masster 0.5.22__py3-none-any.whl → 0.5.24__py3-none-any.whl

masster/sample/processing.py

@@ -253,8 +253,7 @@ def get_spectrum(self, scan, **kwargs):
                 spec=spect,
                 scan_uid=scan_uid,
                 feature_uid=scan_info["feature_uid"][0]
-                if "feature_uid" in scan_info
-                and scan_info["feature_uid"][0] is not None
+                if "feature_uid" in scan_info and scan_info["feature_uid"][0] is not None
                 else feature_uid,
                 q1_step=2,
                 deisotope=deisotope,
@@ -447,9 +446,7 @@ def _spec_to_mat(
             closest_index = np.argmin(np.abs(ar2 - val1))
             closest_indices.append((i, closest_index))
         # filter out pairs that are not within the specified tolerance
-        closest_indices = [
-            (i, j) for i, j in closest_indices if np.abs(ar1[i] - ar2[j]) <= tol
-        ]
+        closest_indices = [(i, j) for i, j in closest_indices if np.abs(ar1[i] - ar2[j]) <= tol]
         # remove duplicates from the list of indices
         closest_indices = list(set(closest_indices))
         # sort the list of indices by the first element (i) in ascending order
@@ -621,8 +618,7 @@ def find_features(self, **kwargs):
     mtd_par.setValue("noise_threshold_int", float(params.get("noise")))
     mtd_par.setValue(
         "min_trace_length",
-        float(params.get("min_trace_length_multiplier"))
-        * float(params.get("chrom_fwhm_min")),
+        float(params.get("min_trace_length_multiplier")) * float(params.get("chrom_fwhm_min")),
     )
     mtd_par.setValue(
         "trace_termination_outliers",
@@ -801,7 +797,7 @@ def find_features(self, **kwargs):
     )
 
     self.features_df = df
-    #self._features_sync()
+    # self._features_sync()
     self.logger.success(f"Feature detection completed. Total features: {len(df)}")
 
     # store params
@@ -1134,9 +1130,7 @@ def find_ms2(self, **kwargs):
     feature_rt_start = features_subset.select("rt_start").to_numpy().flatten()
     feature_rt_end = features_subset.select("rt_end").to_numpy().flatten()
     feature_uids = features_subset.select("feature_uid").to_numpy().flatten()
-    feature_indices = (
-        features_subset.with_row_index().select("index").to_numpy().flatten()
-    )
+    feature_indices = features_subset.with_row_index().select("index").to_numpy().flatten()
 
     # Pre-compute RT radius for all features
     rt_radius = np.minimum(feature_rt - feature_rt_start, feature_rt_end - feature_rt)
@@ -1283,16 +1277,16 @@ def find_ms2(self, **kwargs):
 
 def find_iso(self, rt_tolerance: float = 0.1, **kwargs):
     """Extract isotopic distributions from MS1 data and add to features_df.
-    
+
     This method processes each feature to find isotopic distributions from MS1 data,
     similar to the study.find_iso() method but for individual samples. The method
     adds a new 'ms1_spec' column to features_df containing numpy arrays with
     isotopic distribution data.
-    
+
     Args:
         rt_tolerance (float): RT tolerance in minutes for matching MS1 scans. Default 0.1.
         **kwargs: Additional parameters
-    
+
     Notes:
         - Adds a new 'ms1_spec' column to features_df containing numpy arrays
         - Each array contains [mz, intensity] pairs for the isotopic distribution
@@ -1302,11 +1296,11 @@ def find_iso(self, rt_tolerance: float = 0.1, **kwargs):
     if self.features_df is None or self.features_df.is_empty():
         self.logger.warning("No features found. Run find_features() first.")
         return
-        
+
     if self.ms1_df is None or self.ms1_df.is_empty():
         self.logger.warning("No MS1 data found.")
         return
-    
+
     # Check if ms1_spec column already exists
     if "ms1_spec" in self.features_df.columns:
         features_without_spec = self.features_df.filter(pl.col("ms1_spec").is_null())
@@ -1316,9 +1310,7 @@ def find_iso(self, rt_tolerance: float = 0.1, **kwargs):
         self.logger.info(f"Processing {len(features_without_spec)} features without isotopic distributions.")
     else:
         # Add the ms1_spec column with None values
-        self.features_df = self.features_df.with_columns(
-            pl.lit(None, dtype=pl.Object).alias("ms1_spec")
-        )
+        self.features_df = self.features_df.with_columns(pl.lit(None, dtype=pl.Object).alias("ms1_spec"))
         features_without_spec = self.features_df
         self.logger.info(f"Processing {len(features_without_spec)} features for isotopic distributions.")
 
