masster 0.5.15__py3-none-any.whl → 0.5.17__py3-none-any.whl

masster/wizard/wizard.py

@@ -228,9 +228,17 @@ class Wizard:
     that process raw MS data through the complete pipeline: file discovery, feature
     detection, sample processing, study assembly, alignment, merging, and export.
     
-    This simplified version focuses on three core functions:
-    - create_scripts(): Generate workflow and interactive analysis scripts
-    - analyze(): Create and run analysis scripts with interactive notebook
+    Core functions:
+    - create_scripts(): Generate standalone analysis scripts
+    - test_only(): Process only one file for parameter validation
+    - test_and_run(): Test with single file, then run full batch if successful
+    - run(): Execute full batch processing on all files
+    
+    Recommended workflow:
+    1. wizard = Wizard(source="raw_data", folder="output")
+    2. wizard.create_scripts()  # Generate analysis scripts
+    3. wizard.test_only()       # Validate with single file
+    4. wizard.run()             # Process all files
     """
     
     def __init__(
@@ -239,7 +247,7 @@ class Wizard:
         folder: str = "",
         polarity: str = "positive",
         adducts: Optional[List[str]] = None,
-        num_cores: int = 0,
+        num_cores: int = 6,
         **kwargs
     ):
         """
@@ -290,14 +298,6 @@ class Wizard:
         self.folder_path = Path(self.params.folder) 
         self.folder_path.mkdir(parents=True, exist_ok=True)
         
-        # Initialize logger
-        self.logger = MassterLogger(
-            instance_type="wizard",
-            level="INFO",
-            label="Wizard",
-            sink=None
-        )
-        
         # 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()
@@ -306,164 +306,6 @@ class Wizard:
                 # Update adducts based on inferred polarity  
                 self.params.__post_init__()
 
-    def _analyze_source_files(self) -> Dict[str, Any]:
-        """
-        Analyze source files to extract metadata: number of files, file type, polarity, and acquisition length.
-        
-        Returns:
-            Dictionary containing:
-            - number_of_files: Total count of data files found
-            - file_types: List of file extensions found 
-            - polarity: Detected polarity ("positive" or "negative")
-            - length_minutes: Acquisition length in minutes
-            - first_file: Path to first file analyzed
-        """
-        result = {
-            'number_of_files': 0,
-            'file_types': [],
-            'polarity': 'positive',
-            'length_minutes': 0.0,
-            'first_file': None
-        }
-        
-        try:
-            # Find all data files
-            all_files = []
-            file_types_found = set()
-            
-            for extension in self.params.file_extensions:
-                if self.params.search_subfolders:
-                    pattern = f"**/*{extension}"
-                    files = list(self.source_path.rglob(pattern))
-                else:
-                    pattern = f"*{extension}"
-                    files = list(self.source_path.glob(pattern))
-                
-                if files:
-                    all_files.extend(files)
-                    file_types_found.add(extension)
-            
-            result['number_of_files'] = len(all_files)
-            result['file_types'] = list(file_types_found)
-            
-            if not all_files:
-                return result
-                
-            # Analyze first file for polarity and acquisition length
-            first_file = all_files[0]
-            result['first_file'] = str(first_file)
-            
-            # Extract metadata based on file type
-            if first_file.suffix.lower() == '.wiff':
-                metadata = self._analyze_wiff_file(first_file)
-            elif first_file.suffix.lower() == '.mzml':
-                metadata = self._analyze_mzml_file(first_file)
-            elif first_file.suffix.lower() == '.raw':
-                metadata = self._analyze_raw_file(first_file)
-            else:
-                metadata = {'polarity': 'positive', 'length_minutes': 0.0}
-                
-            result['polarity'] = metadata.get('polarity', 'positive')
-            result['length_minutes'] = metadata.get('length_minutes', 0.0)
-            
-        except Exception as e:
-            self.logger.warning(f"Failed to analyze source files: {e}")
-            
-        return result
-    
-    def _analyze_wiff_file(self, file_path: Path) -> Dict[str, Any]:
-        """Analyze WIFF file to extract polarity and acquisition length."""
-        try:
-            from masster.sample.load import _wiff_to_dict
-            
-            # Extract metadata from WIFF file
-            metadata_df = _wiff_to_dict(str(file_path))
-            
-            result = {'polarity': 'positive', 'length_minutes': 0.0}
-            
-            if not metadata_df.empty:
-                # Get polarity from first experiment
-                if 'polarity' in metadata_df.columns:
-                    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', '+']:
-                        result['polarity'] = "positive"
-                    elif first_polarity == -1 or str(first_polarity).lower() in ['negative', 'neg', '-']:
-                        result['polarity'] = "negative"
-                
-                # Estimate acquisition length by loading the file briefly
-                # For a rough estimate, we'll load just the scan info
-                from masster.sample import Sample
-                sample = Sample()
-                sample.logger_update(level="ERROR")  # Suppress logs
-                sample.load(str(file_path))
-                
-                if hasattr(sample, 'scans_df') and sample.scans_df is not None:
-                    if not sample.scans_df.is_empty():
-                        rt_values = sample.scans_df.select('rt').to_numpy().flatten()
-                        if len(rt_values) > 0:
-                            # RT is in seconds, convert to minutes
-                            result['length_minutes'] = float(rt_values.max()) / 60.0
-            
-            return result
-            
-        except Exception as e:
-            self.logger.debug(f"Failed to analyze WIFF file {file_path}: {e}")
-            return {'polarity': 'positive', 'length_minutes': 0.0}
-    
-    def _analyze_mzml_file(self, file_path: Path) -> Dict[str, Any]:
-        """Analyze mzML file to extract polarity and acquisition length."""
-        try:
-            from masster.sample import Sample
-            
-            sample = Sample()
-            sample.logger_update(level="ERROR")  # Suppress logs
-            sample.load(str(file_path))
-            
-            result = {'polarity': 'positive', 'length_minutes': 0.0}
-            
-            if hasattr(sample, 'scans_df') and sample.scans_df is not None:
-                if not sample.scans_df.is_empty():
-                    rt_values = sample.scans_df.select('rt').to_numpy().flatten()
-                    if len(rt_values) > 0:
-                        # RT is in seconds, convert to minutes
-                        result['length_minutes'] = float(rt_values.max()) / 60.0
-                        
-            # For mzML, polarity detection would require more detailed parsing
-            # For now, use default
-            return result
-            
-        except Exception as e:
-            self.logger.debug(f"Failed to analyze mzML file {file_path}: {e}")
-            return {'polarity': 'positive', 'length_minutes': 0.0}
-    
-    def _analyze_raw_file(self, file_path: Path) -> Dict[str, Any]:
-        """Analyze RAW file to extract polarity and acquisition length."""
-        try:
-            from masster.sample import Sample
-            
-            sample = Sample()
-            sample.logger_update(level="ERROR")  # Suppress logs
-            sample.load(str(file_path))
-            
-            result = {'polarity': 'positive', 'length_minutes': 0.0}
-            
-            if hasattr(sample, 'scans_df') and sample.scans_df is not None:
-                if not sample.scans_df.is_empty():
-                    rt_values = sample.scans_df.select('rt').to_numpy().flatten()
-                    if len(rt_values) > 0:
-                        # RT is in seconds, convert to minutes
-                        result['length_minutes'] = float(rt_values.max()) / 60.0
-                        
-            # For RAW files, polarity detection would require more detailed parsing
-            # For now, use default
-            return result
-            
-        except Exception as e:
-            self.logger.debug(f"Failed to analyze RAW file {file_path}: {e}")
-            return {'polarity': 'positive', 'length_minutes': 0.0}
-
     def _infer_polarity_from_first_file(self) -> str:
         """
         Infer polarity from the first available raw data file.
@@ -538,10 +380,8 @@ class Wizard:
             source_info = self._analyze_source_files()
             
