masster 0.3.10__py3-none-any.whl → 0.3.12__py3-none-any.whl

masster/sample/processing.py

@@ -519,6 +519,10 @@ def find_features(self, **kwargs):
         low-quality peaks), lower values make it more permissive. Typical tuning range: ~3 (relaxed) to >10
         (stringent). Default: 10.0.
 
+    - isotope_filtering_model (str):
+        Isotope filtering model ('metabolites (2% RMS)', 'metabolites (5% RMS)', 'peptides', 'none').
+        Default: 'metabolites (5% RMS)'.
+
     Tuning recommendation: first set ``chrom_fwhm`` to match your LC peak shape, then set ``noise`` to a baseline
     intensity filter for your data, and finally adjust ``chrom_peak_snr`` to reach the desired balance between
     sensitivity and specificity.
@@ -556,24 +560,25 @@ def find_features(self, **kwargs):
                 self.logger.warning(f"Unknown parameter {key} ignored")
 
     # Set global parameters
-    if hasattr(params, 'threads') and params.threads is not None:
+    if hasattr(params, "threads") and params.threads is not None:
         try:
             # Try setting via OpenMP environment variable first (newer approach)
             import os
-            os.environ['OMP_NUM_THREADS'] = str(params.threads)
+
+            os.environ["OMP_NUM_THREADS"] = str(params.threads)
             self.logger.debug(f"Set thread count to {params.threads} via OMP_NUM_THREADS")
         except Exception:
             self.logger.warning(f"Could not set thread count to {params.threads} - using default")
-    
+
     # Set debug mode if enabled
-    if hasattr(params, 'debug') and params.debug:
+    if hasattr(params, "debug") and params.debug:
         self.logger.debug("Debug mode enabled")
-    elif hasattr(params, 'no_progress') and params.no_progress:
+    elif hasattr(params, "no_progress") and params.no_progress:
         self.logger.debug("No progress mode enabled")
-    
+
     self.logger.info("Starting feature detection...")
     self.logger.debug(
-        f"Parameters: chrom_fwhm={params.get('chrom_fwhm')}, noise={params.get('noise')}, tol_ppm={params.get('tol_ppm')}",
+        f"Parameters: chrom_fwhm={params.get('chrom_fwhm')}, noise={params.get('noise')}, tol_ppm={params.get('tol_ppm')}, isotope_filtering_model={params.get('isotope_filtering_model')}",
     )
 
     exp = oms.MSExperiment()
@@ -602,7 +607,8 @@ def find_features(self, **kwargs):
     # Apply MTD parameters
     mtd_par.setValue("mass_error_ppm", float(params.get("tol_ppm")))
     mtd_par.setValue("noise_threshold_int", float(params.get("noise")))
-    mtd_par.setValue("min_trace_length",
+    mtd_par.setValue(
+        "min_trace_length",
         float(params.get("min_trace_length_multiplier")) * float(params.get("chrom_fwhm_min")),
     )
     mtd_par.setValue(
@@ -610,7 +616,7 @@ def find_features(self, **kwargs):
         int(params.get("trace_termination_outliers")),
     )
     mtd_par.setValue("chrom_peak_snr", float(params.get("chrom_peak_snr")))
-    
+
     # Additional MTD parameters
     mtd_par.setValue("min_sample_rate", float(params.get("min_sample_rate")))
     mtd_par.setValue("min_trace_length", float(params.get("min_trace_length")))
@@ -636,10 +642,10 @@ def find_features(self, **kwargs):
         epd_par.setValue("masstrace_snr_filtering", "true")
     if params.get("mz_scoring_13C"):
         epd_par.setValue("mz_scoring_13C", "true")
-    
+
     # Additional EPD parameters
     epd_par.setValue("enabled", "true" if params.get("enabled") else "false")
-    
+
     epd.setParameters(epd_par)
     epd.detectPeaks(mass_traces, mass_traces_deconvol)
 
@@ -675,7 +681,7 @@ def find_features(self, **kwargs):
     ffm_par.setValue("local_mz_range", float(params.get("local_mz_range")))
     ffm_par.setValue("charge_lower_bound", int(params.get("charge_lower_bound")))
     ffm_par.setValue("charge_upper_bound", int(params.get("charge_upper_bound")))
-    
+    ffm_par.setValue("isotope_filtering_model", params.get("isotope_filtering_model"))
 
     ffm.setParameters(ffm_par)
 

masster/sample/sample.py

@@ -62,6 +62,7 @@ from masster.sample.helpers import select_closest_scan
 from masster.sample.helpers import get_dda_stats
 from masster.sample.helpers import get_feature
 from masster.sample.helpers import get_scan
+from masster.sample.helpers import get_eic
 from masster.sample.helpers import set_source
 from masster.sample.load import _load_featureXML
 from masster.sample.load import _load_ms2data
@@ -80,6 +81,8 @@ from masster.sample.plot import plot_feature_stats
 from masster.sample.plot import plot_ms2_cycle
 from masster.sample.plot import plot_ms2_eic
 from masster.sample.plot import plot_ms2_q1
+from masster.sample.plot import plot_bpc
+from masster.sample.plot import plot_tic
 from masster.sample.processing import _clean_features_df
 from masster.sample.processing import _features_deisotope
 from masster.sample.processing import _get_ztscan_stats
@@ -229,6 +232,9 @@ class Sample:
     plot_ms2_cycle = plot_ms2_cycle
     plot_ms2_eic = plot_ms2_eic
     plot_ms2_q1 = plot_ms2_q1
+    plot_bpc = plot_bpc
+    plot_tic = plot_tic
+    get_eic = get_eic
     get_feature = get_feature
     get_scan = get_scan
     get_dda_stats = get_dda_stats
@@ -333,15 +339,15 @@ class Sample:
             if module_name.startswith(study_module_prefix) and module_name != current_module:
                 study_modules.append(module_name)
 
-        ''' # Add parameters submodules
+        """ # Add parameters submodules
         parameters_modules = []
         parameters_module_prefix = f"{base_modname}.parameters."
         for module_name in sys.modules:
             if module_name.startswith(parameters_module_prefix) and module_name != current_module:
                 parameters_modules.append(module_name)
-        '''
-    
-        all_modules_to_reload = core_modules + sample_modules + study_modules #+ parameters_modules
+        """
+
+        all_modules_to_reload = core_modules + sample_modules + study_modules  # + parameters_modules
 
         # Reload all discovered modules
         for full_module_name in all_modules_to_reload:

masster/sample/sample5_schema.json

@@ -7,6 +7,9 @@
       "feature_id": {
         "dtype": "pl.Utf8"
       },
+      "sample_uid": {
+        "dtype": "pl.Int32"
+      },
       "mz": {
         "dtype": "pl.Float64"
       },
@@ -46,18 +49,24 @@
       "iso_of": {
         "dtype": "pl.Int64"
       },
-      "adduct_group": {
-        "dtype": "pl.Int64"
-      },
       "adduct": {
         "dtype": "pl.Utf8"
       },
       "adduct_mass": {
         "dtype": "pl.Float64"
       },
+      "adduct_group": {
+        "dtype": "pl.Int64"
+      },
       "chrom": {
         "dtype": "pl.Object"
       },
+      "filled": {
+        "dtype": "pl.Boolean"
+      },
+      "chrom_area": {
+        "dtype": "pl.Float64"
+      },
       "chrom_coherence": {
         "dtype": "pl.Float64"
       },
@@ -100,64 +109,64 @@
   },
   "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 +178,10 @@
       "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}",
     )