@@ -1336,60 +1328,59 @@ def find_iso(self, rt_tolerance: float = 0.1, **kwargs):
         6.02010,
         7.02345,
     ])
-    
+
     # Convert rt_tolerance from minutes to seconds
     rt_tolerance_s = rt_tolerance * 60
-    
+
     # Process each feature
     ms1_specs = []
     feature_indices = []
-    
-    for i, row in enumerate(tqdm(
-        features_without_spec.rows(named=True), 
-        desc=f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Extracting isotope patterns"
-    )):
+
+    for i, row in enumerate(
+        tqdm(
+            features_without_spec.rows(named=True),
+            desc=f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Extracting isotope patterns",
+        )
+    ):
         feature_rt = row["rt"]
         feature_mz = row["mz"]
-        
+
         # Find MS1 scans within RT tolerance
-        rt_mask = (
-            (self.ms1_df["rt"] >= (feature_rt - rt_tolerance_s)) & 
-            (self.ms1_df["rt"] <= (feature_rt + rt_tolerance_s))
+        rt_mask = (self.ms1_df["rt"] >= (feature_rt - rt_tolerance_s)) & (
+            self.ms1_df["rt"] <= (feature_rt + rt_tolerance_s)
         )
         ms1_in_range = self.ms1_df.filter(rt_mask)
-        
+
         if ms1_in_range.is_empty():
             ms1_specs.append(None)
             feature_indices.append(row["feature_uid"])
             continue
-        
+
         # Extract isotopic pattern
         isotope_pattern = []
-        
+
         # Start with the monoisotopic peak (M+0)
         base_intensity = 0
         mz_tolerance = 0.01  # 10 ppm at 1000 Da
-        
+
         # Find the base peak intensity
-        base_mask = (
-            (ms1_in_range["mz"] >= (feature_mz - mz_tolerance)) & 
-            (ms1_in_range["mz"] <= (feature_mz + mz_tolerance))
+        base_mask = (ms1_in_range["mz"] >= (feature_mz - mz_tolerance)) & (
+            ms1_in_range["mz"] <= (feature_mz + mz_tolerance)
         )
         base_peaks = ms1_in_range.filter(base_mask)
-        
+
         if not base_peaks.is_empty():
             base_intensity = base_peaks["inty"].max()
             isotope_pattern.append([feature_mz, base_intensity])
-        
+
         # Look for isotope peaks
         for shift in isotope_shifts:
             isotope_mz = feature_mz + shift
-            isotope_mask = (
-                (ms1_in_range["mz"] >= (isotope_mz - mz_tolerance)) & 
-                (ms1_in_range["mz"] <= (isotope_mz + mz_tolerance))
+            isotope_mask = (ms1_in_range["mz"] >= (isotope_mz - mz_tolerance)) & (
+                ms1_in_range["mz"] <= (isotope_mz + mz_tolerance)
             )
             isotope_peaks = ms1_in_range.filter(isotope_mask)
-            
+
             if not isotope_peaks.is_empty():
                 max_intensity = isotope_peaks["inty"].max()
                 # Only keep isotope peaks that are at least 1% of base peak
@@ -1397,29 +1388,25 @@ def find_iso(self, rt_tolerance: float = 0.1, **kwargs):
                     # Get the mz of the most intense peak
                     max_peak = isotope_peaks.filter(pl.col("inty") == max_intensity).row(0, named=True)
                     isotope_pattern.append([max_peak["mz"], max_intensity])
-        
+
         # Convert to numpy array or None if empty
         if len(isotope_pattern) > 1:  # Need at least 2 points (monoisotopic + 1 isotope)
             ms1_spec = np.array(isotope_pattern, dtype=np.float64)
         else:
             ms1_spec = None
-            
+
         ms1_specs.append(ms1_spec)
         feature_indices.append(row["feature_uid"])
-    
+
     # Update the features_df with the isotopic spectra
     update_df = pl.DataFrame({
         "feature_uid": feature_indices,
-        "ms1_spec_new": pl.Series("ms1_spec_new", ms1_specs, dtype=pl.Object)
+        "ms1_spec_new": pl.Series("ms1_spec_new", ms1_specs, dtype=pl.Object),
     })
-    
+
     # Join and update
     self.features_df = (
-        self.features_df.join(
-            update_df,
-            on="feature_uid",
-            how="left"
-        )
+        self.features_df.join(update_df, on="feature_uid", how="left")
         .with_columns([
             pl.when(pl.col("ms1_spec_new").is_not_null())
             .then(pl.col("ms1_spec_new"))
@@ -1428,11 +1415,11 @@ def find_iso(self, rt_tolerance: float = 0.1, **kwargs):
         ])
         .drop("ms1_spec_new")
     )
-    
+
     # Log results
     non_null_count = len([spec for spec in ms1_specs if spec is not None])
     self.logger.success(f"Extracted isotopic distributions for {non_null_count}/{len(ms1_specs)} features.")
-    
+
     # Store parameters in history
     params_dict = {"rt_tolerance": rt_tolerance}
     params_dict.update(kwargs)

