masster 0.4.18__py3-none-any.whl → 0.4.20__py3-none-any.whl

masster/wizard/wizard.py

@@ -44,7 +44,9 @@ wizard.export_results()
 from __future__ import annotations
 
 import os
+import sys
 import time
+import importlib
 import multiprocessing
 from pathlib import Path
 from typing import Optional, Any, Dict, List
@@ -124,17 +126,18 @@ class wizard_def:
     checkpoint_interval: int = 10  # Save progress every N files
     
     # === Study Assembly ===
-    min_samples_for_merge: int = 50
+    min_samples_for_merge: int = 2
     rt_tolerance: float = 1.5
-    mz_tolerance: float = 0.01
+    mz_max_diff: float = 0.01
     alignment_algorithm: str = "kd"
     merge_method: str = "chunked"
     
     # === Feature Detection ===
-    chrom_fwhm: float = 0.2
-    noise_threshold: float = 1e5
+    chrom_fwhm: float = 0.5
+    noise_threshold: float = 200.0
     chrom_peak_snr: float = 5.0
     tol_ppm: float = 10.0
+    detector_type: str = "unknown"  # Detected detector type ("orbitrap", "quadrupole", "unknown")
     
     # === Output & Export ===
     generate_plots: bool = True
@@ -232,10 +235,16 @@ class Wizard:
     of mass spectrometry files from raw data to final study results, including:
     
     1. Raw data discovery and batch conversion to sample5 format
-    2. Study assembly with feature alignment and merging 
-    3. Automated plot generation and result export
-    4. Intelligent resume capability for interrupted processes
-    5. Adaptive optimization based on study size and system resources
+    2. Automatic detector type detection and parameter optimization
+    3. Study assembly with feature alignment and merging 
+    4. Automated plot generation and result export
+    5. Intelligent resume capability for interrupted processes
+    6. Adaptive optimization based on study size and system resources
+    
+    The wizard automatically detects the type of MS detector using simplified rules:
+    - .raw files: Assume Orbitrap (noise threshold = 1e5)
+    - .wiff files: Assume Quadrupole (noise threshold = 200)
+    - .mzML files: Check metadata for Orbitrap detection
     
     The wizard handles the complete workflow with minimal user intervention
     while providing comprehensive logging and progress tracking.
@@ -262,6 +271,10 @@ class Wizard:
             **kwargs: Additional parameters (see wizard_def for full list)
         """
         
+        # Auto-detect optimal number of cores (75% of total)
+        if num_cores <= 0:
+            num_cores = max(1, int(multiprocessing.cpu_count() * 0.75))
+            
         # Create parameters instance
         if "params" in kwargs and isinstance(kwargs["params"], wizard_def):
             self.params = kwargs.pop("params")
@@ -293,6 +306,14 @@ class Wizard:
         self.study_folder_path = Path(self.params.study_folder) 
         self.study_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:
+            inferred_polarity = self._infer_polarity_from_first_file()
+            if inferred_polarity:
+                self.params.polarity = inferred_polarity
+                # Update adducts based on inferred polarity  
+                self.params.__post_init__()
+        
         # Setup logging
         self._setup_logging()
         
@@ -315,6 +336,47 @@ class Wizard:
         if self.params.resume_enabled:
             self._load_checkpoint()
     
+    def _infer_polarity_from_first_file(self) -> str:
+        """
+        Infer polarity from the first available raw data file.
+        
+        Returns:
+            Inferred polarity string ("positive" or "negative") or None if detection fails
+        """
+        try:
+            # Find first file
+            for extension in ['.wiff', '.raw', '.mzML', '.d']:
+                pattern = f"**/*{extension}" if True else f"*{extension}"  # search_subfolders=True
+                files = list(self.data_source_path.rglob(pattern))
+                if files:
+                    first_file = files[0]
+                    break
+            else:
+                return None
+            
+            # Only implement for .wiff files initially (most common format)
+            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"
+                    
+        except Exception:
+            # Silently fall back to default if inference fails
+            pass
+            
+        return None
+    
     @property
     def polarity(self) -> str:
         """Get the polarity setting."""
@@ -324,6 +386,93 @@ class Wizard:
     def adducts(self) -> List[str]:
         """Get the adducts list."""
         return self.params.adducts
+    
+    def _reload(self):
+        """
+        Reloads all masster modules to pick up any changes to their source code,
+        and updates the instance's class reference to the newly reloaded class version.
+        This ensures that the instance uses the latest implementation without restarting the interpreter.
+        """
+        # Reset logger configuration flags to allow proper reconfiguration after reload
+        try:
+            import masster.logger as logger_module
+
+            if hasattr(logger_module, "_WIZARD_LOGGER_CONFIGURED"):
+                logger_module._WIZARD_LOGGER_CONFIGURED = False
+        except Exception:
+            pass
+
+        # Get the base module name (masster)
+        base_modname = self.__class__.__module__.split(".")[0]
+        current_module = self.__class__.__module__
+
+        # Dynamically find all wizard submodules
+        wizard_modules = []
+        wizard_module_prefix = f"{base_modname}.wizard."
+
+        # Get all currently loaded modules that are part of the wizard package
+        for module_name in sys.modules:
+            if (
+                module_name.startswith(wizard_module_prefix)
+                and module_name != current_module
+            ):
+                wizard_modules.append(module_name)
+
+        # Add core masster modules
+        core_modules = [
+            f"{base_modname}._version",
+            f"{base_modname}.chromatogram",
+            f"{base_modname}.spectrum",
+            f"{base_modname}.logger",
+        ]
+
+        # Add sample submodules
+        sample_modules = []
+        sample_module_prefix = f"{base_modname}.sample."
+        for module_name in sys.modules:
+            if (
+                module_name.startswith(sample_module_prefix)
+                and module_name != current_module
+            ):
+                sample_modules.append(module_name)
+
+        # Add study submodules
+        study_modules = []
+        study_module_prefix = f"{base_modname}.study."
+        for module_name in sys.modules:
+            if (
+                module_name.startswith(study_module_prefix)
+                and module_name != current_module
+            ):
+                study_modules.append(module_name)
+
+        all_modules_to_reload = (
+            core_modules + wizard_modules + sample_modules + study_modules
+        )
+
+        # Reload all discovered modules
+        for full_module_name in all_modules_to_reload:
+            try:
+                if full_module_name in sys.modules:
+                    mod = sys.modules[full_module_name]
+                    importlib.reload(mod)
+                    self.logger.debug(f"Reloaded module: {full_module_name}")
+            except Exception as e:
+                self.logger.warning(f"Failed to reload module {full_module_name}: {e}")
+
+        # Finally, reload the current module (wizard.py)
+        try:
+            mod = __import__(current_module, fromlist=[current_module.split(".")[0]])
+            importlib.reload(mod)
+
+            # Get the updated class reference from the reloaded module
+            new = getattr(mod, self.__class__.__name__)
+            # Update the class reference of the instance
+            self.__class__ = new
+
+            self.logger.debug("Module reload completed")
+        except Exception as e:
+            self.logger.error(f"Failed to reload current module {current_module}: {e}")
         
     def _setup_logging(self):
         """Setup comprehensive logging system."""
@@ -526,6 +675,15 @@ class Wizard:
                 chrom_fwhm=2.0  # Wider peaks
             )
             
