masster 0.5.3__tar.gz → 0.5.5__tar.gz

{masster-0.5.3 → masster-0.5.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.3
+Version: 0.5.5
 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-0.5.3 → masster-0.5.5}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.3"
+version = "0.5.5"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.3 → masster-0.5.5}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.4"
+__version__ = "0.5.5"
 
 
 def get_version():

{masster-0.5.3 → masster-0.5.5}/src/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-0.5.3 → masster-0.5.5}/src/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-0.5.3 → masster-0.5.5}/src/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-0.5.3 → masster-0.5.5}/src/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:

{masster-0.5.3 → masster-0.5.5}/src/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-0.5.3 → masster-0.5.5}/src/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-0.5.3 → masster-0.5.5}/src/masster/sample/save.py

@@ -411,6 +411,11 @@ def export_mgf(
             rt_str = f"{rt:.2f}"
             mz_str = f"{mz:.4f}"
 
+            # Initialize charge for this feature
+            charge = preferred_charge
+            if row["charge"] is not None and row["charge"] != 0:
+                charge = row["charge"]
+
             # Skip features without MS2 data (unless include_all_ms1 is True, but we already handled MS1 above)
             if row["ms2_scans"] is None:
                 skip = skip + 1

{masster-0.5.3 → masster-0.5.5}/src/masster/study/h5.py

@@ -304,6 +304,30 @@ def _save_object_columns_optimized(group, df, object_cols, logger, chunk_size):
                     serialized_chunk.append(item.to_json())
                 else:
                     serialized_chunk.append("None")
+        elif col_name == "iso":
+            # Handle isotope patterns (numpy arrays with [mz, intensity] data)
+            for item in chunk_data:
+                if item is not None:
+                    try:
+                        # Convert numpy array to nested list for JSON serialization
+                        serialized_chunk.append(json.dumps(item.tolist()))
+                    except (AttributeError, TypeError):
+                        # Fallback for non-numpy data
+                        serialized_chunk.append(json.dumps(list(item) if hasattr(item, '__iter__') else []))
+                else:
+                    serialized_chunk.append("None")
+        elif col_name == "ms1_spec":
+            # Handle MS1 spectra patterns (numpy arrays with [mz, intensity] data)
+            for item in chunk_data:
+                if item is not None:
+                    try:
+                        # Convert numpy array to nested list for JSON serialization
+                        serialized_chunk.append(json.dumps(item.tolist()))
+                    except (AttributeError, TypeError):
+                        # Fallback for non-numpy data
+                        serialized_chunk.append(json.dumps(list(item) if hasattr(item, '__iter__') else []))
+                else:
+                    serialized_chunk.append("None")
         else:
             logger.warning(
                 f"Unknown object column '{col_name}', using default serialization",
@@ -564,6 +588,34 @@ def _save_dataframe_column_legacy(
                 else:
                     data_as_str.append("None")
             group.create_dataset(col, data=data_as_str, compression=compression)
+        elif col == "iso":
+            # Handle isotope patterns (numpy arrays with [mz, intensity] data)
+            data_as_json_strings = []
+            for item in data:
+                if item is not None:
+                    try:
+                        # Convert numpy array to nested list for JSON serialization
+                        data_as_json_strings.append(json.dumps(item.tolist()))
+                    except (AttributeError, TypeError):
+                        # Fallback for non-numpy data
+                        data_as_json_strings.append(json.dumps(list(item) if hasattr(item, '__iter__') else []))
+                else:
+                    data_as_json_strings.append("None")
+            group.create_dataset(col, data=data_as_json_strings, **optimal_compression)
+        elif col == "ms1_spec":
+            # Handle MS1 spectra patterns (numpy arrays with [mz, intensity] data)
+            data_as_json_strings = []
+            for item in data:
+                if item is not None:
+                    try:
+                        # Convert numpy array to nested list for JSON serialization
+                        data_as_json_strings.append(json.dumps(item.tolist()))
+                    except (AttributeError, TypeError):
+                        # Fallback for non-numpy data
+                        data_as_json_strings.append(json.dumps(list(item) if hasattr(item, '__iter__') else []))
+                else:
+                    data_as_json_strings.append("None")
+            group.create_dataset(col, data=data_as_json_strings, **optimal_compression)
         else:
             logger.warning(
                 f"Unexpectedly, column '{col}' has dtype '{dtype}'. Implement serialization for this column.",
@@ -666,6 +718,24 @@ def _reconstruct_object_column(data_col, col_name: str):
                             },
                         )
                 reconstructed_data.append(converted_adducts)
+            elif col_name == "iso":
+                # Handle isotope patterns (numpy arrays with [mz, intensity] data)
+                try:
+                    import numpy as np
+                    iso_data = json.loads(item)
+                    # Convert back to numpy array
+                    reconstructed_data.append(np.array(iso_data) if iso_data else None)
+                except (json.JSONDecodeError, ValueError, ImportError):
+                    reconstructed_data.append(None)
+            elif col_name == "ms1_spec":
+                # Handle MS1 spectra patterns (numpy arrays with [mz, intensity] data)
+                try:
+                    import numpy as np
+                    ms1_spec_data = json.loads(item)
+                    # Convert back to numpy array
+                    reconstructed_data.append(np.array(ms1_spec_data) if ms1_spec_data else None)
+                except (json.JSONDecodeError, ValueError, ImportError):
+                    reconstructed_data.append(None)
             else:
                 # Unknown object column
                 reconstructed_data.append(None)