masster/sample/sample.py

@@ -1,8 +1,8 @@
 """
 sample.py - Mass Spectrometry Sample Analysis Module
 
-This module provides comprehensive tools for processing and analyzing Data-Dependent Acquisition (DDA) 
-mass spectrometry data. It defines the `Sample` class, which offers methods to load, process, analyze, 
+This module provides comprehensive tools for processing and analyzing Data-Dependent Acquisition (DDA)
+mass spectrometry data. It defines the `Sample` class, which offers methods to load, process, analyze,
 and visualize mass spectrometry data from various file formats.
 
 Supported File Formats:
@@ -31,7 +31,7 @@ Core Dependencies:
     - `h5py`: HDF5 file format support for Sample5 files
 
 Classes:
-    Sample: Main class for handling DDA mass spectrometry data, providing methods for 
+    Sample: Main class for handling DDA mass spectrometry data, providing methods for
             data import, processing, analysis, and visualization.
 
 Typical Workflow:
@@ -43,43 +43,43 @@ Typical Workflow:
 
 Example Usage:
     Basic analysis workflow:
-    
+
     ```python
     from masster.sample import Sample
-    
+
     # Load a mass spectrometry file
     sample = Sample(filename="experiment.mzML")
-    
+
     # Detect features
     sample.find_features()
-    
+
     # Find MS2 spectra for features
     sample.find_ms2()
-    
+
     # Generate 2D visualization
     sample.plot_2d()
-    
+
     # Export results
     sample.export_features("features.xlsx")
     ```
-    
+
     Advanced usage with custom parameters:
-    
+
     ```python
     from masster.sample import Sample
     from masster.sample.defaults import sample_defaults, find_features_defaults
-    
+
     # Create custom parameters
     params = sample_defaults(log_level="DEBUG", label="My Experiment")
     ff_params = find_features_defaults(noise_threshold_int=1000)
-    
+
     # Initialize with custom parameters
     sample = Sample(params=params)
     sample.load("data.raw")
-    
+
     # Feature detection with custom parameters
     sample.find_features(params=ff_params)
-    
+
     # Generate comprehensive statistics
     stats = sample.get_dda_stats()
     sample.plot_dda_stats()
@@ -275,7 +275,7 @@ class Sample:
     save = save
     find_features = find_features
     find_adducts = find_adducts
-    _get_adducts= _get_adducts
+    _get_adducts = _get_adducts
     find_iso = find_iso
     find_ms2 = find_ms2
     get_spectrum = get_spectrum
@@ -348,45 +348,44 @@ class Sample:
 