             # Update wizard parameters based on detected metadata
-            if source_info['polarity'] != 'positive':  # Only update if different from default
+            if source_info.get('polarity') and source_info['polarity'] != 'positive':
                 self.params.polarity = source_info['polarity']
-                # Update adducts based on detected polarity
-                self.params.__post_init__()
             
             files_created = []
             
@@ -549,6 +389,9 @@ class Wizard:
             workflow_script_path = self.folder_path / "1_masster_workflow.py"
             workflow_content = self._generate_workflow_script_content(source_info)
             
+            # Apply test mode modifications
+            workflow_content = self._add_test_mode_support(workflow_content)
+            
             with open(workflow_script_path, 'w', encoding='utf-8') as f:
                 f.write(workflow_content)
             files_created.append(str(workflow_script_path))
@@ -573,7 +416,6 @@ class Wizard:
             }
             
         except Exception as e:
-            self.logger.error(f"Failed to create scripts: {e}")
             return {
                 "status": "error", 
                 "message": f"Failed to create scripts: {e}",
@@ -582,120 +424,109 @@ class Wizard:
                 "source_info": {}
             }
 
-    def _generate_workflow_script_content(self, source_info: Dict[str, Any]) -> str:
-        """Generate the content for 1_masster_workflow.py script."""
+    def _analyze_source_files(self) -> Dict[str, Any]:
+        """Analyze source files to extract metadata."""
+        result = {
+            "number_of_files": 0,
+            "file_types": [],
+            "polarity": "positive", 
+            "length_minutes": 0.0,
+            "first_file": None
+        }
         
-        # Convert Path objects to strings for JSON serialization
-        params_dict = {}
-        for key, value in self.params.__dict__.items():
-            if key == '_param_metadata':  # Skip metadata in generated script
-                continue
-            if isinstance(value, Path):
-                params_dict[key] = str(value)
-            else:
-                params_dict[key] = value
+        try:
+            # Find raw data files
+            extensions = [".wiff", ".raw", ".mzML"]
+            raw_files = []
+            
+            for ext in extensions:
+                pattern = f"**/*{ext}"
+                files = list(self.source_path.rglob(pattern))
+                if files:
+                    raw_files.extend(files)
+                    if ext not in result["file_types"]:
+                        result["file_types"].append(ext)
+            
+            result["number_of_files"] = len(raw_files)
+            
+            if raw_files:
+                result["first_file"] = str(raw_files[0])
+                # Simple heuristic: assume 30 minutes per file if we can't determine
+                result["length_minutes"] = 30.0
+                
+        except Exception as e:
+            print(f"Warning: Could not analyze source files: {e}")
+            
+        return result
 
-        # Create readable PARAMS dict with comments including discovered info
-        params_lines = []
-        params_lines.append('# Analysis parameters (auto-detected from source files)')
-        params_lines.append('PARAMS = {')
-        
-        # File Discovery Summary
-        params_lines.append('    # === Source File Analysis ===')
-        params_lines.append(f'    "number_of_files": {source_info.get("number_of_files", 0)},  # Total raw data files found')
-        params_lines.append(f'    "file_types": {source_info.get("file_types", [])!r},  # Detected file extensions')
-        params_lines.append(f'    "length_minutes": {source_info.get("length_minutes", 0.0):.1f},  # Estimated acquisition length per file (minutes)')
-        if source_info.get('first_file'):
-            params_lines.append(f'    "first_file": {source_info["first_file"]!r},  # First file analyzed for metadata')
-        params_lines.append('')
-        
-        # Core Configuration
-        params_lines.append('    # === Core Configuration ===')
-        params_lines.append(f'    "source": {params_dict.get("source", "")!r},  # Directory containing raw data files')
-        params_lines.append(f'    "folder": {params_dict.get("folder", "")!r},  # Output directory for processed study')
-        params_lines.append(f'    "polarity": {params_dict.get("polarity", "positive")!r},  # Ion polarity mode (auto-detected)')
-        params_lines.append(f'    "num_cores": {params_dict.get("num_cores", 4)},  # Number of CPU cores for parallel processing')
-        params_lines.append('')
-        
-        # File Discovery
-        params_lines.append('    # === File Discovery ===')
-        params_lines.append(f'    "file_extensions": {params_dict.get("file_extensions", [".wiff", ".raw", ".mzML"])!r},  # File extensions to search for')
-        params_lines.append(f'    "search_subfolders": {params_dict.get("search_subfolders", True)},  # Whether to search subdirectories recursively')
-        params_lines.append(f'    "skip_patterns": {params_dict.get("skip_patterns", ["blank", "condition"])!r},  # Filename patterns to skip')
-        params_lines.append('')
-        
-        # Processing Parameters - Critical values to review
-        params_lines.append('    # === Processing Parameters (REVIEW THESE VALUES) ===')
-        params_lines.append(f'    "adducts": {params_dict.get("adducts", [])!r},  # Adduct specifications for feature detection and annotation')
-        params_lines.append(f'    "detector_type": {params_dict.get("detector_type", "unknown")!r},  # MS detector type ("orbitrap", "tof", "unknown")')
-        params_lines.append(f'    "noise": {params_dict.get("noise", 50.0)},  # REVIEW: Noise threshold for feature detection. Set to 1e5 for Orbitraps')
-        params_lines.append(f'    "chrom_fwhm": {params_dict.get("chrom_fwhm", 0.5)},  # REVIEW: Chromatographic peak FWHM (seconds)')
-        params_lines.append(f'    "chrom_peak_snr": {params_dict.get("chrom_peak_snr", 5.0)},  # Minimum signal-to-noise ratio for chromatographic peaks')
-        params_lines.append('')
-        
-        # Other parameters...
-        params_lines.append('    # === Alignment & Merging ===')
-        params_lines.append(f'    "rt_tol": {params_dict.get("rt_tol", 5.0)},  # Retention time tolerance for alignment (seconds)')
-        params_lines.append(f'    "mz_tol": {params_dict.get("mz_tol", 0.01)},  # Mass-to-charge ratio tolerance for alignment (Da)')
-        params_lines.append(f'    "alignment_method": {params_dict.get("alignment_method", "kd")!r},  # Algorithm for sample alignment')
-        params_lines.append(f'    "min_samples_per_feature": {params_dict.get("min_samples_per_feature", 1)},  # Minimum samples required per consensus feature')
-        params_lines.append(f'    "merge_method": {params_dict.get("merge_method", "qt")!r},  # Method for merging consensus features')
-        params_lines.append('')
-        
-        # Other params
-        params_lines.append('    # === Sample Processing ===')
-        params_lines.append(f'    "batch_size": {params_dict.get("batch_size", 8)},  # Number of files to process per batch')
-        params_lines.append(f'    "memory_limit_gb": {params_dict.get("memory_limit_gb", 16.0)},  # Memory limit for processing (GB)')
-        params_lines.append('')
-        
-        params_lines.append('    # === Script Options ===')
-        params_lines.append(f'    "resume_enabled": {params_dict.get("resume_enabled", True)},  # Enable automatic resume capability')
-        params_lines.append(f'    "force_reprocess": {params_dict.get("force_reprocess", False)},  # Force reprocessing of existing files')
-        params_lines.append(f'    "cleanup_temp_files": {params_dict.get("cleanup_temp_files", True)},  # Clean up temporary files after processing')
-        
-        params_lines.append('}')
+    def _generate_workflow_script_content(self, source_info: Dict[str, Any]) -> str:
+        """Generate the content for 1_masster_workflow.py script."""
         
