Merge pull request #26 from MannLabs/development

Author: PatriciaSkowronek

.github/workflows/pip_installation.yml

@@ -13,7 +13,8 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, macOS-latest, windows-latest]
+        # os: [ubuntu-latest, macOS-latest, windows-latest]
+        os: [ubuntu-latest, windows-latest]
     steps:
       - uses: actions/checkout@v2
       - uses: conda-incubator/setup-miniconda@v2
@@ -38,7 +39,8 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, macOS-latest, windows-latest]
+        # os: [ubuntu-latest, macOS-latest, windows-latest]
+        os: [ubuntu-latest, windows-latest]
     steps:
       - uses: actions/checkout@v2
       - uses: conda-incubator/setup-miniconda@v2

.github/workflows/publish_and_release.yml

@@ -73,38 +73,38 @@ jobs:
           asset_path: release/one_click_linux_gui/dist/pydiaid_gui_installer_linux.deb
           asset_name: pydiaid_gui_installer_linux.deb
           asset_content_type: application/octet-stream
-  Create_MacOS_Release:
-    runs-on: macos-latest
-    needs: Create_Draft_On_GitHub
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v2
-      - uses: conda-incubator/setup-miniconda@v2
-        with:
-          auto-update-conda: true
-          python-version: ${{ matrix.python-version }}
-      - name: Conda info
-        shell: bash -l {0}
-        run: conda info
-      - name: Creating installer for MacOS
-        shell: bash -l {0}
-        run: |
-          cd release/one_click_macos_gui
-          . ./create_installer_macos.sh
-      - name: Test installer for MacOS
-        shell: bash -l {0}
-        run: |
-          sudo installer -pkg release/one_click_macos_gui/dist/pydiaid_gui_installer_macos.pkg -target /
-      - name: Upload MacOS Installer
-        id: upload-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: release/one_click_macos_gui/dist/pydiaid_gui_installer_macos.pkg
-          asset_name: pydiaid_gui_installer_macos.pkg
-          asset_content_type: application/octet-stream
+  # Create_MacOS_Release:
+  #   runs-on: macos-latest
+  #   needs: Create_Draft_On_GitHub
+  #   steps:
+  #     - name: Checkout code
+  #       uses: actions/checkout@v2
+  #     - uses: conda-incubator/setup-miniconda@v2
+  #       with:
+  #         auto-update-conda: true
+  #         python-version: ${{ matrix.python-version }}
+  #     - name: Conda info
+  #       shell: bash -l {0}
+  #       run: conda info
+  #     - name: Creating installer for MacOS
+  #       shell: bash -l {0}
+  #       run: |
+  #         cd release/one_click_macos_gui
+  #         . ./create_installer_macos.sh
+  #     - name: Test installer for MacOS
+  #       shell: bash -l {0}
+  #       run: |
+  #         sudo installer -pkg release/one_click_macos_gui/dist/pydiaid_gui_installer_macos.pkg -target /
+  #     - name: Upload MacOS Installer
+  #       id: upload-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: release/one_click_macos_gui/dist/pydiaid_gui_installer_macos.pkg
+  #         asset_name: pydiaid_gui_installer_macos.pkg
+  #         asset_content_type: application/octet-stream
   Create_Windows_Release:
     runs-on: windows-latest
     needs: Create_Draft_On_GitHub

README.md

@@ -165,7 +165,7 @@ In case of issues, check out the following links:
 ---
 ## Citations
 
-Check out the [dia-PASEF publication](https://doi.org/10.1016/j.mcpro.2022.100279) and [synchro-PASEF publication](https://doi.org/10.1016/j.mcpro.2022.100489).
+Check out the [optimal dia-PASEF](https://doi.org/10.1016/j.mcpro.2022.100279), [synchro-PASEF](https://doi.org/10.1016/j.mcpro.2022.100489) and [PASEF workflows and py_diAID](https://doi.org/10.1038/s41596-024-01104-w) publications.
 