+            # STEP 3.5: Validate feature detection results
+            if not hasattr(sample, 'features_df') or sample.features_df is None or len(sample.features_df) == 0:
+                self.logger.warning(f"No features detected in {file_path.name} - skipping additional processing")
+                # Still save the sample5 file for record keeping
+                sample.save(filename=str(output_file))
+                return output_file.stem
+            
+            self.logger.info(f"Detected {len(sample.features_df)} features in {file_path.name}")
+            
             # STEP 4: Adduct detection
             sample.find_adducts(adducts=self.adducts)
             
@@ -535,17 +693,11 @@ class Wizard:
             # STEP 6: Save processed data
             sample.save(filename=str(output_file))
             
-            # STEP 7: Generate additional outputs if requested
-            if "csv" in self.params.export_formats:
-                csv_file = output_file.with_suffix('.features.csv')
-                sample.export_features(filename=str(csv_file))
-            
-            if "mgf" in self.params.export_formats:
-                mgf_file = output_file.with_suffix('.mgf')
-                sample.export_mgf(filename=str(mgf_file), use_cache=False)
+            # STEP 7: Generate additional outputs (only for samples with features)
+            # Skip CSV export and individual MGF export as requested
             
             if self.params.generate_plots:
-                plot_file = output_file.with_suffix('_2d.html')
+                plot_file = output_file.parent / (output_file.stem + "_2d.html")
                 sample.plot_2d(filename=str(plot_file), markersize=4)
             
             # Memory cleanup
@@ -592,6 +744,10 @@ class Wizard:
             self.logger.warning("No files found for conversion")
             return False
         
+        # Detect detector type and adjust parameters before processing
+        detector_type = self._detect_detector_type()
+        self._adjust_parameters_for_detector(detector_type)
+        
         # Filter out already processed files if resuming
         if self.params.resume_enabled and self.processed_files:
             remaining_files = []
@@ -705,6 +861,125 @@ class Wizard:
         self._save_checkpoint()
         return successful_count > 0
     
+    def _detect_detector_type(self) -> str:
+        """
+        Detect the type of MS detector from the first available file.
+        
+        Simplified detection rules:
+        - .raw files: Assume Orbitrap (Thermo instruments)
+        - .wiff files: Assume Quadrupole (SCIEX instruments)  
+        - .mzML files: Check metadata for Orbitrap detection
+        
+        Returns:
+            String indicating detector type ("orbitrap", "quadrupole", "unknown")
+        """
+        try:
+            # Find first raw file to analyze
+            for extension in ['.raw', '.wiff', '.mzML', '.d']:
+                if self.params.search_subfolders:
+                    pattern = f"**/*{extension}"
+                    files = list(self.data_source_path.rglob(pattern))
+                else:
+                    pattern = f"*{extension}"
+                    files = list(self.data_source_path.glob(pattern))
+                if files:
+                    first_file = files[0]
+                    break
+            else:
+                self.logger.warning("No raw files found for detector detection")
+                return "unknown"
+            
+            self.logger.info(f"Detecting detector type from: {first_file.name}")
+            
+            # Simplified detection rules
+            if first_file.suffix.lower() == '.raw':
+                # RAW files are Thermo -> assume Orbitrap
+                detector_type = "orbitrap"
+                self.logger.info("Detected .raw file -> Thermo Orbitrap detector")
+                return detector_type
+                
+            elif first_file.suffix.lower() in ['.wiff', '.wiff2']:
+                # WIFF files are SCIEX -> assume Quadrupole
+                detector_type = "quadrupole"
+                self.logger.info("Detected .wiff file -> SCIEX Quadrupole detector")
+                return detector_type
+            
+            elif first_file.suffix.lower() == '.mzml':
+                # For mzML files, check metadata for Orbitrap detection
+                try:
+                    import warnings
+                    with warnings.catch_warnings():
+                        warnings.filterwarnings("ignore", message="Warning: OPENMS_DATA_PATH environment variable already exists.*", category=UserWarning)
+                        import pyopenms as oms
+                    
+                    exp = oms.MSExperiment()
+                    oms.MzMLFile().load(str(first_file), exp)
+                    
+                    # Check instrument metadata for Orbitrap keywords
+                    instrument_info = []
+                    if hasattr(exp, 'getExperimentalSettings'):
+                        settings = exp.getExperimentalSettings()
+                        if hasattr(settings, 'getInstrument'):
+                            instrument = settings.getInstrument()
+                            if hasattr(instrument, 'getName'):
+                                name = instrument.getName().decode() if hasattr(instrument.getName(), 'decode') else str(instrument.getName())
+                                instrument_info.append(name.lower())
+                            if hasattr(instrument, 'getModel'):
+                                model = instrument.getModel().decode() if hasattr(instrument.getModel(), 'decode') else str(instrument.getModel())
+                                instrument_info.append(model.lower())
+                    
+                    # Check for Orbitrap keywords in instrument info
+                    orbitrap_keywords = ['orbitrap', 'exactive', 'q-exactive', 'exploris', 'fusion', 'lumos', 'velos', 'elite']
+                    instrument_text = ' '.join(instrument_info)
+                    
+                    if any(keyword in instrument_text for keyword in orbitrap_keywords):
+                        detector_type = "orbitrap"
+                        self.logger.info(f"Detected mzML with Orbitrap instrument: {instrument_text}")
+                    else:
+                        detector_type = "unknown"
+                        self.logger.info(f"Detected mzML with unknown instrument: {instrument_text}")
+                    
+                    return detector_type
+                        
+                except Exception as e:
+                    self.logger.warning(f"Failed to analyze mzML file for detector type: {e}")
+                    return "unknown"
+        
+        except Exception as e:
+            self.logger.warning(f"Detector type detection failed: {e}")
+        
+        return "unknown"
+    
+    def _adjust_parameters_for_detector(self, detector_type: str):
+        """
+        Adjust processing parameters based on detected detector type.
+        
+        Simplified rules:
+        - "orbitrap": Use 1e5 noise threshold (high background noise)
+        - "quadrupole": Use 200 noise threshold (default, lower noise)
+        - "unknown": Use 200 noise threshold (default)
+        
+        Parameters:
+            detector_type: Type of detector detected ("orbitrap", "quadrupole", "unknown")
+        """
+        original_noise = self.params.noise_threshold
+        self.params.detector_type = detector_type  # Store the detected type
+        
+        if detector_type == "orbitrap":
+            # Orbitraps have much higher background noise, use 1e5 threshold
+            self.params.noise_threshold = 1e5
+            self._log_progress(f"Detector: Orbitrap detected - adjusted noise threshold: {original_noise} -> {self.params.noise_threshold}")
+            
+        elif detector_type == "quadrupole":
+            # Quadrupole instruments have lower noise, use default threshold
+            self.params.noise_threshold = 200.0
+            self._log_progress(f"Detector: Quadrupole detected - noise threshold: {self.params.noise_threshold}")
+            
+        else:
+            # Unknown detector type, keep default
+            self.params.noise_threshold = 200.0
+            self._log_progress(f"Detector: Unknown type detected - using default noise threshold: {self.params.noise_threshold}")
+    
     def assemble_study(self) -> bool:
         """
         Assemble processed sample5 files into a study.
@@ -725,6 +1000,10 @@ class Wizard:
         self._log_progress(f"Assembling study from {len(sample5_files)} sample5 files")
         