-        # Create script lines
         script_lines = [
             '#!/usr/bin/env python3',
             '"""',
-            'MASSter Workflow Script - Sample Processing',
-            f'Generated by masster wizard v{version}',
-            '',
-            'Source Analysis:',
-            f'  - Files found: {source_info.get("number_of_files", 0)}',
-            f'  - File types: {", ".join(source_info.get("file_types", []))}',
-            f'  - Polarity detected: {source_info.get("polarity", "unknown")}',
-            f'  - Acquisition length: ~{source_info.get("length_minutes", 0.0):.1f} minutes per file',
-            '',
-            'This script processes raw MS data files into sample5 format.',
-            'Review the NOISE and CHROM_FWHM parameters below before running.',
+            'Automated Mass Spectrometry Data Analysis Pipeline',
+            'Generated by masster wizard',
             '"""',
             '',
+            'import os',
             'import sys',
             'import time',
             'from pathlib import Path',
-            'import concurrent.futures',
-            'import os',
             '',
             '# Import masster modules',
-            'from masster.sample import Sample',
+            'from masster.study import Study',
             'from masster import __version__',
             '',
-        ]
-        
-        # Add the formatted PARAMS
-        script_lines.extend(params_lines)
-        
-        # Add the functions
-        script_lines.extend([
+            '# Test mode configuration',
+            'TEST_MODE = os.environ.get("MASSTER_TEST_MODE", "0") == "1"',
+            'TEST_ONLY = os.environ.get("MASSTER_TEST_ONLY", "0") == "1"  # Only run test, don\'t continue to full batch',
+            '',
+            '# Analysis parameters',
+            'PARAMS = {',
+            '    # === Core Configuration ===',
+            f'    "source": {str(self.source_path)!r},  # Directory containing raw data files',
+            f'    "folder": {str(self.folder_path)!r},  # Output directory for processed study',
+            f'    "polarity": {self.params.polarity!r},  # Ion polarity mode ("positive" or "negative")',
+            f'    "num_cores": {self.params.num_cores},  # Number of CPU cores for parallel processing',
+            '',
+            '    # === Test Mode ===',
+            '    "test_mode": TEST_MODE,  # Process only first file for testing',
+            '    "test_only": TEST_ONLY,  # Stop after test, don\'t run full batch',
+            '',
+            '    # === File Discovery ===',
+            f'    "file_extensions": {self.params.file_extensions!r},  # File extensions to search for',
+            f'    "search_subfolders": {self.params.search_subfolders},  # Whether to search subdirectories recursively',
+            f'    "skip_patterns": {self.params.skip_patterns!r},  # Filename patterns to skip',
+            '',
+            '    # === Processing Parameters ===',
+            f'    "adducts": {self.params.adducts!r},  # Adduct specifications for feature detection and annotation',
+            f'    "noise": {self.params.noise},  # Noise threshold for feature detection',
+            f'    "chrom_fwhm": {self.params.chrom_fwhm},  # Chromatographic peak full width at half maximum (seconds)',
+            f'    "chrom_peak_snr": {self.params.chrom_peak_snr},  # Minimum signal-to-noise ratio for chromatographic peaks',
+            '',
+            '    # === Alignment & Merging ===',
+            f'    "rt_tol": {self.params.rt_tolerance},  # Retention time tolerance for alignment (seconds)',
+            f'    "mz_tol": {self.params.mz_max_diff},  # Mass-to-charge ratio tolerance for alignment (Da)',
+            f'    "alignment_method": {self.params.alignment_algorithm!r},  # Algorithm for sample alignment',
+            f'    "min_samples_per_feature": {self.params.min_samples_for_merge},  # Minimum samples required per consensus feature',
+            f'    "merge_method": {self.params.merge_method!r},  # Method for merging consensus features',
+            '',
+            '    # === Sample Processing (used in add_samples_from_folder) ===',
+            f'    "batch_size": {self.params.batch_size},  # Number of files to process per batch',
+            f'    "memory_limit_gb": {self.params.memory_limit_gb},  # Memory limit for processing (GB)',
+            '',
+            '    # === Script Options ===',
+            f'    "resume_enabled": {self.params.resume_enabled},  # Enable automatic resume capability',
+            f'    "force_reprocess": {self.params.force_reprocess},  # Force reprocessing of existing files',
+            f'    "cleanup_temp_files": {self.params.cleanup_temp_files},  # Clean up temporary files after processing',
+            '}',
             '',
             '',
-            'def discover_raw_files(source_folder, file_extensions, search_subfolders=True, skip_patterns=None):',
+            'def discover_raw_files(source_folder, file_extensions, search_subfolders=True):',
             '    """Discover raw data files in the source folder."""',
             '    source_path = Path(source_folder)',
             '    raw_files = []',
-            '    skip_patterns = skip_patterns or []',
             '    ',
             '    for ext in file_extensions:',
             '        if search_subfolders:',
@@ -704,191 +535,189 @@ class Wizard:
             '        else:',
             '            pattern = f"*{ext}"',
             '            files = list(source_path.glob(pattern))',
-            '        ',
-            '        # Filter out files matching skip patterns',
-            '        for file in files:',
-            '            skip_file = False',
-            '            for skip_pattern in skip_patterns:',
-            '                if skip_pattern.lower() in file.name.lower():',
-            '                    skip_file = True',
-            '                    break',
-            '            if not skip_file:',
-            '                raw_files.append(file)',
+            '        raw_files.extend(files)',
             '    ',
             '    return raw_files',
             '',
             '',
             'def process_single_file(args):',
-            '    """Process a single raw file to sample5 format - designed for multiprocessing."""',
-            '    raw_file, output_folder, params = args',
+            '    """Process a single raw file to sample5 format - module level for multiprocessing."""',
+            '    raw_file, output_folder = args',
+            '    from masster.sample import Sample',
             '    ',
             '    try:',
             '        # Create sample5 filename',
             '        sample_name = raw_file.stem',
             '        sample5_path = Path(output_folder) / f"{sample_name}.sample5"',
             '        ',
-            '        # Skip if sample5 already exists and resume is enabled',
-            '        if sample5_path.exists() and params["resume_enabled"]:',
-            '            print(f"    ✓ Skipping {raw_file.name} (sample5 already exists)")',
-            '            return {"status": "skipped", "file": str(sample5_path), "message": "Already exists"}',
+            '        # Skip if sample5 already exists',
+            '        if sample5_path.exists() and not PARAMS["force_reprocess"]:',
+            '            print(f"  Skipping {raw_file.name} (sample5 already exists)")',
+            '            return str(sample5_path)',
             '        ',
-            '        print(f"    🔄 Processing {raw_file.name}...")',
-            '        start_time = time.time()',
+            '        print(f"  Converting {raw_file.name}...")',
             '        ',
             '        # Load and process raw file with full pipeline',
             '        sample = Sample(log_label=sample_name)',
             '        sample.load(filename=str(raw_file))',
             '        sample.find_features(',
-            '            noise=params["noise"],',
-            '            chrom_fwhm=params["chrom_fwhm"],',
-            '            chrom_peak_snr=params["chrom_peak_snr"]',
+            '            noise=PARAMS["noise"],',
+            '            chrom_fwhm=PARAMS["chrom_fwhm"],',
+            '            chrom_peak_snr=PARAMS["chrom_peak_snr"]',
             '        )',
-            '        # sample.find_adducts(adducts=params["adducts"])',
             '        sample.find_ms2()',
-            '        # sample.find_iso()  # Optional - can be uncommented if needed',
+            '        sample.find_iso()',
+            '        # sample.export_mgf()',
+            '        # sample.plot_2d(filename=f"{sample5_path.replace(".sample5", ".html")}")',
             '        sample.save(str(sample5_path))',
             '        ',
-            '        elapsed = time.time() - start_time',
-            '        print(f"    ✅ Completed {raw_file.name} -> {sample5_path.name} ({elapsed:.1f}s)")',
-            '        ',
-            '        return {"status": "success", "file": str(sample5_path), "elapsed": elapsed}',
+            '        # print(f"  Completed {raw_file.name} -> {sample5_path.name}")',
+            '        return str(sample5_path)',
             '        ',
             '    except Exception as e:',
-            '        print(f"    ❌ ERROR processing {raw_file.name}: {e}")',
-            '        return {"status": "error", "file": str(raw_file), "error": str(e)}',
+            '        print(f"  ERROR processing {raw_file.name}: {e}")',
+            '        return None',
             '',
             '',
-            'def convert_raw_to_sample5_parallel(raw_files, output_folder, params):',
