masster 0.5.0__tar.gz → 0.5.3__tar.gz

{masster-0.5.0 → masster-0.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.0
+Version: 0.5.3
 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-0.5.3}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.0"
+version = "0.5.3"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.0 → masster-0.5.3}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.0"
+__version__ = "0.5.4"
 
 
 def get_version():

masster-0.5.3/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-0.5.3}/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-0.5.3}/src/masster/sample/load.py

@@ -155,13 +155,14 @@ def load_noms1(
 
     # check if file is mzML
     if filename.lower().endswith(".mzml"):
-        self._load_mzML(filename)
+        _load_mzML(self, filename)
     elif filename.lower().endswith(".wiff") or filename.lower().endswith(".wiff2"):
-        self._load_wiff(filename)
+        _load_wiff(self, filename)
     elif filename.lower().endswith(".raw"):
-        self._load_raw(filename)
+        _load_raw(self, filename)
     elif filename.lower().endswith(".sample5"):
-        self._load_sample5_study(filename)  # Use optimized version for study loading
+        from masster.sample.h5 import _load_sample5_study
+        _load_sample5_study(self, filename)  # Use optimized version for study loading
     else:
         raise ValueError("File must be .mzML, .wiff, *.raw, or .sample5")
 

masster-0.5.0/src/masster/study/defaults/fill_chrom_def.py → masster-0.5.3/src/masster/study/defaults/align_def.py

@@ -1,65 +1,104 @@
-"""Parameter class for Study fill_chrom method."""
+"""Parameter class for Study align method."""
 
 from dataclasses import dataclass, field
-from typing import Optional, Any
+from typing import Any
 
 
 @dataclass
-class fill_chrom_defaults:
+class align_defaults:
     """
-    Parameter class for Study fill_chrom method.
+    Parameter class for Study align method.
 
-    This class encapsulates parameters for filling missing chromatograms
-    by extracting them from raw data across samples.
+    This class encapsulates parameters for feature alignment across samples,
+    including retention time and m/z tolerances, warping parameters, and
+    alignment algorithm settings.
 
     Attributes:
-        uids (Optional[list]): List of consensus UIDs to process. Default is None (all).
-        mz_tol (float): m/z tolerance for chromatogram extraction (Da). Default is 0.010.
-        rt_tol (float): RT tolerance for chromatogram extraction (seconds). Default is 10.0.
-        min_samples_rel (float): Minimum relative samples threshold. Default is 0.05.
-        min_samples_abs (int): Minimum absolute samples threshold. Default is 5.
+        algorithm (str): Alignment algorithm ('pc' for PoseClustering, 'kd' for KD). Default is 'pc'.
+        rt_tol (float): Maximum retention time difference for alignment. Default is 60.0.
+        mz_max_diff (float): Maximum m/z difference for alignment. Default is 0.02.
+        rt_pair_distance_frac (float): Fraction of RT difference for pair distance. Default is 0.2.
+        mz_pair_max_distance (float): Maximum m/z pair distance. Default is 0.01.
+        num_used_points (int): Number of points used for alignment. Default is 1000.
+        save_features (bool): Whether to save features after alignment. Default is False.
+        skip_blanks (bool): Whether to skip blank samples. Default is False.
+
+        KD algorithm specific parameters:
+        warp_mz_tol (float): m/z tolerance for the LOWESS fit. Default is 0.05.
     """
 
-    uids: Optional[list] = None
-    mz_tol: float = 0.010
-    rt_tol: float = 10.0
-    min_samples_rel: float = 0.05
-    min_samples_abs: int = 5
+    rt_tol: float = 5.0
+    mz_max_diff: float = 0.01
+    rt_pair_distance_frac: float = 0.5
+    mz_pair_max_distance: float = 0.01
+    num_used_points: int = 1000
+    save_features: bool = False
+    skip_blanks: bool = False
+    algorithm: str = "kd"
+
+    # KD algorithm specific parameters
+    warp_mz_tol: float = 0.05
 