         try:
+            # Detect detector type and adjust parameters if needed
+            detector_type = self._detect_detector_type()
+            self._adjust_parameters_for_detector(detector_type)
+            
             # Create study with optimized settings
             import masster
             study_params = study_defaults(
@@ -779,25 +1058,39 @@ class Wizard:
             return False
         
         try:
+            # Determine optimal algorithms based on study size
+            num_samples = len(self.study.samples_df)
+            
+            if num_samples < 500:
+                # For smaller studies: use qt for both alignment and merge
+                alignment_algorithm = "qt"
+                merge_method = "qt"
+                self.logger.info(f"Small study ({num_samples} samples) - using qt algorithms")
+            else:
+                # For larger studies: use kd for alignment and qt-chunked for merge
+                alignment_algorithm = "kd"
+                merge_method = "qt-chunked"
+                self.logger.info(f"Large study ({num_samples} samples) - using kd alignment and qt-chunked merge")
+            
             # Align features across samples
             align_params = align_defaults(
                 rt_tol=self.params.rt_tolerance,
-                mz_tol=self.params.mz_tolerance,
-                algorithm=self.params.alignment_algorithm
+                mz_max_diff=self.params.mz_max_diff,
+                algorithm=alignment_algorithm
             )
-            
-            self.logger.info(f"Aligning features with RT tolerance {self.params.rt_tolerance}s, m/z tolerance {self.params.mz_tolerance} Da")
+
+            self.logger.info(f"Aligning features with RT tolerance {self.params.rt_tolerance}s, m/z max diff {self.params.mz_max_diff} Da, algorithm: {alignment_algorithm}")
             self.study.align(params=align_params)
             
             # Merge aligned features
             merge_params = merge_defaults(
-                method=self.params.merge_method,
+                method=merge_method,
                 rt_tol=self.params.rt_tolerance,
-                mz_tol=self.params.mz_tolerance,
+                mz_tol=self.params.mz_max_diff,
                 min_samples=self.params.min_samples_for_merge
             )
             
-            self.logger.info(f"Merging features using {self.params.merge_method} method")
+            self.logger.info(f"Merging features using {merge_method} method")
             self.study.merge(params=merge_params)
             
             # Log results
@@ -920,12 +1213,47 @@ class Wizard:
             
             self._log_progress(f"Completed {exports_completed} exports")
             self._save_checkpoint()
+            
+            # Always perform additional export methods as requested
+            self._export_additional_formats()
+            
             return True
             
         except Exception as e:
             self.logger.error(f"Failed to export results: {e}")
             return False
     
+    def _export_additional_formats(self):
+        """Export additional formats: xlsx, parquet, save, and mgf."""
+        self.logger.info("=== Exporting Additional Formats ===")
+        
+        try:
+            # Force export xlsx (study results in Excel format)
+            xlsx_file = self.study_folder_path / "study_results.xlsx"
+            if hasattr(self.study, 'export_xlsx'):
+                self.study.export_xlsx(filename=str(xlsx_file))
+                self.logger.info(f"Exported Excel: {xlsx_file}")
+            
+            # Force export parquet (efficient binary format)
+            parquet_file = self.study_folder_path / "study_data.parquet" 
+            if hasattr(self.study, 'export_parquet'):
+                self.study.export_parquet(filename=str(parquet_file))
+                self.logger.info(f"Exported Parquet: {parquet_file}")
+            
+            # Force save the study in study5 format
+            study_file = self.study_folder_path / "final_study.study5"
+            self.study.save(filename=str(study_file))
+            self.logger.info(f"Saved study: {study_file}")
+            
+            # Force export MGF for MS2 spectra
+            mgf_file = self.study_folder_path / "consensus_ms2.mgf"
+            if hasattr(self.study, 'export_mgf'):
+                self.study.export_mgf(filename=str(mgf_file))
+                self.logger.info(f"Exported MGF: {mgf_file}")
+            
+        except Exception as e:
+            self.logger.warning(f"Some additional exports failed: {e}")
+    
     def save_study(self) -> bool:
         """
         Save the final study in optimized format.
@@ -977,7 +1305,7 @@ class Wizard:
                 f.write(f"Successful Files: {len(self.processed_files)}\n")
                 f.write(f"Failed Files: {len(self.failed_files)}\n")
                 f.write(f"RT Tolerance: {self.params.rt_tolerance}s\n")
-                f.write(f"m/z Tolerance: {self.params.mz_tolerance} Da\n")
+                f.write(f"m/z Max Diff: {self.params.mz_max_diff} Da\n")
                 f.write(f"Merge Method: {self.params.merge_method}\n")
                 f.write(f"Processing Time: {self._get_total_processing_time()}\n")
             
