masster 0.4.14__py3-none-any.whl → 0.4.16__py3-none-any.whl

masster/study/processing.py

@@ -1,8 +1,6 @@
 from __future__ import annotations
 
 from datetime import datetime
-from collections import defaultdict
-import time
 
 import numpy as np
 import polars as pl
@@ -14,7 +12,6 @@ from masster.study.defaults import (
     align_defaults,
     find_ms2_defaults,
     integrate_defaults,
-    merge_defaults,
 )
 
 
@@ -250,905 +247,6 @@ def align(self, **kwargs):
         self.save_samples()
 
 
-def merge(self, **kwargs):
-    """Group features across samples into consensus features.
-
-    Parameters can be provided as a ``merge_defaults`` instance or as
-    individual keyword arguments; they are validated against the defaults class.
-
-    Key parameters (from ``merge_defaults``):
-        - algorithm (str): Grouping algorithm to use ('qt', 'kd', 'unlabeled', 'sequential').
-        - min_samples (int): Minimum number of samples required for a consensus feature.
-        - link_ms2 (bool): Whether to attach/link MS2 spectra to consensus features.
-        - mz_tol (float): m/z tolerance for grouping (Da).
-        - rt_tol (float): RT tolerance for grouping (seconds).
-    """
-    # Initialize
-    self._reset_consensus_data()
-    self.logger.info("Merging...")
-    
-    # Process parameters
-    params = self._process_merge_parameters(**kwargs)
-    algorithm = params.get("algorithm")
-    min_samples = params.get("min_samples")
-    link_ms2 = params.get("link_ms2")
-    mz_tol = kwargs.get("mz_tol", 0.01)
-    rt_tol = kwargs.get("rt_tol", 1.0)
-    
-    # Validate and prepare
-    self._validate_merge_inputs(algorithm)
-    
-    # Perform feature grouping using OpenMS
-    consensus_map = self._perform_feature_grouping(algorithm, params, mz_tol, rt_tol)
-    
-    # Extract consensus features and build metadata
-    self._extract_consensus_features(consensus_map, min_samples)
-    
-    # Perform adduct grouping optimization
-    self._perform_adduct_grouping(rt_tol, mz_tol)
-    
-    # Complete merge process
-    self._finalize_merge(link_ms2, min_samples)
-
-def _perform_adduct_grouping(self, rt_tol, mz_tol):
-    """Perform adduct grouping on consensus features."""
-    # Add adduct grouping and adduct_of assignment
-    if len(self.consensus_df) > 0:
-        # Get relevant columns for grouping
-        consensus_data = []
-        for row in self.consensus_df.iter_rows(named=True):
-            consensus_data.append(
-                {
-                    "consensus_uid": row["consensus_uid"],
-                    "rt": row["rt"],
-                    "adduct_mass_neutral_top": row.get("adduct_mass_neutral_top"),
-                    "adduct_top": row.get("adduct_top"),
-                    "inty_mean": row.get("inty_mean", 0),
-                },
-            )
-
-        # Use optimized adduct grouping
-        adduct_group_list, adduct_of_list = _optimized_adduct_grouping(
-            self, consensus_data, rt_tol, mz_tol
-        )
-
-        # Add the new columns to consensus_df
-        self.consensus_df = self.consensus_df.with_columns(
-            [
-                pl.Series("adduct_group", adduct_group_list, dtype=pl.Int64),
-                pl.Series("adduct_of", adduct_of_list, dtype=pl.Int64),
-            ],
-        )
-
-def _finalize_merge(self, link_ms2, min_samples):
-    """Complete the merge process with final calculations and cleanup."""
