masster 0.5.1__py3-none-any.whl → 0.5.4__py3-none-any.whl

masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.1"
+__version__ = "0.5.5"
 
 
 def get_version():

masster/sample/adducts.py

@@ -473,7 +473,7 @@ def find_adducts(self, **kwargs):
     self.logger.debug(f"Min probability threshold: {min_probability}")
 
     # Generate comprehensive adduct specifications using the Sample method
-    adducts_df = self._get_adducts(
+    adducts_df = _get_adducts(self, 
         adducts_list=adducts_list,
         charge_min=charge_min,
         charge_max=charge_max,

masster/sample/h5.py

@@ -62,8 +62,8 @@ def _save_sample5(
             return
 
     # synchronize feature_map if it exists
-    if hasattr(self, "_feature_map") and self._feature_map is not None:
-        self._features_sync()
+    #if hasattr(self, "_feature_map") and self._feature_map is not None:
+    #    self._features_sync()
 
     # if no extension is given, add .sample5
     if not filename.endswith(".sample5"):
@@ -1057,15 +1057,15 @@ def _load_sample5(self, filename: str, map: bool = False):
         # Parameters are now loaded from metadata JSON (see above)
         # Lib and lib_match are no longer saved/loaded
 
-    if map:
-        featureXML = filename.replace(".sample5", ".featureXML")
-        if os.path.exists(featureXML):
-            self._load_featureXML(featureXML)
-            self._features_sync()
-        else:
-            self.logger.warning(
-                f"Feature XML file {featureXML} not found, skipping loading.",
-            )
+    #if map:
+    #    featureXML = filename.replace(".sample5", ".featureXML")
+    #    if os.path.exists(featureXML):
+    #        self._load_featureXML(featureXML)
+    #        #self._features_sync()
+    #    else:
+    #        self.logger.warning(
+    #            f"Feature XML file {featureXML} not found, skipping loading.",
+    #        )
 
     # set self.file_path to *.sample5
     self.file_path = filename

masster/sample/helpers.py

@@ -569,7 +569,7 @@ def select(
         self.logger.info(f"Selected features. Features remaining: {len(feats)}")
     return feats
 
-
+'''
 def _features_sync(self):
     """
     Synchronizes the cached FeatureMap with features_df.
@@ -675,7 +675,7 @@ def _features_sync(self):
         self.logger.warning("PyOpenMS not available, cannot sync FeatureMap")
     except Exception as e:
         self.logger.error(f"Error during feature synchronization: {e}")
-
+'''
 
 def features_delete(self, features: list | None = None):
     """

masster/sample/load.py

@@ -46,6 +46,7 @@ import polars as pl
 from tqdm import tqdm
 
 from masster.chromatogram import Chromatogram
+from .h5 import _load_sample5
 from masster.spectrum import Spectrum
 
 # Suppress pyOpenMS warnings globally
@@ -96,13 +97,13 @@ def load(
 
     # 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(filename)
+        _load_sample5(self, filename)
     # elif filename.lower().endswith(".h5"):
     #    self._load_h5(filename)
     else:
@@ -155,13 +156,14 @@ 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/sample/processing.py

@@ -795,7 +795,7 @@ def find_features(self, **kwargs):
     )
 
     self.features_df = df
-    self._features_sync()
+    #self._features_sync()
     self.logger.info(f"Feature detection completed. Total features: {len(df)}")
 
     # store params

masster/sample/sample.py

@@ -48,9 +48,9 @@ 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 - keeping these private, only for internal use
-# from masster.sample.h5 import _load_sample5
+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.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
@@ -263,12 +263,16 @@ class Sample:
     _get_feature_map = _get_feature_map
 
     # Additional method assignments for all imported functions
-    # Removed internal-only methods: _load_sample5, _load_sample5_study, _save_sample5, _delete_ms2, _features_sync
+    # Removed internal-only methods: _load_sample5_study, _delete_ms2, _features_sync
     _estimate_memory_usage = _estimate_memory_usage
     _get_scan_uids = _get_scan_uids
     _get_feature_uids = _get_feature_uids
     features_delete = features_delete
     features_filter = features_filter
+    _save_sample5 = _save_sample5
+    _load_sample5 = _load_sample5
+
+
     # Removed internal-only load methods: _load_featureXML, _load_ms2data, _load_mzML, _load_raw, _load_wiff
     chrom_extract = chrom_extract
     _index_file = _index_file  # Renamed from index_file to be internal-only

masster/study/defaults/align_def.py

@@ -24,30 +24,7 @@ class align_defaults:
         skip_blanks (bool): Whether to skip blank samples. Default is False.
 