@@ -1144,6 +1472,753 @@ class Wizard:
             }
         }
     
+    def execute(self) -> bool:
+        """
+        Execute the complete automated processing pipeline.
+        
+        This is a convenience method that runs the full pipeline with the wizard's
+        current configuration. It performs standalone analysis of the samples/studies
+        as proposed by the Wizard.
+        
+        Returns:
+            True if execution completed successfully, False otherwise
+        """
+        self._log_progress("Executing Wizard automated processing...")
+        return self.run_full_pipeline()
+    
+    def export_script(self, filename: str) -> bool:
+        """
+        Generate a Python script that replicates the wizard's processing steps.
+        
+        Creates a standalone Python script that can be executed independently
+        to perform the same analysis as the wizard with the current configuration.
+        The script will be saved in the study folder.
+        
+        This is useful for:
+        - Creating reproducible analysis scripts
+        - Customizing processing steps
+        - Running analysis in different environments
+        - Batch processing automation
+        
+        Parameters:
+            filename: Filename for the script (should end with .py). Script will be saved in the study folder.
+        
+        Returns:
+            True if script was generated successfully, False otherwise
+        """
+        self._log_progress("Generating analysis script...")
+        
+        try:
+            # Ensure the filename is just a filename, not a full path
+            script_filename = Path(filename).name
+            if not script_filename.endswith('.py'):
+                script_filename = script_filename.replace(Path(script_filename).suffix, '') + '.py'
+            
+            # Place the script in the study folder
+            script_path = self.study_folder_path / script_filename
+            
+            # Generate the script content
+            script_content = self._generate_script_content()
+            
+            # Write the script
+            with open(script_path, 'w', encoding='utf-8') as f:
+                f.write(script_content)
+
+            self._log_progress(f"Analysis script saved: {os.path.abspath(script_path)}")
+            self.logger.info(f"Generated standalone analysis script: {os.path.abspath(script_path)}")
+
+            return True
+            
+        except Exception as e:
+            self.logger.error(f"Failed to generate script: {e}")
+            return False
+    
+    def to_script(self, filename: str) -> bool:
+        """
+        [DEPRECATED] Use export_script() instead.
+        
+        Backward compatibility alias for export_script().
+        """
+        return self.export_script(filename)
+    
+    def _generate_script_content(self) -> str:
+        """
+        Generate the content for the standalone analysis script.
+        
+        Returns:
+            Complete Python script content as string
+        """
+        timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        
+        # Create script header
+        script_lines = [
+            '#!/usr/bin/env python3',
+            '"""',
+            'Standalone Mass Spectrometry Analysis Script',
+            f'Generated by masster.Wizard on {timestamp}',
+            '',
+            'This script replicates the automated processing pipeline configured',
+            'in the Wizard with the following settings:',
+            f'- Data Source: {self.params.data_source.replace(chr(92), chr(92)*2)}',
+            f'- Study Folder: {self.params.study_folder.replace(chr(92), chr(92)*2)}',
+            f'- Polarity: {self.params.polarity}',
+            f'- Number of Cores: {self.params.num_cores}',
+            f'- Adducts: {", ".join(self.params.adducts)}',
+            f'- RT Tolerance: {self.params.rt_tolerance}s',
+            f'- m/z Max Diff: {self.params.mz_max_diff} Da',
+            f'- Merge Method: {self.params.merge_method}',
+            '"""',
+            '',
+            'import os',
+            'import sys',
+            'import time',
+            'import multiprocessing',
+            'from pathlib import Path',
+            'from typing import List, Optional',
+            'import concurrent.futures',
+            'from datetime import datetime',
+            '',
+            '# Add error handling for masster import',
+            '# First, try to add the masster directory to the Python path',
+            'try:',
+            '    # Try to find masster by looking for it in common development locations',
+            '    possible_paths = [',
+            '        Path(__file__).parent.parent,  # Script is in masster subfolder',
+            '        Path(__file__).parent.parent.parent,  # Script is in study folder', 
+            '        Path(os.getcwd()),  # Current working directory',
+            '        Path(os.getcwd()).parent,  # Parent of current directory',
+            '        Path(r"D:\\SW\\massistant"),  # Specific development path',
+            '        Path.home() / "massistant",  # Home directory',
+            '        Path.home() / "SW" / "massistant",  # Common dev location',
+            '    ]',
+            '    ',
+            '    masster_found = False',
+            '    for possible_path in possible_paths:',
+            '        masster_dir = possible_path / "masster"',
+            '        if masster_dir.exists() and (masster_dir / "__init__.py").exists():',
+            '            if str(possible_path) not in sys.path:',
+            '                sys.path.insert(0, str(possible_path))',
+            '            masster_found = True',
+            '            print(f"Found masster at: {possible_path}")',
+            '            break',
+            '    ',
+            '    if not masster_found:',
+            '        # Try adding current directory to path as fallback',
+            '        current_dir = Path(os.getcwd())',
+            '        if str(current_dir) not in sys.path:',
+            '            sys.path.insert(0, str(current_dir))',
+            '    ',
+            '    import masster',
+            'except ImportError as e:',
+            '    print(f"Error: masster library not found. {e}")',
+            '    print("Please ensure masster is installed or run this script from the masster directory.")',
+            '    print("You can install masster with: pip install -e .")',
+            '    sys.exit(1)',
+            '',
+            '',
+            'def infer_polarity_from_first_file():',
+            '    """Infer polarity from the first available raw data file."""',
+            '    try:',
+            '        data_source_path = Path(DATA_SOURCE)',
+            '        # Find first file',
+            '        for extension in [\'.wiff\', \'.raw\', \'.mzML\', \'.d\']:',
+            '            pattern = f"**/*{extension}"',
+            '            files = list(data_source_path.rglob(pattern))',
+            '            if files:',
+            '                first_file = files[0]',
+            '                break',
+            '        else:',
+            '            return None',
+            '        ',
+            '        # Only implement for .wiff files initially',
+            '        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"',
+            '    except Exception:',
+            '        pass',
+            '    return None',
+            '',
+            '',
+            '# Configuration Parameters',
+            f'DATA_SOURCE = r"{self.params.data_source}"',
+            f'STUDY_FOLDER = r"{self.params.study_folder}"',
+            '',
+            '# Auto-infer polarity from first file, fall back to default',
+            'detected_polarity = infer_polarity_from_first_file()',
+            f'POLARITY = detected_polarity or "{self.params.polarity}"',
+            'NUM_CORES = max(1, int(multiprocessing.cpu_count() * 0.75))  # Auto-detect 75% of cores',
+            '',
+            '# Set adducts based on detected polarity',
+            'if POLARITY.lower() in ["positive", "pos"]:',
+            '    ADDUCTS = ["H:+:0.8", "Na:+:0.1", "NH4:+:0.1"]',
+            'elif POLARITY.lower() in ["negative", "neg"]:',
+            '    ADDUCTS = ["H-1:-:1.0", "CH2O2:0:0.5"]',
+            'else:',
+            f'    ADDUCTS = {self.params.adducts!r}  # Fall back to original',
+            f'RT_TOLERANCE = {self.params.rt_tolerance}',
+            f'MZ_TOLERANCE = {self.params.mz_max_diff}',
+            f'MERGE_METHOD = "{self.params.merge_method}"',
+            f'BATCH_SIZE = {self.params.batch_size}',
+            f'CHROM_FWHM = {self.params.chrom_fwhm}',
+            f'NOISE_THRESHOLD = {self.params.noise_threshold}',
+            f'CHROM_PEAK_SNR = {self.params.chrom_peak_snr}',
+            f'TOL_PPM = {self.params.tol_ppm}',
+            f'MIN_SAMPLES_FOR_MERGE = {self.params.min_samples_for_merge}',
+            '',
+            '# File discovery settings',
+            "FILE_EXTENSIONS = ['.wiff', '.raw', '.mzML']",
+            f'SEARCH_SUBFOLDERS = {self.params.search_subfolders}',
+            "SKIP_PATTERNS = []",
+            f'MAX_FILE_SIZE_GB = {self.params.max_file_size_gb}',
+            '',
+            '# Output settings',
+            f'GENERATE_PLOTS = {self.params.generate_plots}',
+            f'EXPORT_FORMATS = {self.params.export_formats!r}',
+            f'COMPRESS_OUTPUT = {self.params.compress_output}',