{masster-0.5.3 → masster-0.5.5}/src/masster/study/helpers.py

@@ -500,7 +500,7 @@ def align_reset(self):
 # TODO I don't get this param
 def get_consensus(self, quant="chrom_area"):
     if self.consensus_df is None:
-        self.logger.error("No consensus map found.")
+        self.logger.error("No consensus found.")
         return None
 
     # Convert Polars DataFrame to pandas for this operation since the result is used for export
@@ -613,7 +613,7 @@ def get_gaps_matrix(self, uids=None, samples=None):
     import polars as pl
     
     if self.consensus_df is None or self.consensus_df.is_empty():
-        self.logger.error("No consensus map found.")
+        self.logger.error("No consensus found.")
         return None
     
     if self.consensus_mapping_df is None or self.consensus_mapping_df.is_empty():

{masster-0.5.3 → masster-0.5.5}/src/masster/study/plot.py

@@ -564,6 +564,10 @@ def plot_consensus_2d(
     Parameters:
         filename (str, optional): Path to save the plot
         colorby (str): Column name to use for color mapping (default: "number_samples")
+                      Automatically detects if column contains categorical (string) or 
+                      numeric data and applies appropriate color mapping:
+                      - Categorical: Uses factor_cmap with distinct colors and legend
+                      - Numeric: Uses LinearColorMapper with continuous colorbar
         sizeby (str): Column name to use for size mapping (default: "inty_mean")
         markersize (int): Base marker size (default: 6)
         scaling (str): Controls whether points scale with zoom. Options:
@@ -603,7 +607,7 @@ def plot_consensus_2d(
                 pl.when(
                     (pl.col(sizeby).is_not_null()) & (pl.col(sizeby).is_finite()) & (pl.col(sizeby) > 0),
                 )
-                .then((pl.col(sizeby).log10() * markersize / 12).pow(2))
+                .then((pl.col(sizeby).log10() * markersize / 12).pow(1.5))
                 .otherwise(markersize)
                 .alias("markersize"),
             ])
@@ -645,12 +649,13 @@ def plot_consensus_2d(
     from bokeh.models import HoverTool
     from bokeh.models import LinearColorMapper
     from bokeh.io.export import export_png
+    from bokeh.transform import factor_cmap
 
     try:
         from bokeh.models import ColorBar  # type: ignore[attr-defined]
     except ImportError:
         from bokeh.models.annotations import ColorBar
-    from bokeh.palettes import viridis
+    from bokeh.palettes import viridis, Category20
 
     # Import cmap for colormap handling
     from cmap import Colormap
@@ -695,61 +700,144 @@ def plot_consensus_2d(
         self.logger.warning(f"Could not interpret colormap '{cmap}': {e}, falling back to viridis")
         palette = viridis(256)
 