     def __dir__(self):
         """
-        Custom __dir__ implementation to hide internal methods starting with '_' 
-        and backward compatibility aliases from tab completion and dir() calls, 
+        Custom __dir__ implementation to hide internal methods starting with '_'
+        and backward compatibility aliases from tab completion and dir() calls,
         while keeping them accessible to class methods.
-        
+
         Returns:
             list: List of public attribute and method names (excluding internal and deprecated methods)
         """
         # Define backward compatibility aliases to hide
         backward_compatibility_aliases = {
-            'load_study',           # deprecated alias for _load_ms1
-            'filter_features',      # alias for filter (deprecated naming)
-            'select_features',      # alias for select (deprecated naming)
-            'features_filter',      # confusing duplicate of filter
-            'features_select',      # confusing duplicate of select
-            'merge_defaults',       # alias for find_features_defaults (confusing)
-            'plot_feature_stats',   # backward compatibility for plot_features_stats
-            'store_history',        # deprecated alias for update_history
+            "load_study",  # deprecated alias for _load_ms1
+            "filter_features",  # alias for filter (deprecated naming)
+            "select_features",  # alias for select (deprecated naming)
+            "features_filter",  # confusing duplicate of filter
+            "features_select",  # confusing duplicate of select
+            "merge_defaults",  # alias for find_features_defaults (confusing)
+            "plot_feature_stats",  # backward compatibility for plot_features_stats
+            "store_history",  # deprecated alias for update_history
         }
-        
+
         # Get all attributes from the class
         all_attrs = set()
-        
+
         # Add attributes from the class and all its bases
         for cls in self.__class__.__mro__:
             all_attrs.update(cls.__dict__.keys())
-        
+
         # Add instance attributes
         all_attrs.update(self.__dict__.keys())
-        
+
         # Filter out attributes starting with '_' (but keep special methods like __init__, __str__, etc.)
         # Also filter out backward compatibility aliases
         public_attrs = [
-            attr for attr in all_attrs 
-            if not attr.startswith('_') or attr.startswith('__') and attr.endswith('__')
+            attr for attr in all_attrs if not attr.startswith("_") or attr.startswith("__") and attr.endswith("__")
         ]
-        
+
         # Remove backward compatibility aliases from the public attributes
         public_attrs = [attr for attr in public_attrs if attr not in backward_compatibility_aliases]
-        
+
         return sorted(public_attrs)
 
     def logger_update(
@@ -442,10 +441,7 @@ class Sample:
 
         # Get all currently loaded modules that are part of the sample package
         for module_name in sys.modules:
-            if (
-                module_name.startswith(sample_module_prefix)
-                and module_name != current_module
-            ):
+            if module_name.startswith(sample_module_prefix) and module_name != current_module:
                 sample_modules.append(module_name)
 
         # Add core masster modules
@@ -461,15 +457,10 @@ class Sample:
         study_modules = []
         study_module_prefix = f"{base_modname}.study."
         for module_name in sys.modules:
-            if (
-                module_name.startswith(study_module_prefix)
-                and module_name != current_module
-            ):
+            if module_name.startswith(study_module_prefix) and module_name != current_module:
                 study_modules.append(module_name)
 
-        all_modules_to_reload = (
-            core_modules + sample_modules + study_modules
-        )
+        all_modules_to_reload = core_modules + sample_modules + study_modules
 
         # Reload all discovered modules
         for full_module_name in all_modules_to_reload:

masster/sample/save.py

@@ -105,7 +105,8 @@ def save(self, filename=None):
     self._save_sample5(filename=filename)
     self.file_path = filename
 
-'''
+
+"""
 def _save_featureXML(self, filename="features.featureXML"):
     if self._oms_features_map is None:
         self.logger.warning("No features found.")
@@ -114,7 +115,9 @@ def _save_featureXML(self, filename="features.featureXML"):
     fh.store(filename, self._oms_features_map)
     self.logger.debug(f"Features Map saved to {filename}")
 
-'''
+"""
+
+
 def export_features(self, filename="features.csv"):
     """
     Export the features DataFrame to a CSV or Excel file.
@@ -140,11 +143,7 @@ def export_features(self, filename="features.csv"):
             (pl.col("ms2_scans").is_not_null()).alias("has_ms2"),
         )
     clean_df = self.features_df.select(
-        [
-            col
-            for col in self.features_df.columns
-            if self.features_df[col].dtype not in (pl.List, pl.Object)
-        ],
+        [col for col in self.features_df.columns if self.features_df[col].dtype not in (pl.List, pl.Object)],
     )
     if filename.lower().endswith((".xls", ".xlsx")):
         clean_df.to_pandas().to_excel(filename, index=False)
@@ -231,7 +230,7 @@ def export_mgf(
     if rt_end is not None:
         features = features.filter(pl.col("rt") <= rt_end)
     # Note: We no longer filter out features without MS2 data here since we want to export
-    # MS1 spectra for ALL features with isotope data. The MS2 filtering is done in the 
+    # MS1 spectra for ALL features with isotope data. The MS2 filtering is done in the
     # second pass where we specifically check for ms2_scans.
 