-            '    """Convert raw data files to sample5 format with parallel processing and progress tracking."""',
+            'def convert_raw_to_sample5(raw_files, output_folder, polarity, num_cores):',
+            '    """Convert raw data files to sample5 format."""',
             '    import concurrent.futures',
             '    import os',
             '    ',
             '    # Create output directory',
             '    os.makedirs(output_folder, exist_ok=True)',
             '    ',
-            '    print(f"\\n🚀 Processing {len(raw_files)} files using {params[\'num_cores\']} CPU cores...")',
-            '    print("=" * 70)',
-            '    ',
             '    # Prepare arguments for multiprocessing',
-            '    file_args = [(raw_file, output_folder, params) for raw_file in raw_files]',
-            '    ',
-            '    # Process files in parallel with progress tracking',
-            '    results = []',
-            '    successful = 0',
-            '    skipped = 0',
-            '    failed = 0',
-            '    total_elapsed = 0',
+            '    file_args = [(raw_file, output_folder) for raw_file in raw_files]',
             '    ',
-            '    with concurrent.futures.ProcessPoolExecutor(max_workers=params["num_cores"]) as executor:',
-            '        # Submit all jobs',
-            '        future_to_file = {executor.submit(process_single_file, args): args[0] for args in file_args}',
+            '    # Process files in parallel',
+            '    sample5_files = []',
+            '    with concurrent.futures.ProcessPoolExecutor(max_workers=num_cores) as executor:',
+            '        futures = [executor.submit(process_single_file, args) for args in file_args]',
             '        ',
-            '        # Collect results as they complete',
-            '        for i, future in enumerate(concurrent.futures.as_completed(future_to_file), 1):',
+            '        for future in concurrent.futures.as_completed(futures):',
             '            result = future.result()',
-            '            results.append(result)',
-            '            ',
-            '            if result["status"] == "success":',
-            '                successful += 1',
-            '                total_elapsed += result.get("elapsed", 0)',
-            '            elif result["status"] == "skipped":',
-            '                skipped += 1',
-            '            else:',
-            '                failed += 1',
-            '            ',
-            '            # Progress update',
-            '            print(f"\\r    Progress: {i}/{len(raw_files)} files completed ({successful} success, {skipped} skipped, {failed} failed)", end="", flush=True)',
-            '    ',
-            '    print()  # New line after progress',
-            '    print("=" * 70)',
-            '    ',
-            '    # Summary',
-            '    if successful > 0:',
-            '        avg_time = total_elapsed / successful',
-            '        print(f"✅ Successfully processed {successful} files (avg: {avg_time:.1f}s per file)")',
-            '    if skipped > 0:',
-            '        print(f"⏩ Skipped {skipped} files (already exist)")',
-            '    if failed > 0:',
-            '        print(f"❌ Failed to process {failed} files")',
-            '        for result in results:',
-            '            if result["status"] == "error":',
-            '                print(f"    - {Path(result[\'file\']).name}: {result[\'error\']}")',
+            '            if result:',
+            '                sample5_files.append(result)',
             '    ',
-            '    # Return list of successful sample5 files',
-            '    sample5_files = [result["file"] for result in results if result["status"] in ["success", "skipped"]]',
             '    return sample5_files',
             '',
             '',
             'def main():',
-            '    """Main sample processing workflow."""',
+            '    """Main analysis pipeline."""',
             '    try:',
             '        print("=" * 70)',
-            f'        print("MASSter {version} - Sample Processing Workflow")',
+            f'        print("masster {version} - Automated MS Data Analysis")',
             '        print("=" * 70)',
             '        print(f"Source: {PARAMS[\'source\']}")',
             '        print(f"Output: {PARAMS[\'folder\']}")',
-            '        print(f"Polarity: {PARAMS[\'polarity\']} (detected)")',
+            '        print(f"Polarity: {PARAMS[\'polarity\']}")',
             '        print(f"CPU Cores: {PARAMS[\'num_cores\']}")',
             '        print("=" * 70)',
-            '        print("\\n⚙️  IMPORTANT: Review these parameters before processing:")',
-            '        print(f"   NOISE threshold: {PARAMS[\'noise\']} (adjust based on your instrument)")',
-            '        print(f"   CHROM_FWHM: {PARAMS[\'chrom_fwhm\']}s (adjust based on your chromatography)")',
-            '        print("   You can edit these values in the PARAMS section above.")',
-            '        print("=" * 70)',
             '        ',
             '        start_time = time.time()',
             '        ',
             '        # Step 1: Discover raw data files',
-            '        print("\\n📁 Step 1/2: Discovering raw data files...")',
+            '        print("\\nStep 1/7: Discovering raw data files...")',
             '        raw_files = discover_raw_files(',
             '            PARAMS[\'source\'],',
             '            PARAMS[\'file_extensions\'],',
-            '            PARAMS[\'search_subfolders\'],',
-            '            PARAMS[\'skip_patterns\']',
+            '            PARAMS[\'search_subfolders\']',
             '        )',
             '        ',
             '        if not raw_files:',
-            '            print("❌ No raw data files found!")',
+            '            print("No raw data files found!")',
             '            return False',
             '        ',
             '        print(f"Found {len(raw_files)} raw data files")',
-            '        for i, f in enumerate(raw_files[:5]):  # Show first 5 files',
-            '            print(f"  {i+1}. {f.name}")',
+            '        for f in raw_files[:5]:  # Show first 5 files',
+            '            print(f"  {f.name}")',
             '        if len(raw_files) > 5:',
-            '            print(f"  ... and {len(raw_files) - 5} more files")',
+            '            print(f"  ... and {len(raw_files) - 5} more")',
             '        ',
-            '        # Step 2: Process raw files to sample5',
-            '        print("\\n🔄 Step 2/2: Processing raw files to sample5 format...")',
-            '        sample5_files = convert_raw_to_sample5_parallel(',
+            '        # Step 2: Process raw files',
+            '        print("\\nStep 2/7: Processing raw files...")',
+            '        sample5_files = convert_raw_to_sample5(',
             '            raw_files,',
             '            PARAMS[\'folder\'],',
-            '            PARAMS',
+            '            PARAMS[\'polarity\'],',
+            '            PARAMS[\'num_cores\']',
             '        )',
             '        ',
             '        if not sample5_files:',
-            '            print("❌ No sample5 files were created!")',
+            '            print("No sample5 files were created!")',
             '            return False',
             '        ',
-            '        # Summary',
+            '        print(f"Successfully processed {len(sample5_files)} files to sample5")',
+            '        ',
+            '        # Step 3: Create and configure study',
+            '        print("\\nStep 3/7: Initializing study...")',
+            '        study = Study(folder=PARAMS[\'folder\'])',
+            '        study.polarity = PARAMS[\'polarity\']',
+            '        study.adducts = PARAMS[\'adducts\']',
+            '        ',
+            '        # Step 4: Add sample5 files to study',
+            '        print("\\nStep 4/7: Adding samples to study...")',
+            '        study.add(str(Path(PARAMS[\'folder\']) / "*.sample5"))',
+            '        study.features_filter(study.features_select(chrom_coherence=0.1, chrom_prominence_scaled=1))',
+            '        ',
+            '        # Step 5: Core processing',
+            '        print("\\nStep 5/7: Processing...")',
+            '        study.align(',
+            '            algorithm=PARAMS[\'alignment_method\'],',
+            '            rt_tol=PARAMS[\'rt_tol\']',
+            '        )',
+            '        ',
+            '        study.merge(',
+            '            method="qt",',
+            '            min_samples=PARAMS[\'min_samples_per_feature\'],',
+            '            threads=PARAMS[\'num_cores\'],',
+            '            rt_tol=PARAMS[\'rt_tol\']',
+            '        )',
+            '        study.find_iso()',
+            '        study.fill()',
+            '        study.integrate()',
+            '        ',
+            '        # Step 6/7: Saving results',
+            '        print("\\nStep 6/7: Saving results...")',
+            '        study.save()',
+            '        study.export_xlsx()',
+            '        study.export_mgf()',
+            '        study.export_mztab()',
+            '        ',
+            '        # Step 7: Plots',
+            '        print("\\nStep 7/7: Exporting plots...")',
+            '        study.plot_consensus_2d(filename="consensus.html")',
+            '        study.plot_consensus_2d(filename="consensus.png")',
+            '        study.plot_alignment(filename="alignment.html")',
