masster 0.3.9__py3-none-any.whl → 0.3.11__py3-none-any.whl

masster/sample/sample5_schema.json

@@ -1,44 +1,41 @@
 {
   "features_df": {
     "columns": {
-      "feature_uid": {
-        "dtype": "pl.Int64"
-      },
-      "feature_id": {
+      "adduct": {
         "dtype": "pl.Utf8"
       },
-      "mz": {
-        "dtype": "pl.Float64"
+      "adduct_group": {
+        "dtype": "pl.Int64"
       },
-      "rt": {
+      "adduct_mass": {
         "dtype": "pl.Float64"
       },
-      "rt_original": {
-        "dtype": "pl.Float64"
+      "charge": {
+        "dtype": "pl.Int32"
       },
-      "rt_start": {
-        "dtype": "pl.Float64"
+      "chrom": {
+        "dtype": "pl.Object"
       },
-      "rt_end": {
+      "chrom_coherence": {
         "dtype": "pl.Float64"
       },
-      "rt_delta": {
+      "chrom_height_scaled": {
         "dtype": "pl.Float64"
       },
-      "mz_start": {
+      "chrom_prominence": {
         "dtype": "pl.Float64"
       },
-      "mz_end": {
+      "chrom_prominence_scaled": {
         "dtype": "pl.Float64"
       },
-      "inty": {
-        "dtype": "pl.Float64"
+      "feature_id": {
+        "dtype": "pl.Utf8"
       },
-      "quality": {
-        "dtype": "pl.Float64"
+      "feature_uid": {
+        "dtype": "pl.Int64"
       },
-      "charge": {
-        "dtype": "pl.Int32"
+      "inty": {
+        "dtype": "pl.Float64"
       },
       "iso": {
         "dtype": "pl.Int64"
@@ -46,35 +43,38 @@
       "iso_of": {
         "dtype": "pl.Int64"
       },
-      "adduct_group": {
-        "dtype": "pl.Int64"
+      "ms2_scans": {
+        "dtype": "pl.Object"
       },
-      "adduct": {
-        "dtype": "pl.Utf8"
+      "ms2_specs": {
+        "dtype": "pl.Object"
       },
-      "adduct_mass": {
+      "mz": {
         "dtype": "pl.Float64"
       },
-      "chrom": {
-        "dtype": "pl.Object"
+      "mz_end": {
+        "dtype": "pl.Float64"
       },
-      "chrom_coherence": {
+      "mz_start": {
         "dtype": "pl.Float64"
       },
-      "chrom_prominence": {
+      "quality": {
         "dtype": "pl.Float64"
       },
-      "chrom_prominence_scaled": {
+      "rt": {
         "dtype": "pl.Float64"
       },
-      "chrom_height_scaled": {
+      "rt_delta": {
         "dtype": "pl.Float64"
       },
-      "ms2_scans": {
-        "dtype": "pl.Object"
+      "rt_end": {
+        "dtype": "pl.Float64"
       },
-      "ms2_specs": {
-        "dtype": "pl.Object"
+      "rt_original": {
+        "dtype": "pl.Float64"
+      },
+      "rt_start": {
+        "dtype": "pl.Float64"
       }
     }
   },
@@ -100,64 +100,64 @@
   },
   "scans_df": {
     "columns": {
-      "scan_uid": {
-        "dtype": "pl.Int64"
+      "bl": {
+        "dtype": "pl.Float64"
+      },
+      "comment": {
+        "dtype": "pl.Utf8"
       },
       "cycle": {
         "dtype": "pl.Int64"
       },
-      "ms_level": {
+      "energy": {
+        "dtype": "pl.Float64"
+      },
+      "feature_uid": {
         "dtype": "pl.Int64"
       },
-      "rt": {
-        "dtype": "pl.Float64"
+      "id": {
+        "dtype": "pl.Utf8"
       },
-      "inty_tot": {
+      "inty_max": {
         "dtype": "pl.Float64"
       },
       "inty_min": {
         "dtype": "pl.Float64"
       },
-      "inty_max": {
+      "inty_tot": {
         "dtype": "pl.Float64"
       },
-      "bl": {
-        "dtype": "pl.Float64"
+      "ms2_n": {
+        "dtype": "pl.Int64"
       },
-      "mz_min": {
-        "dtype": "pl.Float64"
+      "ms_level": {
+        "dtype": "pl.Int64"
       },
       "mz_max": {
         "dtype": "pl.Float64"
       },
-      "comment": {
-        "dtype": "pl.Utf8"
+      "mz_min": {
+        "dtype": "pl.Float64"
       },
       "name": {
         "dtype": "pl.Utf8"
       },
-      "id": {
-        "dtype": "pl.Utf8"
-      },
-      "prec_mz": {
+      "prec_inty": {
         "dtype": "pl.Float64"
       },
-      "prec_mz_min": {
+      "prec_mz": {
         "dtype": "pl.Float64"
       },
       "prec_mz_max": {
         "dtype": "pl.Float64"
       },
-      "prec_inty": {
+      "prec_mz_min": {
         "dtype": "pl.Float64"
       },
-      "energy": {
+      "rt": {
         "dtype": "pl.Float64"
       },
-      "feature_uid": {
-        "dtype": "pl.Int64"
-      },
-      "ms2_n": {
+      "scan_uid": {
         "dtype": "pl.Int64"
       },
       "time_cycle": {
@@ -169,10 +169,10 @@
       "time_ms1_to_ms2": {
         "dtype": "pl.Float64"
       },
-      "time_ms2_to_ms2": {
+      "time_ms2_to_ms1": {
         "dtype": "pl.Float64"
       },
-      "time_ms2_to_ms1": {
+      "time_ms2_to_ms2": {
         "dtype": "pl.Float64"
       }
     }