+            f'CLEANUP_TEMP_FILES = {self.params.cleanup_temp_files}',
+            '',
+            '',
+            'def log_progress(message: str):',
+            '    """Log progress message with timestamp."""',
+            '    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")',
+            '    print(f"[{timestamp}] {message}")',
+            '',
+            '',
+            'def discover_files() -> List[Path]:',
+            '    """Discover raw data files in the source directory."""',
+            '    log_progress("Discovering raw data files...")',
+            '    data_source_path = Path(DATA_SOURCE)',
+            '    found_files = []',
+            '    ',
+            '    for extension in FILE_EXTENSIONS:',
+            '        if SEARCH_SUBFOLDERS:',
+            '            pattern = f"**/*{extension}"',
+            '            files = list(data_source_path.rglob(pattern))',
+            '        else:',
+            '            pattern = f"*{extension}"',
+            '            files = list(data_source_path.glob(pattern))',
+            '        ',
+            '        # Filter out files matching skip patterns',
+            '        filtered_files = []',
+            '        for file_path in files:',
+            '            skip_file = False',
+            '            for pattern in SKIP_PATTERNS:',
+            '                if pattern.lower() in file_path.name.lower():',
+            '                    skip_file = True',
+            '                    print(f"Skipping file (matches pattern \'{pattern}\'): {file_path.name}")',
+            '                    break',
+            '            ',
+            '            if not skip_file:',
+            '                # Check file size',
+            '                try:',
+            '                    file_size_gb = file_path.stat().st_size / (1024**3)',
+            '                    if file_size_gb > MAX_FILE_SIZE_GB:',
+            '                        print(f"Large file ({file_size_gb:.1f}GB): {file_path.name}")',
+            '                    filtered_files.append(file_path)',
+            '                except Exception as e:',
+            '                    print(f"Could not check file size for {file_path}: {e}")',
+            '                    filtered_files.append(file_path)',
+            '        ',
+            '        found_files.extend(filtered_files)',
+            '        log_progress(f"Found {len(filtered_files)} {extension} files")',
+            '    ',
+            '    # Remove duplicates and sort',
+            '    found_files = sorted(list(set(found_files)))',
+            '    log_progress(f"Total files discovered: {len(found_files)}")',
+            '    return found_files',
+            '',
+            '',
+            'def process_single_file(file_path: Path) -> Optional[str]:',
+            '    """Process a single file to sample5 format."""',
+            '    import gc',
+            '    study_folder_path = Path(STUDY_FOLDER)',
+            '    ',
+            '    # Generate output filename',
+            '    file_out = file_path.stem + ".sample5"',
+            '    output_file = study_folder_path / file_out',
+            '    ',
+            '    # Check if file already exists',
+            '    if output_file.exists():',
+            '        try:',
+            '            # Try to load existing file to verify it\'s valid',
+            '            sample = masster.Sample(log_level="ERROR")',
+            '            sample.load(str(output_file))',
+            '            print(f"Skipping {file_path.name} (already processed)")',
+            '            return output_file.stem',
+            '        except Exception:',
+            '            # If loading fails, file needs to be reprocessed',
+            '            pass',
+            '    ',
+            '    print(f"Processing {file_path.name}")',
+            '    ',
+            '    try:',
+            '        # Initialize sample',
+            '        sample = masster.Sample(',
+            '            log_label=file_path.name,',
+            '            log_level="ERROR"  # Reduce logging overhead',
+            '        )',
+            '        ',
+            '        # STEP 1: Load raw data',
+            '        sample.load(str(file_path))',
+            '        ',
+            '        # STEP 2: Feature detection - First pass (strict parameters)',
+            '        sample.find_features(',
+            '            chrom_fwhm=CHROM_FWHM,',
+            '            noise=NOISE_THRESHOLD,',
+            '            tol_ppm=TOL_PPM,',
+            '            chrom_peak_snr=CHROM_PEAK_SNR,',
+            '            min_trace_length_multiplier=0.5,',
+            '            chrom_fwhm_min=CHROM_FWHM',
+            '        )',
+            '        ',
+            '        # STEP 3: Feature detection - Second pass (relaxed parameters)',
+            '        sample.find_features(',
+            '            chrom_peak_snr=CHROM_PEAK_SNR,',
+            '            noise=NOISE_THRESHOLD / 10,  # Lower noise threshold',
+            '            chrom_fwhm=2.0  # Wider peaks',
+            '        )',
+            '        ',
+            '        # STEP 3.5: Validate feature detection results',
+            '        if not hasattr(sample, "features_df") or sample.features_df is None or len(sample.features_df) == 0:',
+            '            print(f"WARNING: No features detected in {file_path.name} - skipping additional processing")',
+            '            # Still save the sample5 file for record keeping',
+            '            sample.save(filename=str(output_file))',
+            '            return output_file.stem',
+            '        ',
+            '        print(f"Detected {len(sample.features_df)} features in {file_path.name}")',
+            '        ',
+            '        # STEP 4: Adduct detection',
+            '        sample.find_adducts(adducts=ADDUCTS)',
+            '        ',
+            '        # STEP 5: MS2 spectrum identification',
+            '        sample.find_ms2()',
+            '        ',
+            '        # STEP 6: Save processed data',
+            '        sample.save(filename=str(output_file))',
+            '        ',
+            '        # STEP 7: Generate additional outputs (only for samples with features)',
+            '        # Skip CSV export and individual MGF export as requested',
+            '        ',
+            '        if GENERATE_PLOTS:',
+            '            plot_file = output_file.parent / (output_file.stem + "_2d.html")',
+            '            sample.plot_2d(filename=str(plot_file), markersize=4)',
+            '        ',
+            '        # Memory cleanup',
+            '        result = output_file.stem',
+            '        del sample',
+            '        gc.collect()',
+            '        return result',
+            '        ',
+            '    except Exception as e:',
+            '        print(f"Error processing {file_path.name}: {e}")',
+            '        gc.collect()',
+            '        return None',
+            '',
+            '',
+            'def convert_to_sample5(file_list: List[Path]) -> bool:',
+            '    """Convert raw data files to sample5 format in parallel."""',
+            '    log_progress("=== Starting Sample5 Conversion ===")',
+            '    log_progress(f"Converting {len(file_list)} files to sample5 format")',
+            '    ',
+            '    conversion_start = time.time()',
+            '    successful_count = 0',
+            '    failed_count = 0',
+            '    ',
+            '    with concurrent.futures.ProcessPoolExecutor(max_workers=NUM_CORES) as executor:',
+            '        futures = [executor.submit(process_single_file, file_path) for file_path in file_list]',
+            '        ',
+            '        for i, future in enumerate(concurrent.futures.as_completed(futures)):',
+            '            result = future.result()',
+            '            if result:',
+            '                successful_count += 1',
+            '            else:',
+            '                failed_count += 1',
+            '            ',
+            '            # Progress update',
+            '            if (successful_count + failed_count) % 10 == 0:',
+            '                progress = (successful_count + failed_count) / len(file_list) * 100',
+            '                log_progress(f"Progress: {progress:.1f}% ({successful_count} successful, {failed_count} failed)")',
+            '    ',
+            '    conversion_time = time.time() - conversion_start',
+            '    log_progress("=== Sample5 Conversion Complete ===")',
+            '    log_progress(f"Successful: {successful_count}")',
+            '    log_progress(f"Failed: {failed_count}")',
+            '    log_progress(f"Total time: {conversion_time:.1f} seconds")',
+            '    ',
+            '    return successful_count > 0',
+            '',
+            '',
+            'def assemble_study() -> masster.Study:',
+            '    """Assemble processed sample5 files into a study."""',
+            '    log_progress("=== Starting Study Assembly ===")',
+            '    study_folder_path = Path(STUDY_FOLDER)',
+            '    ',
+            '    # Find all sample5 files',
+            '    sample5_files = list(study_folder_path.glob("*.sample5"))',
+            '    if not sample5_files:',
