masster 0.5.18__tar.gz → 0.5.19__tar.gz

{masster-0.5.18 → masster-0.5.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.18
+Version: 0.5.19
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster

{masster-0.5.18 → masster-0.5.19}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.18"
+version = "0.5.19"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.18 → masster-0.5.19}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.18"
+__version__ = "0.5.19"
 
 
 def get_version():

{masster-0.5.18 → masster-0.5.19}/src/masster/sample/defaults/find_ms2_def.py

@@ -42,7 +42,7 @@ class find_ms2_defaults:
         - get_description(param_name): Get parameter description
         - get_info(param_name): Get full parameter metadata
         - list_parameters(): Get list of all parameter names
-        - get_mz_tolerance(file_type): Get appropriate m/z tolerance based on file type
+        - get_mz_tolerance(type): Get appropriate m/z tolerance based on type
     """
 
     # Core MS2 linking parameters
@@ -270,16 +270,16 @@ class find_ms2_defaults:
 
         return len(invalid_params) == 0, invalid_params
 
-    def get_mz_tolerance(self, file_type=None):
+    def get_mz_tolerance(self, type=None):
         """
-        Get the appropriate m/z tolerance based on file type.
+        Get the appropriate m/z tolerance based on type.
 
         Args:
-            file_type (str, optional): File type ('ztscan', 'dia', or other)
+            type (str, optional): Acquisition type ('ztscan', 'dia', or other)
 
         Returns:
             float: Appropriate m/z tolerance value
         """
-        if file_type is not None and file_type.lower() in ["ztscan", "dia"]:
+        if type is not None and type.lower() in ["ztscan", "dia"]:
             return self.get("mz_tol_ztscan")
         return self.get("mz_tol")

{masster-0.5.18 → masster-0.5.19}/src/masster/sample/h5.py

@@ -1,4 +1,4 @@
-import json
+import json
 import os
 
 import h5py
@@ -94,8 +94,8 @@ def _save_sample5(
             metadata_group.attrs["file_source"] = str(self.file_source)
         else:
             metadata_group.attrs["file_source"] = ""
-        if hasattr(self, 'file_type') and self.file_type is not None:
-            metadata_group.attrs["file_type"] = str(self.file_type)
+        if hasattr(self, 'type') and self.type is not None:
+            metadata_group.attrs["file_type"] = str(self.type)
         else:
             metadata_group.attrs["file_type"] = ""
         if self.label is not None:
@@ -393,7 +393,7 @@ def _load_sample5(self, filename: str, map: bool = False):
             else:
                 self.file_source = self.file_path
 
-            self.file_type = decode_metadata_attr(
+            self.type = decode_metadata_attr(
                 metadata_group.attrs.get("file_type", ""),
             )
             self.label = decode_metadata_attr(metadata_group.attrs.get("label", ""))
@@ -1160,7 +1160,7 @@ def _load_sample5_study(self, filename: str, map: bool = False):
             else:
                 self.file_source = self.file_path
 
-            self.file_type = decode_metadata_attr(
+            self.type = decode_metadata_attr(
                 metadata_group.attrs.get("file_type", ""),
             )
             self.label = decode_metadata_attr(metadata_group.attrs.get("label", ""))
@@ -2302,7 +2302,7 @@ def create_h5_metadata_group(
     f: h5py.File,
     file_path: Optional[str],
     file_source: Optional[str],
-    file_type: Optional[str],
+    type: Optional[str],
     label: Optional[str],
 ) -> None:
     """
@@ -2312,7 +2312,7 @@ def create_h5_metadata_group(
         f: The HDF5 file object
         file_path: Source file path
         file_source: Original source file path
-        file_type: Source file type
+        type: Source file type
         label: Sample label
     """
     metadata_group = f.create_group("metadata")
@@ -2321,5 +2321,5 @@ def create_h5_metadata_group(
     metadata_group.attrs["file_source"] = (
         str(file_source) if file_source is not None else ""
     )
-    metadata_group.attrs["file_type"] = str(file_type) if file_type is not None else ""
+    metadata_group.attrs["file_type"] = str(type) if type is not None else ""
     metadata_group.attrs["label"] = str(label) if label is not None else ""