+            '        study.plot_alignment(filename="alignment.png")',
+            '        study.plot_samples_pca(filename="pca.html")',
+            '        study.plot_samples_pca(filename="pca.png")',
+            '        study.plot_bpc(filename="bpc.html")',
+            '        study.plot_bpc(filename="bpc.png")',
+            '        study.plot_rt_correction(filename="rt_correction.html")',
+            '        study.plot_rt_correction(filename="rt_correction.png")',
+            '        ',
+            '        # Print summary',
+            '        study.info()',
             '        total_time = time.time() - start_time',
             '        print("\\n" + "=" * 70)',
-            '        print("🎉 SAMPLE PROCESSING COMPLETE")',
+            '        print("ANALYSIS COMPLETE")',
             '        print("=" * 70)',
-            '        print(f"Processing time: {total_time/60:.1f} minutes")',
-            '        print(f"Raw files found: {len(raw_files)}")',
+            '        print(f"Total processing time: {total_time:.1f} seconds ({total_time/60:.1f} minutes)")',
+            '        print(f"Raw files processed: {len(raw_files)}")',
             '        print(f"Sample5 files created: {len(sample5_files)}")',
-            '        print("\\nNext steps:")',
-            '        print("1. Run the interactive analysis: uv run marimo edit 2_interactive_analysis.py")',
-            '        print("2. Or use the sample5 files in your own analysis scripts")',
+            '        if hasattr(study, "consensus_df"):',
+            '            print(f"Consensus features generated: {len(study.consensus_df)}")',
             '        print("=" * 70)',
             '        ',
             '        return True',
             '        ',
             '    except KeyboardInterrupt:',
-            '        print("\\n❌ Processing interrupted by user")',
+            '        print("\\nAnalysis interrupted by user")',
             '        return False',
             '    except Exception as e:',
-            '        print(f"❌ Processing failed with error: {e}")',
+            '        print(f"Analysis failed with error: {e}")',
             '        import traceback',
             '        traceback.print_exc()',
             '        return False',
@@ -897,115 +726,292 @@ class Wizard:
             'if __name__ == "__main__":',
             '    success = main()',
             '    sys.exit(0 if success else 1)',
-        ])
+        ]
+        
+        return '\n'.join(script_lines)
+
+    def _generate_interactive_notebook_content(self, source_info: Dict[str, Any]) -> str:
+        """Generate the content for 2_interactive_analysis.py marimo notebook."""
+        
+        notebook_lines = [
+            'import marimo',
+            '',
+            '__generated_with = "0.9.14"',
+            'app = marimo.App(width="medium")',
+            '',
+            '@app.cell',
+            'def __():',
+            '    import marimo as mo',
+            '    return (mo,)',
+            '',
+            '@app.cell',
+            'def __(mo):',
+            '    mo.md(r"""',
+            '    # MASSter Interactive Analysis',
+            '    ',
+            f'    **Source:** {source_info.get("number_of_files", 0)} files detected',
+            f'    **Polarity:** {source_info.get("polarity", "unknown")}',
+            '    ',
+            '    This notebook provides interactive exploration of your processed study.',
+            '    Make sure you have run `python 1_masster_workflow.py` first.',
+            '    """)',
+            '    return ()',
+            '',
+            '@app.cell',
+            'def __():',
+            '    import masster',
+            '    return (masster,)',
+            '',
+            '@app.cell',
+            'def __(masster):',
+            '    study = masster.Study(folder=".")',
+            '    return (study,)',
+            '',
+            '@app.cell',
+            'def __(study):',
+            '    study.info()',
+            '    return ()',
+            '',
+            'if __name__ == "__main__":',
+            '    app.run()',
+        ]
+        
+        return '\n'.join(notebook_lines)
+
+    def _generate_instructions(self, source_info: Dict[str, Any], files_created: List[str]) -> List[str]:
+        """Generate usage instructions for the created scripts."""
+        instructions = [f"Source analysis: {source_info.get('number_of_files', 0)} files found",
+            f"Polarity detected: {source_info.get('polarity', 'unknown')}",
+            "Files created:"]
+        for file_path in files_created:
+            instructions.append(f"  ✅ {str(Path(file_path).resolve())}")
+        
+        # Find the workflow script name from created files
+        workflow_script_name = "1_masster_workflow.py"
+        for file_path in files_created:
+            if Path(file_path).name == "1_masster_workflow.py":
+                workflow_script_name = Path(file_path).name
+                break
+            
+        instructions.extend([
+            "",
+            "Next steps:",
+            f"1. REVIEW PARAMETERS in {workflow_script_name}:",
+            f"   In particular, verify the NOISE, CHROM_FWHM, and MIN_SAMPLES_FOR_MERGE",
+            "",
+            "2. TEST SINGLE FILE (RECOMMENDED):",
+            f"   wizard.test_only()  # Validate parameters with first file only",
+            "",
+            "3. EXECUTE FULL BATCH:",
+            f"   wizard.run()        # Process all files",
+            f"   # OR: wizard.test_and_run()  # Test first, then run all",
+            f"   # OR: uv run python {workflow_script_name}",
+            "",
+            "4. INTERACTIVE ANALYSIS:",
+            f"   uv run marimo edit {Path('2_interactive_analysis.py').name}",
+            ""]            
+        )
+        
+        return instructions
+
+    def _add_test_mode_support(self, workflow_content: str) -> str:
+        """Add test mode functionality to the generated workflow script."""
+        lines = workflow_content.split('\n')
+        
+        # Insert test mode code after print statements in main function
+        for i, line in enumerate(lines):
+            # Add test mode print after the masster version line
+            if 'print("masster' in line and 'Automated MS Data Analysis")' in line:
+                lines.insert(i + 1, '        if TEST_MODE:')
+                lines.insert(i + 2, '            print("🧪 TEST MODE: Processing single file only")')
+                break
+        
+        # Add mode info after num_cores print
+        for i, line in enumerate(lines):
+            if 'print(f"CPU Cores: {PARAMS[\'num_cores\']}")' in line:
+                lines.insert(i + 1, '        if TEST_MODE:')
+                lines.insert(i + 2, '            print(f"Mode: {\'Test Only\' if TEST_ONLY else \'Test + Full Batch\'}")')
+                break
+                
+        # Add file limitation logic after file listing
+        for i, line in enumerate(lines):
+            if 'print(f"  ... and {len(raw_files) - 5} more")' in line:
+                lines.insert(i + 1, '        ')
+                lines.insert(i + 2, '        # Limit to first file in test mode')
+                lines.insert(i + 3, '        if TEST_MODE:')
+                lines.insert(i + 4, '            raw_files = raw_files[:1]')
+                lines.insert(i + 5, '            print(f"\\n🧪 TEST MODE: Processing only first file: {raw_files[0].name}")')
+                break
+        
+        # Modify num_cores for test mode
+        for i, line in enumerate(lines):
+            if 'PARAMS[\'num_cores\']' in line and 'convert_raw_to_sample5(' in lines[i-2:i+3]:
+                lines[i] = line.replace('PARAMS[\'num_cores\']', 'PARAMS[\'num_cores\'] if not TEST_MODE else 1  # Use single core for test')
+                break
+        
+        # Add test-only exit logic after successful processing
+        for i, line in enumerate(lines):
+            if 'print(f"Successfully processed {len(sample5_files)} files to sample5")' in line:
+                lines.insert(i + 1, '        ')
+                lines.insert(i + 2, '        # Stop here if test-only mode')
+                lines.insert(i + 3, '        if TEST_ONLY:')
+                lines.insert(i + 4, '            print("\\n🧪 TEST ONLY mode: Stopping after successful single file processing")')
+                lines.insert(i + 5, '            print(f"Test file created: {sample5_files[0]}")')
+                lines.insert(i + 6, '            print("\\nTo run full batch, use: wizard.run()")')
+                lines.insert(i + 7, '            total_time = time.time() - start_time')
+                lines.insert(i + 8, '            print(f"\\nTest processing time: {total_time:.1f} seconds")')
+                lines.insert(i + 9, '            return True')
+                break
+                
+        return '\n'.join(lines)
+
+    def test_and_run(self) -> Dict[str, Any]:
+        """
+        Test the sample processing workflow with a single file, then run full batch.
+        
+        This method runs the 1_masster_workflow.py script in test mode to process
+        the first raw file for validation, then automatically continues with the 
+        full batch if the test succeeds. The script must already exist - call 
+        create_scripts() first if needed.
+        
+        Returns:
+            Dictionary containing:
+            - status: "success" or "error"
+            - message: Status message
+            - instructions: List of next steps
+        """
+        return self._execute_workflow(test_mode=True)
+
+    def test_only(self) -> Dict[str, Any]:
+        """
+        Test the sample processing workflow with a single file only.
         