masster/sample/save.py

@@ -134,10 +134,10 @@ def export_features(self, filename="features.csv"):
     # clone df
     clean_df = self.features_df.clone()
     filename = os.path.abspath(filename)
-    # add a column has_ms2=True if colum ms2_scans is not None
+    # 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")
+            (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)
@@ -215,7 +215,7 @@ def export_mgf(
             return
         else:
             self.features_df = self.features.get_df()
-    
+
     # Apply filtering at DataFrame level for better performance
     features = self.features_df
     if mz_start is not None:
@@ -228,7 +228,7 @@ def export_mgf(
         features = features.filter(pl.col("rt") <= rt_end)
     if not include_all_ms1:
         features = features.filter(pl.col("ms2_scans").is_not_null())
-    
+
     # Convert to list of dictionaries for faster iteration
     features_list = features.to_dicts()
 
@@ -286,7 +286,10 @@ def export_mgf(
             centroid_algo = "cr"
 
     # 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] > 0:
+    if (
+        self.features_df.filter(pl.col("charge") < 0).shape[0] - self.features_df.filter(pl.col("charge") > 0).shape[0]
+        > 0
+    ):
         preferred_charge = -1
     else:
         preferred_charge = 1
@@ -312,7 +315,7 @@ def export_mgf(
             rt = row["rt"]
             rt_str = f"{rt:.2f}"
             mz_str = f"{mz:.4f}"
-            
+
             # Filtering is now done at DataFrame level, so we can skip these checks
             if row["ms2_scans"] is None and not include_all_ms1:
                 skip = skip + 1
@@ -338,7 +341,7 @@ def export_mgf(
 
             charge = preferred_charge
             if row["charge"] is not None and row["charge"] != 0:
-                    charge = row["charge"]
+                charge = row["charge"]
 
             write_ion(
                 f,
@@ -397,7 +400,7 @@ def export_mgf(
                                 )
                                 c += 1
                         continue  # Skip the rest of the processing for this feature
-            
+
             # If we reach here, either use_cache=False or no cached spectra were available
             if split_energy:
                 # get energy of all scans with scan_uid in ms2_scans by fetching them
@@ -408,20 +411,20 @@ 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]] = {}
                     for scan_uid, energy in spectra_with_energy:
                         if energy not in energy_groups:
                             energy_groups[energy] = []
                         energy_groups[energy].append(scan_uid)
-                    
+
                     for energy, scan_uids_for_energy in energy_groups.items():
                         if selection == "best":
                             # Keep only the first scan for this energy
                             scan_uids_for_energy = [scan_uids_for_energy[0]]
-                        
+
                         for scan_uid in scan_uids_for_energy:
                             spect = self.get_spectrum(
                                 scan_uid,
@@ -556,7 +559,7 @@ def export_mgf(
     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"
     eic_corr_min_str = f"{eic_corr_min:.3f}" if eic_corr_min is not None else "None"
-    
+
     self.logger.debug(
         f"MGF created with int>{inty_min_str}, q1_ratio>{q1_ratio_min_str}, eic_corr>{eic_corr_min_str}",
     )