masster 0.4.22__py3-none-any.whl → 0.5.1__py3-none-any.whl

masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.4.22"
+__version__ = "0.5.1"
 
 
 def get_version():

masster/data/libs/aa.csv

@@ -0,0 +1,22 @@
+name,smiles,inchikey,formula,db_id,db
+L-Glutamic acid,N[C@@H](CCC(O)=O)C(O)=O,WHUUTDBJXJRKMK-VKHMYHEASA-N,C5H9NO4,CID:33032,pubchem
+L-Tyrosine,N[C@@H](CC1=CC=C(O)C=C1)C(O)=O,OUYCCCASQSFEME-QMMMGPOBSA-N,C9H11NO3,CID:6057,pubchem
+L-Phenylalanine,N[C@@H](CC1=CC=CC=C1)C(O)=O,COLNVLDHVKWLRT-QMMMGPOBSA-N,C9H11NO2,CID:6140,pubchem
+L-Alanine,C[C@H](N)C(O)=O,QNAYBMKLOCPYGJ-REOHCLBHSA-N,C3H7NO2,CID:5950,pubchem
+L-Proline,OC(=O)[C@@H]1CCCN1,ONIBWKKTOPOVIA-BYPYZUCNSA-N,C5H9NO2,CID:145742,pubchem
+L-Threonine,C[C@@H](O)[C@H](N)C(O)=O,AYFVYJQAPQTCCC-GBXIJSLDSA-N,C4H9NO3,CID:6288,pubchem
+L-Asparagine,N[C@@H](CC(N)=O)C(O)=O,DCXYFEDJOCDNAF-REOHCLBHSA-N,C4H8N2O3,CID:6267,pubchem
+L-Isoleucine,CC[C@H](C)[C@H](N)C(O)=O,AGPKZVBTJJNPAG-WHFBIAKZSA-N,C6H13NO2,CID:6306,pubchem
+L-Histidine,N[C@@H](CC1=CN=CN1)C(O)=O,HNDVDQJCIGZPNO-YFKPBYRVSA-N,C6H9N3O2,CID:6274,pubchem
+L-Lysine,NCCCC[C@H](N)C(O)=O,KDXKERNSBIXSRK-YFKPBYRVSA-N,C6H14N2O2,CID:5962,pubchem
+L-Serine,N[C@@H](CO)C(O)=O,MTCFGRXMJLQNBG-REOHCLBHSA-N,C3H7NO3,CID:5951,pubchem
+L-Aspartic acid,N[C@@H](CC(O)=O)C(O)=O,CKLJMWTZIZZHCS-REOHCLBHSA-N,C4H7NO4,CID:5960,pubchem
+L-Cystine,N[C@@H](CSSC[C@H](N)C(O)=O)C(O)=O,LEVWYRKDKASIDU-IMJSIDKUSA-N,C6H12N2O4S2,CID:67678,pubchem
+L-Arginine,N[C@@H](CCCNC(N)=N)C(O)=O,ODKSFYDXXFIFQN-BYPYZUCNSA-N,C6H14N4O2,CID:6322,pubchem
+L-Cysteine,N[C@@H](CS)C(O)=O,XUJNEKJLAYXESH-REOHCLBHSA-N,C3H7NO2S,CID:5862,pubchem
+L-Glutamine,N[C@@H](CCC(N)=O)C(O)=O,ZDXPYRJPNDTMRX-VKHMYHEASA-N,C5H10N2O3,CID:5961,pubchem
+L-Leucine,CC(C)C[C@H](N)C(O)=O,ROHFNLRQFUQHCH-YFKPBYRVSA-N,C6H13NO2,CID:6106,pubchem
+L-Methionine,CSCC[C@H](N)C(O)=O,FFEARJCKVFRZRR-BYPYZUCNSA-N,C5H11NO2S,CID:6137,pubchem
+L-Valine,CC(C)[C@H](N)C(O)=O,KZSNJWFQEVHDMF-BYPYZUCNSA-N,C5H11NO2,CID:6287,pubchem
+L-Tryptophan,N[C@@H](CC1=CNC2=C1C=CC=C2)C(O)=O,QIVBCDIJIAJPQS-VIFPVBQESA-N,C11H12N2O2,CID:6305,pubchem
+Glycine,NCC(O)=O,QNAYBMKLOCPYGJ-UHFFFAOYSA-N,C2H5NO2,CID:750,Glycine