+            '        raise RuntimeError("No sample5 files found for study assembly")',
+            '    ',
+            '    log_progress(f"Assembling study from {len(sample5_files)} sample5 files")',
+            '    ',
+            '    # Create study with optimized settings',
+            '    from masster.study.defaults.study_def import study_defaults',
+            '    study_params = study_defaults(',
+            '        folder=str(study_folder_path),',
+            '        polarity=POLARITY,',
+            '        log_level="INFO",',
+            f'        log_label="Study-{self.params.polarity}",',
+            '        adducts=ADDUCTS',
+            '    )',
+            '    ',
+            '    study = masster.Study(params=study_params)',
+            '    ',
+            '    # Add all sample5 files',
+            '    sample5_pattern = str(study_folder_path / "*.sample5")',
+            '    study.add(sample5_pattern)',
+            '    log_progress(f"Added {len(study.samples_df)} samples to study")',
+            '    ',
+            '    # Filter features based on quality criteria',
+            '    if hasattr(study, "features_filter"):',
+            '        initial_features = len(study.features_df) if hasattr(study, "features_df") else 0',
+            '        feature_selection = study.features_select(',
+            '            chrom_coherence=0.3,',
+            '            chrom_prominence_scaled=1',
+            '        )',
+            '        study.features_filter(feature_selection)',
+            '        final_features = len(study.features_df) if hasattr(study, "features_df") else 0',
+            '        log_progress(f"Feature filtering: {initial_features} -> {final_features} features")',
+            '    ',
+            '    return study',
+            '',
+            '',
+            'def align_and_merge(study: masster.Study) -> masster.Study:',
+            '    """Perform feature alignment and merging."""',
+            '    log_progress("=== Starting Feature Alignment and Merging ===")',
+            '    ',
+            '    # Import alignment and merge defaults',
+            '    from masster.study.defaults.align_def import align_defaults',
+            '    from masster.study.defaults.merge_def import merge_defaults',
+            '    ',
+            '    # Determine optimal algorithms based on study size',
+            '    num_samples = len(study.samples_df)',
+            '    ',
+            '    if num_samples < 500:',
+            '        # For smaller studies: use qt for both alignment and merge',
+            '        alignment_algorithm = "qt"',
+            '        merge_method = "qt"',
+            '        log_progress(f"Small study ({num_samples} samples) - using qt algorithms")',
+            '    else:',
+            '        # For larger studies: use kd for alignment and qt-chunked for merge',
+            '        alignment_algorithm = "kd"',
+            '        merge_method = "qt-chunked"',
+            '        log_progress(f"Large study ({num_samples} samples) - using kd alignment and qt-chunked merge")',
+            '    ',
+            '    # Align features across samples',
+            '    align_params = align_defaults(',
+            '        rt_tol=RT_TOLERANCE,',
+            '        mz_max_diff=MZ_TOLERANCE,',
+            '        algorithm=alignment_algorithm',
+            '    )',
+            '    ',
+            '    log_progress(f"Aligning features with RT tolerance {RT_TOLERANCE}s, m/z tolerance {MZ_TOLERANCE} Da, algorithm: {alignment_algorithm}")',
+            '    study.align(params=align_params)',
+            '    ',
+            '    # Merge aligned features',
+            '    merge_params = merge_defaults(',
+            '        method=merge_method,',
+            '        rt_tol=RT_TOLERANCE,',
+            '        mz_tol=MZ_TOLERANCE,',
+            '        min_samples=MIN_SAMPLES_FOR_MERGE',
+            '    )',
+            '    ',
+            '    log_progress(f"Merging features using {merge_method} method")',
+            '    study.merge(params=merge_params)',
+            '    ',
+            '    # Log results',
+            '    num_consensus = len(study.consensus_df) if hasattr(study, "consensus_df") else 0',
+            '    log_progress(f"Generated {num_consensus} consensus features")',
+            '    ',
+            '    # Get study info',
+            '    if hasattr(study, "info"):',
+            '        study.info()',
+            '    ',
+            '    return study',
+            '',
+            '',
+            'def generate_plots(study: masster.Study) -> bool:',
+            '    """Generate visualization plots for the study."""',
+            '    if not GENERATE_PLOTS:',
+            '        log_progress("Plot generation disabled, skipping...")',
+            '        return True',
+            '    ',
+            '    log_progress("=== Generating Visualization Plots ===")',
+            '    study_folder_path = Path(STUDY_FOLDER)',
+            '    plots_generated = 0',
+            '    ',
+            '    try:',
+            '        # Alignment plot',
+            '        if hasattr(study, "plot_alignment"):',
+            '            alignment_plot = study_folder_path / "alignment_plot.html"',
+            '            study.plot_alignment(filename=str(alignment_plot))',
+            '            plots_generated += 1',
+            '            log_progress(f"Generated alignment plot: {alignment_plot}")',
+            '        ',
+            '        # Consensus 2D plot',
+            '        if hasattr(study, "plot_consensus_2d"):',
+            '            consensus_2d_plot = study_folder_path / "consensus_2d.html"',
+            '            study.plot_consensus_2d(filename=str(consensus_2d_plot))',
+            '            plots_generated += 1',
+            '            log_progress(f"Generated consensus 2D plot: {consensus_2d_plot}")',
+            '        ',
+            '        # PCA plot',
+            '        if hasattr(study, "plot_pca"):',
+            '            pca_plot = study_folder_path / "pca_plot.html"',
+            '            study.plot_pca(filename=str(pca_plot))',
+            '            plots_generated += 1',
+            '            log_progress(f"Generated PCA plot: {pca_plot}")',
+            '        ',
+            '        # Consensus statistics',
+            '        if hasattr(study, "plot_consensus_stats"):',
+            '            stats_plot = study_folder_path / "consensus_stats.html"',
+            '            study.plot_consensus_stats(filename=str(stats_plot))',
+            '            plots_generated += 1',
+            '            log_progress(f"Generated statistics plot: {stats_plot}")',
+            '        ',
+            '        log_progress(f"Generated {plots_generated} visualization plots")',
+            '        return True',
+            '        ',
+            '    except Exception as e:',
+            '        print(f"Failed to generate plots: {e}")',
+            '        return False',
+            '',
+            '',
+            'def export_results(study: masster.Study) -> bool:',
+            '    """Export study results in requested formats."""',
+            '    log_progress("=== Exporting Study Results ===")',
+            '    study_folder_path = Path(STUDY_FOLDER)',
+            '    exports_completed = 0',
+            '    ',
+            '    try:',
+            '        # Skip CSV export as requested',
+            '        ',
+            '        # Export as Excel',
+            '        if "xlsx" in EXPORT_FORMATS and hasattr(study, "export_xlsx"):',
+            '            xlsx_file = study_folder_path / "study_results.xlsx"',
+            '            study.export_xlsx(filename=str(xlsx_file))',
+            '            exports_completed += 1',
+            '            log_progress(f"Exported Excel: {xlsx_file}")',
+            '        ',
+            '        # Export MGF for MS2 spectra',
+            '        if "mgf" in EXPORT_FORMATS and hasattr(study, "export_mgf"):',
+            '            mgf_file = study_folder_path / "consensus_ms2.mgf"',
+            '            study.export_mgf(filename=str(mgf_file))',
+            '            exports_completed += 1',
+            '            log_progress(f"Exported MGF: {mgf_file}")',
+            '        ',
+            '        # Export as Parquet for efficient storage',
+            '        if "parquet" in EXPORT_FORMATS and hasattr(study, "export_parquet"):',
+            '            parquet_file = study_folder_path / "study_data.parquet"',
+            '            study.export_parquet(filename=str(parquet_file))',
+            '            exports_completed += 1',
+            '            log_progress(f"Exported Parquet: {parquet_file}")',
+            '        ',
+            '        log_progress(f"Completed {exports_completed} exports")',
+            '        ',
+            '        # Always perform additional exports as requested',
+            '        log_progress("=== Exporting Additional Formats ===")',
+            '        ',
+            '        try:',
+            '            # Force export xlsx (study results in Excel format)',
+            '            xlsx_file = study_folder_path / "study_results.xlsx"',
+            '            if hasattr(study, "export_xlsx"):',
+            '                study.export_xlsx(filename=str(xlsx_file))',