 ---
 ## How to contribute

misc/bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.0.30
+current_version = 0.0.40
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?

pydiaid/__init__.py

@@ -2,7 +2,7 @@
 
 
 __project__ = "pydiaid"
-__version__ = "0.0.30"
+__version__ = "0.0.40"
 __license__ = "Apache"
 __description__ = "An open-source Python package of the AlphaPept ecosystem"
 __author__ = "Mann Labs"

pydiaid/gui.py

@@ -481,7 +481,7 @@ def __init__(self, start_server=False):
             name="py_diAID",
             github_url='https://github.com/MannLabs/pydiaid',
         )
-        self.project_description = """#### py_diAID is a Python tool that automatically and optimally places DIA (Data-Independent Acquisition) window schemes for efficient precursor coverage. Using pre-acquired precursor information, it generates dia-PASEF, synchro-PASEF, and Orbitrap Astral DIA methods. The name diAID stands for Automated Isolation Design for DIA.\n <i style="font-size: 0.8em; display: block">  Please cite: Skowronek, … , Mann, MCP, 2022 for dia-PASEF and \n Skowronek, … , Willems, Raether, Mann, MCP, 2023 for synchro-PASEF.</i>"""
+        self.project_description = """#### py_diAID is a Python tool that automatically and optimally places DIA (Data-Independent Acquisition) window schemes for efficient precursor coverage. Using pre-acquired precursor information, it generates dia-PASEF, synchro-PASEF, and Orbitrap Astral DIA methods. The name diAID stands for Automated Isolation Design for DIA.\n <i style="font-size: 0.8em; display: block">  Please cite: Skowronek et al., Mann, MCP, 2022 for optimal dia-PASEF methods, \n Skowronek et al., Willems, Raether, Mann, MCP, 2023 for synchro-PASEF, \n Skowronek et al., Mann, Nat Protoc, 2025 for PASEF workflows and py_diAID.</i>"""
 
         self.manual_path = os.path.join(
             DOCS_PATH,

pydiaid/loader.py

@@ -31,7 +31,11 @@ def load_library(
     try:
         # Special case for DIANN single-run which needs the file path directly
         if analysis_software == 'DIANN single-run':
-            return __parse_diann_single_run(library_name, ptm_list, require_im)
+            if library_name.split(".")[-1] == "parquet":
+                analysis_software = 'DIANN library'
+            else:
+                return __parse_diann_single_run(library_name, ptm_list, require_im)
+
 
         # For all other software, load the dataframe first
         dataframe = __load_dataframe_from_file(library_name)
@@ -73,9 +77,67 @@ def __load_dataframe_from_file(
 
     if library_name.split(".")[-1] == "csv":
         return pd.read_csv(library_name, sep=',')
+    if library_name.split(".")[-1] == "parquet":
+        return pd.read_parquet(library_name, engine='fastparquet')
     else:
         return pd.read_csv(library_name, sep='\t')  # .xls, .tsv, .txt
 
+class ColumnMapper:
+    """Handles column name mapping across different software versions."""
+    
+    # Define all possible column variants as class attributes
+    COLUMN_VARIANTS = {
+        'decoy': ['decoy', 'Decoy', 'is_decoy'],
+        'qvalue': ['QValue', 'Q.Value', 'q_value', 'Q_Value'],
+        'mobility': [
+            'PrecursorIonMobility',
+            'IonMobility',
+            'Ion Mobility',
+            'ion_mobility',
+            'IM',
+            'Mobility',
+            '1/K0'
+        ],
+        'mz': ['PrecursorMz', 'Precursor.Mz', 'Mz', 'PrecursorMZ', 'Calibrated Observed M/Z'],
+        'charge': ['PrecursorCharge', 'Precursor.Charge', 'Charge'],
+        'protein': ['ProteinId', 'ProteinName', 'Protein.Names', 'Protein', 'Protein ID'],
+        'modified_peptide': [
+            'ModifiedPeptideSequence',
+            'ModifiedPeptide',
+            'Modified.Sequence',
+            'Modified Sequence',
+            'Modified Peptide'
+        ],
+        'peptide': ['Peptide', 'PeptideSequence', 'Sequence']
+    }
+
+    def __init__(self, dataframe: pd.DataFrame):
+        """Initialize with a dataframe and map its columns."""
+        self.df = dataframe
+        self.column_map = self._create_column_map()
+
+    def _create_column_map(self) -> dict:
+        """Create mapping of standard names to actual column names in dataframe."""
+        column_map = {}
+        for standard_name, variants in self.COLUMN_VARIANTS.items():
+            found_col = next((col for col in variants if col in self.df.columns), None)
+            column_map[standard_name] = found_col
+        return column_map
+
+    def get_column(self, standard_name: str) -> str:
+        """Get the actual column name for a standard column identifier."""
+        return self.column_map.get(standard_name)
+
+    def validate_required_columns(self, required_columns: list) -> None:
+        """Validate that all required columns exist."""
+        missing = [col for col in required_columns if self.get_column(col) is None]
+        if missing:
+            raise ValueError(f"Required columns missing: {', '.join(missing)}")
+
+    def has_column(self, standard_name: str) -> bool:
+        """Check if a standard column exists in the dataframe."""
+        return self.get_column(standard_name) is not None
+
 