     _param_metadata: dict[str, dict[str, Any]] = field(
         default_factory=lambda: {
-            "uids": {
-                "dtype": "Optional[list]",
-                "description": "List of consensus UIDs to process (None for all)",
-                "default": None,
+            "rt_tol": {
+                "dtype": float,
+                "description": "Maximum retention time difference for alignment (seconds)",
+                "default": 5.0,
+                "min_value": 1.0,
+                "max_value": 30.0,
             },
-            "mz_tol": {
+            "mz_max_diff": {
                 "dtype": float,
-                "description": "m/z tolerance for chromatogram extraction (Da)",
-                "default": 0.010,
+                "description": "Maximum m/z difference for alignment (Da)",
+                "default": 0.01,
                 "min_value": 0.001,
-                "max_value": 0.1,
+                "max_value": 0.05,
             },
-            "rt_tol": {
+            "rt_pair_distance_frac": {
                 "dtype": float,
-                "description": "RT tolerance for chromatogram extraction (seconds)",
-                "default": 10.0,
-                "min_value": 1.0,
-                "max_value": 300.0,
+                "description": "Fraction of RT difference for pair distance calculation",
+                "default": 0.2,
+                "min_value": 0.1,
+                "max_value": 1.0,
             },
-            "min_samples_rel": {
+            "mz_pair_max_distance": {
                 "dtype": float,
-                "description": "Minimum relative samples threshold (fraction)",
-                "default": 0.05,
-                "min_value": 0.01,
-                "max_value": 1.0,
+                "description": "Maximum m/z pair distance (Da)",
+                "default": 0.01,
+                "min_value": 0.001,
+                "max_value": 0.2,
             },
-            "min_samples_abs": {
+            "num_used_points": {
                 "dtype": int,
-                "description": "Minimum absolute samples threshold",
-                "default": 5,
-                "min_value": 1,
-                "max_value": 100,
+                "description": "Number of points used for alignment",
+                "default": 1000,
+                "min_value": 10,
+                "max_value": 10000,
+            },
+            "save_features": {
+                "dtype": bool,
+                "description": "Whether to save features after alignment",
+                "default": False,
+            },
+            "skip_blanks": {
+                "dtype": bool,
+                "description": "Whether to skip blank samples during alignment",
+                "default": False,
+            },
+            "algorithm": {
+                "dtype": str,
+                "description": "Alignment algorithm to use",
+                "default": "pc",
+                "allowed_values": ["pc", "kd"],
+            },
+            # KD algorithm specific parameters
+            "warp_mz_tol": {
+                "dtype": float,
+                "description": "m/z tolerance for the LOWESS fit in KD algorithm (Da)",
+                "default": 0.05,
+                "min_value": 0.001,
+                "max_value": 1.0,
             },
         },
         repr=False,
@@ -111,14 +150,6 @@ class fill_chrom_defaults:
         metadata = self._param_metadata[param_name]
         expected_dtype = metadata["dtype"]
 
-        # Handle optional types
-        if isinstance(expected_dtype, str) and expected_dtype.startswith("Optional"):
-            if value is None:
-                return True
-            # Extract the inner type for validation
-            if "list" in expected_dtype:
-                expected_dtype = list
-
         # Type checking
         if expected_dtype is int:
             if not isinstance(value, int):
@@ -132,8 +163,8 @@ class fill_chrom_defaults:
                     value = float(value)
                 except (ValueError, TypeError):
                     return False
-        elif expected_dtype is list:
-            if not isinstance(value, list):
+        elif expected_dtype is bool:
+            if not isinstance(value, bool):
                 return False
 
         # Range validation for numeric types
@@ -143,6 +174,11 @@ class fill_chrom_defaults:
             if "max_value" in metadata and value > metadata["max_value"]:
                 return False
 
+        # Allowed values validation for string types
+        if expected_dtype is str and "allowed_values" in metadata:
+            if value not in metadata["allowed_values"]:
+                return False
+
         return True
 
     def set(self, param_name: str, value: Any, validate: bool = True) -> bool:
@@ -167,20 +203,18 @@ class fill_chrom_defaults:
         if param_name in self._param_metadata:
             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 "int" in expected_dtype and not isinstance(value, int):
-                    try:
-                        value = int(value)
-                    except (ValueError, TypeError):
-                        if validate:
-                            return False
-                elif "float" in expected_dtype and not isinstance(value, float):
-                    try:
-                        value = float(value)
-                    except (ValueError, TypeError):
-                        if validate:
-                            return False
+            if expected_dtype is int and not isinstance(value, int):
+                try:
+                    value = int(value)
+                except (ValueError, TypeError):
+                    if validate:
+                        return False
+            elif expected_dtype is float and not isinstance(value, float):
+                try:
+                    value = float(value)
+                except (ValueError, TypeError):
+                    if validate:
+                        return False
 
         setattr(self, param_name, value)
         return True

{masster-0.5.0 → masster-0.5.3}/src/masster/study/defaults/fill_def.py

@@ -21,10 +21,11 @@ class fill_defaults:
     """
 
     uids: Optional[list] = None
-    mz_tol: float = 0.010
+    mz_tol: float = 0.050
     rt_tol: float = 10.0
     min_samples_rel: float = 0.00
     min_samples_abs: int = 5
+    threads: int = 6
 
