masster 0.3.10__py3-none-any.whl → 0.3.11__py3-none-any.whl

masster/study/processing.py

@@ -17,7 +17,7 @@ from masster.study.defaults import (
 
 
 def align(self, **kwargs):
-    """Align feature maps using pose clustering and update feature RTs.
+    """Align feature maps using pose clustering or KD algorithm and update feature RTs.
 
     Parameters can be provided as an ``align_defaults`` instance or as
     individual keyword arguments; they are validated against the defaults class.
@@ -30,6 +30,32 @@ def align(self, **kwargs):
         - num_used_points (int): Number of points to use for alignment estimation.
         - save_features (bool): If True, save updated features after alignment.
         - skip_blanks (bool): If True, skip blank samples during alignment.
+        - algo (str): Alignment algorithm ('pc' for PoseClustering, 'kd' for KD).
+
+        KD algorithm specific parameters:
+        - nr_partitions (int): Number of partitions in m/z dimension.
+        - warp_enabled (bool): Enable non-linear retention time transformation.
+        - warp_rt_tol (float): RT tolerance for the LOWESS fit.
+        - warp_mz_tol (float): m/z tolerance for the LOWESS fit.
+        - warp_max_pairwise_log_fc (float): Maximum absolute log10 fold-change threshold for pairing.
+        - warp_min_rel_cc_size (float): Minimum relative connected component size.
+        - warp_max_nr_conflicts (int): Allow up to this many conflicts per connected component for alignment.
+        - link_rt_tol (float): Width of RT tolerance window for linking features.
+        - link_mz_tol (float): m/z tolerance for linking features.
+        - link_charge_merging (str): Charge merging strategy for linking features.
+        - link_adduct_merging (str): Adduct merging strategy for linking features.
+        - distance_RT_exponent (float): Exponent for normalized RT differences.
+        - distance_RT_weight (float): Weight factor for final RT distances.
+        - distance_MZ_exponent (float): Exponent for normalized m/z differences.
+        - distance_MZ_weight (float): Weight factor for final m/z distances.
+        - distance_intensity_exponent (float): Exponent for differences in relative intensity.
+        - distance_intensity_weight (float): Weight factor for final intensity distances.
+        - distance_intensity_log_transform (str): Log-transform intensities.
+        - LOWESS_span (float): Fraction of datapoints for each local regression.
+        - LOWESS_num_iterations (int): Number of robustifying iterations for LOWESS fitting.
+        - LOWESS_delta (float): Parameter for LOWESS computations (negative auto-computes).
+        - LOWESS_interpolation_type (str): Method for interpolation between datapoints.
+        - LOWESS_extrapolation_type (str): Method for extrapolation outside data range.
     """
     # parameters initialization
     params = align_defaults()
@@ -57,78 +83,135 @@ def align(self, **kwargs):
         self.features_maps = []
         self.load_features()
 
-    self.logger.debug("Starting alignment")
+    # self.logger.debug("Starting alignment")
 
     fmaps = self.features_maps
-    # set ref_index to feature map index with largest number of features
-    ref_index = [i[0] for i in sorted(enumerate([fm.size() for fm in fmaps]), key=lambda x: x[1])][-1]
-
-    self.logger.info(
-        f"Align on {self.samples_df.row(ref_index, named=True)['sample_name']}",
-    )
-
-    aligner = oms.MapAlignmentAlgorithmPoseClustering()
 