-    color_mapper = LinearColorMapper(
-        palette=palette,
-        low=data[colorby].min(),
-        high=data[colorby].max(),
+    # Check if colorby column contains categorical data (string/object)
+    colorby_values = data[colorby].to_list()
+    is_categorical = (
+        data_pd[colorby].dtype in ["object", "string", "category"] or
+        isinstance(colorby_values[0], str) if colorby_values else False
     )
+    
+    if is_categorical:
+        # Handle categorical coloring
+        # Use natural order of unique values - don't sort to preserve correct legend mapping
+        # Sorting would break the correspondence between legend labels and point colors
+        unique_values = [v for v in data_pd[colorby].unique() if v is not None]
+        
+        if len(unique_values) <= 20:
+            palette = Category20[min(20, max(3, len(unique_values)))]
+        else:
+            # For many categories, use a subset of the viridis palette
+            palette = viridis(min(256, len(unique_values)))
+        
+        color_mapper = factor_cmap(colorby, palette, unique_values)
+    else:
+        # Handle numeric coloring with LinearColorMapper
+        color_mapper = LinearColorMapper(
+            palette=palette,
+            low=data[colorby].min(),
+            high=data[colorby].max(),
+        )
     # scatter plot rt vs mz
     p = bp.figure(
         width=width,
         height=height,
-        title="Consensus map",
+        title=f"Consensus features, colored by {colorby}",
     )
-    p.xaxis.axis_label = "Retention Time (min)"
-    p.yaxis.axis_label = "m/z"
+    p.xaxis.axis_label = "RT [s]"
+    p.yaxis.axis_label = "m/z [Th]"
     scatter_renderer: Any = None
-    if scaling.lower() in ["dyn", "dynamic"]:
-        # Calculate appropriate radius for dynamic scaling based on data range
-        rt_range = data["rt"].max() - data["rt"].min()
-        mz_range = data["mz"].max() - data["mz"].min()
-        # Use a fraction of the smaller dimension for radius, similar to sample plotting
-        dynamic_radius = min(rt_range, mz_range) * 0.0005 * markersize
+    if is_categorical:
+        # For categorical data, create separate renderers for each category
+        # This enables proper legend interactivity where each category can be toggled independently
+        unique_values = [v for v in data_pd[colorby].unique() if v is not None]
+        
+        if len(unique_values) <= 20:
+            palette = Category20[min(20, max(3, len(unique_values)))]
+        else:
+            palette = viridis(min(256, len(unique_values)))
+        
+        # Create a separate renderer for each category
+        for i, category in enumerate(unique_values):
+            # Filter data for this category
+            category_data = data.filter(pl.col(colorby) == category)
+            category_data_pd = category_data.to_pandas()
+            category_source = bp.ColumnDataSource(category_data_pd)
+            
+            color = palette[i % len(palette)]
+            
+            if scaling.lower() in ["dyn", "dynamic"]:
+                # Calculate appropriate radius for dynamic scaling
+                rt_range = data["rt"].max() - data["rt"].min()
+                mz_range = data["mz"].max() - data["mz"].min()
+                dynamic_radius = min(rt_range, mz_range) * 0.0005 * markersize
+                
+                renderer = p.circle(
+                    x="rt",
+                    y="mz", 
+                    radius=dynamic_radius,
+                    fill_color=color,
+                    line_color=None,
+                    alpha=alpha,
+                    source=category_source,
+                    legend_label=str(category),
+                )
+            else:
+                renderer = p.scatter(
+                    x="rt",
+                    y="mz",
+                    size="markersize", 
+                    fill_color=color,
+                    line_color=None,
+                    alpha=alpha,
+                    source=category_source,
+                    legend_label=str(category),
+                )
+        
+        # No single scatter_renderer for categorical data
+        scatter_renderer = None
         
-        scatter_renderer = p.circle(
-            x="rt",
-            y="mz",
-            radius=dynamic_radius,
-            fill_color={"field": colorby, "transform": color_mapper},
-            line_color=None,
-            alpha=alpha,
-            source=source,
-        )
     else:
-        scatter_renderer = p.scatter(
-            x="rt",
-            y="mz",
-            size="markersize",
-            fill_color={"field": colorby, "transform": color_mapper},
-            line_color=None,
-            alpha=alpha,
-            source=source,
-        )
+        # Handle numeric coloring - single renderer with color mapping
+        if scaling.lower() in ["dyn", "dynamic"]:
+            # Calculate appropriate radius for dynamic scaling
+            rt_range = data["rt"].max() - data["rt"].min()
+            mz_range = data["mz"].max() - data["mz"].min()
+            dynamic_radius = min(rt_range, mz_range) * 0.0005 * markersize
+            
+            scatter_renderer = p.circle(
+                x="rt",
+                y="mz",
+                radius=dynamic_radius,
+                fill_color={"field": colorby, "transform": color_mapper},
+                line_color=None,
+                alpha=alpha,
+                source=source,
+            )
+        else:
+            scatter_renderer = p.scatter(
+                x="rt",
+                y="mz",
+                size="markersize",
+                fill_color={"field": colorby, "transform": color_mapper},
+                line_color=None,
+                alpha=alpha,
+                source=source,
+            )
     # add hover tool
-    # Start with base tooltips
+    # Start with base tooltips - rt and mz moved to top, removed consensus_id and iso_mean
     tooltips = [
+        ("rt", "@rt"),
+        ("mz", "@mz"),
         ("consensus_uid", "@consensus_uid"),
-        ("consensus_id", "@consensus_id"),
         ("number_samples", "@number_samples"),
         ("number_ms2", "@number_ms2"),
-        ("rt", "@rt"),
-        ("mz", "@mz"),
         ("inty_mean", "@inty_mean"),
-        ("iso_mean", "@iso_mean"),
         ("coherence_mean", "@chrom_coherence_mean"),
         ("prominence_scaled_mean", "@chrom_prominence_scaled_mean"),
     ]
     