{masster-0.5.18 → masster-0.5.19}/src/masster/sample/processing.py

@@ -1028,7 +1028,7 @@ def find_ms2(self, **kwargs):
 
     - mz_tol (float):
         Precursor m/z tolerance used for matching. The effective tolerance may be
-        adjusted by file type (the defaults class provides ``get_mz_tolerance(file_type)``).
+        adjusted by type (the defaults class provides ``get_mz_tolerance(type)``).
         Default: 0.5 (ztscan/DIA defaults may be larger).
 
     - centroid (bool):
@@ -1077,7 +1077,7 @@ def find_ms2(self, **kwargs):
 
     # Extract parameter values
     features = params.get("features")
-    mz_tol = params.get_mz_tolerance(self.file_type)
+    mz_tol = params.get_mz_tolerance(self.type)
     centroid = params.get("centroid")
     deisotope = params.get("deisotope")
     dia_stats = params.get("dia_stats")

{masster-0.5.18 → masster-0.5.19}/src/masster/sample/sciex.py

@@ -379,7 +379,7 @@ class SciexWiffData:
         self._raw_file_path = ""
         self.centroided = centroided
         self.creation_time = ""
-        self.file_type = "sciex"
+        self.type = "sciex"
         self.instrument = "sciex"
 
         if self.centroided:
@@ -616,7 +616,7 @@ if __name__ == "__main__":
             print(f"  - Number of spectra: {len(wiff_data.spectrum_df)}")
             print(f"  - Number of peaks: {len(wiff_data.peak_df)}")
             print(f"  - Creation time: {wiff_data.creation_time}")
-            print(f"  - File type: {wiff_data.file_type}")
+            print(f"  - File type: {wiff_data.type}")
             print(f"  - Instrument: {wiff_data.instrument}")
 
             # Test getting peaks from first spectrum

{masster-0.5.18 → masster-0.5.19}/src/masster/sample/thermo.py

@@ -524,7 +524,7 @@ class ThermoRawData:
         # File and instrument information
         self._raw_file_path = ""
         self.creation_time = ""
-        self.file_type = "thermo"
+        self.type = "thermo"
         self.instrument = "thermo"
         
         # Processing parameters

{masster-0.5.18 → masster-0.5.19}/src/masster/wizard/README.md

@@ -12,7 +12,7 @@ from masster import Wizard
 # Create wizard with minimal configuration
 wizard = Wizard(
     data_source="./raw_data",      # Directory with raw files
-    study_folder="./processed",    # Output directory  
+    study_folder="./processed",    # Output directory
     polarity="positive",           # or "negative"
     num_cores=4                    # CPU cores to use
 )
@@ -35,22 +35,22 @@ params = wizard_def(
     study_folder="./processed_advanced",
     polarity="negative",
     num_cores=8,
-    
+
     # File discovery
     file_extensions=[".wiff", ".raw", ".mzML"],
     search_subfolders=True,
     skip_patterns=["blank", "QC", "test"],
-    
+
     # Processing parameters
     adducts=["H-1:-:0.95", "Cl:-:0.05", "CH2O2:0:0.2"],
     chrom_fwhm=0.15,
     noise_threshold=5e4,
-    
+
     # Study assembly
     rt_tolerance=1.0,
     mz_tolerance=0.008,
     min_samples_for_merge=30,
-    
+
     # Output options
     export_formats=["csv", "xlsx", "mgf", "parquet"],
     generate_plots=True,
@@ -73,7 +73,7 @@ wizard.run_full_pipeline()
 