+    # Initialize OpenMS parameters
     params_oms = oms.Param()
-    params_oms.setValue("pairfinder:distance_intensity:log_transform", "disabled")
-    params_oms.setValue("pairfinder:ignore_charge", "true")
-    params_oms.setValue("max_num_peaks_considered", 1000)
-    params_oms.setValue("pairfinder:distance_RT:max_difference", params.get("rt_max_diff"))
-    params_oms.setValue("pairfinder:distance_MZ:max_difference", params.get("mz_max_diff"))
-    params_oms.setValue("superimposer:rt_pair_distance_fraction", params.get("rt_pair_distance_frac"))
-    params_oms.setValue("superimposer:mz_pair_max_distance", params.get("mz_pair_max_distance"))
-    params_oms.setValue("superimposer:num_used_points", params.get("num_used_points"))
-    params_oms.setValue("pairfinder:distance_MZ:exponent", 3.0)
-    params_oms.setValue("pairfinder:distance_RT:exponent", 2.0)
-    aligner.setParameters(params_oms)
-    """
-    {b'max_num_peaks_considered': 1000,
-    b'superimposer:mz_pair_max_distance': 0.5,
-    b'superimposer:rt_pair_distance_fraction': 0.1,
-    b'superimposer:num_used_points': 2000,
-    b'superimposer:scaling_bucket_size': 0.005,
-    b'superimposer:shift_bucket_size': 3.0,
-    b'superimposer:max_shift': 1000.0,
-    b'superimposer:max_scaling': 2.0,
-    b'superimposer:dump_buckets': '',
-    b'superimposer:dump_pairs': '',
-    b'pairfinder:second_nearest_gap': 2.0,
-    b'pairfinder:use_identifications': 'false',
-    b'pairfinder:ignore_charge': 'false',
-    b'pairfinder:ignore_adduct': 'true',
-    b'pairfinder:distance_RT:max_difference': 100.0,
-    b'pairfinder:distance_RT:exponent': 1.0,
-    b'pairfinder:distance_RT:weight': 1.0,
-    b'pairfinder:distance_MZ:max_difference': 0.3,
-    b'pairfinder:distance_MZ:unit': 'Da',
-    b'pairfinder:distance_MZ:exponent': 2.0,
-    b'pairfinder:distance_MZ:weight': 1.0,
-    b'pairfinder:distance_intensity:exponent': 1.0,
-    b'pairfinder:distance_intensity:weight': 0.0,
-    b'pairfinder:distance_intensity:log_transform': 'disabled'} """
-
-    aligner.setReference(fmaps[ref_index])
-
-    self.logger.debug(f"Parameters for alignment: {params}")
-
-    tdqm_disable = self.log_level not in ["TRACE", "DEBUG", "INFO"]
-    # perform alignment and transformation of feature maps to the reference map (exclude reference map)
-    for index, fm in tqdm(
-        list(enumerate(fmaps)),
-        total=len(fmaps),
-        desc=f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Align feature maps",
-        disable=tdqm_disable,
-    ):
-        if index == ref_index:
-            continue
-        if params.get("skip_blanks") and self.samples_df.row(index, named=True)["sample_type"] == "blank":
-            continue
-        trafo = oms.TransformationDescription()
-        aligner.align(fm, trafo)
-        transformer = oms.MapAlignmentTransformer()
-        transformer.transformRetentionTimes(fm, trafo, True)
+    # Choose alignment algorithm based on parameter
+    algo = params.get("algo").lower()
+
+    # Set common parameters for both algorithms
+    if algo == "pc":
+        # Parameters specific to PoseClustering
+        params_oms.setValue("pairfinder:distance_intensity:log_transform", "disabled")
+        params_oms.setValue("pairfinder:ignore_charge", "true")
+        params_oms.setValue("max_num_peaks_considered", 1000)
+        params_oms.setValue("pairfinder:distance_RT:max_difference", params.get("rt_max_diff"))
+        params_oms.setValue("pairfinder:distance_MZ:max_difference", params.get("mz_max_diff"))
+        params_oms.setValue("superimposer:rt_pair_distance_fraction", params.get("rt_pair_distance_frac"))
+        params_oms.setValue("superimposer:mz_pair_max_distance", params.get("mz_pair_max_distance"))
+        params_oms.setValue("superimposer:num_used_points", params.get("num_used_points"))
+        params_oms.setValue("pairfinder:distance_MZ:exponent", 3.0)
+        params_oms.setValue("pairfinder:distance_RT:exponent", 2.0)
+
+        """
+        {b'max_num_peaks_considered': 1000,
+        b'superimposer:mz_pair_max_distance': 0.5,
+        b'superimposer:rt_pair_distance_fraction': 0.1,
+        b'superimposer:num_used_points': 2000,
+        b'superimposer:scaling_bucket_size': 0.005,
+        b'superimposer:shift_bucket_size': 3.0,
+        b'superimposer:max_shift': 1000.0,
+        b'superimposer:max_scaling': 2.0,
+        b'superimposer:dump_buckets': '',
+        b'superimposer:dump_pairs': '',
+        b'pairfinder:second_nearest_gap': 2.0,
+        b'pairfinder:use_identifications': 'false',
+        b'pairfinder:ignore_charge': 'false',
+        b'pairfinder:ignore_adduct': 'true',
+        b'pairfinder:distance_RT:max_difference': 100.0,
+        b'pairfinder:distance_RT:exponent': 1.0,
