masster 0.5.22__py3-none-any.whl → 0.5.24__py3-none-any.whl

masster/sample/helpers.py

@@ -113,9 +113,7 @@ def _get_scan_uids(self, scans=None, verbose=True):
         scans_uids = self.scans_df.get_column("scan_uid").to_list()
     elif isinstance(scans, list):
         # if scans is a list, ensure all elements are valid scan_uids
-        scans_uids = [
-            s for s in scans if s in self.scans_df.get_column("scan_uid").to_list()
-        ]
+        scans_uids = [s for s in scans if s in self.scans_df.get_column("scan_uid").to_list()]
         if verbose and not scans_uids:
             self.logger.error("No valid scan_uids provided.")
 
@@ -340,9 +338,7 @@ def get_eic(self, mz, mz_tol=None):
             return None
 
         # Aggregate intensities per retention time. Use sum in case multiple points per rt.
-        chrom = (
-            matches.group_by("rt").agg([pl.col("inty").sum().alias("inty")]).sort("rt")
-        )
+        chrom = matches.group_by("rt").agg([pl.col("inty").sum().alias("inty")]).sort("rt")
 
         # Attach to Sample
         self.chrom_df = chrom
@@ -401,16 +397,14 @@ def features_select(
         # self.logger.info("No features found. R")
         return
     feats = self.features_df.clone()
-    
+
     # Filter by feature UIDs if provided
     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)
-            )
+            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)}",
             )
@@ -420,13 +414,13 @@ def features_select(
             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
         if not has_coherence:
@@ -437,8 +431,7 @@ def features_select(
             if isinstance(coherence, tuple) and len(coherence) == 2:
                 min_coherence, max_coherence = coherence
                 feats = feats.filter(
-                    (pl.col("chrom_coherence") >= min_coherence)
-                    & (pl.col("chrom_coherence") <= max_coherence),
+                    (pl.col("chrom_coherence") >= min_coherence) & (pl.col("chrom_coherence") <= max_coherence),
                 )
             else:
                 feats = feats.filter(pl.col("chrom_coherence") >= coherence)
@@ -489,8 +482,7 @@ def features_select(
         if isinstance(rt_delta, tuple) and len(rt_delta) == 2:
             min_rt_delta, max_rt_delta = rt_delta
             feats = feats.filter(
-                (pl.col("rt_delta") >= min_rt_delta)
-                & (pl.col("rt_delta") <= max_rt_delta),
+                (pl.col("rt_delta") >= min_rt_delta) & (pl.col("rt_delta") <= max_rt_delta),
             )
         else:
             feats = feats.filter(pl.col("rt_delta") >= rt_delta)
@@ -567,8 +559,7 @@ def features_select(
         if isinstance(prominence, tuple) and len(prominence) == 2:
             min_prominence, max_prominence = prominence
             feats = feats.filter(
-                (pl.col("chrom_prominence") >= min_prominence)
-                & (pl.col("chrom_prominence") <= max_prominence),
+                (pl.col("chrom_prominence") >= min_prominence) & (pl.col("chrom_prominence") <= max_prominence),
             )
         else:
             feats = feats.filter(pl.col("chrom_prominence") >= prominence)
@@ -579,9 +570,7 @@ def features_select(
     if height is not None:
         feats_len_before_filter = len(feats)
         # Check if chrom_height column exists, if not use chrom_height_scaled
-        height_col = (
-            "chrom_height" if "chrom_height" in feats.columns else "chrom_height_scaled"
-        )
+        height_col = "chrom_height" if "chrom_height" in feats.columns else "chrom_height_scaled"
         if isinstance(height, tuple) and len(height) == 2:
             min_height, max_height = height
             feats = feats.filter(
@@ -617,6 +606,7 @@ def features_select(
         self.logger.info(f"Selected features. Features remaining: {len(feats)}")
     return feats
 
+
 '''
 def _features_sync(self):
     """
@@ -725,6 +715,7 @@ def _features_sync(self):
         self.logger.error(f"Error during feature synchronization: {e}")
 '''
 