-    # Validate min_samples parameter
-    if min_samples is None:
-        min_samples = 1
-    if min_samples < 1:
-        min_samples = int(min_samples * len(self.samples_df))
-
-    # Validate that min_samples doesn't exceed the number of samples
-    if min_samples > len(self.samples_df):
-        self.logger.warning(
-            f"min_samples ({min_samples}) exceeds the number of samples ({len(self.samples_df)}). "
-            f"Setting min_samples to {len(self.samples_df)}.",
-        )
-        min_samples = len(self.samples_df)
-
-    # Filter out consensus features with less than min_samples features
-    l1 = len(self.consensus_df)
-    self.consensus_df = self.consensus_df.filter(
-        pl.col("number_samples") >= min_samples,
-    )
-    self.logger.debug(
-        f"Filtered {l1 - len(self.consensus_df)} consensus features with less than {min_samples} samples.",
-    )
-    
-    # Filter out consensus mapping with less than min_samples features
-    self.consensus_mapping_df = self.consensus_mapping_df.filter(
-        pl.col("consensus_uid").is_in(self.consensus_df["consensus_uid"].to_list()),
-    )
-
-    # Calculate the completeness of the consensus map
-    if len(self.consensus_df) > 0 and len(self.samples_df) > 0:
-        c = (
-            len(self.consensus_mapping_df)
-            / len(self.consensus_df)
-            / len(self.samples_df)
-        )
-        self.logger.info(
-            f"Merging completed. Consensus features: {len(self.consensus_df)}. Completeness: {c:.2f}.",
-        )
-    else:
-        self.logger.warning(
-            f"Merging completed with empty result. Consensus features: {len(self.consensus_df)}. "
-            f"This may be due to min_samples ({min_samples}) being too high for the available data.",
-        )
-    
-    if link_ms2:
-        self.find_ms2()
-
-def _reset_consensus_data(self):
-    """Reset consensus-related DataFrames at the start of merge."""
-    self.consensus_df = pl.DataFrame()
-    self.consensus_ms2 = pl.DataFrame()
-    self.consensus_mapping_df = pl.DataFrame()
-
-def _process_merge_parameters(self, **kwargs):
-    """Process and validate merge parameters."""
-    params = merge_defaults()
-    for key, value in kwargs.items():
-        if isinstance(value, merge_defaults):
-            params = value
-            self.logger.debug("Using provided merge_defaults parameters")
-        else:
-            if hasattr(params, key):
-                if params.set(key, value, validate=True):
-                    self.logger.debug(f"Updated parameter {key} = {value}")
-                else:
-                    self.logger.warning(
-                        f"Failed to set parameter {key} = {value} (validation failed)",
-                    )
-            else:
-                self.logger.debug(f"Unknown parameter {key} ignored")
-    
-    # Store parameters in the Study object
-    self.store_history(["merge"], params.to_dict())
-    self.logger.debug("Parameters stored to merge")
-    return params
-
-def _validate_merge_inputs(self, algorithm):
-    """Validate merge inputs and provide warnings for performance."""
-    if len(self.samples_df) > 200 and algorithm == "qt":
-        self.logger.warning(
-            "Using QT for large datasets is NOT recommended [O(n²)], consider using KDTree instead [O(n log n)].",
-        )
-    
-    # Check that features_maps is not empty
-    if not self.features_maps or len(self.features_maps) == 0:
-        self.load_features()
-
-def _perform_feature_grouping(self, algorithm, params, mz_tol, rt_tol):
-    """Perform feature grouping using OpenMS algorithms."""
-    params_oms = oms.Param()
-    ## TODO expose these
-
-    feature_grouper: object  # Use generic type for different OpenMS algorithms
-    match algorithm.lower():
-        case "kd":
-            feature_grouper = oms.FeatureGroupingAlgorithmKD()
-            self.logger.debug("Merging features with KDTree...")
-            params_oms.setValue("mz_unit", "Da")
-            params_oms.setValue("nr_partitions", len(self.samples_df))
-
-            params_oms.setValue("warp:enabled", "true")
-            params_oms.setValue("warp:rt_tol", rt_tol)
-            params_oms.setValue("warp:mz_tol", mz_tol)
-
-            params_oms.setValue("link:rt_tol", rt_tol)
-            params_oms.setValue("link:mz_tol", mz_tol)
-        case "unlabeled":
-            feature_grouper = oms.FeatureGroupingAlgorithmUnlabeled()
-            self.logger.debug("Merging features with Unlabelled algorithm...")
-            params_oms.setValue("second_nearest_gap", 2.0)
-            params_oms.setValue("ignore_charge", "true")
-            params_oms.setValue("distance_RT:max_difference", rt_tol * 3)
-            params_oms.setValue("distance_MZ:max_difference", mz_tol * 3)
-            params_oms.setValue("distance_MZ:unit", "Da")
-        case "sequential":
-            self.logger.debug(
-                "Merging features sequentially with Unlabelled algorithm...",
-            )
-            params_oms.setValue("second_nearest_gap", 2.0)
-            params_oms.setValue("ignore_charge", "true")
-            params_oms.setValue("distance_RT:max_difference", rt_tol * 3)
-            params_oms.setValue("distance_MZ:max_difference", mz_tol * 3)
-            params_oms.setValue("distance_MZ:unit", "Da")
-        case "qt":
-            feature_grouper = oms.FeatureGroupingAlgorithmQT()
-            self.logger.debug("Grouping features with QT...")