+    # Add adduct_top if it exists in data
+    if "adduct_top" in data.columns:
+        tooltips.append(("adduct_top", "@adduct_top"))
+    
+    # Add id_top_name if it exists in data
+    if "id_top_name" in data.columns:
+        tooltips.append(("id_top_name", "@id_top_name"))
+    
+    # Add id_top_adduct if it exists in data
+    if "id_top_adduct" in data.columns:
+        tooltips.append(("id_top_adduct", "@id_top_adduct"))
+    
     # Add id_top_* columns if they exist and have non-null values
     id_top_columns = ["id_top_name", "id_top_class", "id_top_adduct", "id_top_score"]
     for col in id_top_columns:
@@ -764,19 +852,28 @@ def plot_consensus_2d(
     
     hover = HoverTool(
         tooltips=tooltips,
-        renderers=[scatter_renderer],
     )
+    # For categorical data, hover will work on all renderers automatically
+    # For numeric data, specify the single renderer
+    if not is_categorical and scatter_renderer:
+        hover.renderers = [scatter_renderer]
+    
     p.add_tools(hover)
 
-    # add colorbar
-    color_bar = ColorBar(
-        color_mapper=color_mapper,
-        label_standoff=12,
-        location=(0, 0),
-        title=colorby,
-        ticker=BasicTicker(desired_num_ticks=8),
-    )
-    p.add_layout(color_bar, "right")
+    # add colorbar only for numeric data (LinearColorMapper)
+    if not is_categorical:
+        color_bar = ColorBar(
+            color_mapper=color_mapper,
+            label_standoff=12,
+            location=(0, 0),
+            title=colorby,
+            ticker=BasicTicker(desired_num_ticks=8),
+        )
+        p.add_layout(color_bar, "right")
+    else:
+        # For categorical data, configure the legend that was automatically created
+        p.legend.location = "top_right"
+        p.legend.click_policy = "hide"
 
     if filename is not None:
         # Convert relative paths to absolute paths using study folder as base
@@ -1421,46 +1518,60 @@ def plot_rt_correction(
     p.xaxis.axis_label = f"Retention Time ({rt_unit})"
     p.yaxis.axis_label = "RT - RT_original (s)"
 
-    samples_info = None
+    # Create sample name lookup dictionary from samples_df (all in Polars)
+    sample_names_dict = {}
     if hasattr(self, "samples_df") and self.samples_df is not None:
         try:
-            samples_info = self.samples_df.to_pandas()
+            sample_name_mapping = (
+                self.samples_df
+                .filter(pl.col("sample_uid").is_in(sample_uids))
+                .select(["sample_uid", "sample_name"])
+            )
+            sample_names_dict = dict(zip(
+                sample_name_mapping["sample_uid"].to_list(), 
+                sample_name_mapping["sample_name"].to_list()
+            ))
         except Exception:
-            samples_info = None
+            pass
 
     renderers = []
 
-    # Iterate samples and build curves
-    for uid in sample_uids:
-        # Select features belonging to this sample
-        try:
-            if "sample_uid" in self.features_df.columns:
-                sample_feats = self.features_df.filter(pl.col("sample_uid") == uid)
-            elif "sample_name" in self.features_df.columns:
-                sample_feats = self.features_df.filter(pl.col("sample_name") == uid)
-            else:
-                self.logger.debug("No sample identifier column in features_df; skipping sample filtering")
-                continue
-        except Exception as e:
-            self.logger.debug(f"Error filtering features for sample {uid}: {e}")
-            continue
+    # Check sample identifier column
+    if "sample_uid" not in self.features_df.columns:
+        if "sample_name" in self.features_df.columns:
+            sample_id_col = "sample_name"
+        else:
+            self.logger.debug("No sample identifier column in features_df")
+            return
+    else:
+        sample_id_col = "sample_uid"
 