+
 def features_delete(self, features: list | None = None):
     """
     Delete features from both self.features_df and self._oms_features_map based on a list of feature UIDs.
@@ -841,10 +832,7 @@ def _delete_ms2(self):
 
     # Update scans_df to remove feature_uid association for linked MS2 spectra
     self.scans_df = self.scans_df.with_columns(
-        pl.when(pl.col("ms_level") == 2)
-        .then(None)
-        .otherwise(pl.col("feature_uid"))
-        .alias("feature_uid"),
+        pl.when(pl.col("ms_level") == 2).then(None).otherwise(pl.col("feature_uid")).alias("feature_uid"),
     )
     self.logger.info("MS2 spectra unlinked from features.")
 
@@ -930,11 +918,7 @@ def features_filter(self, features):
             )
 
     # Update scans_df to remove feature_uid associations for deleted features
-    if (
-        hasattr(self, "scans_df")
-        and self.scans_df is not None
-        and feature_uids_to_delete
-    ):
+    if hasattr(self, "scans_df") and self.scans_df is not None and feature_uids_to_delete:
         self.scans_df = self.scans_df.with_columns(
             pl.when(pl.col("feature_uid").is_in(feature_uids_to_delete))
             .then(None)

masster/sample/lib.py

@@ -221,11 +221,11 @@ def lib_load(self, csvfile=None, polarity=None):
     self.lib = self.lib.where(pd.notnull(self.lib), None)
     # find all elements == nan and replace them with None
     self.lib = self.lib.replace({np.nan: None})
-    
+
     # Use sample.polarity if polarity parameter is None
     if polarity is None:
-        polarity = getattr(self, 'polarity', 'positive')
-    
+        polarity = getattr(self, "polarity", "positive")
+
     if polarity is not None:
         if polarity.lower() == "positive":
             self.lib = self.lib[self.lib["z"] > 0]

masster/sample/load.py

@@ -13,11 +13,6 @@ Key Features:
 - **Error Handling**: Comprehensive error reporting for file loading issues.
 - **Raw Data Processing**: Handle centroided and profile data with signal smoothing.
 
-Dependencies:
-- `pyopenms`: For standard mass spectrometry file format support.
-- `polars` and `pandas`: For efficient data handling and manipulation.
-- `numpy`: For numerical array operations.
-
 Functions:
 - `load()`: Main file loading function with format detection.
 - `_load_mzML()`: Specialized mzML file loader.
@@ -55,7 +50,9 @@ warnings.filterwarnings("ignore", message="Warning: OPENMS_DATA_PATH.*", categor
 
 # Import pyopenms with suppressed warnings
 with warnings.catch_warnings():
-    warnings.filterwarnings("ignore", message=".*OPENMS_DATA_PATH environment variable already exists.*", category=UserWarning)
+    warnings.filterwarnings(
+        "ignore", message=".*OPENMS_DATA_PATH environment variable already exists.*", category=UserWarning
+    )
     warnings.filterwarnings("ignore", message="Warning: OPENMS_DATA_PATH.*", category=UserWarning)
     import pyopenms as oms
 
@@ -163,6 +160,7 @@ def load_noms1(
         _load_raw(self, filename)
     elif filename.lower().endswith(".sample5"):
         from masster.sample.h5 import _load_sample5_study
+
         _load_sample5_study(self, filename)  # Use optimized version for study loading
     else:
         raise ValueError("File must be .mzML, .wiff, *.raw, or .sample5")
@@ -286,12 +284,8 @@ def _load_mzML(
             if len(prec_mz) == 0:
                 continue
             prec_mz = prec_mz[0].getMZ()
-            precursorIsolationWindowLowerMZ = s.getPrecursors()[
-                0
-            ].getIsolationWindowLowerOffset()
-            precursorIsolationWindowUpperMZ = s.getPrecursors()[
-                0
-            ].getIsolationWindowUpperOffset()
+            precursorIsolationWindowLowerMZ = s.getPrecursors()[0].getIsolationWindowLowerOffset()
+            precursorIsolationWindowUpperMZ = s.getPrecursors()[0].getIsolationWindowUpperOffset()
             prec_inty = s.getPrecursors()[0].getIntensity()
             # Try to get collision energy from meta values first, fallback to getActivationEnergy()
             try:
@@ -416,7 +410,7 @@ def _load_raw(
         - Updates instance attributes including self.file_path, self.file_obj, self.file_interface, and self.label.
         - Initiates further analysis by invoking analyze_dda().
     """
-    #from alpharaw.thermo import ThermoRawData
+    # from alpharaw.thermo import ThermoRawData
     from masster.sample.thermo import ThermoRawData
 
