masster 0.4.4__py3-none-any.whl → 0.4.6__py3-none-any.whl

masster/sample/save.py

@@ -139,9 +139,13 @@ def export_features(self, filename="features.csv"):
         clean_df = clean_df.with_columns(
             (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)
-    ])
+    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)
+        ],
+    )
     if filename.lower().endswith((".xls", ".xlsx")):
         clean_df.to_pandas().to_excel(filename, index=False)
         self.logger.info(f"Features exported to {filename} (Excel format)")
@@ -275,7 +279,10 @@ def export_mgf(
             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")
 
@@ -287,7 +294,8 @@ 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
@@ -388,7 +396,9 @@ 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"
+                                )
                                 write_ion(
                                     f,
                                     f"fid:{feature_uid}, rt:{rt_str}, mz:{mz_str}, scan_uid:{current_scan_uid}",
@@ -411,7 +421,12 @@ def export_mgf(
                     for scan_uid in ms2_scan_uids:
                         spec = self.get_spectrum(scan_uid)
                         if spec is not None:
-                            spectra_with_energy.append((scan_uid, spec.energy if hasattr(spec, "energy") else 0))
+                            spectra_with_energy.append(
+                                (
+                                    scan_uid,
+                                    spec.energy if hasattr(spec, "energy") else 0,
+                                ),
+                            )
 
                     # Group by energy
                     energy_groups: dict[float, list[int]] = {}
@@ -496,14 +511,18 @@ 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:
@@ -595,7 +614,9 @@ 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
@@ -610,7 +631,9 @@ 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
 

masster/spectrum.py

@@ -138,10 +138,10 @@ class Spectrum:
 
     Example Usage:
         >>> import numpy as np
-        >>> from masster import spec
+        >>> from masster import Spectrum
         >>> mz = np.array([100.0, 150.0, 200.0, 250.0])
         >>> intensity = np.array([1000, 5000, 3000, 800])
-        >>> spectrum = spec(mz=mz, inty=intensity, ms_level=1)
+        >>> spectrum = Spectrum(mz=mz, inty=intensity, ms_level=1)
         >>> spectrum.find_peaks()
         >>> spectrum.plot()
 

masster/study/defaults/align_def.py

@@ -298,7 +298,11 @@ class align_defaults:
                 "dtype": str,
                 "description": "Method to use for extrapolation outside the data range in LOWESS",
                 "default": "four-point-linear",
-                "allowed_values": ["two-point-linear", "four-point-linear", "global-linear"],
+                "allowed_values": [
+                    "two-point-linear",
+                    "four-point-linear",
+                    "global-linear",
+                ],
             },
         },
         repr=False,

masster/study/defaults/identify_def.py

@@ -158,7 +158,9 @@ 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/study_def.py

@@ -33,7 +33,7 @@ class study_defaults:
 
