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

masster/study/defaults/identify_def.py

@@ -158,9 +158,7 @@ class identify_defaults:
             if not isinstance(value, list):
                 return False
             # For heteroatoms, ensure all elements are strings
-            if param_name == "heteroatoms" and not all(
-                isinstance(item, str) for item in value
-            ):
+            if param_name == "heteroatoms" and not all(isinstance(item, str) for item in value):
                 return False
 
         # Range validation for numeric types

masster/study/defaults/merge_def.py

@@ -36,10 +36,10 @@ class merge_defaults:
     max_nr_conflicts: int = 0
     link_ms2: bool = True
     extract_ms1: bool = True
-    
+
     # Cross-chunk merging parameters
     dechunking: str = "hierarchical"
-    
+
     # Parallel processing parameters
     threads: Optional[int] = None
 
@@ -49,8 +49,7 @@ class merge_defaults:
                 "dtype": str,
                 "description": "Merge method (algorithm) to use",
                 "default": "kd",
-                "allowed_values": ["kd", "qt", 
-                                 "kd_chunked", "kd-chunked", "qt_chunked", "qt-chunked"],
+                "allowed_values": ["kd", "qt", "kd_chunked", "kd-chunked", "qt_chunked", "qt-chunked"],
             },
             "min_samples": {
                 "dtype": int,
@@ -198,14 +197,14 @@ class merge_defaults:
                 elif dtype is str and isinstance(value, str):
                     valid_type = True
                     break
-            
+
             if not valid_type:
                 return False
-            
+
             # For None values, skip further validation
             if value is None:
                 return True
-            
+
             # Use the first non-None type for range validation
             expected_dtype = next((dt for dt in expected_dtype if dt is not type(None)), expected_dtype[0])
 

masster/study/defaults/study_def.py

@@ -345,11 +345,7 @@ class study_defaults:
             expected_dtype = self._param_metadata[param_name]["dtype"]
 
             # Handle optional types
-            if (
-                isinstance(expected_dtype, str)
-                and expected_dtype.startswith("Optional")
-                and value is not None
-            ):
+            if isinstance(expected_dtype, str) and expected_dtype.startswith("Optional") and value is not None:
                 if "int" in expected_dtype and not isinstance(value, int):
                     try:
                         value = int(value)

masster/study/export.py

@@ -78,7 +78,7 @@ def _get_mgf_df(self, **kwargs):
     if self.consensus_df is None:
         self.logger.error("No consensus map found. Please run merge() first.")
         return None
-    
+
     # MS2 data is optional - we can generate MS1 data without it
     ms2_available = self.consensus_ms2 is not None and not self.consensus_ms2.is_empty()
     if not ms2_available:
@@ -112,11 +112,7 @@ def _get_mgf_df(self, **kwargs):
             mask = mask & (spec.inty >= inty_min)
         for attr in spec.__dict__:
             arr = getattr(spec, attr)
-            if (
-                isinstance(arr, list | np.ndarray)
-                and hasattr(arr, "__len__")
-                and len(arr) == length
-            ):
+            if isinstance(arr, list | np.ndarray) and hasattr(arr, "__len__") and len(arr) == length:
                 setattr(spec, attr, np.array(arr)[mask])
         return spec
 
@@ -132,12 +128,8 @@ def _get_mgf_df(self, **kwargs):
             return None
 
         # Prepare spectrum data
-        spectrum_mz = (
-            spect.mz.tolist() if hasattr(spect.mz, "tolist") else list(spect.mz)
-        )
-        spectrum_inty = (
-            spect.inty.tolist() if hasattr(spect.inty, "tolist") else list(spect.inty)
-        )
+        spectrum_mz = spect.mz.tolist() if hasattr(spect.mz, "tolist") else list(spect.mz)
+        spectrum_inty = spect.inty.tolist() if hasattr(spect.inty, "tolist") else list(spect.inty)
 