         KD algorithm specific parameters:
-        min_samples (int): Minimum number of samples required for KD alignment. Default is 3.
-        nr_partitions (int): Number of partitions in m/z dimension. Default is 100.
-        warp_enabled (bool): Enable non-linear retention time transformation. Default is True.
-        warp_rt_tol (float): RT tolerance for the LOWESS fit. Default is 5.0.
         warp_mz_tol (float): m/z tolerance for the LOWESS fit. Default is 0.05.
-        warp_max_pairwise_log_fc (float): Maximum absolute log10 fold change threshold for pairing. Default is 0.5.
-        warp_min_rel_cc_size (float): Minimum relative connected component size. Default is 0.5.
-        warp_max_nr_conflicts (int): Allow up to this many conflicts per connected component for alignment. Default is 0.
-        link_rt_tol (float): Width of RT tolerance window for linking (seconds). Default is 30.0.
-        link_mz_tol (float): m/z tolerance for linking features (ppm or Da). Default is 10.0.
-        link_charge_merging (str): Charge merging strategy for linking. Default is "With_charge_zero".
-        link_adduct_merging (str): Adduct merging strategy for linking. Default is "Any".
-        distance_RT_exponent (float): Exponent for normalized RT differences. Default is 1.0.
-        distance_RT_weight (float): Weight factor for final RT distances. Default is 1.0.
-        distance_MZ_exponent (float): Exponent for normalized m/z differences. Default is 2.0.
-        distance_MZ_weight (float): Weight factor for final m/z distances. Default is 1.0.
-        distance_intensity_exponent (float): Exponent for differences in relative intensity. Default is 1.0.
-        distance_intensity_weight (float): Weight factor for final intensity distances. Default is 1.0.
-        distance_intensity_log_transform (str): Log-transform intensities. Default is "enabled".
-        LOWESS_span (float): Fraction of datapoints for each local regression. Default is 0.666666666666667.
-        LOWESS_num_iterations (int): Number of robustifying iterations for LOWESS fitting. Default is 3.
-        LOWESS_delta (float): Parameter for LOWESS computations (negative auto-computes). Default is -1.0.
-        LOWESS_interpolation_type (str): Method for interpolation between datapoints. Default is "cspline".
-        LOWESS_extrapolation_type (str): Method for extrapolation outside data range. Default is "four-point-linear".
     """
 
     rt_tol: float = 5.0
@@ -60,30 +37,7 @@ class align_defaults:
     algorithm: str = "kd"
 
     # KD algorithm specific parameters
-    min_samples: int = 3
-    nr_partitions: int = 100
-    warp_enabled: bool = True
-    warp_rt_tol: float = 5.0
     warp_mz_tol: float = 0.05
-    warp_max_pairwise_log_fc: float = 0.5
-    warp_min_rel_cc_size: float = 0.5
-    warp_max_nr_conflicts: int = 0
-    link_rt_tol: float = 30.0
-    link_mz_tol: float = 10.0
-    link_charge_merging: str = "With_charge_zero"
-    link_adduct_merging: str = "Any"
-    distance_RT_exponent: float = 1.0
-    distance_RT_weight: float = 1.0
-    distance_MZ_exponent: float = 2.0
-    distance_MZ_weight: float = 1.0
-    distance_intensity_exponent: float = 1.0
-    distance_intensity_weight: float = 1.0
-    distance_intensity_log_transform: str = "enabled"
-    LOWESS_span: float = 0.666666666666667
-    LOWESS_num_iterations: int = 3
-    LOWESS_delta: float = -1.0
-    LOWESS_interpolation_type: str = "cspline"
-    LOWESS_extrapolation_type: str = "four-point-linear"
 