masster/lib/lib.py

@@ -123,11 +123,13 @@ class Lib:
             "inchi": pl.Series([], dtype=pl.Utf8),
             "inchikey": pl.Series([], dtype=pl.Utf8),
             "formula": pl.Series([], dtype=pl.Utf8),
+            "iso": pl.Series([], dtype=pl.Int64),
             "adduct": pl.Series([], dtype=pl.Utf8),
             "m": pl.Series([], dtype=pl.Float64),
             "z": pl.Series([], dtype=pl.Int8),
             "mz": pl.Series([], dtype=pl.Float64),
             "rt": pl.Series([], dtype=pl.Float64),
+            "quant_group": pl.Series([], dtype=pl.Int64),
             "db_id": pl.Series([], dtype=pl.Utf8),
             "db": pl.Series([], dtype=pl.Utf8),
         })
@@ -245,11 +247,13 @@ class Lib:
                 "inchi": compound_data.get("inchi", ""),
                 "inchikey": compound_data.get("inchikey", ""),
                 "formula": compound_data["formula"],
+                "iso": 0,  # Default to zero
                 "adduct": adduct,
                 "m": adducted_mass,
                 "z": charge,
                 "mz": mz,
                 "rt": compound_data.get("rt", None),
+                "quant_group": counter,  # Use same as lib_uid for default
                 "db_id": compound_data.get("db_id", None),
                 "db": compound_data.get("db", None),
             }
@@ -526,12 +530,14 @@ class Lib:
                     "source_id": match_row.get("source_id"),
                     "name": match_row["name"],
                     "formula": match_row["formula"],
+                    "iso": match_row.get("iso", 0),
                     "adduct": match_row["adduct"],
                     "smiles": match_row["smiles"],
                     "inchi": match_row["inchi"],
                     "inchikey": match_row["inchikey"],
                     "lib_mz": match_row["mz"],
                     "lib_rt": match_row["rt"],
+                    "quant_group": match_row.get("quant_group"),
                     "delta_mz": abs(feature_mz - match_row["mz"]),
                     "delta_rt": abs(feature_rt - match_row["rt"]) if feature_rt is not None and match_row["rt"] is not None else None,
                 }

masster/sample/adducts.py

@@ -809,5 +809,5 @@ def find_adducts(self, **kwargs):
         ["name", "charge", "mass_shift", "probability"],
     ).to_dicts()
 
-    self.store_history(["find_adducts"], history_params)
+    self.update_history(["find_adducts"], history_params)
     self.logger.debug("Parameters stored successfully")

masster/sample/load.py

@@ -173,8 +173,8 @@ def load_noms1(
         self.label = label
 
 
-# Backward compatibility alias
-def load_study(
+# Renamed for clarity and internal use
+def _load_ms1(
     self,
     filename=None,
     ondisk=False,
@@ -182,7 +182,8 @@ def load_study(
     label=None,
 ):
     """
-    Backward compatibility alias for load_noms1().
+    Load MS1-only data (renamed from load_study for clarity).
+    Optimized version for study loading that excludes MS2 data.
 
     This method is deprecated. Use load_noms1() instead.
     """
@@ -828,11 +829,11 @@ def _load_mzpkl(
             continue
         if k == "spectra_df":
             k = "scans_df"
-        setattr(self, k, v)
+    setattr(self, k, v)
 
-    self.sanitize()
-
-    if self.ondisk:
+# Import and call internal sanitize function
+from masster.study.load import _sanitize
+_sanitize(self)    if self.ondisk:
         self.file_obj = oms.OnDiscMSExperiment()
     else:
         self.file_obj = oms.MSExperiment()
@@ -955,7 +956,7 @@ def sanitize(self):
                         self.features_df.at[_i, "ms2_specs"][_j] = new_ms2_specs
 
 
-def index_file(self):
+def _index_file(self):
     """
     Reload raw data from a file based on its extension.
 
