masster 0.5.3__tar.gz → 0.5.4__tar.gz

{masster-0.5.3 → masster-0.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.3
+Version: 0.5.4
 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-0.5.4}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.3"
+version = "0.5.4"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.3 → masster-0.5.4}/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-0.5.4}/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-0.5.4}/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-0.5.4}/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-0.5.4}/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-0.5.4}/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-0.5.4}/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-0.5.4}/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-0.5.4}/src/masster/study/plot.py

@@ -603,7 +603,7 @@ 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"),
             ])
@@ -1421,46 +1421,60 @@ 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 +1482,36 @@ 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-0.5.4}/uv.lock

@@ -1393,7 +1393,7 @@ wheels = [
 
 [[package]]
 name = "masster"
-version = "0.5.3"
+version = "0.5.4"
 source = { editable = "." }
 dependencies = [
     { name = "alpharaw" },