     _param_metadata: dict[str, dict[str, Any]] = field(
         default_factory=lambda: {
@@ -139,32 +93,6 @@ class align_defaults:
                 "allowed_values": ["pc", "kd"],
             },
             # KD algorithm specific parameters
-            "min_samples": {
-                "dtype": int,
-                "description": "Minimum number of samples required for KD alignment algorithm",
-                "default": 3,
-                "min_value": 2,
-                "max_value": 1000,
-            },
-            "nr_partitions": {
-                "dtype": int,
-                "description": "Number of partitions in m/z dimension for KD algorithm",
-                "default": 100,
-                "min_value": 1,
-                "max_value": 1000,
-            },
-            "warp_enabled": {
-                "dtype": bool,
-                "description": "Enable non-linear retention time transformation for KD algorithm",
-                "default": True,
-            },
-            "warp_rt_tol": {
-                "dtype": float,
-                "description": "RT tolerance for the LOWESS fit in KD algorithm (seconds)",
-                "default": 5.0,
-                "min_value": 0.1,
-                "max_value": 60.0,
-            },
             "warp_mz_tol": {
                 "dtype": float,
                 "description": "m/z tolerance for the LOWESS fit in KD algorithm (Da)",
@@ -172,138 +100,6 @@ class align_defaults:
                 "min_value": 0.001,
                 "max_value": 1.0,
             },
-            "warp_max_pairwise_log_fc": {
-                "dtype": float,
-                "description": "Maximum absolute log10 fold change between two compatible signals during compatibility graph construction in KD algorithm",
-                "default": 0.5,
-                "min_value": -1.0,
-                "max_value": 10.0,
-            },
-            "warp_min_rel_cc_size": {
-                "dtype": float,
-                "description": "Minimum relative connected component size for KD algorithm",
-                "default": 0.5,
-                "min_value": 0.0,
-                "max_value": 1.0,
-            },
-            "warp_max_nr_conflicts": {
-                "dtype": int,
-                "description": "Allow up to this many conflicts (features from the same map) per connected component to be used for alignment (-1 means allow any number of conflicts)",
-                "default": 0,
-                "min_value": -1,
-                "max_value": 1000,
-            },
-            "link_rt_tol": {
-                "dtype": float,
-                "description": "Width of RT tolerance window for linking in KD algorithm (seconds)",
-                "default": 30.0,
-                "min_value": 0.0,
-                "max_value": 300.0,
-            },
-            "link_mz_tol": {
-                "dtype": float,
-                "description": "m/z tolerance for linking features in KD algorithm (ppm or Da)",
-                "default": 10.0,
-                "min_value": 0.0,
-                "max_value": 100.0,
-            },
-            "link_charge_merging": {
-                "dtype": str,
-                "description": "Charge merging strategy for linking features in KD algorithm",
-                "default": "With_charge_zero",
-                "allowed_values": ["Identical", "With_charge_zero", "Any"],
-            },
-            "link_adduct_merging": {
-                "dtype": str,
-                "description": "Adduct merging strategy for linking features in KD algorithm",
-                "default": "Any",
-                "allowed_values": ["Identical", "With_unknown_adducts", "Any"],
-            },
-            "distance_RT_exponent": {
-                "dtype": float,
-                "description": "Normalized RT differences are raised to this power in KD algorithm",
-                "default": 1.0,
-                "min_value": 0.0,
-                "max_value": 10.0,
-            },
-            "distance_RT_weight": {
-                "dtype": float,
-                "description": "Final RT distances are weighted by this factor in KD algorithm",
-                "default": 1.0,
-                "min_value": 0.0,
-                "max_value": 100.0,
-            },
-            "distance_MZ_exponent": {
-                "dtype": float,
-                "description": "Normalized m/z differences are raised to this power in KD algorithm",
-                "default": 2.0,
-                "min_value": 0.0,
-                "max_value": 10.0,
-            },
-            "distance_MZ_weight": {
-                "dtype": float,
-                "description": "Final m/z distances are weighted by this factor in KD algorithm",
-                "default": 1.0,
-                "min_value": 0.0,
-                "max_value": 100.0,
-            },
-            "distance_intensity_exponent": {
-                "dtype": float,
-                "description": "Differences in relative intensity are raised to this power in KD algorithm",
-                "default": 1.0,
-                "min_value": 0.0,
-                "max_value": 10.0,
-            },
-            "distance_intensity_weight": {
-                "dtype": float,
-                "description": "Final intensity distances are weighted by this factor in KD algorithm",
-                "default": 1.0,
-                "min_value": 0.0,
-                "max_value": 100.0,
-            },
-            "distance_intensity_log_transform": {
-                "dtype": str,
-                "description": "Log-transform intensities in KD algorithm distance calculation",
-                "default": "enabled",
-                "allowed_values": ["enabled", "disabled"],
-            },
-            "LOWESS_span": {
-                "dtype": float,
-                "description": "Fraction of datapoints to use for each local regression in LOWESS fitting",
-                "default": 0.666666666666667,
-                "min_value": 0.0,
-                "max_value": 1.0,
-            },
-            "LOWESS_num_iterations": {
-                "dtype": int,
-                "description": "Number of robustifying iterations for LOWESS fitting",
-                "default": 3,
-                "min_value": 0,
-                "max_value": 10,
-            },
-            "LOWESS_delta": {
-                "dtype": float,
-                "description": "Nonnegative parameter for LOWESS computations (negative value auto-computes)",
-                "default": -1.0,
-                "min_value": -1.0,
-                "max_value": 1000.0,
-            },
-            "LOWESS_interpolation_type": {
-                "dtype": str,
-                "description": "Method to use for interpolation between datapoints computed by LOWESS",
-                "default": "cspline",
-                "allowed_values": ["linear", "cspline", "akima"],
-            },
-            "LOWESS_extrapolation_type": {
-                "dtype": str,
-                "description": "Method to use for extrapolation outside the data range in LOWESS",
-                "default": "four-point-linear",
-                "allowed_values": [
-                    "two-point-linear",
-                    "four-point-linear",
-                    "global-linear",
-                ],
-            },
         },
         repr=False,
     )

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: {
@@ -61,6 +62,13 @@ class fill_defaults:
                 "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/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/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():