     _param_metadata: dict[str, dict[str, Any]] = field(
         default_factory=lambda: {
@@ -58,9 +59,16 @@ class fill_defaults:
                 "dtype": int,
                 "description": "Minimum absolute samples threshold",
                 "default": 5,
-                "min_value": 1,
+                "min_value": 0,
                 "max_value": 100,
             },
+            "threads": {
+                "dtype": int,
+                "description": "Number of parallel threads",
+                "default": 6,
+                "min_value": 1,
+                "max_value": 32,
+            },
         },
         repr=False,
     )

{masster-0.5.0 → masster-0.5.3}/src/masster/study/defaults/merge_def.py

@@ -13,7 +13,7 @@ class merge_defaults:
     method selection, grouping tolerances, and algorithm-specific parameters.
 
     Attributes:
-        method (str): Merge method to use ('kd', 'qt', 'kd-nowarp', 'chunked'). Default is "kd".
+        method (str): Merge method to use ('kd', 'qt', 'kd_chunked', 'qt_chunked'). Default is "kd".
         min_samples (int): Minimum number of samples for a consensus feature. Default is 50.
         rt_tol (float): RT tolerance for grouping (seconds). Default is 2.0.
         mz_tol (float): m/z tolerance for grouping (Da for all methods). Default is 0.01.
@@ -25,38 +25,31 @@ class merge_defaults:
         link_ms2 (bool): Whether to link MS2 spectra to consensus features. Default is True.
     """
 
-    method: str = "qt"
+    method: str = "kd"
     min_samples: int = 2
     rt_tol: float = 5.0
-    mz_tol: float = 0.01
+    mz_tol: float = 0.05
     chunk_size: int = 500
     nr_partitions: int = 1000
     min_rel_cc_size: float = 0.1
     max_pairwise_log_fc: float = -1.0
     max_nr_conflicts: int = 0
     link_ms2: bool = True
+    extract_ms1: bool = True
+    
+    # Cross-chunk merging parameters
+    dechunking: str = "hierarchical"
     
     # Parallel processing parameters
     threads: Optional[int] = None
-    
-    # KD-Strict specific parameters
-    optimize_rt_tol: bool = False
-    rt_tol_range: tuple = (0.5, 4.0)  
-    rt_tol_steps: int = 7
-    secondary_merge_rt_tol: float = 1.0
-    secondary_merge_mz_tol: float = 0.005
-    min_sample_overlap: float = 0.8
-    max_rt_spread: float = 2.0  # Will default to 2x rt_tol
-    min_coherence: float = 0.0
 