 ### 💾 Intelligent Resume
 - **Checkpoint System**: Automatically saves progress at key points
-- **File Tracking**: Remembers which files have been processed successfully  
+- **File Tracking**: Remembers which files have been processed successfully
 - **Smart Recovery**: Resumes from last successful step after interruption
 - **Validation**: Verifies existing outputs before skipping
 
@@ -112,7 +112,7 @@ wizard.run_full_pipeline()
 
 ### 4. Feature Alignment
 - **RT Alignment**: Corrects retention time shifts between samples
-- **Mass Alignment**: Accounts for mass calibration differences  
+- **Mass Alignment**: Accounts for mass calibration differences
 - **Algorithm Selection**: Supports KD-tree, QT-clustering, and chunked methods
 - **Validation**: Reports alignment statistics and quality metrics
 
@@ -232,7 +232,7 @@ Returns detailed status dictionary with current step, processed files, timing, a
 - Ensure sufficient disk space in output directory
 - Close any applications that might lock files
 
-**Processing Failures** 
+**Processing Failures**
 - Check individual file integrity
 - Review `skip_patterns` to exclude problematic files
 - Examine detailed logs in `wizard.log` and `processing.log`
@@ -249,7 +249,7 @@ The Wizard includes built-in validation at each step:
 
 - **File Validation**: Checks file accessibility and format compatibility
 - **Processing Validation**: Verifies sample5 outputs can be loaded
-- **Study Validation**: Ensures study assembly completed successfully  
+- **Study Validation**: Ensures study assembly completed successfully
 - **Alignment Validation**: Reports alignment statistics and warnings
 - **Export Validation**: Confirms all requested outputs were created
 
@@ -257,7 +257,7 @@ The Wizard includes built-in validation at each step:
 
 ### System Requirements
 - **Minimum**: 4 CPU cores, 8 GB RAM
-- **Recommended**: 8+ CPU cores, 16+ GB RAM  
+- **Recommended**: 8+ CPU cores, 16+ GB RAM
 - **Large Studies**: 16+ CPU cores, 32+ GB RAM
 - **Storage**: SSD recommended, ~2-3x raw data size free space
 
@@ -265,7 +265,7 @@ The Wizard includes built-in validation at each step:
 
 **For Small Studies (< 50 samples)**
 - Use `num_cores = 4-6`
-- Set `batch_size = 4-8`  
+- Set `batch_size = 4-8`
 - Use `merge_method = "kd"`
 - Enable all export formats
 
@@ -297,7 +297,7 @@ if not wizard.study_folder_path.glob("*.sample5"):
 
 # Continue with study-level processing
 wizard.assemble_study()
-wizard.align_and_merge() 
+wizard.align_and_merge()
 wizard.export_results()
 ```
 
@@ -312,7 +312,7 @@ studies = [
 for study_config in studies:
     wizard = Wizard(**study_config, num_cores=8)
     success = wizard.run_full_pipeline()
-    
+
     if success:
         print(f"✅ {study_config['output']} completed")
     else:
@@ -338,7 +338,7 @@ if hasattr(wizard.study, 'features_filter'):
     )
     wizard.study.features_filter(selection)
 
-# Continue with standard pipeline  
+# Continue with standard pipeline
 wizard.align_and_merge()
 wizard.generate_plots()
 ```
@@ -370,4 +370,4 @@ The Wizard generates several types of output files:
 - `sample_name.mgf` - Individual sample MS2 spectra
 - `sample_name_2d.html` - Individual sample 2D plot
 
-The Wizard provides a complete, automated solution for mass spectrometry data processing while maintaining flexibility for custom workflows and providing robust error handling and recovery capabilities.
+The Wizard provides a complete, automated solution for mass spectrometry data processing while maintaining flexibility for custom workflows and providing robust error handling and recovery capabilities.