 def __parse_alpha_pept(
     dataframe: pd.DataFrame,
@@ -175,8 +237,8 @@ def __parse_ms_fragger(
         columns.
 
     Parameters:
-    dataframe (pd.DataFrame): imported output file from the analysis software
-        "MSFragger".
+    dataframe (pd.DataFrame): imported library or psm file from the analysis software
+        "MSFragger". Required columns (supports multiple naming variants)
     File format: .tsv, required columns: 'PrecursorMz', 'PrecursorIonMobility',
         'PrecursorCharge', 'ProteinId', 'ModifiedPeptideSequence'.
     ptm_list (list): a list with identifiers used for filtering a specific dataframe column.
@@ -186,19 +248,28 @@ def __parse_ms_fragger(
     pd.DataFrame: returns a pre-filtered data frame with unified column names.
     """
 
-    im_col = 'PrecursorIonMobility' if 'PrecursorIonMobility' in dataframe.columns else None
+    mapper = ColumnMapper(dataframe)
 
-    if require_im and im_col is None:
-        raise Exception("Ion mobility data required but not found in MSFragger output")
+    required_columns = ['mz', 'charge', 'protein', 'modified_peptide']
+    if require_im:
+        required_columns.append('mobility')
+    
+    mapper.validate_required_columns(required_columns)
+    
+    if mapper.has_column('peptide'):
+        peptide_col = mapper.get_column('peptide')
+        mod_peptide_col = mapper.get_column('modified_peptide')
+        dataframe[mod_peptide_col] = dataframe[mod_peptide_col].replace('', pd.NA)
+        dataframe[mod_peptide_col] = dataframe[mod_peptide_col].fillna(dataframe[peptide_col])
 
     return library_loader(
         dataframe,
         ptm_list,
-        mz='PrecursorMz',
-        im=im_col,
-        charge='PrecursorCharge',
-        protein='ProteinId',
-        modified_peptide='ModifiedPeptideSequence'
+        mz=mapper.get_column('mz'),
+        im=mapper.get_column('mobility'),
+        charge=mapper.get_column('charge'),
+        protein=mapper.get_column('protein'),
+        modified_peptide=mapper.get_column('modified_peptide')
     )
 
 
@@ -313,40 +384,37 @@ def __parse_diann_lib(
 
     Parameters:
     dataframe (pd.DataFrame): imported library file from the analysis software
-        "DIANN". Required columns:
-        'PrecursorMz',
-        'IonMobility',
-        'PrecursorCharge',
-        'ProteinName',
-        'ModifiedPeptide',
-        'decoy',
-        'QValue'.
+        "DIANN". Required columns (supports multiple naming variants)
     ptm_list (list): a list with identifiers used for filtering a specific dataframe column.
     require_im (bool): if True, requires ion mobility data; if False, makes ion mobility optional.
 