+        b'pairfinder:distance_RT:weight': 1.0,
+        b'pairfinder:distance_MZ:max_difference': 0.3,
+        b'pairfinder:distance_MZ:unit': 'Da',
+        b'pairfinder:distance_MZ:exponent': 2.0,
+        b'pairfinder:distance_MZ:weight': 1.0,
+        b'pairfinder:distance_intensity:exponent': 1.0,
+        b'pairfinder:distance_intensity:weight': 0.0,
+        b'pairfinder:distance_intensity:log_transform': 'disabled'}
+        """
+    elif algo == "kd":
+        # Parameters specific to KD algorithm
+        params_oms.setValue("mz_unit", "Da")
+        params_oms.setValue("nr_partitions", params.get("nr_partitions"))
+
+        # Warp parameters for non-linear RT transformation
+        params_oms.setValue("warp:enabled", "true" if params.get("warp_enabled") else "false")
+        params_oms.setValue("warp:rt_tol", params.get("warp_rt_tol"))
+        params_oms.setValue("warp:mz_tol", params.get("warp_mz_tol"))
+        params_oms.setValue("warp:max_pairwise_log_fc", params.get("warp_max_pairwise_log_fc"))
+        params_oms.setValue("warp:min_rel_cc_size", params.get("warp_min_rel_cc_size"))
+        params_oms.setValue("warp:max_nr_conflicts", params.get("warp_max_nr_conflicts"))
+
+        # Link parameters
+        params_oms.setValue("link:rt_tol", params.get("link_rt_tol"))
+        params_oms.setValue("link:mz_tol", params.get("link_mz_tol"))
+        params_oms.setValue("link:charge_merging", params.get("link_charge_merging"))
+        params_oms.setValue("link:adduct_merging", params.get("link_adduct_merging"))
+
+        # Distance parameters
+        params_oms.setValue("distance_RT:exponent", params.get("distance_RT_exponent"))
+        params_oms.setValue("distance_RT:weight", params.get("distance_RT_weight"))
+        params_oms.setValue("distance_MZ:exponent", params.get("distance_MZ_exponent"))
+        params_oms.setValue("distance_MZ:weight", params.get("distance_MZ_weight"))
+        params_oms.setValue("distance_intensity:exponent", params.get("distance_intensity_exponent"))
+        params_oms.setValue("distance_intensity:weight", params.get("distance_intensity_weight"))
+        params_oms.setValue("distance_intensity:log_transform", params.get("distance_intensity_log_transform"))
+
+        # LOWESS parameters
+        params_oms.setValue("LOWESS:span", params.get("LOWESS_span"))
+        params_oms.setValue("LOWESS:num_iterations", params.get("LOWESS_num_iterations"))
+        params_oms.setValue("LOWESS:delta", params.get("LOWESS_delta"))
+        params_oms.setValue("LOWESS:interpolation_type", params.get("LOWESS_interpolation_type"))
+        params_oms.setValue("LOWESS:extrapolation_type", params.get("LOWESS_extrapolation_type"))
+
+    if algo == "pc":
+        aligner = oms.MapAlignmentAlgorithmPoseClustering()
+        self.logger.info("Starting alignment with PoseClustering")
+        # set ref_index to feature map index with largest number of features
+        ref_index = [i[0] for i in sorted(enumerate([fm.size() for fm in fmaps]), key=lambda x: x[1])][-1]
+        self.logger.debug(
+            f"Reference map is {self.samples_df.row(ref_index, named=True)['sample_name']}",
+        )
+        aligner.setParameters(params_oms)
+        aligner.setReference(fmaps[ref_index])
+        self.logger.debug(f"Parameters for alignment: {params}")
+        # perform alignment and transformation of feature maps to the reference map (exclude reference map)
+        tdqm_disable = self.log_level not in ["TRACE", "DEBUG", "INFO"]
+        for index, fm in tqdm(
+            list(enumerate(fmaps)),
+            total=len(fmaps),
+            desc=f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Align feature maps",
+            disable=tdqm_disable,
+        ):
+            if index == ref_index:
+                continue
+            if params.get("skip_blanks") and self.samples_df.row(index, named=True)["sample_type"] == "blank":
+                continue
+            trafo = oms.TransformationDescription()
+            aligner.align(fm, trafo)
+            transformer = oms.MapAlignmentTransformer()
+            transformer.transformRetentionTimes(fm, trafo, True)
+
+        self.alignment_ref_index = ref_index
+
+    elif algo == "kd":
+        # KD algorithm requires num_maps and Param parameters
+        num_maps = len(fmaps)
+        aligner = oms.MapAlignmentAlgorithmKD(3, params_oms)
+        self.logger.info(f"Starting alignment with KD algorithm using {num_maps} maps")
+
+        kdtree = oms.KDTreeFeatureMaps()
+        kdtree.addMaps(fmaps)  # Add all feature maps to the KDTree
+        # kdtree.optimizeTree()
+        aligner.addRTFitData(kdtree)
+        aligner.fitLOWESS()
+        aligner.transform(kdtree)
 