-        if sample_feats.is_empty():
-            continue
+    # OPTIMIZED: Filter once, group once instead of per-sample filtering
+    try:
+        # Filter all data once for selected samples and required conditions
+        all_sample_feats = self.features_df.filter(
+            pl.col(sample_id_col).is_in(sample_uids)
+        )
+        
+        if all_sample_feats.is_empty():
+            self.logger.warning("No features found for the selected samples.")
+            return
 
-        # Filter to only use features with filled==False
-        if "filled" in sample_feats.columns:
-            sample_feats = sample_feats.filter(~pl.col("filled"))
-            if sample_feats.is_empty():
-                continue
+        # Filter to only use features with filled==False if column exists
+        if "filled" in all_sample_feats.columns:
+            all_sample_feats = all_sample_feats.filter(~pl.col("filled"))
+            if all_sample_feats.is_empty():
+                self.logger.warning("No non-filled features found for the selected samples.")
+                return
 
-        # Stay in Polars - much faster than pandas conversion!
-        if "rt" not in sample_feats.columns or "rt_original" not in sample_feats.columns:
-            continue
+        # Check required columns
+        if "rt" not in all_sample_feats.columns or "rt_original" not in all_sample_feats.columns:
+            self.logger.error("Required columns 'rt' or 'rt_original' not found in features_df.")
+            return
 
-        # Filter nulls and add delta column in Polars
-        sample_feats = (
-            sample_feats
+        # Filter nulls, add delta column, and sort - all in one operation
+        all_sample_feats = (
+            all_sample_feats
             .filter(
                 pl.col("rt").is_not_null() &
                 pl.col("rt_original").is_not_null()
@@ -1468,33 +1579,36 @@ def plot_rt_correction(
             .with_columns([
                 (pl.col("rt") - pl.col("rt_original")).alias("delta")
             ])
-            .sort("rt")
+            .sort([sample_id_col, "rt"])
         )
 
-        if sample_feats.is_empty():
-            continue
+        if all_sample_feats.is_empty():
+            self.logger.warning("No valid RT data found for the selected samples.")
+            return
 
-        # Extract arrays directly from Polars
-        rt = sample_feats["rt"].to_numpy()
-        delta = sample_feats["delta"].to_numpy()
+        # Group by sample and process each group (much faster than individual filtering)
+        for (sample_uid,), sample_group in all_sample_feats.group_by(sample_id_col):
+            if sample_group.is_empty():
+                continue
 
-        sample_name = str(uid)
-        if samples_info is not None:
-            try:
-                row = samples_info[samples_info["sample_uid"] == uid]
-                if not row.empty:
-                    sample_name = row.iloc[0].get("sample_name", sample_name)
-            except Exception:
-                pass
+            # Extract arrays directly from Polars
+            rt = sample_group["rt"].to_numpy()
+            delta = sample_group["delta"].to_numpy()
 
-        color = color_map.get(uid, "#000000")
+            # Get sample name efficiently from pre-built dictionary
+            sample_name = sample_names_dict.get(sample_uid, str(sample_uid))
+            color = color_map.get(sample_uid, "#000000")
 
-        data = {"rt": rt, "delta": delta, "sample": [sample_name] * len(rt), "sample_color": [color] * len(rt)}
-        src = ColumnDataSource(data)
+            data = {"rt": rt, "delta": delta, "sample": [sample_name] * len(rt), "sample_color": [color] * len(rt)}
+            src = ColumnDataSource(data)
 
-        r_line = p.line("rt", "delta", source=src, line_width=1, color=color)
-        p.scatter("rt", "delta", source=src, size=2, color=color, alpha=0.6)
-        renderers.append(r_line)
+            r_line = p.line("rt", "delta", source=src, line_width=1, color=color)
+            p.scatter("rt", "delta", source=src, size=2, color=color, alpha=0.6)
+            renderers.append(r_line)
+
+    except Exception as e:
+        self.logger.error(f"Error in optimized RT correction plotting: {e}")
+        return
 
     if not renderers:
         self.logger.warning("No RT correction curves to plot for the selected samples.")