     # Convert to list of dictionaries for faster iteration
@@ -269,26 +268,26 @@ def export_mgf(
     def write_ion(f, title, fuid, fid, mz, rt, charge, spect):
         if spect is None:
             return "none"
-        
+
         # For MSLEVEL=2 ions, don't write empty spectra
         ms_level = spect.ms_level if spect.ms_level is not None else 1
         if ms_level > 1 and (len(spect.mz) == 0 or len(spect.inty) == 0):
             return "empty_ms2"
-        
+
         # Create dynamic title based on MS level
         if ms_level == 1:
             # MS1: uid, rt, mz
             dynamic_title = f"uid:{fuid}, rt:{rt:.2f}, mz:{mz:.4f}"
         else:
             # MS2: uid, rt, mz, energy
-            energy = spect.energy if hasattr(spect, 'energy') else 0
+            energy = spect.energy if hasattr(spect, "energy") else 0
             dynamic_title = f"uid:{fuid}, rt:{rt:.2f}, mz:{mz:.4f}, energy:{energy}"
-            
+
         f.write(f"BEGIN IONS\nTITLE={dynamic_title}\n")
         f.write(f"FEATURE_UID={fuid}\n")
         f.write(f"FEATURE_ID={fid}\n")
         f.write(f"CHARGE={charge}\nPEPMASS={mz}\nRTINSECONDS={rt}\n")
-        
+
         if spect.ms_level is None:
             f.write("MSLEVEL=1\n")
             # Add PRECURSORINTENSITY for MS1 spectra
@@ -301,15 +300,12 @@ def export_mgf(
             if spect.ms_level == 1 and len(spect.inty) > 0:
                 precursor_intensity = max(spect.inty)
                 f.write(f"PRECURSORINTENSITY={precursor_intensity:.0f}\n")
-        
+
         if spect.ms_level is not None:
             if spect.ms_level > 1 and hasattr(spect, "energy"):
                 f.write(f"ENERGY={spect.energy}\n")
         # Use list comprehension for better performance
-        peak_lines = [
-            f"{mz_val:.5f} {inty_val:.0f}\n"
-            for mz_val, inty_val in zip(spect.mz, spect.inty, strict=False)
-        ]
+        peak_lines = [f"{mz_val:.5f} {inty_val:.0f}\n" for mz_val, inty_val in zip(spect.mz, spect.inty, strict=False)]
         f.writelines(peak_lines)
         f.write("END IONS\n\n")
         return "written"
@@ -322,8 +318,7 @@ def export_mgf(
 
     # count how many features have charge < 0
     if (
-        self.features_df.filter(pl.col("charge") < 0).shape[0]
-        - self.features_df.filter(pl.col("charge") > 0).shape[0]
+        self.features_df.filter(pl.col("charge") < 0).shape[0] - self.features_df.filter(pl.col("charge") > 0).shape[0]
         > 0
     ):
         preferred_charge = -1
@@ -342,7 +337,7 @@ def export_mgf(
     filename = os.path.abspath(filename)
     with open(filename, "w", encoding="utf-8") as f:
         tdqm_disable = self.log_level not in ["TRACE", "DEBUG", "INFO"]
-        
+
         # First pass: Export MS1 spectra for ALL features with ms1_spec data
         for row in tqdm(
             features_list,
@@ -362,19 +357,15 @@ def export_mgf(
             if "ms1_spec" in row and row["ms1_spec"] is not None:
                 # Create spectrum from ms1_spec isotope pattern data
                 from masster.spectrum import Spectrum
-                
+
                 iso_data = row["ms1_spec"]
                 if len(iso_data) >= 2:  # Ensure we have mz and intensity arrays
                     ms1_mz = iso_data[0]
                     ms1_inty = iso_data[1]
-                    
+
                     # Create a Spectrum object from the isotope data
-                    spect = Spectrum(
-                        mz=np.array(ms1_mz),
-                        inty=np.array(ms1_inty),
-                        ms_level=1
-                    )
-                    
+                    spect = Spectrum(mz=np.array(ms1_mz), inty=np.array(ms1_inty), ms_level=1)
+
                     charge = preferred_charge
                     if row["charge"] is not None and row["charge"] != 0:
                         charge = row["charge"]
@@ -395,7 +386,7 @@ def export_mgf(
             else:
                 # No MS1 spectrum exported for features without ms1_spec data
                 ms1_fallback_count += 1
-        
+
         # Second pass: Export MS2 spectra for features with MS2 data
         for row in tqdm(
             features_list,
@@ -453,9 +444,7 @@ def export_mgf(
                                     q1_max=q1_ratio_max,
                                 )
                                 # Get the corresponding scan_uid from the list
-                                current_scan_uid = (
-                                    scan_uids[i] if i < len(scan_uids) else "unknown"
-                                )
+                                current_scan_uid = scan_uids[i] if i < len(scan_uids) else "unknown"
                                 result = write_ion(
                                     f,
                                     f"uid:{feature_uid}",
@@ -580,18 +569,14 @@ def export_mgf(
                                 spect = spect.centroid(
                                     tolerance=self.parameters["mz_tol_ms1_da"],
                                     ppm=self.parameters["mz_tol_ms1_ppm"],
-                                    min_points=self.parameters[
-                                        "centroid_min_points_ms1"
-                                    ],
+                                    min_points=self.parameters["centroid_min_points_ms1"],
                                     algo=centroid_algo,
                                 )
                             elif spect.ms_level == 2:
                                 spect = spect.centroid(
                                     tolerance=self.parameters["mz_tol_ms2_da"],
                                     ppm=self.parameters["mz_tol_ms2_ppm"],
-                                    min_points=self.parameters[
-                                        "centroid_min_points_ms2"
-                                    ],
+                                    min_points=self.parameters["centroid_min_points_ms2"],
                                     algo=centroid_algo,
                                 )
                         if deisotope:
@@ -654,7 +639,7 @@ def export_mgf(
         self.logger.info(f"Skipped {empty_ms2_count} empty MS2 spectra")
     if ms1_fallback_count > 0:
         self.logger.info(f"Skipped MS1 export for {ms1_fallback_count} features without isotope patterns")
-    
+
     # Handle None values in logging
     inty_min_str = f"{inty_min:.3f}" if inty_min != float("-inf") else "None"
     q1_ratio_min_str = f"{q1_ratio_min:.3f}" if q1_ratio_min is not None else "None"
@@ -695,9 +680,7 @@ def export_dda_stats(self, filename="stats.csv"):
     ms2_count = len(self.scans_df.filter(pl.col("ms_level") == 2))
     features_count = len(self.features_df) if self.features_df is not None else 0
     features_with_ms2 = (
-        self.features_df.filter(pl.col("ms2_scans").is_not_null()).height
-        if self.features_df is not None
-        else 0
+        self.features_df.filter(pl.col("ms2_scans").is_not_null()).height if self.features_df is not None else 0
     )
 