-        return '\n'.join(script_lines)
+        This method runs the 1_masster_workflow.py script in test-only mode to process
+        only the first raw file and then stops (does not continue to full study processing).
+        The script must already exist - call create_scripts() first if needed.
+        
+        Returns:
+            Dictionary containing:
+            - status: "success" or "error"
+            - message: Status message
+            - instructions: List of next steps
+            - test_file: Path to the processed test file (if successful)
+        """
+        return self._execute_workflow(test_mode=True, test_only=True)
 
-    def analyze(self) -> Dict[str, Any]:
+    def run(self) -> Dict[str, Any]:
         """
-        Execute the complete analysis workflow.
+        Run the sample processing workflow.
         
-        This method:
-        1. Checks if 1_masster_workflow.py exists and runs it
-        2. If not, creates scripts first then runs the workflow
-        3. Provides clear feedback about next steps
+        This method runs the 1_masster_workflow.py script to process raw files.
+        The script must already exist - call create_scripts() first if needed.
         
         Returns:
-            Dictionary containing execution results and instructions
+            Dictionary containing:
+            - status: "success" or "error"
+            - message: Status message
+            - instructions: List of next steps
+        """
+        return self._execute_workflow(test_mode=False)
+
+    def _execute_workflow(self, test_mode: bool = False, test_only: bool = False) -> Dict[str, Any]:
         """
-        workflow_script = self.folder_path / "1_masster_workflow.py"
+        Execute the workflow script in either test or full mode.
         
+        Args:
+            test_mode: If True, run in test mode (single file), otherwise full batch
+            test_only: If True, stop after single file test (only used with test_mode=True)
+        """
         try:
+            workflow_script_path = self.folder_path / "1_masster_workflow.py"
+            
             # Check if workflow script exists
-            if workflow_script.exists():
-                print("📋 Found existing workflow script, executing...")
-                return self._execute_workflow_script(workflow_script)
+            if not workflow_script_path.exists():
+                return {
+                    "status": "error",
+                    "message": "Workflow script not found. Please run create_scripts() first.",
+                    "instructions": [
+                        "❌ Missing 1_masster_workflow.py",
+                        "Run: wizard.create_scripts()",
+                        "Then: wizard.run()"
+                    ]
+                }
+            
+            # Setup execution mode
+            if test_only:
+                mode_label = "test-only"
+            elif test_mode:
+                mode_label = "test"
             else:
-                print("📝 Creating analysis scripts...")
-                # Create scripts first
-                result = self.create_scripts()
-                
-                if result["status"] != "success":
-                    return result
-                    
-                # Print instructions
-                print("\n" + "="*70)
-                for instruction in result["instructions"]:
-                    print(instruction)
-                print("="*70)
+                mode_label = "full batch"
                 
-                # Ask user if they want to proceed with execution
-                print("\n🤔 Would you like to proceed with sample processing now?")
-                print("   This will execute 1_masster_workflow.py")
-                response = input("   Proceed? [y/N]: ").strip().lower()
+            env = None
+            if test_mode:
+                import os
+                env = os.environ.copy()
+                env['MASSTER_TEST_MODE'] = '1'
+                if test_only:
+                    env['MASSTER_TEST_ONLY'] = '1'
                 
-                if response in ['y', 'yes']:
-                    return self._execute_workflow_script(workflow_script)
-                else:
-                    print("✋ Processing paused. Run the scripts manually when ready.")
-                    return {
-                        "status": "scripts_created",
-                        "message": "Scripts created successfully, execution deferred",
-                        "instructions": result["instructions"],
-                        "files_created": result["files_created"]
-                    }
-                    
-        except Exception as e:
-            self.logger.error(f"Analysis failed: {e}")
-            return {
-                "status": "error",
-                "message": f"Analysis failed: {e}",
-                "instructions": [],
-                "files_created": []
-            }
-    
-    def _execute_workflow_script(self, script_path: Path) -> Dict[str, Any]:
-        """Execute the workflow script and return results."""
-        try:
-            print(f"🚀 Executing {script_path.name}...")
+            # Execute the workflow script
+            print(f"🚀 Executing {mode_label} processing workflow...")
+            print(f"📄 Running: {workflow_script_path.name}")
+            print("=" * 60)
             
             import subprocess
             result = subprocess.run([
-                sys.executable, str(script_path)
-            ], cwd=str(self.folder_path), capture_output=False, text=True)
+                sys.executable, str(workflow_script_path)
+            ], cwd=str(self.folder_path), env=env)
             