+            '                log_progress(f"Exported Excel: {xlsx_file}")',
+            '            ',
+            '            # Force export parquet (efficient binary format)',
+            '            parquet_file = study_folder_path / "study_data.parquet"',
+            '            if hasattr(study, "export_parquet"):',
+            '                study.export_parquet(filename=str(parquet_file))',
+            '                log_progress(f"Exported Parquet: {parquet_file}")',
+            '            ',
+            '            # Force save the study in study5 format',
+            '            study_file = study_folder_path / "final_study.study5"',
+            '            study.save(filename=str(study_file))',
+            '            log_progress(f"Saved study: {study_file}")',
+            '            ',
+            '            # Force export MGF for MS2 spectra',
+            '            mgf_file = study_folder_path / "consensus_ms2.mgf"',
+            '            if hasattr(study, "export_mgf"):',
+            '                study.export_mgf(filename=str(mgf_file))',
+            '                log_progress(f"Exported MGF: {mgf_file}")',
+            '        ',
+            '        except Exception as e:',
+            '            print(f"Some additional exports failed: {e}")',
+            '        ',
+            '        return True',
+            '        ',
+            '    except Exception as e:',
+            '        print(f"Failed to export results: {e}")',
+            '        return False',
+            '',
+            '',
+            'def save_study(study: masster.Study) -> bool:',
+            '    """Save the final study in optimized format."""',
+            '    log_progress("=== Saving Final Study ===")',
+            '    study_folder_path = Path(STUDY_FOLDER)',
+            '    ',
+            '    try:',
+            '        study_file = study_folder_path / "final_study.study5"',
+            '        ',
+            '        # Determine optimal save format based on study size',
+            '        num_samples = len(study.samples_df)',
+            '        num_features = len(study.consensus_df) if hasattr(study, "consensus_df") else 0',
+            '        ',
+            '        if num_samples > 50 or num_features > 10000:',
+            '            log_progress(f"Large study detected ({num_samples} samples, {num_features} features) - using compressed format")',
+            '            compress_output = True',
+            '        else:',
+            '            log_progress(f"Small study ({num_samples} samples, {num_features} features) - using standard format")',
+            '            compress_output = False',
+            '        ',
+            '        # Save study',
+            '        if compress_output and hasattr(study, "save_compressed"):',
+            '            study.save_compressed(filename=str(study_file))',
+            '            log_progress(f"Saved compressed study: {study_file}")',
+            '        else:',
+            '            study.save(filename=str(study_file))',
+            '            log_progress(f"Saved study: {study_file}")',
+            '        ',
+            '        # Save metadata summary',
+            '        metadata_file = study_folder_path / "study_metadata.txt"',
+            '        with open(metadata_file, "w") as f:',
+            '            f.write("Study Processing Summary\\n")',
+            '            f.write("========================\\n")',
+            '            f.write(f"Processing Date: {datetime.now().strftime(\'%Y-%m-%d %H:%M:%S\')}\\n")',
+            '            f.write(f"Polarity: {POLARITY}\\n")',
+            '            f.write(f"Adducts: {\', \'.join(ADDUCTS)}\\n")',
+            '            f.write(f"Number of Samples: {num_samples}\\n")',
+            '            f.write(f"Number of Consensus Features: {num_features}\\n")',
+            '            f.write(f"RT Tolerance: {RT_TOLERANCE}s\\n")',
+            '            f.write(f"m/z Tolerance: {MZ_TOLERANCE} Da\\n")',
+            '            f.write(f"Merge Method: {MERGE_METHOD}\\n")',
+            '        ',
+            '        log_progress(f"Saved study metadata: {metadata_file}")',
+            '        return True',
+            '        ',
+            '    except Exception as e:',
+            '        print(f"Failed to save study: {e}")',
+            '        return False',
+            '',
+            '',
+            'def cleanup_temp_files() -> bool:',
+            '    """Clean up temporary files if requested."""',
+            '    if not CLEANUP_TEMP_FILES:',
+            '        return True',
+            '    ',
+            '    log_progress("=== Cleaning Up Temporary Files ===")',
+            '    study_folder_path = Path(STUDY_FOLDER)',
+            '    ',
+            '    try:',
+            '        cleaned_count = 0',
+            '        ',
+            '        # Remove individual sample plots if study plots were generated',
+            '        if GENERATE_PLOTS:',
+            '            temp_plots = list(study_folder_path.glob("*_2d.html"))',
+            '            for plot_file in temp_plots:',
+            '                if plot_file.name not in ["alignment_plot.html", "consensus_2d.html", "pca_plot.html"]:',
+            '                    plot_file.unlink()',
+            '                    cleaned_count += 1',
+            '        ',
+            '        log_progress(f"Cleaned up {cleaned_count} temporary files")',
+            '        return True',
+            '        ',
+            '    except Exception as e:',
+            '        print(f"Failed to cleanup temp files: {e}")',
+            '        return False',
+            '',
+            '',
+            'def main():',
+            '    """Main execution function."""',
+            '    print("=" * 70)',
+            '    print("AUTOMATED MASS SPECTROMETRY ANALYSIS SCRIPT")',
+            f'    print("Generated by masster.Wizard on {timestamp}")',
+            '    print("=" * 70)',
+            '    ',
+            '    start_time = time.time()',
+            '    ',
+            '    try:',
+            '        # Ensure output directory exists',
+            '        Path(STUDY_FOLDER).mkdir(parents=True, exist_ok=True)',
+            '        ',
+            '        # Step 1: Discover files',
+            '        file_list = discover_files()',
+            '        if not file_list:',
+            '            print("No files found for processing")',
+            '            return False',
+            '        ',
+            '        # Step 2: Convert to sample5',
+            '        if not convert_to_sample5(file_list):',
+            '            print("Sample5 conversion failed")',
+            '            return False',
+            '        ',
+            '        # Step 3: Assemble study',
+            '        study = assemble_study()',
+            '        ',
+            '        # Step 4: Align and merge',
+            '        study = align_and_merge(study)',
+            '        ',
+            '        # Step 5: Generate plots',
+            '        generate_plots(study)',
+            '        ',
+            '        # Step 6: Export results',
+            '        export_results(study)',
+            '        ',
+            '        # Step 7: Save study',
+            '        save_study(study)',
+            '        ',
+            '        # Step 8: Cleanup',
+            '        cleanup_temp_files()',
+            '        ',
+            '        # Final summary',
+            '        total_time = time.time() - start_time',
+            '        print("=" * 70)',
+            '        print("ANALYSIS COMPLETED SUCCESSFULLY")',
+            '        print(f"Total processing time: {total_time:.1f} seconds ({total_time/60:.1f} minutes)")',
+            '        if hasattr(study, "consensus_df"):',
+            '            print(f"Consensus features generated: {len(study.consensus_df)}")',
+            '        print("=" * 70)',
+            '        ',
+            '        return True',
+            '        ',
+            '    except KeyboardInterrupt:',
+            '        print("\\nAnalysis interrupted by user")',
+            '        return False',
+            '    except Exception as e:',
+            '        print(f"Analysis failed with error: {e}")',
+            '        import traceback',
+            '        traceback.print_exc()',
+            '        return False',
+            '',
+            '',
+            'if __name__ == "__main__":',
+            '    success = main()',
+            '    sys.exit(0 if success else 1)',
+        ]
+        
+        return '\n'.join(script_lines)
+    
     def info(self):
         """Print comprehensive wizard status information."""
         status = self.get_status()
@@ -1157,6 +2232,8 @@ class Wizard:
         print(f"Polarity: {status['parameters']['polarity']}")
         print(f"CPU Cores: {status['parameters']['num_cores']}")
         print(f"Adducts: {', '.join(status['parameters']['adducts'])}")
+        print(f"Detector Type: {self.params.detector_type}")
+        print(f"Noise Threshold: {self.params.noise_threshold}")
         print(f"Processing Time: {status['processing_time']}")
         print(f"Files Processed: {status['processed_files']}")
         print(f"Files Failed: {status['failed_files']}")
@@ -1171,5 +2248,100 @@ class Wizard:
         print("=" * 50)
 