@@ -1022,7 +1023,7 @@ def index_file(self):
             raise FileNotFoundError(
                 f"File {self.file_source} not found. Did the path change? Consider running source().",
             )
-        self.index_file()
+        self._index_file()
     else:
         raise FileNotFoundError(
             f"File {self.file_source} not found. Did the path change? Consider running source().",

masster/sample/plot.py

@@ -1955,7 +1955,7 @@ def plot_dda_stats(
         return _display_plot(layout, layout_obj)
 
 
-def plot_feature_stats(
+def plot_features_stats(
     self,
     filename=None,
 ):

masster/sample/processing.py

@@ -799,7 +799,7 @@ def find_features(self, **kwargs):
     self.logger.info(f"Feature detection completed. Total features: {len(df)}")
 
     # store params
-    self.store_history(["find_features"], params.to_dict())
+    self.update_history(["find_features"], params.to_dict())
     self.logger.debug(
         "Parameters stored to find_features",
     )
@@ -1114,7 +1114,7 @@ def find_ms2(self, **kwargs):
     c = 0
 
     if self.file_interface is None:
-        self.index_file()
+        self._index_file()
 
     # Vectorize the entire operation for better performance
     features_subset = features_df.filter(pl.col("feature_uid").is_in(feature_uid_list))
@@ -1269,7 +1269,7 @@ def find_ms2(self, **kwargs):
     self.features_df = features_df
 
     # store params
-    self.store_history(["find_ms2"], params.to_dict())
+    self.update_history(["find_ms2"], params.to_dict())
     self.logger.debug(
         "Parameters stored to find_ms2",
     )
@@ -1430,4 +1430,4 @@ def find_iso(self, rt_tolerance: float = 0.1, **kwargs):
     # Store parameters in history
     params_dict = {"rt_tolerance": rt_tolerance}
     params_dict.update(kwargs)
-    self.store_history(["find_iso"], params_dict)
+    self.update_history(["find_iso"], params_dict)

masster/sample/sample.py

@@ -47,17 +47,17 @@ from masster.sample.defaults.find_adducts_def import find_adducts_defaults
 from masster.sample.defaults.find_ms2_def import find_ms2_defaults
 from masster.sample.defaults.get_spectrum_def import get_spectrum_defaults
 
-# Sample-specific imports
-from masster.sample.h5 import _load_sample5
-from masster.sample.h5 import _load_sample5_study
-from masster.sample.h5 import _save_sample5
-from masster.sample.helpers import _delete_ms2
+# Sample-specific imports - keeping these private, only for internal use
+# from masster.sample.h5 import _load_sample5
+# from masster.sample.h5 import _load_sample5_study
+# from masster.sample.h5 import _save_sample5
+# from masster.sample.helpers import _delete_ms2
 from masster.sample.helpers import _estimate_memory_usage
 from masster.sample.helpers import _get_scan_uids
 from masster.sample.helpers import _get_feature_uids
-from masster.sample.helpers import _features_sync
-from masster.sample.adducts import _get_adducts
+# from masster.sample.helpers import _features_sync - made internal only
 from masster.sample.adducts import find_adducts
+# Removed _get_adducts - only used in study modules
 from masster.sample.helpers import features_delete
 from masster.sample.helpers import features_filter
 from masster.sample.helpers import select
@@ -69,22 +69,23 @@ from masster.sample.helpers import get_eic
 from masster.sample.helpers import set_source
 from masster.sample.helpers import _recreate_feature_map
 from masster.sample.helpers import _get_feature_map
-from masster.sample.load import _load_featureXML
-from masster.sample.load import _load_ms2data
-from masster.sample.load import _load_mzML
-from masster.sample.load import _load_raw
-from masster.sample.load import _load_wiff
+# Load functions - keeping only specific ones needed for external API
+# from masster.sample.load import _load_featureXML - made internal only
+# from masster.sample.load import _load_ms2data - made internal only  
+# from masster.sample.load import _load_mzML - made internal only
+# from masster.sample.load import _load_raw - made internal only
+# from masster.sample.load import _load_wiff - made internal only
 from masster.sample.load import chrom_extract
-from masster.sample.load import index_file
+from masster.sample.load import _index_file
 from masster.sample.load import load
 from masster.sample.load import load_noms1
-from masster.sample.load import load_study
+from masster.sample.load import _load_ms1  # Renamed from load_study
 from masster.sample.load import sanitize
 from masster.sample.plot import plot_2d
 from masster.sample.plot import plot_2d_oracle
 from masster.sample.plot import plot_dda_stats
 from masster.sample.plot import plot_chrom
-from masster.sample.plot import plot_feature_stats
+from masster.sample.plot import plot_features_stats  # Renamed from 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
@@ -105,12 +106,12 @@ from masster.sample.parameters import get_parameters
 from masster.sample.parameters import update_parameters
 from masster.sample.parameters import get_parameters_property
 from masster.sample.parameters import set_parameters_property
-from masster.sample.save import _save_featureXML
 from masster.sample.save import export_chrom
 from masster.sample.save import export_dda_stats
 from masster.sample.save import export_features
 from masster.sample.save import export_mgf
 from masster.sample.save import save
+# Removed internal-only import: _save_featureXML
 
