masster 0.5.18__tar.gz → 0.5.20__tar.gz

{masster-0.5.18 → masster-0.5.20}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.18
+Version: 0.5.20
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster

{masster-0.5.18 → masster-0.5.20}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.18"
+version = "0.5.20"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.18 → masster-0.5.20}/src/masster/_version.py

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

{masster-0.5.18 → masster-0.5.20}/src/masster/lib/lib.py

@@ -46,6 +46,7 @@ annotations = lib.annotate_features(sample.features_df)
 """
 
 import os
+import json
 from typing import Optional, Union, List, Dict, Any, TYPE_CHECKING
 import warnings
 
@@ -685,6 +686,142 @@ class Lib:
             if skipped_compounds > 0:
                 print(f"All {total_compounds} compounds were skipped due to invalid formulas")
     
+    def import_json(self, 
+                   jsonfile: str, 
+                   polarity: Optional[str] = None,
+                   adducts: Optional[List[str]] = None,
+                   min_probability: float = 0.03) -> None:
+        """
+        Import compound library from a JSON file created by csv_to_json.py.
+        
+        This method reads a JSON file with the structure created by csv_to_json.py
+        and generates adduct variants for each compound.
+        
+        Args:
+            jsonfile: Path to the JSON file
+            polarity: Ionization polarity ("positive", "negative", or None for positive)
+            adducts: Specific adducts to generate. If None, generates defaults for the polarity
+            min_probability: Minimum probability threshold for adduct filtering
+            
+        Expected JSON structure:
+            {
+                "version": "1.0",
+                "creation_date": "2025-10-07T09:17:06.142290",
+                "description": "Converted from CSV file...",
+                "source_file": "filename.csv",
+                "record_count": 123,
+                "data": [
+                    {
+                        "name": "compound name",
+                        "smiles": "SMILES string",
+                        "inchikey": "InChI key",
+                        "formula": "molecular formula",
+                        "db_id": "database ID",
+                        "db": "database name"
+                    },
+                    ...
+                ]
+            }
+            
+        Raises:
+            FileNotFoundError: If JSON file doesn't exist
+            ValueError: If JSON structure is invalid or required data is missing
+        """
+        if not os.path.exists(jsonfile):
+            raise FileNotFoundError(f"JSON file not found: {jsonfile}")
+        
+        # Read and parse JSON file
+        try:
+            with open(jsonfile, 'r', encoding='utf-8') as f:
+                json_data = json.load(f)
+        except json.JSONDecodeError as e:
+            raise ValueError(f"Invalid JSON file: {e}") from e
+        except Exception as e:
+            raise ValueError(f"Error reading JSON file: {e}") from e
+        
+        # Validate JSON structure
+        if not isinstance(json_data, dict):
+            raise ValueError("JSON file must contain a dictionary at root level")
+        
+        if "data" not in json_data:
+            raise ValueError("JSON file must contain a 'data' field with compound records")
+        
+        data = json_data["data"]
+        if not isinstance(data, list):
+            raise ValueError("'data' field must be a list of compound records")
+        
+        # Extract metadata for reporting
+        version = json_data.get("version", "unknown")
+        source_file = json_data.get("source_file", "unknown")
+        record_count = json_data.get("record_count", len(data))
+        
+        print(f"Loading JSON library: version {version}, source: {source_file}, records: {record_count}")
+        
+        # Process each compound
+        all_variants = []
+        cmpd_id_counter = 1
+        lib_id_counter = 1
+        total_compounds = 0
+        skipped_compounds = 0
+        
+        for compound_record in data:
+            total_compounds += 1
+            
+            # Validate required fields
+            if not isinstance(compound_record, dict):
+                skipped_compounds += 1
+                continue
+            
+            formula = compound_record.get("formula", "")
+            if not formula or not isinstance(formula, str):
+                skipped_compounds += 1
+                continue
+            
+            # Extract compound data, handling both CSV column names and JSON field names
+            compound_level_uid = cmpd_id_counter
+            cmpd_id_counter += 1
+            
+            compound_data = {
+                "name": compound_record.get("name", compound_record.get("Name", "")),
+                "shortname": compound_record.get("shortname", ""),
+                "class": compound_record.get("class", ""),
+                "smiles": compound_record.get("smiles", compound_record.get("SMILES", "")),
+                "inchi": compound_record.get("inchi", compound_record.get("InChI", "")),
+                "inchikey": compound_record.get("inchikey", compound_record.get("InChIKey", "")),
+                "formula": formula,
+                "rt": self._safe_float_conversion(compound_record.get("rt", compound_record.get("RT", None))),
+                "db_id": compound_record.get("db_id", compound_record.get("database_id", None)),
+                "db": compound_record.get("db", compound_record.get("database", None)),
+                "cmpd_uid": compound_level_uid,
+            }
+            
+            # Generate adduct variants
+            variants, lib_id_counter = self._generate_adduct_variants(
+                compound_data, adducts=adducts, polarity=polarity, 
+                lib_id_counter=lib_id_counter, min_probability=min_probability
+            )
+            all_variants.extend(variants)
+            
+            # Track if compound was skipped due to invalid formula
+            if len(variants) == 0:
+                skipped_compounds += 1
+        
+        # Convert to DataFrame and store
+        if all_variants:
+            new_lib_df = pl.DataFrame(all_variants)
+            
+            # Combine with existing data if any
+            if self.lib_df is not None and len(self.lib_df) > 0:
+                self.lib_df = pl.concat([self.lib_df, new_lib_df])
+            else:
+                self.lib_df = new_lib_df
+                
+            print(f"Imported {len(all_variants)} library entries from {jsonfile}")
+        else:
+            print(f"No valid compounds found in {jsonfile}")
+            if skipped_compounds > 0:
+                print(f"All {total_compounds} compounds were skipped due to invalid formulas")
+    
     def _map_csv_columns(self, columns: List[str]) -> Dict[str, str]:
         """
         Map CSV column names to standardized internal names (case-insensitive).