     Returns:
     pd.DataFrame: returns a pre-filtered data frame with unified column names.
     """
-    # Filter out decoys and apply Q-value thresholdt
+        # Initialize column mapper
+    mapper = ColumnMapper(dataframe)
+    
+    # Check required columns
+    required_columns = ['decoy', 'qvalue', 'mz', 'charge', 'protein', 'modified_peptide']
+    if require_im:
+        required_columns.append('mobility')
+    
+    mapper.validate_required_columns(required_columns)
+    
+    # Filter dataframe
     filtered_dataframe = dataframe[
-        (dataframe['decoy'] == 0) &  # Remove decoy entries
-        (dataframe['QValue'] <= 0.01)  # Filter for 1% FDR
+        (dataframe[mapper.get_column('decoy')] == 0) &
+        (dataframe[mapper.get_column('qvalue')] <= 0.01)
     ]
-
-    # Check if IM column exists
-    im_col = 'IonMobility' if 'IonMobility' in dataframe.columns else None
 
-    if require_im and im_col is None:
-        raise Exception("Ion mobility data required but not found in DIANN library")
-
     return library_loader(
         filtered_dataframe,
         ptm_list,
-        mz='PrecursorMz',
-        im=im_col,
-        charge='PrecursorCharge',
-        protein='ProteinName',
-        modified_peptide='ModifiedPeptide'
+        mz=mapper.get_column('mz'),
+        im=mapper.get_column('mobility'),
+        charge=mapper.get_column('charge'),
+        protein=mapper.get_column('protein'),
+        modified_peptide=mapper.get_column('modified_peptide')
     )
 
 

pydiaid/oadia/method_generator.py

@@ -901,17 +901,9 @@ def adjust_bin_boundaries(bins, phospho_enriched=False):
         start_value = bins[i][0]
         end_value = bins[i][1]
 
-        # Adjust start value (except for first bin)
-        if i == 0:
-            adjusted_start = start_value
-        else:
-            adjusted_start = find_closest_forbidden_zone(start_value, phospho_enriched)
-            
-        # Adjust end value (except for last bin)
-        if i == len(bins) - 1:
-            adjusted_end = end_value
-        else:
-            adjusted_end = find_closest_forbidden_zone(end_value, phospho_enriched)
+        # Adjust value (including first and lastbin)
+        adjusted_start = find_closest_forbidden_zone(start_value, phospho_enriched)
+        adjusted_end = find_closest_forbidden_zone(end_value, phospho_enriched)
 
         adjusted_bins.append([adjusted_start, adjusted_end])
 

pydiaid/synchropasef/method_creator.py

@@ -373,6 +373,15 @@ def calculate_scan_area(
 
 
     return df_scan_area
+
+
+def check_slope(params_list):
+    """Fix floating-point precision errors in parameter lists"""
+    for i, params in enumerate(params_list):
+        col0, col1, col2, col3, col4 = params
+        slope = (col4 - col1) / (col3 - col0)
+        print(slope)
+        print(params)
 
 
 def generate_isolation_windows(
@@ -438,17 +447,19 @@ def generate_isolation_windows(
         "2"
     )
 
+    rounding_factor = 0
     list_method_parameters = list()
     for index in range(len(mz_start_lower_IM)):
         list_temp = [
             df_scan_area["lower_IM"].iloc[0], 
-            round(mz_start_lower_IM[index], 1), 
-            round(mz_start_lower_IM[index]+mz_width_lower_IM[index], 1),
+            np.round(mz_start_lower_IM[index], rounding_factor), 
+            np.round(mz_start_lower_IM[index]+mz_width_lower_IM[index], rounding_factor),
             df_scan_area["upper_IM"].iloc[0],
-            round(mz_start_upper_IM[index], 1)
+            np.round(mz_start_upper_IM[index], rounding_factor)
         ]
         list_method_parameters.append(list_temp)
-    list_method_parameters 
+    
+    # check_slope(list_method_parameters)
 
     df_method_parameters = pd.DataFrame(
         list_method_parameters,

release/one_click_linux_gui/control

@@ -1,5 +1,5 @@
 Package: pydiaid
-Version: 0.0.30
+Version: 0.0.40
 Architecture: all
 Maintainer: Mann Labs <opensource@alphapept.com>
 Description: py_diAID