 
-# Export the main classes
-__all__ = ["Wizard", "wizard_def"]
+def create_script(
+    source: str, 
+    study_folder: str, 
+    filename: str, 
+    polarity: str = "positive",
+    adducts: Optional[List[str]] = None,
+    params: Optional[wizard_def] = None,
+    num_cores: int = 0,
+    **kwargs
+) -> bool:
+    """
+    Create a standalone analysis script without initializing a Wizard instance.
+    
+    This function generates a Python script that replicates automated processing
+    steps with the specified configuration. The script can be executed independently
+    to perform the same analysis.
+    
+    Parameters:
+        source: Directory containing raw data files
+        study_folder: Output directory for processed study  
+        filename: Filename for the generated script (should end with .py)
+        polarity: Ion polarity mode ("positive" or "negative")
+        adducts: List of adduct specifications (auto-set if None)
+        params: Custom wizard_def parameters (optional)
+        num_cores: Number of CPU cores (0 = auto-detect)
+        **kwargs: Additional parameters to override defaults
+        
+    Returns:
+        True if script was generated successfully, False otherwise
+        
+    Example:
+        >>> from masster.wizard import create_script
+        >>> create_script(
+        ...     source=r'D:\\Data\\raw_files',
+        ...     study_folder=r'D:\\Data\\output', 
+        ...     filename='run_masster.py',
+        ...     polarity='positive'
+        ... )
+    """
+    
+    try:
+        # Create parameters
+        if params is not None:
+            # Use provided params as base
+            wizard_params = params
+            # Update with provided values
+            wizard_params.data_source = source
+            wizard_params.study_folder = study_folder
+            if polarity != "positive":  # Only override if explicitly different
+                wizard_params.polarity = polarity
+            if num_cores > 0:
+                wizard_params.num_cores = num_cores
+            if adducts is not None:
+                wizard_params.adducts = adducts
+        else:
+            # Create new params with provided values
+            wizard_params = wizard_def(
+                data_source=source,
+                study_folder=study_folder,
+                polarity=polarity,
+                num_cores=max(1, int(multiprocessing.cpu_count() * 0.75)) if num_cores <= 0 else num_cores
+            )
+            
+            if adducts is not None:
+                wizard_params.adducts = adducts
+            
+            # Apply any additional kwargs
+            for key, value in kwargs.items():
+                if hasattr(wizard_params, key):
+                    setattr(wizard_params, key, value)
+        
+        # Ensure study folder exists
+        study_path = Path(study_folder)
+        study_path.mkdir(parents=True, exist_ok=True)
+        
+        # Create a temporary Wizard instance to generate the script
+        temp_wizard = Wizard(params=wizard_params)
+        
+        # Generate the script using the existing method
+        success = temp_wizard.export_script(filename)
+        
+        if success:
+            script_path = study_path / Path(filename).name
+            print(f"Analysis script created: {script_path.absolute()}")
+            print(f"Run with: python \"{script_path}\"")
+            
+        return success
+        
+    except Exception as e:
+        print(f"Failed to create script: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+
+# Export the main classes and functions
+__all__ = ["Wizard", "wizard_def", "create_script"]