{masster-0.5.18 → masster-0.5.19}/src/masster/wizard/wizard.py

@@ -66,7 +66,7 @@ class wizard_def:
         # Core Configuration
         source (str): Path to directory containing raw data files
         folder (str): Output directory for processed study
-        polarity (str): Ion polarity mode ("positive" or "negative")
+        polarity (Optional[str]): Ion polarity mode ("positive", "negative", or None for auto-detection)
         num_cores (int): Number of CPU cores to use for parallel processing
         
         # File Discovery
@@ -98,7 +98,7 @@ class wizard_def:
     # === Core Configuration ===
     source: str = ""
     folder: str = ""  
-    polarity: str = "positive"
+    polarity: Optional[str] = None
     num_cores: int = 4
     
     # === File Discovery ===
@@ -198,12 +198,12 @@ class wizard_def:
         """Set polarity-specific defaults after initialization."""
         # Set default adducts based on polarity if not provided
         if not self.adducts:
-            if self.polarity.lower() in ["positive", "pos"]:
+            if self.polarity and self.polarity.lower() in ["positive", "pos"]:
                 self.adducts = ["H:+:0.8", "Na:+:0.1", "NH4:+:0.1"]
-            elif self.polarity.lower() in ["negative", "neg"]: 
+            elif self.polarity and self.polarity.lower() in ["negative", "neg"]: 
                 self.adducts = ["H-1:-:1.0", "CH2O2:0:0.5"]
             else:
-                # Default to positive
+                # Default to positive if polarity is None or unknown
                 self.adducts = ["H:+:0.8", "Na:+:0.1", "NH4:+:0.1"]
         
         # Validate num_cores
@@ -245,7 +245,7 @@ class Wizard:
         self,
         source: str = "",
         folder: str = "",
-        polarity: str = "positive",
+        polarity: Optional[str] = None,
         adducts: Optional[List[str]] = None,
         num_cores: int = 6,
         **kwargs
@@ -256,7 +256,7 @@ class Wizard:
         Parameters:
             source: Directory containing raw data files
             folder: Output directory for processed study
-            polarity: Ion polarity mode ("positive" or "negative")
+            polarity: Ion polarity mode ("positive", "negative", or None for auto-detection)
             adducts: List of adduct specifications (auto-set if None)
             num_cores: Number of CPU cores (0 = auto-detect 75% of available)
             **kwargs: Additional parameters (see wizard_def for full list)
@@ -298,8 +298,8 @@ class Wizard:
         self.folder_path = Path(self.params.folder) 
         self.folder_path.mkdir(parents=True, exist_ok=True)
         
-        # Auto-infer polarity from the first file if not explicitly set by user
-        if polarity == "positive" and "polarity" not in kwargs:
+        # Auto-infer polarity from the first file if polarity is None
+        if self.params.polarity is None:
             inferred_polarity = self._infer_polarity_from_first_file()
             if inferred_polarity:
                 self.params.polarity = inferred_polarity
@@ -311,7 +311,7 @@ class Wizard:
         Infer polarity from the first available raw data file.
         
         Returns:
-            Inferred polarity string ("positive" or "negative") or None if detection fails
+            Inferred polarity string ("positive" or "negative") or "positive" as fallback
         """
         try:
             # Find first file
@@ -324,31 +324,85 @@ class Wizard:
             else:
                 return 'positive'
 
-            # Only implement for .wiff files initially (most common format)
+            # Handle different file formats
             if first_file.suffix.lower() == '.wiff':
-                from masster.sample.load import _wiff_to_dict
-                
-                # Extract metadata from first file
-                metadata_df = _wiff_to_dict(str(first_file))
-                
-                if not metadata_df.empty and 'polarity' in metadata_df.columns:
-                    # Get polarity from first experiment  
-                    first_polarity = metadata_df['polarity'].iloc[0]
-                    
-                    # Convert numeric polarity codes to string
-                    if first_polarity == 1 or str(first_polarity).lower() in ['positive', 'pos', '+']:
-                        return "positive"
-                    elif first_polarity == -1 or str(first_polarity).lower() in ['negative', 'neg', '-']:
-                        return "negative"
+                return self._infer_polarity_from_wiff(str(first_file))
+            elif first_file.suffix.lower() == '.raw':
+                return self._infer_polarity_from_raw(str(first_file))
+            elif first_file.suffix.lower() == '.mzml':
+                return self._infer_polarity_from_mzml(str(first_file))
                     