         # Determine MS level
         ms_level = spect.ms_level if spect.ms_level is not None else 1
@@ -181,7 +173,7 @@ def _get_mgf_df(self, **kwargs):
         consensus_mz = row["mz"]
         consensus_rt = row["rt"]
         consensus_inty_mean = row.get("inty_mean", 0)
-        
+
         if mz_start is not None and consensus_mz < mz_start:
             continue
         if mz_end is not None and consensus_mz > mz_end:
@@ -190,10 +182,10 @@ def _get_mgf_df(self, **kwargs):
             continue
         if rt_end is not None and consensus_rt > rt_end:
             continue
-        
+
         # Create MS1 spectrum using isotope data
         iso_data = row.get("iso", None)
-        
+
         if iso_data is not None and len(iso_data) > 0:
             # Use isotope data for spectrum
             spectrum_mz = [float(peak[0]) for peak in iso_data]
@@ -202,10 +194,12 @@ def _get_mgf_df(self, **kwargs):
             # Use consensus mz and inty_mean as single peak
             spectrum_mz = [float(consensus_mz)]
             spectrum_inty = [float(consensus_inty_mean)]
-        
+
         # Apply intensity minimum filter if specified
         if inty_min is not None and inty_min > 0:
-            filtered_pairs = [(mz, inty) for mz, inty in zip(spectrum_mz, spectrum_inty, strict=False) if inty >= inty_min]
+            filtered_pairs = [
+                (mz, inty) for mz, inty in zip(spectrum_mz, spectrum_inty, strict=False) if inty >= inty_min
+            ]
             if filtered_pairs:
                 spectrum_mz, spectrum_inty = zip(*filtered_pairs, strict=False)
                 spectrum_mz = list(spectrum_mz)
@@ -213,9 +207,9 @@ def _get_mgf_df(self, **kwargs):
             else:
                 # If all peaks are below threshold, skip this feature
                 continue
-        
+
         mgf_counter += 1
-        
+
         # Create MS1 spectrum object to use with create_ion_dict
         class SimpleSpectrum:
             def __init__(self, mz_list, inty_list):
@@ -223,9 +217,9 @@ def _get_mgf_df(self, **kwargs):
                 self.inty = np.array(inty_list)
                 self.ms_level = 1
                 self.energy = None
-        
+
         ms1_spectrum = SimpleSpectrum(spectrum_mz, spectrum_inty)
-        
+
         # Use create_ion_dict to ensure consistent schema
         ion_dict = create_ion_dict(
             f"uid:{consensus_uid}, rt:{consensus_rt:.2f}, mz:{consensus_mz:.4f}, MS1",
@@ -237,7 +231,7 @@ def _get_mgf_df(self, **kwargs):
             ms1_spectrum,
             mgf_counter,
         )
-        
+
         if ion_dict is not None:
             ion_data.append(ion_dict)
 
@@ -350,11 +344,7 @@ def _get_mgf_df(self, **kwargs):
 
                 elif selection == "all":
                     if merge:
-                        specs = [
-                            row_e["spec"]
-                            for row_e in cons_ms2.iter_rows(named=True)
-                            if row_e["spec"] is not None
-                        ]
+                        specs = [row_e["spec"] for row_e in cons_ms2.iter_rows(named=True) if row_e["spec"] is not None]
                         if not specs:
                             continue
                         spect = combine_peaks(specs)
@@ -443,6 +433,7 @@ def export_mgf(self, **kwargs):
     """
     # Get mgf data as DataFrame
     from masster.study.export import _get_mgf_df
+
     mgf_data = _get_mgf_df(self, **kwargs)
 
     if mgf_data is None or len(mgf_data) == 0:
@@ -543,11 +534,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
                 .sort("consensus_uid")
             )
             # Keep raw id_data for backward compatibility (if needed elsewhere)
-            id_data = (
-                self.id_df
-                if hasattr(self, "id_df") and self.id_df is not None
-                else None
-            )
+            id_data = self.id_df if hasattr(self, "id_df") and self.id_df is not None else None
         else:
             self.logger.info("No identification data available for mzTab export")
     except Exception as e:
@@ -561,6 +548,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
     mgf_mapping: dict[str, list[int]] = {}
     if include_mgf:
         from masster.study.export import _get_mgf_df
+
         mgf_data = _get_mgf_df(self, **kwargs)
         # Create mapping from feature_uid to MGF indexes
         if mgf_data is not None and len(mgf_data) > 0:
@@ -616,12 +604,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
     mtd_lines.append("")
 
     # Database information - updated based on identification data
-    if (
-        full_id_data is not None
-        and hasattr(self, "lib_df")
-        and self.lib_df is not None
-        and not self.lib_df.is_empty()
-    ):
+    if full_id_data is not None and hasattr(self, "lib_df") and self.lib_df is not None and not self.lib_df.is_empty():
         mtd_lines.append('MTD\tdatabase[1]\t[, , "compound library", ]')
         mtd_lines.append("MTD\tdatabase[1]-prefix\tcmpd")
         mtd_lines.append("MTD\tdatabase[1]-version\tUnknown")
@@ -688,11 +671,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
     # round to int - handle both Polars and Pandas DataFrames
     if hasattr(abundance_matrix, "with_columns"):
         # Polars DataFrame
-        numeric_cols = [
-            col
-            for col in abundance_matrix.columns
-            if abundance_matrix[col].dtype.is_numeric()
-        ]
+        numeric_cols = [col for col in abundance_matrix.columns if abundance_matrix[col].dtype.is_numeric()]
         abundance_matrix = abundance_matrix.with_columns(
             [abundance_matrix[col].round(0) for col in numeric_cols],
         )
@@ -738,9 +717,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
         best_id_confidence_measure = "null"
         best_id_confidence_value = "null"
         reliability = "4"  # Default: unknown compound
-        theoretical_neutral_mass = (
-            "null"  # Only set when we have database identification
-        )
+        theoretical_neutral_mass = "null"  # Only set when we have database identification
 
         if id_info:
             # Use cmpd_uid as database identifier with prefix
@@ -817,27 +794,15 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
             # Get the first (and should be only) matching row
             abundance_row = filtered_matrix.row(0, named=True)
             # Extract values excluding the consensus_uid column
-            abundance_values = [
-                abundance_row[col]
-                for col in abundance_matrix.columns
-                if col != "consensus_uid"
-            ]
-            sml_row += [
-                safe_str(val) if val is not None else "null" for val in abundance_values
-            ]
+            abundance_values = [abundance_row[col] for col in abundance_matrix.columns if col != "consensus_uid"]
+            sml_row += [safe_str(val) if val is not None else "null" for val in abundance_values]
 