{masster-0.5.18 → masster-0.5.20}/src/masster/sample/defaults/find_ms2_def.py

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

{masster-0.5.18 → masster-0.5.20}/src/masster/sample/h5.py

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

{masster-0.5.18 → masster-0.5.20}/src/masster/sample/processing.py

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

{masster-0.5.18 → masster-0.5.20}/src/masster/sample/sciex.py

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

{masster-0.5.18 → masster-0.5.20}/src/masster/sample/thermo.py

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

{masster-0.5.18 → masster-0.5.20}/src/masster/study/id.py

@@ -21,10 +21,10 @@ def lib_load(
 
     Args:
         study: Study instance
-        lib_source: either a CSV file path (str) or a Lib instance
-        polarity: ionization polarity ("positive" or "negative") - used when lib_source is a CSV path.
+        lib_source: either a CSV/JSON file path (str) or a Lib instance
+        polarity: ionization polarity ("positive" or "negative") - used when lib_source is a CSV/JSON path.
                  If None, uses study.polarity automatically.
-        adducts: specific adducts to generate - used when lib_source is a CSV path
+        adducts: specific adducts to generate - used when lib_source is a CSV/JSON path
         iso: isotope generation mode ("13C" to generate 13C isotopes, None for no isotopes)
 
     Side effects:
@@ -38,7 +38,7 @@ def lib_load(
         Lib = None
 
     if lib_source is None:
-        raise ValueError("lib_source must be a CSV file path (str) or a Lib instance")
+        raise ValueError("lib_source must be a CSV/JSON file path (str) or a Lib instance")
 
     # Use study polarity if not explicitly provided
     if polarity is None:
@@ -52,15 +52,23 @@ def lib_load(
             polarity = "positive"  # Default fallback
         study.logger.debug(f"Using study polarity: {polarity}")
 
-    # Handle string input (CSV file path)
+    # Handle string input (CSV or JSON file path)
     if isinstance(lib_source, str):
         if Lib is None:
             raise ImportError(
-                "Could not import masster.lib.lib.Lib - required for CSV loading",
+                "Could not import masster.lib.lib.Lib - required for CSV/JSON loading",
             )
 
         lib_obj = Lib()
-        lib_obj.import_csv(lib_source, polarity=polarity, adducts=adducts)
+        
+        # Determine file type by extension
+        if lib_source.lower().endswith('.json'):
+            lib_obj.import_json(lib_source, polarity=polarity, adducts=adducts)
+        elif lib_source.lower().endswith('.csv'):
+            lib_obj.import_csv(lib_source, polarity=polarity, adducts=adducts)
+        else:
+            # Default to CSV behavior for backward compatibility
+            lib_obj.import_csv(lib_source, polarity=polarity, adducts=adducts)
 
     # Handle Lib instance
     elif Lib is not None and isinstance(lib_source, Lib):
@@ -72,7 +80,7 @@ def lib_load(
 
     else:
         raise TypeError(
-            "lib_source must be a CSV file path (str), a masster.lib.Lib instance, or have a 'lib_df' attribute",
+            "lib_source must be a CSV/JSON file path (str), a masster.lib.Lib instance, or have a 'lib_df' attribute",
         )
 
     # Ensure lib_df is populated
@@ -101,7 +109,7 @@ def lib_load(
     # Store pointer and DataFrame on study
     study._lib = lib_obj
 
-    # Add source_id column with filename (without path) if loading from CSV
+    # Add source_id column with filename (without path) if loading from CSV/JSON
     if isinstance(lib_source, str):
         import os
         filename_only = os.path.basename(lib_source)

{masster-0.5.18 → masster-0.5.20}/src/masster/wizard/README.md

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