             success = result.returncode == 0
             
             if success:
-                print("="*70)
-                print("✅ Workflow execution completed successfully!")
-                print("="*70)
-                print("Next step: Run interactive analysis")
-                print("  uv run marimo edit 2_interactive_analysis.py")
-                print("="*70)
+                print("=" * 60)
+                if test_only:
+                    print("✅ Test-only processing completed successfully!")
+                    print("📋 Single file validated - ready for full batch")
+                    print("   wizard.run()")
+                elif test_mode:
+                    print("✅ Test processing completed successfully!")
+                    print("📋 Next step: Run full batch")
+                    print("   wizard.run()")
+                else:
+                    print("✅ Sample processing completed successfully!")
+                    print("📋 Next step: Run interactive analysis")
+                    print("   uv run marimo edit 2_interactive_analysis.py")
+                print("=" * 60)
+                
+                next_step = ("Next: wizard.run()" if test_mode else 
+                           "Next: uv run marimo edit 2_interactive_analysis.py")
                 
                 return {
                     "status": "success",
-                    "message": "Workflow completed successfully",
+                    "message": f"{mode_label.capitalize()} processing completed successfully",
                     "instructions": [
-                        "✅ Sample processing completed",
-                        "Next: uv run marimo edit 2_interactive_analysis.py"
-                    ],
-                    "files_created": []
+                        f"✅ {mode_label.capitalize()} processing completed",
+                        next_step
+                    ]
                 }
             else:
                 return {
                     "status": "error",
-                    "message": f"Workflow execution failed with code {result.returncode}",
+                    "message": f"Workflow execution failed with return code {result.returncode}",
                     "instructions": [
                         "❌ Check the error messages above",
                         "Review parameters in 1_masster_workflow.py",
-                        "Try running: python 1_masster_workflow.py"
-                    ],
-                    "files_created": []
+                        f"Try running manually: python {workflow_script_path.name}"
+                    ]
                 }
                 
         except Exception as e:
             return {
                 "status": "error",
                 "message": f"Failed to execute workflow: {e}",
-                "instructions": [],
-                "files_created": []
+                "instructions": [
+                    "❌ Execution failed",
+                    "Check that source files exist and are accessible",
+                    "Verify folder permissions"
+                ]
             }
 
     def _generate_script_content(self) -> str:
@@ -1313,413 +1319,74 @@ class Wizard:
         
         return '\n'.join(script_lines)
 
-    def _generate_notebook_content(self) -> str:
-        """Generate the content for a marimo interactive notebook."""
-        
-        notebook_lines = [
-            'import marimo',
-            '',
-            '__generated_with = "0.9.14"',
-            'app = marimo.App(width="medium")',
-            '',
-            '',
-            '@app.cell',
-            'def __():',
-            '    import marimo as mo',
-            '    return (mo,)',
-            '',
-            '',
-            '@app.cell',
-            'def __(mo):',
-            '    mo.md(r"""',
-            '    # MASSter Interactive Analysis',
-            '    ',
-            '    This notebook provides interactive exploration of your mass spectrometry study results.',
-            '    The study has been processed and is ready for analysis.',
-            '    """)',
-            '',
-            '',
-            '@app.cell',
-            'def __():',
-            '    # Import masster',
-            '    import masster',
-            '    return (masster,)',
-            '',
-            '',
-            '@app.cell',
-            'def __(masster):',
-            '    # Load the processed study',
-            '    study = masster.Study(folder=".")',
-            '    study.load()',
-            '    return (study,)',
-            '',
-            '',
-            '@app.cell',
-            'def __(mo, study):',
-            '    # Display study information',
-            '    mo.md(f"""',
-            '    ## Study Overview',
-            '    ',
-            '    **Samples:** {len(study.samples) if hasattr(study, "samples") else "Not loaded"}',
-            '    ',
-            '    **Features:** {len(study.consensus_df) if hasattr(study, "consensus_df") else "Not available"}',
-            '    ',
-            '    **Polarity:** {study.polarity if hasattr(study, "polarity") else "Unknown"}',
-            '    """)',
-            '',
-            '',
-            '@app.cell',
-            'def __(study):',
-            '    # Print detailed study info',
-            '    study.info()',
-            '',
-            '',
-            '@app.cell',
-            'def __(mo):',
-            '    mo.md(r"""',
-            '    ## Quick Visualizations',
-            '    ',
-            '    Use the cells below to create interactive plots of your data.',
-            '    """)',
-            '',
-            '',
-            '@app.cell',
-            'def __(study):',
-            '    # Generate consensus 2D plot',
-            '    if hasattr(study, "consensus_df") and len(study.consensus_df) > 0:',
-            '        study.plot_consensus_2d(filename="consensus_interactive.html")',
-            '        print("Consensus 2D plot saved as: consensus_interactive.html")',
-            '    else:',
-            '        print("No consensus features available for plotting")',
-            '',
-            '',
-            '@app.cell',
-            'def __(study):',
-            '    # Generate PCA plot',
-            '    if hasattr(study, "samples") and len(study.samples) > 1:',
-            '        study.plot_samples_pca(filename="pca_interactive.html")',
-            '        print("PCA plot saved as: pca_interactive.html")',
-            '    else:',
-            '        print("Not enough samples for PCA analysis")',
-            '',
-            '',
-            '@app.cell',
-            'def __(mo):',
-            '    mo.md(r"""',
-            '    ## Data Export',
-            '    ',
-            '    Export your processed data in various formats.',
-            '    """)',
-            '',
-            '',
-            '@app.cell',
-            'def __(study):',
-            '    # Export options',
-            '    if hasattr(study, "consensus_df"):',
-            '        # Export to Excel',
-            '        study.export_xlsx(filename="study_results.xlsx")',
-            '        print("✓ Results exported to: study_results.xlsx")',
-            '        ',
-            '        # Export to MGF',
-            '        study.export_mgf(filename="study_spectra.mgf")',
-            '        print("✓ Spectra exported to: study_spectra.mgf")',
-            '    else:',
-            '        print("No data available for export")',
-            '',
-            '',
-            '@app.cell',
-            'def __(mo):',
-            '    mo.md(r"""',
-            '    ## Custom Analysis',
-            '    ',
-            '    Add your own analysis code in the cells below.',
-            '    """)',
-            '',
-            '',
-            '@app.cell',
-            'def __(study):',
-            '    # Access consensus features dataframe',
-            '    if hasattr(study, "consensus_df"):',
-            '        df = study.consensus_df',
-            '        print(f"Consensus features shape: {df.shape}")',
-            '        print("\\nFirst 5 features:")',
-            '        print(df.head())',
-            '    return (df,) if "df" in locals() else ()',
-            '',
-            '',
-            '@app.cell',
-            'def __():',
-            '    # Your custom analysis here',
-            '    pass',
-            '',
-            '',
-            'if __name__ == "__main__":',
-            '    app.run()',
-        ]
-        
-        return '\n'.join(notebook_lines)
-
-
-def create_analysis(
-    source: str, 
-    folder: str, 
-    filename: str = 'run_masster.py', 
-    polarity: str = "positive",
-    adducts: Optional[List[str]] = None,
-    params: Optional[wizard_def] = None,
-    num_cores: int = 0,
-    **kwargs
-) -> bool:
-    """
-    Create standalone analysis scripts without initializing a Wizard instance.
-    
-    This function generates analysis scripts with the specified configuration.
-    
-    Parameters:
-        source: Directory containing raw data files
-        folder: Output directory for processed study  
-        filename: Filename for the generated script (deprecated, will create standard files)
-        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 scripts were generated successfully, False otherwise
-        
-    Example:
-        >>> from masster.wizard import create_analysis
-        >>> create_analysis(
-        ...     source=r'D:\\Data\\raw_files',
-        ...     folder=r'D:\\Data\\output', 
-        ...     polarity='positive'
-        ... )
-    """
-    
-    try:
-        # Create parameters
-        if params is not None:
-            # Use provided params as base
-            wizard_params = params
-            # Update with provided values
-            wizard_params.source = source
-            wizard_params.folder = 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(
-                source=source,
-                folder=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(folder)
-        study_path.mkdir(parents=True, exist_ok=True)
-        
-        # Create a temporary Wizard instance to generate the scripts
-        temp_wizard = Wizard(params=wizard_params)
-        
-        # Generate the scripts using the new method
-        result = temp_wizard.create_scripts()
-        
-        if result["status"] == "success":
-            print("Scripts created successfully!")
-            for instruction in result["instructions"]:
-                print(instruction)
-                
-        return result["status"] == "success"
-        
-    except Exception as e:
-        print(f"Failed to create scripts: {e}")
-        import traceback
-        traceback.print_exc()
-        return False
-
 