             # Calculate study variable statistics
             non_null_values = [val for val in abundance_values if val is not None]
             if non_null_values:
                 abundance_study_variable = sum(non_null_values) / len(non_null_values)
                 abundance_variation_study_variable = (
-                    (
-                        sum(
-                            (x - abundance_study_variable) ** 2 for x in non_null_values
-                        )
-                        / len(non_null_values)
-                    )
-                    ** 0.5
+                    (sum((x - abundance_study_variable) ** 2 for x in non_null_values) / len(non_null_values)) ** 0.5
                     if len(non_null_values) > 1
                     else 0
                 )
@@ -896,9 +861,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
                 some_ids = []
                 for i, some_row in enumerate(some_matches.iter_rows(named=True)):
                     # Create a unique SOME ID based on consensus_uid and position
-                    some_id_base = (
-                        consensus_uid * 1000
-                    )  # Ensure uniqueness across consensus features
+                    some_id_base = consensus_uid * 1000  # Ensure uniqueness across consensus features
                     some_id = some_id_base + i + 1
                     some_ids.append(str(some_id))
 
@@ -950,14 +913,8 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
             # Get the first (and should be only) matching row
             abundance_row = filtered_matrix.row(0, named=True)
             # Extract values excluding the consensus_uid column
-            abundance_values = [
-                abundance_row[col]
-                for col in abundance_matrix.columns
-                if col != "consensus_uid"
-            ]
-            abundance_strings = [
-                safe_str(val) if val is not None else "null" for val in abundance_values
-            ]
+            abundance_values = [abundance_row[col] for col in abundance_matrix.columns if col != "consensus_uid"]
+            abundance_strings = [safe_str(val) if val is not None else "null" for val in abundance_values]
             smf_row += abundance_strings
 
             # Calculate study variable statistics (same as in SML section)
@@ -965,13 +922,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
             if non_null_values:
                 abundance_study_variable = sum(non_null_values) / len(non_null_values)
                 abundance_variation_study_variable = (
-                    (
-                        sum(
-                            (x - abundance_study_variable) ** 2 for x in non_null_values
-                        )
-                        / len(non_null_values)
-                    )
-                    ** 0.5
+                    (sum((x - abundance_study_variable) ** 2 for x in non_null_values) / len(non_null_values)) ** 0.5
                     if len(non_null_values) > 1
                     else 0
                 )
@@ -1023,9 +974,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
         some_lines.append("\t".join(some_header))
 
         # Create SOME entries for all identification results using enriched data
-        for consensus_uid in (
-            self.consensus_df.select("consensus_uid").to_series().unique()
-        ):
+        for consensus_uid in self.consensus_df.select("consensus_uid").to_series().unique():
             # Get consensus feature data for this consensus_uid
             consensus_feature_data = self.consensus_df.filter(
                 pl.col("consensus_uid") == consensus_uid,
@@ -1081,9 +1030,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
 
                     # Theoretical mass-to-charge from lib_df
                     theoretical_mz = "null"
-                    if (
-                        some_row.get("mz") is not None
-                    ):  # This comes from lib_df via get_id() join
+                    if some_row.get("mz") is not None:  # This comes from lib_df via get_id() join
                         theoretical_mz = safe_str(some_row["mz"])
 
                     some_line = [
@@ -1148,23 +1095,15 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
             spec_len = row["spec_len"] if row["spec_len"] is not None else 0
 
             # Format spectrum data as pipe-separated strings
-            spec_mz_str = (
-                "|".join([f"{mz:.4f}" for mz in spectrum_mz]) if spectrum_mz else ""
-            )
-            spec_int_str = (
-                "|".join([f"{int(inty)}" for inty in spectrum_inty])
-                if spectrum_inty
-                else ""
-            )
+            spec_mz_str = "|".join([f"{mz:.4f}" for mz in spectrum_mz]) if spectrum_mz else ""
+            spec_int_str = "|".join([f"{int(inty)}" for inty in spectrum_inty]) if spectrum_inty else ""
 
             mgf_row = [
                 "COM",
                 "MGF",
                 str(row["mgf_index"]) if row["mgf_index"] is not None else "null",
                 str(row["feature_id"]) if row["feature_id"] is not None else "null",
-                f"{row['rtinseconds']:.2f}"
-                if row["rtinseconds"] is not None
-                else "null",
+                f"{row['rtinseconds']:.2f}" if row["rtinseconds"] is not None else "null",
                 f"{row['pepmass']:.4f}" if row["pepmass"] is not None else "null",
                 "null",  # prec_int - not available in current data
                 str(row["energy"]) if row["energy"] is not None else "null",