     if not filename:
@@ -482,11 +476,11 @@ def _load_raw(
 
         # try to get polarity
         if self.polarity is None:
-            if s['polarity'] == 'positive':
-                self.polarity = 'positive'
-            elif s['polarity'] == 'negative':
-                self.polarity = 'negative'
-                
+            if s["polarity"] == "positive":
+                self.polarity = "positive"
+            elif s["polarity"] == "negative":
+                self.polarity = "negative"
+
         peak_start_idx = s["peak_start_idx"]
         peak_stop_idx = s["peak_stop_idx"]
         peaks = raw_data.peak_df.loc[peak_start_idx : peak_stop_idx - 1]
@@ -639,11 +633,11 @@ def _load_wiff(
         ms_level = s["ms_level"]
         # try to get polarity
         if polarity is None:
-            if s['polarity'] == 'positive':
-                polarity = 'positive'
-            elif s['polarity'] == 'negative':
-                polarity = 'negative'
-            
+            if s["polarity"] == "positive":
+                polarity = "positive"
+            elif s["polarity"] == "negative":
+                polarity = "negative"
+
         if ms_level == 1:
             cycle += 1
             prec_mz = None
@@ -745,6 +739,7 @@ def _load_wiff(
     self.file_source = filename
     self.file_obj = raw_data
     self.file_interface = "alpharaw"
+    self.polarity = polarity
     self.label = os.path.basename(filename)
     self.ms1_df = pl.DataFrame(ms1_df_records, schema=schema)
     if self.type != "ztscan":
@@ -775,6 +770,7 @@ def _load_featureXML(
     fh.load(filename, fm)
     self._oms_features_map = fm
 
+
 def _wiff_to_dict(
     filename=None,
 ):
@@ -1161,9 +1157,7 @@ def chrom_extract(
             scan_uid = trace["scan_uid"]
             # find all ms1 data with scan_uid and mz between q1-mz_tol and q1+mz_tol
             d = self.ms1_df.filter(
-                (pl.col("scan_uid").is_in(scan_uid))
-                & (pl.col("mz") >= q1 - mz_tol)
-                & (pl.col("mz") <= q1 + mz_tol),
+                (pl.col("scan_uid").is_in(scan_uid)) & (pl.col("mz") >= q1 - mz_tol) & (pl.col("mz") <= q1 + mz_tol),
             )
             # for all unique rt values, find the maximum inty
             eic_rt = d.group_by("rt").agg(pl.col("inty").max())
@@ -1182,9 +1176,7 @@ def chrom_extract(
             scan_uid = trace["scan_uid"]
             # find all ms2 data with scan_uid and mz between q3-mz_tol and q3+mz_tol
             d = self.ms2data.filter(
-                (pl.col("scan_uid").is_in(scan_uid))
-                & (pl.col("mz") >= q3 - mz_tol)
-                & (pl.col("mz") <= q3 + mz_tol),
+                (pl.col("scan_uid").is_in(scan_uid)) & (pl.col("mz") >= q3 - mz_tol) & (pl.col("mz") <= q3 + mz_tol),
             )
             # for all unique rt values, find the maximum inty
             eic_rt = d.group_by("rt").agg(pl.col("inty").max())