-def analyze(
-    source: str, 
-    folder: str, 
-    filename: str = 'run_masster.py', 
+def create_scripts(
+    source: str = "", 
+    folder: str = "", 
     polarity: str = "positive",
     adducts: Optional[List[str]] = None,
-    params: Optional[wizard_def] = None,
     num_cores: int = 0,
     **kwargs
-) -> bool:
+) -> Dict[str, Any]:
     """
-    Create and execute a standalone analysis script for automated MS data processing.
+    Create analysis scripts without explicitly instantiating a Wizard.
     
-    This function generates a Python script with the same parameters as create_analysis(),
-    but immediately executes it after creation. Combines script generation and execution
-    in a single step.
+    This is a convenience function that creates a Wizard instance internally
+    and calls its create_scripts() method.
     
     Parameters:
         source: Directory containing raw data files
-        folder: Output directory for processed study  
-        filename: Filename for the generated script (should end with .py)
+        folder: Output directory for processed study
         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
+        **kwargs: Additional parameters
         
     Returns:
-        True if script was created and executed successfully, False otherwise
+        Dictionary containing:
+        - status: "success" or "error"
+        - message: Status message
+        - instructions: List of next steps
+        - files_created: List of created file paths
+        - source_info: Metadata about source files
         
     Example:
-        >>> from masster.wizard import analyze
-        >>> analyze(
+        >>> import masster.wizard
+        >>> result = masster.wizard.create_scripts(
         ...     source=r'D:\\Data\\raw_files',
         ...     folder=r'D:\\Data\\output', 
-        ...     polarity='positive'
+        ...     polarity='negative'
         ... )
+        >>> print("Status:", result["status"])
     """
     
     try:
-        # Create parameters (same logic as create_analysis)
-        if params is not None:
-            wizard_params = params
-            wizard_params.source = source
-            wizard_params.folder = folder
-            if polarity != "positive":
-                wizard_params.polarity = polarity
-            if num_cores > 0:
-                wizard_params.num_cores = num_cores
-            if adducts is not None:
-                wizard_params.adducts = adducts
-        else:
-            wizard_params = wizard_def(
-                source=source,
-                folder=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)
+        # Auto-detect optimal number of cores if not specified
+        if num_cores <= 0:
+            num_cores = max(1, int(multiprocessing.cpu_count() * 0.75))
         
-        # Create Wizard instance and run analysis
-        wizard = Wizard(params=wizard_params)
-        result = wizard.analyze()
+        # Create Wizard instance
+        wizard = Wizard(
+            source=source,
+            folder=folder,
+            polarity=polarity,
+            adducts=adducts,
+            num_cores=num_cores,
+            **kwargs
+        )
         
-        # Return success status
-        return result.get("status") in ["success", "scripts_created"]
+        # Call the instance method
+        return wizard.create_scripts()
         
     except Exception as e:
-        print(f"Failed to execute script: {e}")
-        import traceback
-        traceback.print_exc()
-        return False
-
-
-    def _generate_interactive_notebook_content(self, source_info: Dict[str, Any]) -> str:
-        """Generate the content for 2_interactive_analysis.py marimo notebook."""
-        
-        notebook_lines = [
-            'import marimo',
-            '',
-            '__generated_with = "0.9.14"',
-            'app = marimo.App(width="medium")',
-            '',
-            '',
-            '@app.cell',
-            'def __():',
-            '    import marimo as mo',
-            '    return (mo,)',
-            '',
-            '',
-            '@app.cell',
-            'def __(mo):',
-            '    mo.md(r"""',
-            '    # MASSter Interactive Analysis',
-            '    ',
-            f'    **Source:** {source_info.get("number_of_files", 0)} files ({", ".join(source_info.get("file_types", []))}) detected',
-            f'    **Polarity:** {source_info.get("polarity", "unknown")} (auto-detected)',
-            f'    **Acquisition length:** ~{source_info.get("length_minutes", 0.0):.1f} minutes per file',
-            '    ',
-            '    This notebook provides interactive exploration of your processed mass spectrometry study.',
-            '    Make sure you have run `python 1_masster_workflow.py` first to create the sample5 files.',
-            '    """)',
-            '',
-            '',
-            '@app.cell',
-            'def __():',
-            '    # Import masster',
-            '    import masster',
-            '    return (masster,)',
-            '',
-            '',
-            '@app.cell',
-            'def __(masster):',
-            '    # Load the study from sample5 files',
-            '    study = masster.Study(folder=".")',
-            '    return (study,)',
-            '',
-            '',
-            '@app.cell',
-            'def __(mo, study):',
-            '    # Display study information',
-            '    study.info()',
-            '    return ()',
-            '',
-            '',
-            'if __name__ == "__main__":',
-            '    app.run()',
-        ]
-        
-        return '\n'.join(notebook_lines)
-
-    def _generate_instructions(self, source_info: Dict[str, Any], files_created: List[str]) -> List[str]:
-        """Generate usage instructions for the created scripts."""
-        instructions = [
-            "🎯 NEXT STEPS:",
-            "",
-            f"Source analysis completed: {source_info.get('number_of_files', 0)} files found",
-            f"Polarity detected: {source_info.get('polarity', 'unknown')}",
-            f"Estimated processing time: {source_info.get('number_of_files', 0) * source_info.get('length_minutes', 0.0) * 0.1:.1f} minutes",
-            "",
-            "1. REVIEW PARAMETERS:",
-            "   Edit 1_masster_workflow.py and verify these key settings:",
-            "   - NOISE threshold (adjust based on your instrument sensitivity)",
-            "   - CHROM_FWHM (adjust based on your chromatography peak width)",
-            "",
-            "2. EXECUTE SAMPLE PROCESSING:",
-            "   python 1_masster_workflow.py",
-            "   (This will process all raw files to sample5 format)",
-            "",
-            "3. INTERACTIVE ANALYSIS:",
-            "   uv run marimo edit 2_interactive_analysis.py",
-            "   (This opens an interactive notebook for data exploration)",
-            "",
-            "FILES CREATED:"
-        ]
-        
-        for file_path in files_created:
-            instructions.append(f"  ✅ {Path(file_path).name}")
-            
-        return instructions
+        return {
+            "status": "error",
+            "message": f"Failed to create scripts: {e}",
+            "instructions": [],
+            "files_created": [],
+            "source_info": {}
+        }
 
 
 # Export the main classes and functions
-__all__ = ["Wizard", "wizard_def", "create_analysis", "analyze"]
+__all__ = ["Wizard", "wizard_def", "create_scripts"]