masster 0.5.0__tar.gz → 0.5.1__tar.gz

{masster-0.5.0 → masster-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.0
+Version: 0.5.1
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster

{masster-0.5.0 → masster-0.5.1}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.0"
+version = "0.5.1"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.0 → masster-0.5.1}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.0"
+__version__ = "0.5.1"
 
 
 def get_version():

masster-0.5.1/src/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-0.5.0 → masster-0.5.1}/src/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-0.5.0 → masster-0.5.1}/src/masster/study/defaults/fill_def.py

@@ -58,7 +58,7 @@ class fill_defaults:
                 "dtype": int,
                 "description": "Minimum absolute samples threshold",
                 "default": 5,
-                "min_value": 1,
+                "min_value": 0,
                 "max_value": 100,
             },
         },

{masster-0.5.0 → masster-0.5.1}/src/masster/study/h5.py

@@ -2007,6 +2007,9 @@ def _load_study5(self, filename=None):
             f"Successfully migrated {sample_count} samples to indexed map_id format (0 to {sample_count - 1})",
         )
 
+    # Sanitize null feature_id and consensus_id values with new UIDs (same method as merge)
+    self._sanitize_null_ids()
+
     self.logger.debug("Study loaded")