     # Initialize a dictionary to hold statistics
@@ -712,9 +695,7 @@ def export_dda_stats(self, filename="stats.csv"):
     if "time_cycle" in self.scans_df.columns:
         ms1_df = self.scans_df.filter(pl.col("ms_level") == 1)
         avg_cycle_time = ms1_df["time_cycle"].mean()
-        stats["Average_cycle_time"] = (
-            avg_cycle_time if avg_cycle_time is not None else ""
-        )
+        stats["Average_cycle_time"] = avg_cycle_time if avg_cycle_time is not None else ""
     else:
         stats["Average_cycle_time"] = 0
 
@@ -851,32 +832,27 @@ def export_xlsx(self, filename="features.xlsx"):
         return
 
     # Validate filename extension
-    if not filename.lower().endswith(('.xlsx', '.xls')):
+    if not filename.lower().endswith((".xlsx", ".xls")):
         raise ValueError("Filename must end with '.xlsx' or '.xls' for Excel export")
-    
+
     filename = os.path.abspath(filename)
-    
+
     # Clone the DataFrame to avoid modifying the original
     clean_df = self.features_df.clone()
-    
+
     # Add a column has_ms2=True if column ms2_scans is not None
     if "ms2_scans" in clean_df.columns:
-        clean_df = clean_df.with_columns(
-            (pl.col("ms2_scans").is_not_null()).alias("has_ms2")
-        )
-    
+        clean_df = clean_df.with_columns((pl.col("ms2_scans").is_not_null()).alias("has_ms2"))
+
     # Filter out columns with List or Object data types that can't be exported to Excel
-    exportable_columns = [
-        col for col in clean_df.columns
-        if clean_df[col].dtype not in (pl.List, pl.Object)
-    ]
-    
+    exportable_columns = [col for col in clean_df.columns if clean_df[col].dtype not in (pl.List, pl.Object)]
+
     clean_df = clean_df.select(exportable_columns)
-    
+
     # Convert to pandas and export to Excel
     pandas_df = clean_df.to_pandas()
     pandas_df.to_excel(filename, index=False)
-    
+
     self.logger.success(f"Features exported to {filename} (Excel format)")
     self.logger.debug(f"Exported {len(clean_df)} features with {len(exportable_columns)} columns")