-            params_oms.setValue("nr_partitions", len(self.samples_df))
-            params_oms.setValue("ignore_charge", "true")
-            params_oms.setValue("distance_RT:max_difference", rt_tol * 3)
-            params_oms.setValue("distance_MZ:max_difference", mz_tol * 3)
-            params_oms.setValue("distance_MZ:unit", "Da")
-    
-    self.logger.debug(f"Parameters for feature grouping: {params_oms}")
-    
-    # Create consensus map and set up file descriptions
-    consensus_map = oms.ConsensusMap()
-    file_descriptions = consensus_map.getColumnHeaders()  # type: ignore
-    feature_maps = self.features_maps
-    for i, feature_map in enumerate(feature_maps):
-        file_description = file_descriptions.get(i, oms.ColumnHeader())
-        file_description.filename = self.samples_df.row(i, named=True)["sample_name"]
-        file_description.size = feature_map.size()
-        file_description.unique_id = feature_map.getUniqueId()
-        file_descriptions[i] = file_description
-
-    consensus_map.setColumnHeaders(file_descriptions)  # type: ignore
-
-    # Execute the grouping algorithm
-    match algorithm.lower():
-        case "sequential":
-            # set the reference map to self.alignment_ref_index
-            if self.alignment_ref_index is None:
-                # pick the feature map with the most features as reference
-                self.alignment_ref_index = max(
-                    range(len(self.features_maps)),
-                    key=lambda i: self.features_maps[i].size(),
-                )
-            feature_grouper = oms.FeatureGroupingAlgorithmUnlabeled()
-            feature_grouper.setParameters(params_oms)
-            feature_grouper.setReference(self.alignment_ref_index)
-            self.logger.debug(f"Sequential mode: reference map = {self.alignment_ref_index}")
-            
-            # Group features sequentially
-            for i in range(len(feature_maps)):
-                if i == self.alignment_ref_index:
-                    continue
-                temp_feature_maps = [feature_maps[self.alignment_ref_index], feature_maps[i]]
-                temp_consensus_map = oms.ConsensusMap()
-                feature_grouper.group(temp_feature_maps, temp_consensus_map)
-                # Merge temp_consensus_map into consensus_map
-                # This is a simplified approach - proper sequential grouping would be more complex
-        case _:
-            feature_grouper.setParameters(params_oms)
-            feature_grouper.group(feature_maps, consensus_map)
-    
-    return consensus_map
-
-def _extract_consensus_features(self, consensus_map, min_samples):
-    """Extract consensus features and build metadata."""
-    # create a dict to map uid to feature_uid using self.features_df
-    feature_uid_map = {
-        row["feature_id"]: row["feature_uid"]
-        for row in self.features_df.iter_rows(named=True)
-    }
-    imax = consensus_map.size()
-
-    self.logger.info(f"Merging completed with {imax} consensus features.")