     _param_metadata: dict[str, dict[str, Any]] = field(
         default_factory=lambda: {
             "method": {
                 "dtype": str,
                 "description": "Merge method (algorithm) to use",
-                "default": "quality",
-                "allowed_values": ["sensitivity", "qt", "nowarp", "chunked", "quality", 
-                                 "kd", "kd-nowarp", "kd_nowarp", "kd-strict", "kd_strict",
+                "default": "kd",
+                "allowed_values": ["kd", "qt", 
                                  "kd_chunked", "kd-chunked", "qt_chunked", "qt-chunked"],
             },
             "min_samples": {
@@ -118,7 +111,17 @@ class merge_defaults:
                 "description": "Whether to link MS2 spectra to consensus features",
                 "default": True,
             },
-            # Parallel processing parameters
+            "extract_ms1": {
+                "dtype": bool,
+                "description": "Whether to extract MS1 chromatograms for consensus features",
+                "default": True,
+            },
+            "dechunking": {
+                "dtype": str,
+                "description": "Cross-chunk merging algorithm for chunked methods",
+                "default": "hierarchical",
+                "allowed_values": ["hierarchical", "kdtree"],
+            },
             "threads": {
                 "dtype": [int, type(None)],
                 "description": "Number of parallel threads/processes for chunked methods (None=original sequential)",
@@ -126,58 +129,6 @@ class merge_defaults:
                 "min_value": 1,
                 "max_value": 32,
             },
-            # KD-Strict specific parameters
-            "optimize_rt_tol": {
-                "dtype": bool,
-                "description": "Enable RT tolerance optimization for kd-strict method",
-                "default": False,
-            },
-            "rt_tol_range": {
-                "dtype": tuple,
-                "description": "RT tolerance range for optimization (min, max) in seconds",
-                "default": (0.8, 2.0),
-            },
-            "rt_tol_steps": {
-                "dtype": int,
-                "description": "Number of steps for RT tolerance optimization",
-                "default": 5,
-                "min_value": 3,
-                "max_value": 20,
-            },
-            "secondary_merge_rt_tol": {
-                "dtype": float,
-                "description": "RT tolerance for secondary clustering in kd-strict (seconds)",
-                "default": 0.5,
-                "min_value": 0.1,
-                "max_value": 5.0,
-            },
-            "secondary_merge_mz_tol": {
-                "dtype": float,
-                "description": "m/z tolerance for secondary clustering in kd-strict (Da)",
-                "default": 0.005,
-                "min_value": 0.001,
-                "max_value": 0.1,
-            },
-            "min_sample_overlap": {
-                "dtype": float,
-                "description": "Minimum sample overlap ratio for merging features (0.0-1.0)",
-                "default": 0.8,
-                "min_value": 0.0,
-                "max_value": 1.0,
-            },
-            "max_rt_spread": {
-                "dtype": float,
-                "description": "Maximum allowed RT spread in seconds (None = 3x rt_tol)",
-                "default": None,
-                "min_value": 0.1,
-            },
-            "min_coherence": {
-                "dtype": float,
-                "description": "Minimum chromatographic coherence score (0.0 = disabled)",
-                "default": 0.0,
-                "min_value": 0.0,
-                "max_value": 1.0,
-            },
         },
         repr=False,
     )

{masster-0.5.0 → masster-0.5.3}/src/masster/study/export.py

@@ -551,7 +551,7 @@ def export_mztab(self, filename: str | None = None, include_mgf=True, **kwargs)
         else:
             self.logger.info("No identification data available for mzTab export")
     except Exception as e:
-        self.logger.warning(f"Could not retrieve identification data: {e}")
+        self.logger.debug(f"Could not retrieve identification data: {e}")
         id_data = None
         top_id_data = None
         full_id_data = None
@@ -1190,10 +1190,12 @@ def export_xlsx(self, filename: str | None = None) -> None:
     """
     Export the study data to an Excel workbook with multiple worksheets.
 
-    The Excel file contains three worksheets:
-    - consensus_df: Consensus features dataframe
-    - matrix: Consensus matrix with samples as columns (get_consensus_matrix)
+    The Excel file contains five worksheets:
+    - samples: Samples dataframe
+    - consensus: Consensus features dataframe
     - identification: Identification results with library annotations (get_id)
+    - gaps: Gaps matrix showing filled vs non-filled features (get_gaps_matrix)
+    - matrix: Consensus matrix with samples as columns (get_consensus_matrix)
 
     Args:
         filename (str, optional): Path to the output Excel file. Defaults to "study.xlsx"
@@ -1263,7 +1265,25 @@ def export_xlsx(self, filename: str | None = None) -> None:
             f"Error getting identification data: {e}. Skipping identification worksheet.",
         )
 
-    # 4. Consensus matrix (last worksheet)
+    # 4. Gaps matrix (filled vs non-filled features)
+    try:
+        gaps_df = self.get_gaps_matrix()
+        if gaps_df is not None and not gaps_df.is_empty():
+            gaps_pandas = gaps_df.to_pandas()
+            worksheets["gaps"] = gaps_pandas
+            self.logger.debug(
+                f"Added gaps worksheet with {len(gaps_pandas)} rows",
+            )
+        else:
+            self.logger.warning(
+                "get_gaps_matrix() returned empty data, skipping gaps worksheet",
+            )
+    except Exception as e:
+        self.logger.debug(
+            f"Error getting gaps data: {e}. Skipping gaps worksheet.",
+        )
+
+    # 5. Consensus matrix (last worksheet)
     try:
         matrix_df = self.get_consensus_matrix()
         if matrix_df is not None and not matrix_df.is_empty():