{masster-0.5.3 → masster-0.5.5}/src/masster/study/processing.py

@@ -341,9 +341,6 @@ def _integrate_chrom_impl(self, **kwargs):
     uids = params.get("uids")
     rt_tol = params.get("rt_tol")
 
-    if self.consensus_map is None:
-        self.logger.error("No consensus map found.")
-        return
     if uids is None:
         # get all consensus_id from consensus_df
         ids = self.consensus_df["consensus_uid"].to_list()

{masster-0.5.3 → masster-0.5.5}/src/masster/wizard/wizard.py

@@ -455,6 +455,9 @@ class Wizard:
         params_lines.append('    # === Processing Parameters ===')
         params_lines.append(f'    "adducts": {params_dict.get("adducts", [])!r},  # Adduct specifications for feature detection and annotation')
         params_lines.append(f'    "detector_type": {params_dict.get("detector_type", "unknown")!r},  # MS detector type ("orbitrap", "tof", "unknown")')
+        params_lines.append(f'    "noise": {params_dict.get("noise", 50.0)},  # Noise threshold for feature detection')
+        params_lines.append(f'    "chrom_fwhm": {params_dict.get("chrom_fwhm", 0.5)},  # Chromatographic peak full width at half maximum (seconds)')
+        params_lines.append(f'    "chrom_peak_snr": {params_dict.get("chrom_peak_snr", 5.0)},  # Minimum signal-to-noise ratio for chromatographic peaks')
         params_lines.append('')
         
         # Alignment & Merging
@@ -643,6 +646,7 @@ class Wizard:
             '        # Step 4: Add sample5 files to study',
             '        print("\\nStep 4/7: Adding samples to study...")',
             '        study.add(str(Path(PARAMS[\'folder\']) / "*.sample5"))',
+            '        study.features_filter(study.features_select(chrom_coherence=0.1, chrom_prominence_scaled=1))',
             '        ',
             '        # Step 5: Core processing',
             '        print("\\nStep 5/7: Processing...")',
@@ -651,29 +655,14 @@ class Wizard:
             '            rt_tol=PARAMS[\'rt_tol\']',
             '        )',
             '        ',
-            '        # Merge and create consensus features',
-            '        # Use optimized method for large datasets (>500 samples)',
-            '        num_samples = len(study.samples)',
-            '        if num_samples > 500:',
-            '            print(f"  Large dataset detected ({num_samples} samples), using optimized qt_chunked + hierarchical method")',
-            '            study.merge(',
-            '                method="qt_chunked",',
-            '                dechunking="hierarchical",', 
-            '                min_samples=PARAMS[\'min_samples_per_feature\'],',
-            '                threads=PARAMS[\'num_cores\'],',
-            '                rt_tol=PARAMS[\'rt_tol\'],',
-            '                mz_tol=PARAMS[\'mz_tol\']',
-            '            )',
-            '        else:',
-            '            print(f"  Using standard merge method for {num_samples} samples")',
-            '            study.merge(',
-            '                min_samples=PARAMS[\'min_samples_per_feature\'],',
-            '                threads=PARAMS[\'num_cores\'],',
-            '                rt_tol=PARAMS[\'rt_tol\'],',
-            '                mz_tol=PARAMS[\'mz_tol\']',
-            '            )',
+            '        study.merge(',
+            '            method="qt",',
+            '            min_samples=PARAMS[\'min_samples_per_feature\'],',
+            '            threads=PARAMS[\'num_cores\'],',
+            '            rt_tol=PARAMS[\'rt_tol\'],'
+            '        )',
             '        study.find_iso()',
-            '        study.fill(min_samples_rel=0.0)',
+            '        study.fill()',
             '        study.integrate()',    
             '        ',
             '        # Step 6/7: Saving results',
@@ -689,8 +678,8 @@ class Wizard:
             '        study.plot_consensus_2d(filename="consensus.png")',
             '        study.plot_alignment(filename="alignment.html")',
             '        study.plot_alignment(filename="alignment.png")',
-            '        study.plot_pca(filename="pca.html")',
-            '        study.plot_pca(filename="pca.png")',
+            '        study.plot_samples_pca(filename="pca.html")',
+            '        study.plot_samples_pca(filename="pca.png")',
             '        study.plot_bpc(filename="bpc.html")',
             '        study.plot_bpc(filename="bpc.png")',
             '        study.plot_rt_correction(filename="rt_correction.html")',

{masster-0.5.3 → masster-0.5.5}/uv.lock

@@ -1393,7 +1393,7 @@ wheels = [
 
 [[package]]
 name = "masster"
-version = "0.5.3"
+version = "0.5.5"
 source = { editable = "." }
 dependencies = [
     { name = "alpharaw" },