-
-    # Pre-build fast lookup tables for features_df data using optimized approach
-    features_lookup = _optimized_feature_lookup(self, self.features_df)
-
-    # create a list to store the consensus mapping
-    consensus_mapping = []
-    metadata_list = []
-
-    tqdm_disable = self.log_level not in ["TRACE", "DEBUG"]
-
-    for i, feature in enumerate(
-        tqdm(
-            consensus_map,
-            total=imax,
-            disable=tqdm_disable,
-            desc=f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Extract metadata",
-        ),
-    ):
-        # get all features in the feature map with the same unique id as the consensus feature
-        features_list = feature.getFeatureList()
-        uids = []
-        feature_data_list = []
-
-        for _j, f in enumerate(features_list):
-            fuid = str(f.getUniqueId())
-            if fuid not in feature_uid_map:
-                # this is a feature that was removed but is still in the feature maps
-                continue
-            fuid = feature_uid_map[fuid]
-            consensus_mapping.append(
-                {
-                    "consensus_uid": i,
-                    "sample_uid": f.getMapIndex() + 1,
-                    "feature_uid": fuid,
-                },
-            )
-            uids.append(fuid)
-
-            # Get feature data from lookup instead of DataFrame filtering
-            feature_data = features_lookup.get(fuid)
-            if feature_data:
-                feature_data_list.append(feature_data)
-
-        if not feature_data_list:
-            # Skip this consensus feature if no valid features found
-            continue
-
-        # Compute statistics using vectorized operations on collected data
-        # Convert to numpy arrays for faster computation
-        rt_values = np.array(
-            [fd.get("rt", 0) for fd in feature_data_list if fd.get("rt") is not None],
-        )
-        mz_values = np.array(
-            [fd.get("mz", 0) for fd in feature_data_list if fd.get("mz") is not None],
-        )
-        rt_start_values = np.array(
-            [
-                fd.get("rt_start", 0)
-                for fd in feature_data_list
-                if fd.get("rt_start") is not None
-            ],
-        )
-        rt_end_values = np.array(
-            [
-                fd.get("rt_end", 0)
-                for fd in feature_data_list
-                if fd.get("rt_end") is not None
-            ],
-        )
-        rt_delta_values = np.array(
-            [
-                fd.get("rt_delta", 0)
-                for fd in feature_data_list
-                if fd.get("rt_delta") is not None
-            ],
-        )
-        mz_start_values = np.array(
-            [
-                fd.get("mz_start", 0)
-                for fd in feature_data_list
-                if fd.get("mz_start") is not None
-            ],
-        )
-        mz_end_values = np.array(
-            [
-                fd.get("mz_end", 0)
-                for fd in feature_data_list
-                if fd.get("mz_end") is not None
-            ],
-        )
-        inty_values = np.array(
-            [
-                fd.get("inty", 0)
-                for fd in feature_data_list
-                if fd.get("inty") is not None
-            ],
-        )
-        coherence_values = np.array(
-            [
-                fd.get("chrom_coherence", 0)
-                for fd in feature_data_list
-                if fd.get("chrom_coherence") is not None
-            ],
-        )
-        prominence_values = np.array(
-            [
-                fd.get("chrom_prominence", 0)
-                for fd in feature_data_list
-                if fd.get("chrom_prominence") is not None
-            ],
-        )
-        prominence_scaled_values = np.array(
-            [
-                fd.get("chrom_prominence_scaled", 0)
-                for fd in feature_data_list
-                if fd.get("chrom_prominence_scaled") is not None
-            ],
-        )
-        height_scaled_values = np.array(
-            [
-                fd.get("chrom_height_scaled", 0)
-                for fd in feature_data_list
-                if fd.get("chrom_height_scaled") is not None
-            ],
-        )
-        iso_values = np.array(
-            [fd.get("iso", 0) for fd in feature_data_list if fd.get("iso") is not None],
-        )
-        charge_values = np.array(
-            [
-                fd.get("charge", 0)
-                for fd in feature_data_list
-                if fd.get("charge") is not None
-            ],
-        )
-
-        # adduct_values
-        # Collect all adducts from feature_data_list to create consensus adduct information
-        # Only consider adducts that are in study._get_adducts() plus items with '?'
-        all_adducts = []
-        adduct_masses = {}
-
-        # Get valid adducts from study._get_adducts()
-        valid_adducts = set()
-        try:
-            study_adducts_df = self._get_adducts()
-            if not study_adducts_df.is_empty():
-                valid_adducts.update(study_adducts_df["name"].to_list())
-        except Exception as e:
-            self.logger.warning(f"Could not retrieve study adducts: {e}")
-
-        # Always allow '?' adducts
-        valid_adducts.add("?")
-
-        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:
-                # Only include adducts that are valid (from study._get_adducts() or contain '?')
-                if adduct in valid_adducts or "?" in adduct:
-                    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:
-            adduct_counts = {
-                adduct: all_adducts.count(adduct) for adduct in set(all_adducts)
-            }
-            total_count = sum(adduct_counts.values())
-            for adduct, count in adduct_counts.items():
-                percentage = (count / total_count) * 100 if total_count > 0 else 0
-                # Store as list with [name, num, %] format for the adducts column
-                adduct_values.append(
-                    [
-                        str(adduct),
-                        int(count),
-                        float(round(percentage, 2)),
-                    ],
-                )
-
-        # Sort adduct_values by count in descending order
-        adduct_values.sort(key=lambda x: x[1], reverse=True)  # Sort by count (index 1)
-        # Store adduct_values for use in metadata
-        consensus_adduct_values = adduct_values
-
-        # Extract top adduct information for new columns
-        adduct_top = None
-        adduct_charge_top = None
-        adduct_mass_neutral_top = None
-        adduct_mass_shift_top = None
-
-        if consensus_adduct_values:
-            top_adduct_name = consensus_adduct_values[0][0]  # Get top adduct name
-            adduct_top = top_adduct_name
-
-            # Parse adduct information to extract charge and mass shift
-            # Handle "?" as "H" and parse common adduct formats
-            if top_adduct_name == "?" or top_adduct_name == "[M+?]+":
-                adduct_charge_top = 1
-                adduct_mass_shift_top = 1.007825  # H mass
-            elif top_adduct_name == "[M+?]-":
-                adduct_charge_top = -1
-                adduct_mass_shift_top = -1.007825  # -H mass
-            else:
-                # Try to get charge and mass shift from study._get_adducts()
-                adduct_found = False
-                try:
-                    study_adducts_df = self._get_adducts()
-                    if not study_adducts_df.is_empty():
-                        # Look for exact match in study adducts
-                        matching_adduct = study_adducts_df.filter(
-                            pl.col("name") == top_adduct_name,
-                        )
-                        if not matching_adduct.is_empty():
-                            adduct_row = matching_adduct.row(0, named=True)
-                            adduct_charge_top = adduct_row["charge"]
-                            adduct_mass_shift_top = adduct_row["mass_shift"]
-                            adduct_found = True
-                except Exception as e:
-                    self.logger.warning(
-                        f"Could not lookup adduct in study adducts: {e}",
-                    )
-
-                if not adduct_found:
-                    # Fallback to regex parsing
-                    import re
-
-                    # Pattern for adducts like [M+H]+, [M-H]-, [M+Na]+, etc.
-                    pattern = r"\[M([+\-])([A-Za-z0-9]+)\]([0-9]*)([+\-])"
-                    match = re.match(pattern, top_adduct_name)
-
-                    if match:
-                        sign = match.group(1)
-                        element = match.group(2)
-                        multiplier_str = match.group(3)
-                        charge_sign = match.group(4)
-
-                        multiplier = int(multiplier_str) if multiplier_str else 1
-                        charge = multiplier if charge_sign == "+" else -multiplier
-                        adduct_charge_top = charge
-
-                        # Calculate mass shift based on element
-                        element_masses = {
-                            "H": 1.007825,
-                            "Na": 22.989769,
-                            "K": 38.963708,
-                            "NH4": 18.033823,
-                            "Li": 7.016930,
-                            "Cl": 34.969401,
-                            "Br": 78.918885,
-                            "HCOO": 44.998201,
-                            "CH3COO": 59.013851,
-                            "H2O": 18.010565,
-                        }
-
-                        base_mass = element_masses.get(
-                            element,
-                            1.007825,
-                        )  # Default to H if unknown
-                        mass_shift = (
-                            base_mass * multiplier
-                            if sign == "+"
-                            else -base_mass * multiplier
-                        )
-                        adduct_mass_shift_top = mass_shift
-                    else:
-                        # Default fallback
-                        adduct_charge_top = 1
-                        adduct_mass_shift_top = 1.007825
-        else:
-            # No valid adducts found - assign default based on study polarity
-            study_polarity = getattr(self, "polarity", "positive")
-            if study_polarity in ["negative", "neg"]:
-                # Negative mode default
-                adduct_top = "[M-?]1-"
-                adduct_charge_top = -1
-                adduct_mass_shift_top = -1.007825  # -H mass (loss of proton)
-            else:
-                # Positive mode default (includes 'positive', 'pos', or any other value)
-                adduct_top = "[M+?]1+"
-                adduct_charge_top = 1
-                adduct_mass_shift_top = 1.007825  # H mass (gain of proton)
-
-            # Create a single default adduct entry in the adducts list for consistency
-            consensus_adduct_values = [[adduct_top, 1, 100.0]]
-
-        # Calculate neutral mass from consensus mz (for both cases)
-        consensus_mz = (
-            round(float(np.mean(mz_values)), 4) if len(mz_values) > 0 else 0.0
-        )
-        if adduct_charge_top and adduct_mass_shift_top is not None:
-            adduct_mass_neutral_top = (
-                consensus_mz * abs(adduct_charge_top) - adduct_mass_shift_top
-            )
-
-        # Calculate number of MS2 spectra
-        ms2_count = 0
-        for fd in feature_data_list:
-            ms2_scans = fd.get("ms2_scans")
-            if ms2_scans is not None:
-                ms2_count += len(ms2_scans)
-
-        metadata_list.append(
-            {
-                "consensus_uid": int(i),  # "consensus_id": i,
-                "consensus_id": str(feature.getUniqueId()),
-                "quality": round(float(feature.getQuality()), 3),
-                "number_samples": len(feature_data_list),
-                # "number_ext": int(len(features_list)),
-                "rt": round(float(np.mean(rt_values)), 4)
-                if len(rt_values) > 0
-                else 0.0,
-                "mz": round(float(np.mean(mz_values)), 4)
-                if len(mz_values) > 0
-                else 0.0,
-                "rt_min": round(float(np.min(rt_values)), 3)
-                if len(rt_values) > 0
-                else 0.0,
-                "rt_max": round(float(np.max(rt_values)), 3)
-                if len(rt_values) > 0
-                else 0.0,
-                "rt_mean": round(float(np.mean(rt_values)), 3)
-                if len(rt_values) > 0
-                else 0.0,
-                "rt_start_mean": round(float(np.mean(rt_start_values)), 3)
-                if len(rt_start_values) > 0
-                else 0.0,
-                "rt_end_mean": round(float(np.mean(rt_end_values)), 3)
-                if len(rt_end_values) > 0
-                else 0.0,
-                "rt_delta_mean": round(float(np.ptp(rt_delta_values)), 3)
-                if len(rt_delta_values) > 0
-                else 0.0,
-                "mz_min": round(float(np.min(mz_values)), 4)
-                if len(mz_values) > 0
-                else 0.0,
-                "mz_max": round(float(np.max(mz_values)), 4)
-                if len(mz_values) > 0
-                else 0.0,
-                "mz_mean": round(float(np.mean(mz_values)), 4)
-                if len(mz_values) > 0
-                else 0.0,
-                "mz_start_mean": round(float(np.mean(mz_start_values)), 4)
-                if len(mz_start_values) > 0
-                else 0.0,
-                "mz_end_mean": round(float(np.mean(mz_end_values)), 4)
-                if len(mz_end_values) > 0
-                else 0.0,
-                "inty_mean": round(float(np.mean(inty_values)), 0)
-                if len(inty_values) > 0
-                else 0.0,
-                "bl": -1.0,
-                "chrom_coherence_mean": round(float(np.mean(coherence_values)), 3)
-                if len(coherence_values) > 0
-                else 0.0,
-                "chrom_prominence_mean": round(float(np.mean(prominence_values)), 0)
-                if len(prominence_values) > 0
-                else 0.0,
-                "chrom_prominence_scaled_mean": round(
-                    float(np.mean(prominence_scaled_values)),
-                    3,
-                )
-                if len(prominence_scaled_values) > 0
-                else 0.0,
-                "chrom_height_scaled_mean": round(
-                    float(np.mean(height_scaled_values)),
-                    3,
-                )
-                if len(height_scaled_values) > 0
-                else 0.0,
-                "iso_mean": round(float(np.mean(iso_values)), 2)
-                if len(iso_values) > 0
-                else 0.0,
-                "charge_mean": round(float(np.mean(charge_values)), 2)
-                if len(charge_values) > 0
-                else 0.0,
-                "number_ms2": int(ms2_count),
-                "adducts": consensus_adduct_values
-                if consensus_adduct_values
-                else [],  # Ensure it's always a list
-                # New columns for top-ranked adduct information
-                "adduct_top": adduct_top,
-                "adduct_charge_top": adduct_charge_top,
-                "adduct_mass_neutral_top": round(adduct_mass_neutral_top, 6)
-                if adduct_mass_neutral_top is not None
-                else None,
-                "adduct_mass_shift_top": round(adduct_mass_shift_top, 6)
-                if adduct_mass_shift_top is not None
-                else None,
-                # New columns for top-scoring identification results
-                "id_top_name": None,
-                "id_top_class": None,
-                "id_top_adduct": None,
-                "id_top_score": None,
-            },
-        )
-
-    consensus_mapping_df = pl.DataFrame(consensus_mapping)
-    # remove all rows in consensus_mapping_df where consensus_id is not in self.featured_df['uid']
-    l1 = len(consensus_mapping_df)
-    consensus_mapping_df = consensus_mapping_df.filter(
-        pl.col("feature_uid").is_in(self.features_df["feature_uid"].to_list()),
-    )
-    self.logger.debug(
-        f"Filtered {l1 - len(consensus_mapping_df)} orphan features from maps.",
-    )
-    self.consensus_mapping_df = consensus_mapping_df
-    self.consensus_df = pl.DataFrame(metadata_list, strict=False)
-
-    if min_samples is None:
-        min_samples = 1
-    if min_samples < 1:
-        min_samples = int(min_samples * len(self.samples_df))
-
-    # Validate that min_samples doesn't exceed the number of samples
-    if min_samples > len(self.samples_df):
-        self.logger.warning(
-            f"min_samples ({min_samples}) exceeds the number of samples ({len(self.samples_df)}). "
-            f"Setting min_samples to {len(self.samples_df)}.",
-        )
-        min_samples = len(self.samples_df)
-
-    # filter out consensus features with less than min_samples features
-    l1 = len(self.consensus_df)
-    self.consensus_df = self.consensus_df.filter(
-        pl.col("number_samples") >= min_samples,
-    )
-    self.logger.debug(
-        f"Filtered {l1 - len(self.consensus_df)} consensus features with less than {min_samples} samples.",
-    )
-    # filter out consensus mapping with less than min_samples features
-    self.consensus_mapping_df = self.consensus_mapping_df.filter(
-        pl.col("consensus_uid").is_in(self.consensus_df["consensus_uid"].to_list()),
-    )
-
-    self.consensus_map = consensus_map
-
-
-def _optimized_feature_lookup(study_obj, features_df):
-    """
-    Optimized feature lookup creation using Polars operations.
-    """
-    study_obj.logger.debug("Creating optimized feature lookup...")
-    start_time = time.time()
-    
-    # Use Polars select for faster conversion
-    feature_columns = [
-        "feature_uid", "rt", "mz", "rt_start", "rt_end", "rt_delta", 
-        "mz_start", "mz_end", "inty", "chrom_coherence", "chrom_prominence", 
-        "chrom_prominence_scaled", "chrom_height_scaled", "iso", "charge", 
-        "ms2_scans", "adduct", "adduct_mass"
-    ]
-    
-    # Filter to only existing columns
-    existing_columns = [col for col in feature_columns if col in features_df.columns]
-    
-    # Convert to dictionary more efficiently
-    selected_df = features_df.select(existing_columns)
-    
-    features_lookup = {}
-    for row in selected_df.iter_rows(named=True):
-        feature_uid = row["feature_uid"]
-        features_lookup[feature_uid] = {k: v for k, v in row.items() if k != "feature_uid"}
-    
-    lookup_time = time.time() - start_time
-    if len(features_lookup) > 50000:
-        study_obj.logger.debug(f"Feature lookup created in {lookup_time:.2f}s for {len(features_lookup)} features")
-    return features_lookup
-
-
-def _optimized_adduct_grouping(study_obj, consensus_data, rt_tol, mz_tol):
-    """
-    Optimized O(n log n) adduct grouping using spatial indexing.
-    
-    Args:
-        study_obj: Study object with logger
-        consensus_data: List of consensus feature dictionaries
-        rt_tol: RT tolerance in minutes
-        mz_tol: m/z tolerance in Da
-        
-    Returns:
-        Tuple of (adduct_group_list, adduct_of_list)
-    """
-    if not consensus_data:
-        return [], []
-    
-    n_features = len(consensus_data)
-    if n_features > 1000:
-        study_obj.logger.info(f"Optimizing adduct grouping for {n_features} consensus features...")
