
+    estimators: 
+        - name: mz
+          model: LOESSRegression
+          model_args:
+            n_kernels: 2
+          input_columns: 
+            - mz_library
+          target_columns:
+            - mz_observed
+          output_columns:
+            - mz_calibrated
+          transform_deviation: 1e6
+        - name: rt
+          model: LOESSRegression
+          model_args:
+            n_kernels: 6
+          input_columns: 
+            - rt_library
+          target_columns:
+            - rt_observed
+          output_columns:
+            - rt_calibrated
+        - name: mobility
+          model: LOESSRegression
+          model_args:
+            n_kernels: 2
+          input_columns: 
+            - mobility_library
+          target_columns:
+            - mobility_observed
+          output_columns:
+            - mobility_calibrated