         except Exception:
             # Silently fall back to default if inference fails
             pass
             
         return 'positive'
+        
+    def _infer_polarity_from_wiff(self, filename: str) -> str:
+        """Infer polarity from WIFF file."""
+        try:
+            from masster.sample.load import _wiff_to_dict
+            
+            # Extract metadata from first file
+            metadata_df = _wiff_to_dict(filename)
+            
+            if not metadata_df.empty and 'polarity' in metadata_df.columns:
+                # Get polarity from first experiment  
+                first_polarity = metadata_df['polarity'].iloc[0]
+                
+                # Convert numeric polarity codes to string
+                if first_polarity == 1 or str(first_polarity).lower() in ['positive', 'pos', '+']:
+                    return "positive"
+                elif first_polarity == -1 or str(first_polarity).lower() in ['negative', 'neg', '-']:
+                    return "negative"
+        except Exception:
+            pass
+        return 'positive'
+        
+    def _infer_polarity_from_raw(self, filename: str) -> str:
+        """Infer polarity from Thermo RAW file."""
+        try:
+            from masster.sample.thermo import ThermoRawFileReader
+            
+            with ThermoRawFileReader(filename) as raw_reader:
+                # Get polarity from first scan
+                first_scan = 1
+                polarity = raw_reader.get_polarity_from_scan_event(first_scan)
+                if polarity in ['positive', 'negative']:
+                    return polarity
+        except Exception:
+            pass
+        return 'positive'
+        
+    def _infer_polarity_from_mzml(self, filename: str) -> str:
+        """Infer polarity from mzML file."""
+        try:
+            # Import pyopenms with warnings suppression
+            import warnings
+            with warnings.catch_warnings():
+                warnings.filterwarnings("ignore", message=".*OPENMS_DATA_PATH.*", category=UserWarning)
+                import pyopenms as oms
+            
+            # Load the first few spectra to check polarity
+            omsexp = oms.MSExperiment()
+            oms.MzMLFile().load(filename, omsexp)
+            
+            if omsexp.getNrSpectra() > 0:
+                first_spectrum = omsexp.getSpectra()[0]
+                try:
+                    pol = first_spectrum.getInstrumentSettings().getPolarity()
+                    if pol == 1:
+                        return "positive"
+                    elif pol == 2:
+                        return "negative"
+                except Exception:
+                    pass
+        except Exception:
+            pass
+        return 'positive'
 
     @property
-    def polarity(self) -> str:
+    def polarity(self) -> Optional[str]:
         """Get the ion polarity mode."""
         return self.params.polarity
 
@@ -1323,7 +1377,7 @@ class Wizard:
 def create_scripts(
     source: str = "", 
     folder: str = "", 
-    polarity: str = "positive",
+    polarity: Optional[str] = None,
     adducts: Optional[List[str]] = None,
     num_cores: int = 0,
     **kwargs
@@ -1337,7 +1391,7 @@ def create_scripts(
     Parameters:
         source: Directory containing raw data files
         folder: Output directory for processed study
-        polarity: Ion polarity mode ("positive" or "negative")
+        polarity: Ion polarity mode ("positive", "negative", or None for auto-detection)
         adducts: List of adduct specifications (auto-set if None)
         num_cores: Number of CPU cores (0 = auto-detect)
         **kwargs: Additional parameters

{masster-0.5.18 → masster-0.5.19}/uv.lock

@@ -1368,7 +1368,7 @@ wheels = [
 
 [[package]]
 name = "masster"
-version = "0.5.18"
+version = "0.5.19"
 source = { editable = "." }
 dependencies = [
     { name = "alpharaw" },