-    
-    start_time = time.time()
-    
-    # Build spatial index using RT and neutral mass as coordinates
-    features_by_mass = defaultdict(list)
-    mass_bin_size = mz_tol * 2  # 2x tolerance for conservative binning
-    
-    valid_features = []
-    for feature in consensus_data:
-        consensus_uid = feature["consensus_uid"]
-        rt = feature["rt"]
-        neutral_mass = feature.get("adduct_mass_neutral_top")
-        intensity = feature.get("inty_mean", 0)
-        adduct = feature.get("adduct_top", "")
-        
-        if neutral_mass is not None:
-            mass_bin = int(neutral_mass / mass_bin_size)
-            features_by_mass[mass_bin].append((consensus_uid, rt, neutral_mass, intensity, adduct))
-            valid_features.append((consensus_uid, rt, neutral_mass, intensity, adduct, mass_bin))
-    
-    # Union-Find for efficient grouping
-    class UnionFind:
-        def __init__(self, n):
-            self.parent = list(range(n))
-            self.rank = [0] * n
-        
-        def find(self, x):
-            if self.parent[x] != x:
-                self.parent[x] = self.find(self.parent[x])
-            return self.parent[x]
-        
-        def union(self, x, y):
-            px, py = self.find(x), self.find(y)
-            if px == py:
-                return
-            if self.rank[px] < self.rank[py]:
-                px, py = py, px
-            self.parent[py] = px
-            if self.rank[px] == self.rank[py]:
-                self.rank[px] += 1
-    
-    uid_to_idx = {feature[0]: i for i, feature in enumerate(valid_features)}
-    uf = UnionFind(len(valid_features))
-    
-    # Find groups using spatial index
-    checked_pairs = set()
-    for i, (uid1, rt1, mass1, inty1, adduct1, bin1) in enumerate(valid_features):
-        for bin_offset in [-1, 0, 1]:
-            check_bin = bin1 + bin_offset
-            if check_bin not in features_by_mass:
-                continue
-                
-            for uid2, rt2, mass2, inty2, adduct2 in features_by_mass[check_bin]:
-                if uid1 >= uid2:
-                    continue
-                
-                pair = (min(uid1, uid2), max(uid1, uid2))
-                if pair in checked_pairs:
-                    continue
-                checked_pairs.add(pair)
-                
-                mass_diff = abs(mass1 - mass2)
-                rt_diff = abs(rt1 - rt2) / 60.0  # Convert to minutes
-                
-                if mass_diff <= mz_tol and rt_diff <= rt_tol:
-                    j = uid_to_idx[uid2]
-                    uf.union(i, j)
-    
-    # Extract groups
-    groups_by_root = defaultdict(list)
-    for i, (uid, rt, mass, inty, adduct, _) in enumerate(valid_features):
-        root = uf.find(i)
-        groups_by_root[root].append((uid, rt, mass, inty, adduct))
-    
-    groups = {}
-    group_id = 1
-    assigned_groups = {}
-    
-    for group_members in groups_by_root.values():
-        member_uids = [uid for uid, _, _, _, _ in group_members]
-        
-        for uid in member_uids:
-            assigned_groups[uid] = group_id
-        groups[group_id] = member_uids
-        group_id += 1
-    
-    # Handle features without neutral mass
-    for feature in consensus_data:
-        uid = feature["consensus_uid"]
-        if uid not in assigned_groups:
-            assigned_groups[uid] = group_id
-            groups[group_id] = [uid]
-            group_id += 1
-    
-    # Determine adduct_of for each group
-    group_adduct_of = {}
-    for grp_id, member_uids in groups.items():
-        best_uid = None
-        best_priority = -1
-        best_intensity = 0
-        
-        for uid in member_uids:
-            feature_data = next((f for f in consensus_data if f["consensus_uid"] == uid), None)
-            if not feature_data:
-                continue
-                
-            adduct = feature_data.get("adduct_top", "")
-            intensity = feature_data.get("inty_mean", 0)
-            
-            priority = 0
-            if adduct and ("[M+H]" in adduct or adduct == "H" or adduct == "?"):
-                priority = 3
-            elif adduct and "[M-H]" in adduct:
-                priority = 2
-            elif adduct and "M" in adduct:
-                priority = 1
-            
-            if priority > best_priority or (priority == best_priority and intensity > best_intensity):
-                best_uid = uid
-                best_priority = priority
-                best_intensity = intensity
-        
-        group_adduct_of[grp_id] = best_uid if best_uid else member_uids[0]
-    
-    # Build final lists in same order as consensus_data
-    adduct_group_list = []
-    adduct_of_list = []
-    
-    for feature in consensus_data:
-        uid = feature["consensus_uid"]
-        group = assigned_groups.get(uid, 0)
-        adduct_of = group_adduct_of.get(group, uid)
-        
-        adduct_group_list.append(group)
-        adduct_of_list.append(adduct_of)
-    
-    grouping_time = time.time() - start_time
-    if n_features > 1000:
-        study_obj.logger.info(f"Adduct grouping completed in {grouping_time:.2f}s ({len(groups)} groups)")
-    
-    return adduct_group_list, adduct_of_list
-
-
-# Backward compatibility alias
-find_consensus = merge
-
-
 def find_ms2(self, **kwargs):
     """
     Links MS2 spectra to consensus features and stores the result in self.consensus_ms2.