     eic_mz_tol: float = 0.01
     eic_rt_tol: float = 10.0
-    
+
     polarity: str = "positive"
     adducts: list[str] | None = None
     adduct_min_probability: float = 0.04
@@ -54,7 +54,14 @@ class study_defaults:
                 "dtype": str,
                 "description": "Logging level to be set for the logger",
                 "default": "INFO",
-                "allowed_values": ["TRACE", "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
+                "allowed_values": [
+                    "TRACE",
+                    "DEBUG",
+                    "INFO",
+                    "WARNING",
+                    "ERROR",
+                    "CRITICAL",
+                ],
             },
             "log_label": {
                 "dtype": "Optional[str]",
@@ -92,14 +99,19 @@ class study_defaults:
                 "default": ["H:+:0.8", "Na:+:0.1", "NH4:+:0.1"],
                 "examples": {
                     "positive": ["H:+:0.8", "Na:+:0.1", "NH4:+:0.1"],
-                    "negative": ["H-1:-:0.95", "Cl:-:0.05", "CH2O2:0:0.2", "H-2-O:0:0.2"]
+                    "negative": [
+                        "H-1:-:0.95",
+                        "Cl:-:0.05",
+                        "CH2O2:0:0.2",
+                        "H-2-O:0:0.2",
+                    ],
                 },
                 "validation_rules": [
                     "Format: element:charge:probability",
                     "Charge must be +, -, or 0 (neutral)",
                     "Probability must be between 0.0 and 1.0",
-                    "Sum of all charged adduct probabilities must equal 1.0"
-                ]
+                    "Sum of all charged adduct probabilities must equal 1.0",
+                ],
             },
             "adduct_min_probability": {
                 "dtype": float,
@@ -116,54 +128,71 @@ class study_defaults:
         """Set polarity-specific defaults for adducts if not explicitly provided."""
         # If adducts is None, set based on polarity
         if self.adducts is None:
-            if self.polarity.lower() in ['positive', 'pos']:
-                self.adducts = ["+H:1:0.65", "+Na:1:0.15", "+NH4:1:0.15", "+K:1:0.05", "-H2O:0:0.15"]
-            elif self.polarity.lower() in ['negative', 'neg']:
-                self.adducts = ["-H:-1:0.9", "+Cl:-1:0.1", "+CH2O2:0:0.15", "-H2O:0:0.15"]
+            if self.polarity.lower() in ["positive", "pos"]:
+                self.adducts = [
+                    "+H:1:0.65",
+                    "+Na:1:0.15",
+                    "+NH4:1:0.15",
+                    "+K:1:0.05",
+                    "-H2O:0:0.15",
+                ]
+            elif self.polarity.lower() in ["negative", "neg"]:
+                self.adducts = [
+                    "-H:-1:0.9",
+                    "+Cl:-1:0.1",
+                    "+CH2O2:0:0.15",
+                    "-H2O:0:0.15",
+                ]
             else:
                 # Default to positive if polarity is not recognized
-                self.adducts = ["+H:1:0.65", "+Na:1:0.15", "+NH4:1:0.15", "+K:1:0.05", "-H2O:0:0.15"]
+                self.adducts = [
+                    "+H:1:0.65",
+                    "+Na:1:0.15",
+                    "+NH4:1:0.15",
+                    "+K:1:0.05",
+                    "-H2O:0:0.15",
+                ]
 
     def _validate_adducts(self, adduct_list: list[str]) -> bool:
         """
         Validate adducts according to OpenMS convention.
-        
+
         Format: element:charge:probability
         - Elements can be molecular formulas (e.g., H, Na, NH4, H-1, CH2O2)
         - Charge must be +, -, or 0 (for neutral)
         - Probability must be a float between 0 and 1
         - Total probability of all charged adducts should sum to 1.0
-        
+
         Args:
             adduct_list: List of adduct strings in OpenMS format
-            
+
         Returns:
             True if all adducts are valid, False otherwise
         """
         if not adduct_list:  # Empty list is valid
             return True
-            
+
         charged_total_prob = 0.0
         neutral_total_prob = 0.0
-        
+
         for adduct in adduct_list:
             if not isinstance(adduct, str):
                 return False
-                
+
             parts = adduct.split(":")
             if len(parts) != 3:
                 return False
-                
+
             element, charge, prob_str = parts
-            
+
             # Validate element (non-empty string)
             if not element:
                 return False
-                
+
             # Validate charge
             if charge not in ["+", "-", "0"]:
                 return False
-                
+
             # Validate probability
             try:
                 probability = float(prob_str)
@@ -171,20 +200,20 @@ class study_defaults:
                     return False
             except (ValueError, TypeError):
                 return False
-                
+
             # Sum probabilities by charge type
             if charge in ["+", "-"]:
                 charged_total_prob += probability
             else:  # charge == "0" (neutral)
                 neutral_total_prob += probability
-        
+
         # Validate probability constraints
         # Charged adducts should sum to 1.0 (within tolerance)
         if charged_total_prob > 0 and abs(charged_total_prob - 1.0) > 1e-6:
             return False
-            
+
         # Neutral adducts can have any total probability (they're optional)
-        
+
         return True
 
     def get_info(self, param_name: str) -> dict[str, Any]:
@@ -316,7 +345,11 @@ 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)