-    self.alignment_ref_index = ref_index
+    else:
+        self.logger.error(f"Unknown alignment algorithm '{algo}'")
 
     # check if rt_original exists in features_df, if not, add it after rt
     if "rt_original" not in self.features_df.columns:
@@ -238,8 +321,8 @@ def merge(self, **kwargs):
     self.consensus_df = pl.DataFrame()
     self.consensus_ms2 = pl.DataFrame()
     self.consensus_mapping_df = pl.DataFrame()
-    
-    self.logger.info('Merging...')
+
+    self.logger.info("Merging...")
     # parameters initialization
     params = merge_defaults()
     for key, value in kwargs.items():
@@ -482,17 +565,17 @@ def merge(self, **kwargs):
         # Collect all adducts from feature_data_list to create consensus adduct information
         all_adducts = []
         adduct_masses = {}
-        
+
         for fd in feature_data_list:
             # Get individual adduct and mass from each feature data (fd)
             adduct = fd.get("adduct")
             adduct_mass = fd.get("adduct_mass")
-            
+
             if adduct is not None:
                 all_adducts.append(adduct)
                 if adduct_mass is not None:
                     adduct_masses[adduct] = adduct_mass
-        
+
         # Calculate adduct_values for the consensus feature
         adduct_values = []
         if all_adducts:
@@ -506,9 +589,9 @@ def merge(self, **kwargs):
                     "adduct": str(adduct),
                     "count": int(count),
                     "percentage": float(round(percentage, 2)),
-                    "mass": float(mass) if mass is not None else None
+                    "mass": float(mass) if mass is not None else None,
                 })
-        
+
         # Sort adduct_values by count in descending order
         adduct_values.sort(key=lambda x: x["count"], reverse=True)  # type: ignore[arg-type,return-value]
         # Store adduct_values for use in metadata
@@ -613,7 +696,7 @@ def find_ms2(self, **kwargs):
     """
     # Reset consensus_ms2 DataFrame at the start
     self.consensus_ms2 = pl.DataFrame()
-    
+
     # parameters initialization
     params = find_ms2_defaults()
     for key, value in kwargs.items():

masster/study/save.py

@@ -21,7 +21,7 @@ def save(self, filename=None, add_timestamp=True, compress=False):
         filename (str, optional): Target file name. If None, uses default.
         add_timestamp (bool, optional): If True, appends timestamp to avoid overwriting.
                                       Default True for safety (original behavior).
-        compress (bool, optional): If True, uses compressed mode and skips 
+        compress (bool, optional): If True, uses compressed mode and skips
                                    some heavy columns for maximum speed. Default False.
     """
 
@@ -46,11 +46,11 @@ def save(self, filename=None, add_timestamp=True, compress=False):
         filename = f"{filename.replace('.study5', '')}_{timestamp}.study5"
 
     # Log file size information for performance monitoring
-    if hasattr(self, 'features_df') and not self.features_df.is_empty():
+    if hasattr(self, "features_df") and not self.features_df.is_empty():
         feature_count = len(self.features_df)
-        sample_count = len(self.samples_df) if hasattr(self, 'samples_df') and not self.samples_df.is_empty() else 0
+        sample_count = len(self.samples_df) if hasattr(self, "samples_df") and not self.samples_df.is_empty() else 0
         self.logger.info(f"Saving study with {sample_count} samples and {feature_count} features to {filename}")
-    
+
     # Use compressed mode for large datasets
     if compress:
         self._save_study5_compressed(filename)
@@ -106,7 +106,7 @@ def save_samples(self, samples=None):
         ddaobj.save()
         sample_name = sample_row.row(0, named=True)["sample_name"]
         sample_path = sample_row.row(0, named=True)["sample_path"]
-        
+
         # Find the index of this sample in the original order for features_maps
         sample_index = next(
             (
@@ -116,7 +116,7 @@ def save_samples(self, samples=None):
             ),
             None,
         )
-        
+
         # Determine where to save the featureXML file based on sample_path location
         if sample_path.endswith(".sample5"):
             # If sample_path is a .sample5 file, save featureXML in the same directory
@@ -135,7 +135,7 @@ def save_samples(self, samples=None):
                     sample_name + ".featureXML",
                 )
             self.logger.debug(f"Saving featureXML to default location: {featurexml_filename}")
-        
+
         fh = oms.FeatureXMLFile()
         if sample_index is not None and sample_index < len(self.features_maps):
             fh.store(featurexml_filename, self.features_maps[sample_index])