 
 class Sample:
@@ -215,7 +216,8 @@ class Sample:
     # Attach module functions as class methods
     load = load
     load_noms1 = load_noms1
-    load_study = load_study
+    _load_ms1 = _load_ms1  # Renamed from load_study for clarity
+    load_study = _load_ms1  # Backward compatibility alias
     save = save
     find_features = find_features
     find_adducts = find_adducts
@@ -230,6 +232,7 @@ class Sample:
     select_features = select
     analyze_dda = analyze_dda
     store_history = store_history
+    update_history = store_history  # Preferred name for consistency with Study class
     get_parameters = get_parameters
     update_parameters = update_parameters
     get_parameters_property = get_parameters_property
@@ -242,7 +245,8 @@ class Sample:
     plot_2d_oracle = plot_2d_oracle
     plot_dda_stats = plot_dda_stats
     plot_chrom = plot_chrom
-    plot_feature_stats = plot_feature_stats
+    plot_features_stats = plot_features_stats  # Renamed from plot_feature_stats
+    plot_feature_stats = plot_features_stats  # Backward compatibility alias
     plot_ms2_cycle = plot_ms2_cycle
     plot_ms2_eic = plot_ms2_eic
     plot_ms2_q1 = plot_ms2_q1
@@ -259,30 +263,21 @@ class Sample:
     _get_feature_map = _get_feature_map
 
     # Additional method assignments for all imported functions
-    _load_sample5 = _load_sample5
-    _load_sample5_study = _load_sample5_study
-    _save_sample5 = _save_sample5
-    _delete_ms2 = _delete_ms2
+    # Removed internal-only methods: _load_sample5, _load_sample5_study, _save_sample5, _delete_ms2, _features_sync
     _estimate_memory_usage = _estimate_memory_usage
     _get_scan_uids = _get_scan_uids
     _get_feature_uids = _get_feature_uids
-    _features_sync = _features_sync
     features_delete = features_delete
     features_filter = features_filter
-    _load_featureXML = _load_featureXML
-    _load_ms2data = _load_ms2data
-    _load_mzML = _load_mzML
-    _load_raw = _load_raw
-    _load_wiff = _load_wiff
+    # Removed internal-only load methods: _load_featureXML, _load_ms2data, _load_mzML, _load_raw, _load_wiff
     chrom_extract = chrom_extract
-    index_file = index_file
+    _index_file = _index_file  # Renamed from index_file to be internal-only
     sanitize = sanitize
     _clean_features_df = _clean_features_df
     _features_deisotope = _features_deisotope
     _get_ztscan_stats = _get_ztscan_stats
     _spec_to_mat = _spec_to_mat
-    _save_featureXML = _save_featureXML
-    _get_adducts = _get_adducts
+    # Removed internal-only methods: _save_featureXML, _get_adducts (used only in study modules)
 
     # defaults
     sample_defaults = sample_defaults
@@ -303,12 +298,14 @@ class Sample:
         """
         # Define backward compatibility aliases to hide
         backward_compatibility_aliases = {
-            'load_study',           # deprecated alias for load_noms1
+            '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