masster 0.5.9__tar.gz → 0.5.11__tar.gz

{masster-0.5.9 → masster-0.5.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.9
+Version: 0.5.11
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster
@@ -685,6 +685,7 @@ Requires-Dist: altair>=5.5.0
 Requires-Dist: bokeh>=3.7.3
 Requires-Dist: cmap>=0.6.2
 Requires-Dist: datashader>=0.18.1
+Requires-Dist: get-gecko-driver>=1.4
 Requires-Dist: h5py>=3.14.0
 Requires-Dist: hdbscan>=0.8.40
 Requires-Dist: holoviews>=1.21.0
@@ -703,6 +704,7 @@ Requires-Dist: scikit-learn>=1.7.1
 Requires-Dist: scipy>=1.12.0
 Requires-Dist: tqdm>=4.65.0
 Requires-Dist: umap-learn>=0.5.9.post2
+Requires-Dist: webdriver-manager>=4.0.2
 Provides-Extra: dev
 Requires-Dist: bandit>=1.7.0; extra == 'dev'
 Requires-Dist: black>=23.0.0; extra == 'dev'

{masster-0.5.9 → masster-0.5.11}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.9"
+version = "0.5.11"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }
@@ -49,6 +49,8 @@ dependencies = [
     "scikit-learn>=1.7.1",
     "umap-learn>=0.5.9.post2",
     "hdbscan>=0.8.40",
+    "get-gecko-driver>=1.4",
+    "webdriver-manager>=4.0.2",
 ]
 
 [project.optional-dependencies]

{masster-0.5.9 → masster-0.5.11}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.9"
+__version__ = "0.5.11"
 
 
 def get_version():

{masster-0.5.9 → masster-0.5.11}/src/masster/sample/adducts.py

@@ -798,8 +798,8 @@ def find_adducts(self, **kwargs):
     total_with_adducts = sum(1 for x in final_adducts if x is not None)
     total_groups = max(final_groups) if final_groups else 0
 
-    self.logger.info(
-        f"Adduct detection completed: {total_with_adducts} features with adducts in {total_groups} groups",
+    self.logger.success(
+        f"Adduct detection completed. Features with adducts: {total_with_adducts}. Adduct groups: {total_groups}.",
     )
 
     # Store parameters including the actual processed adducts list

{masster-0.5.9 → masster-0.5.11}/src/masster/sample/helpers.py

@@ -360,6 +360,7 @@ def get_eic(self, mz, mz_tol=None):
 
 def features_select(
     self,
+    uid=None,
     mz=None,
     rt=None,
     coherence=None,
@@ -369,15 +370,16 @@ def features_select(
     iso_of=None,
     has_MS2=None,
     prominence_scaled=None,
-    height_scaled=None,
     prominence=None,
+    height_scaled=None,
     height=None,
-    uids=None,
+    adduct_group=None,
 ):
     """
     Select features based on specified criteria and return the filtered DataFrame.
 
     Parameters:
+        uid: feature UID filter (list of feature UIDs, tuple for range of feature UIDs, polars/pandas DataFrame with feature_uid/feature_id column, or None for all features)
         mz: m/z range filter (tuple for range, single value for minimum)
         rt: retention time range filter (tuple for range, single value for minimum)
         coherence: chromatogram coherence filter (tuple for range, single value for minimum)
@@ -390,8 +392,7 @@ def features_select(
         height_scaled: scaled height filter (tuple for range, single value for minimum)
         prominence: prominence filter (tuple for range, single value for minimum)
         height: height filter (tuple for range, single value for minimum)
-        uids: feature UID filter (list of feature UIDs, polars/pandas DataFrame with feature_uid/feature_id column, or None for all features)
-
+        adduct_group: adduct group filter (single value for exact match, list of values for multiple groups, tuple for range, or None for all)
     Returns:
         polars.DataFrame: Filtered features DataFrame
     """
@@ -402,17 +403,29 @@ def features_select(
     feats = self.features_df.clone()
     
     # Filter by feature UIDs if provided
-    if uids is not None:
-        feature_uids_to_keep = self._get_feature_uids(features=uids, verbose=True)
-        if not feature_uids_to_keep:
-            self.logger.warning("No valid feature UIDs provided.")
-            return feats.limit(0)  # Return empty DataFrame with same structure
-        
-        feats_len_before_filter = len(feats)
-        feats = feats.filter(pl.col("feature_uid").is_in(feature_uids_to_keep))
-        self.logger.debug(
-            f"Selected features by UIDs. Features removed: {feats_len_before_filter - len(feats)}",
-        )
+    if uid is not None:
+        if isinstance(uid, tuple) and len(uid) == 2:
+            # Handle tuple as range of feature UIDs
+            min_uid, max_uid = uid
+            feats_len_before_filter = len(feats)
+            feats = feats.filter(
+                (pl.col("feature_uid") >= min_uid) & (pl.col("feature_uid") <= max_uid)
+            )
+            self.logger.debug(
+                f"Selected features by UID range ({min_uid}-{max_uid}). Features removed: {feats_len_before_filter - len(feats)}",
+            )
+        else:
+            # Handle list or DataFrame input
+            feature_uids_to_keep = self._get_feature_uids(features=uid, verbose=True)
+            if not feature_uids_to_keep:
+                self.logger.warning("No valid feature UIDs provided.")
+                return feats.limit(0)  # Return empty DataFrame with same structure
+            
+            feats_len_before_filter = len(feats)
+            feats = feats.filter(pl.col("feature_uid").is_in(feature_uids_to_keep))
+            self.logger.debug(
+                f"Selected features by UIDs. Features removed: {feats_len_before_filter - len(feats)}",
+            )
     
     if coherence is not None:
         has_coherence = "chrom_coherence" in self.features_df.columns
@@ -579,6 +592,25 @@ def features_select(
         self.logger.debug(
             f"Selected features by {height_col}. Features removed: {feats_len_before_filter - len(feats)}",
         )
+
+    if adduct_group is not None:
+        feats_len_before_filter = len(feats)
+        if "adduct_group" not in feats.columns:
+            self.logger.warning("No adduct_group data found in features.")
+        else:
+            if isinstance(adduct_group, tuple) and len(adduct_group) == 2:
+                min_adduct_group, max_adduct_group = adduct_group
+                feats = feats.filter(
+                    (pl.col("adduct_group") >= min_adduct_group) & (pl.col("adduct_group") <= max_adduct_group)
+                )
+            elif isinstance(adduct_group, list):
+                feats = feats.filter(pl.col("adduct_group").is_in(adduct_group))
+            else:
+                feats = feats.filter(pl.col("adduct_group") == adduct_group)
+            self.logger.debug(
+                f"Selected features by adduct_group. Features removed: {feats_len_before_filter - len(feats)}",
+            )
+
     if len(feats) == 0:
         self.logger.warning("No features remaining after applying selection criteria.")
     else: