masster 0.5.16__tar.gz → 0.5.18__tar.gz

{masster-0.5.16 → masster-0.5.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.16
+Version: 0.5.18
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster
@@ -681,7 +681,6 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Chemistry
 Requires-Python: >=3.11
 Requires-Dist: alpharaw>=0.4.8
-Requires-Dist: altair>=5.5.0
 Requires-Dist: bokeh>=3.7.3
 Requires-Dist: cmap>=0.6.2
 Requires-Dist: datashader>=0.18.1
@@ -698,7 +697,6 @@ Requires-Dist: pandas>=2.2.0
 Requires-Dist: panel>=1.7.0
 Requires-Dist: polars>=1.0.0
 Requires-Dist: pyopenms>=3.3.0
-Requires-Dist: pyteomics>=4.7.0
 Requires-Dist: pythonnet>=3.0.0
 Requires-Dist: scikit-learn>=1.7.1
 Requires-Dist: scipy>=1.12.0
@@ -749,10 +747,11 @@ pip install masster
 
 ```python
 import masster
-masster.wizard.execute(
+wiz = masster.wizard.create_scripts(
     source=r'..\..\folder_with_raw_data',
     folder=r'..\..folder_to_store_results'
     )
+wiz.run()
 ```
 
 This will run a wizard that should perform all key steps and save the results to the `folder`.

{masster-0.5.16 → masster-0.5.18}/README.md

@@ -19,10 +19,11 @@ pip install masster
 
 ```python
 import masster
-masster.wizard.execute(
+wiz = masster.wizard.create_scripts(
     source=r'..\..\folder_with_raw_data',
     folder=r'..\..folder_to_store_results'
     )
+wiz.run()
 ```
 
 This will run a wizard that should perform all key steps and save the results to the `folder`.

{masster-0.5.16 → masster-0.5.18}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.16"
+version = "0.5.18"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }
@@ -27,7 +27,6 @@ urls.repository = "https://github.com/zamboni-lab/masster"
 urls.documentation = "https://github.com/zamboni-lab/masster#readme"
 dependencies = [
     "alpharaw>=0.4.8",
-    "altair>=5.5.0",
     "bokeh>=3.7.3",
     "datashader>=0.18.1",
     "holoviews>=1.21.0",
@@ -40,7 +39,6 @@ dependencies = [
     "panel>=1.7.0",
     "polars>=1.0.0",
     "pyopenms>=3.3.0",
-    "pyteomics>=4.7.0",
     "pythonnet>=3.0.0",
     "scipy>=1.12.0",
     "tqdm>=4.65.0",

{masster-0.5.16 → masster-0.5.18}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.16"
+__version__ = "0.5.18"
 
 
 def get_version():

{masster-0.5.16 → masster-0.5.18}/src/masster/sample/adducts.py

@@ -403,6 +403,7 @@ def find_adducts(self, **kwargs):
 
     Main parameters (from ``find_adducts_defaults``):
     - adducts (list[str] | str | None): List of potential adduct strings or ionization mode ('pos'/'neg').
+      If None, automatically uses sample.polarity to select appropriate default adducts.
     - charge_min (int): Minimum allowed charge state (default: -4).
     - charge_max (int): Maximum allowed charge state (default: 4).
     - retention_max_diff (float): Maximum RT difference in seconds (default: 1.0).
@@ -431,6 +432,17 @@ def find_adducts(self, **kwargs):
             else:
                 self.logger.warning(f"Unknown parameter {key} ignored")
 
+    # Auto-set adducts based on sample polarity if not explicitly provided
+    if params.adducts is None and hasattr(self, 'polarity') and self.polarity is not None:
+        if self.polarity.lower() in ['positive', 'pos']:
+            params.set('adducts', 'positive', validate=True)
+            self.logger.debug(f"Auto-set adducts to 'positive' based on sample polarity: {self.polarity}")
+        elif self.polarity.lower() in ['negative', 'neg']:
+            params.set('adducts', 'negative', validate=True)
+            self.logger.debug(f"Auto-set adducts to 'negative' based on sample polarity: {self.polarity}")
+        else:
+            self.logger.debug(f"Unknown sample polarity '{self.polarity}', using default adducts")
+
     # Check if features_df exists and has data
     if not hasattr(self, "features_df") or len(self.features_df) == 0:
         self.logger.warning(

{masster-0.5.16 → masster-0.5.18}/src/masster/sample/defaults/sample_def.py

@@ -32,30 +32,42 @@ class sample_defaults:
         centroid_prominence (int): Prominence parameter for centroiding. Default is -1.
         max_points_per_spectrum (int): Maximum number of points per spectrum. Default is 50000.
         dia_window (Optional[float]): DIA window size. Default is None.
+        type (str): Acquisition type/mode. Options are 'dda', 'swath', 'ztscan', 'fia'. Default is 'dda'.
+        polarity (Optional[str]): Ionization polarity. Options are None, 'positive', 'negative'. Default is None.
     """
 
     filename: Optional[str] = None
-    ondisk: bool = False
     label: str | None = None
     log_level: str = "INFO"
     log_label: Optional[str] = ""
     log_sink: str = "sys.stdout"
-    chrom_fwhm: float = 1.0
+    ondisk: bool = False
+
+    # file and data handling settings
+    type: str = "dda"
+    polarity: str | None = None
+    
+    # chromatographic settings
+    #chrom_fwhm: float = 1.0
+    eic_mz_tol: float = 0.01
+    eic_rt_tol: float = 10.0
+    
+    # mz tolerances
     mz_tol_ms1_da: float = 0.002
     mz_tol_ms2_da: float = 0.005
     mz_tol_ms1_ppm: float = 5.0
     mz_tol_ms2_ppm: float = 10.0
+
+    # centroiding settings
     centroid_algo: str = "lmp"
     centroid_min_points_ms1: int = 5
     centroid_min_points_ms2: int = 4
     centroid_smooth: int = 5
     centroid_refine: bool = True
     centroid_prominence: int = -1
+    
+    # data retrieval settings
     max_points_per_spectrum: int = 50000
-    dia_window: float | None = None
-
-    eic_mz_tol: float = 0.01
-    eic_rt_tol: float = 10.0
 
     _param_metadata: dict[str, dict[str, Any]] = field(
         default_factory=lambda: {
@@ -178,6 +190,18 @@ class sample_defaults:
                 "min_value": 0.2,
                 "max_value": 60.0,
             },
+            "type": {
+                "dtype": str,
+                "description": "Acquisition type/mode",
+                "default": "dda",
+                "allowed_values": ["dda", "swath", "ztscan", "fia"],
+            },
+            "polarity": {
+                "dtype": "Optional[str]",
+                "description": "Ionization polarity",
+                "default": None,
+                "allowed_values": ["positive", "negative"],
+            },
         },
         repr=False,
     )

{masster-0.5.16 → masster-0.5.18}/src/masster/sample/h5.py

@@ -94,7 +94,7 @@ def _save_sample5(
             metadata_group.attrs["file_source"] = str(self.file_source)
         else:
             metadata_group.attrs["file_source"] = ""
-        if self.file_type is not None:
+        if hasattr(self, 'file_type') and self.file_type is not None:
             metadata_group.attrs["file_type"] = str(self.file_type)
         else:
             metadata_group.attrs["file_type"] = ""
@@ -287,11 +287,41 @@ def _save_sample5(
                     compression="gzip",
                 )
 
-        # Store parameters as JSON
-        if self.parameters is not None:
-            # Convert parameters dict to JSON string
-            params_json = json.dumps(self.parameters, default=str)
-            metadata_group.attrs["parameters"] = params_json
+        # Store parameters/history as JSON
+        # Always ensure we sync instance attributes to parameters before saving
+        if hasattr(self, 'parameters') and self.parameters is not None:
+            if hasattr(self, 'polarity') and self.polarity is not None:
+                self.parameters.polarity = self.polarity
+            if hasattr(self, 'type') and self.type is not None:
+                self.parameters.type = self.type
+                
+        # Prepare save data
+        save_data = {}
+        
+        # Add parameters as a dictionary
+        if hasattr(self, 'parameters') and self.parameters is not None:
+            save_data["sample"] = self.parameters.to_dict()
+            
+        # Add history data (but ensure it's JSON serializable)
+        if hasattr(self, 'history') and self.history is not None:
+            # Convert any non-JSON-serializable objects to strings/dicts
+            serializable_history = {}
+            for key, value in self.history.items():
+                if key == "sample":
+                    # Use our properly serialized parameters
+                    continue  # Skip, we'll add it from parameters above
+                try:
+                    # Test if value is JSON serializable
+                    json.dumps(value)
+                    serializable_history[key] = value
+                except (TypeError, ValueError):
+                    # Convert to string if not serializable
+                    serializable_history[key] = str(value)
+            save_data.update(serializable_history)
+            
+        # Save as JSON
+        params_json = json.dumps(save_data, indent=2)
+        metadata_group.attrs["parameters"] = params_json
 
         # Store lib and lib_match - removed (no longer saving lib data)
 
@@ -1072,6 +1102,14 @@ def _load_sample5(self, filename: str, map: bool = False):
     # set self.label to basename without extension
     if self.label is None or self.label == "":
         self.label = os.path.splitext(os.path.basename(filename))[0]
+        
+    # Sync instance attributes from loaded parameters
+    if hasattr(self, 'parameters') and self.parameters is not None:
+        if hasattr(self.parameters, 'polarity') and self.parameters.polarity is not None:
+            self.polarity = self.parameters.polarity
+        if hasattr(self.parameters, 'type') and self.parameters.type is not None:
+            self.type = self.parameters.type
+            
     self.logger.info(f"Sample loaded from {filename}")
 
 
@@ -1810,6 +1848,14 @@ def _load_sample5_study(self, filename: str, map: bool = False):
     # set self.label to basename without extension
     if self.label is None or self.label == "":
         self.label = os.path.splitext(os.path.basename(filename))[0]
+        
+    # Sync instance attributes from loaded parameters
+    if hasattr(self, 'parameters') and self.parameters is not None:
+        if hasattr(self.parameters, 'polarity') and self.parameters.polarity is not None:
+            self.polarity = self.parameters.polarity
+        if hasattr(self.parameters, 'type') and self.parameters.type is not None:
+            self.type = self.parameters.type
+            
     self.logger.info(
         f"Sample loaded successfully from {filename} (optimized for study)",
     )

{masster-0.5.16 → masster-0.5.18}/src/masster/sample/lib.py

@@ -71,7 +71,7 @@ def load_lib(self, *args, **kwargs):
     lib_load(self, *args, **kwargs)
 
 
-def lib_load(self, csvfile=None, polarity="positive"):
+def lib_load(self, csvfile=None, polarity=None):
     delta_m = {
         "[M+H]+": 1.007276,
         "[M+Na]+": 22.989218,
@@ -97,10 +97,11 @@ def lib_load(self, csvfile=None, polarity="positive"):
     """
     Load target compounds from a CSV file.
     This method reads a CSV file containing target compounds and their properties, such as m/z, retention time (RT),
-    and adducts. It filters the targets based on the specified adducts and returns a DataFrame of the targets.
+    and adducts. It filters the targets based on the specified polarity and returns a DataFrame of the targets.
     Parameters:
         csvfile (str): The path to the CSV file containing target compounds.
-        adducts (list, optional): A list of adducts to filter the targets. Default is ['[M+H]+', '[M+Na]+', '[M+K]+'].
+        polarity (str, optional): Ion polarity to filter adducts ('positive' or 'negative'). 
+                                  If None, uses the sample's polarity property. Default is None.
     Returns:
         pd.DataFrame: A DataFrame containing the filtered target compounds with columns 'mz', 'rt', 'adduct'.
     """
@@ -220,6 +221,11 @@ def lib_load(self, csvfile=None, polarity="positive"):
     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')
+    
     if polarity is not None:
         if polarity.lower() == "positive":
             self.lib = self.lib[self.lib["z"] > 0]

{masster-0.5.16 → masster-0.5.18}/src/masster/sample/load.py

@@ -73,7 +73,7 @@ def load(
         filename (str): The path to the file to load. The file must exist and have one of the following extensions:
                         .mzML, .wiff, or .raw.
         ondisk (bool, optional): Indicates whether the file should be treated as on disk. Defaults to False.
-        type (str, optional): Specifies the type of file. If provided and set to 'ztscan' (case-insensitive), the file_type
+        type (str, optional): Specifies the type of file. If provided and set to 'ztscan' (case-insensitive), the type
                                 attribute will be adjusted accordingly. Defaults to None.
         label (Any, optional): An optional label to associate with the loaded file. Defaults to None.
     Raises:
@@ -84,7 +84,7 @@ def load(
             - ".mzml": Calls _load_mzML(filename)
             - ".wiff": Calls _load_wiff(filename)
             - ".raw": Calls _load_raw(filename)
-        After loading, the file_type attribute is set to 'dda', unless the optional 'type' parameter is provided as 'ztscan',
+        After loading, the type attribute is set to 'dda', unless the optional 'type' parameter is provided as 'ztscan',
         in which case it is updated to 'ztscan'. The label attribute is updated if a label is provided.
     """
 
@@ -109,9 +109,9 @@ def load(
     else:
         raise ValueError("File must be .mzML, .wiff, *.raw, or .sample5")
 
-    self.file_type = "dda"
+    self.type = "dda"
     if type is not None and type.lower() in ["ztscan"]:
-        self.file_type = "ztscan"
+        self.type = "ztscan"
 
     if label is not None:
         self.label = label
@@ -167,9 +167,9 @@ def load_noms1(
     else:
         raise ValueError("File must be .mzML, .wiff, *.raw, or .sample5")
 
-    self.file_type = "dda"
+    self.type = "dda"
     if type is not None and type.lower() in ["ztscan"]:
-        self.file_type = "ztscan"
+        self.type = "ztscan"
 
     if label is not None:
         self.label = label
@@ -255,6 +255,7 @@ def _load_mzML(
     )
 
     tdqm_disable = self.log_level not in ["TRACE", "DEBUG", "INFO"]
+    polarity = None
     # iterate over all spectra
     for i, s in tqdm(
         enumerate(omsexp.getSpectra()),  # type: ignore[union-attr]
@@ -262,23 +263,36 @@ def _load_mzML(
         desc=f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Scans",
         disable=tdqm_disable,
     ):
+        # try to get polarity
+        if polarity is None:
+            try:
+                pol = s.getInstrumentSettings().getPolarity()
+                if pol == 1:
+                    polarity = "positive"
+                elif pol == 2:
+                    polarity = "negative"
+            except Exception:
+                pass
         # create a dict
         if s.getMSLevel() == 1:
             cycle += 1
             prec_mz = None
             precursorIsolationWindowLowerMZ = None
             precursorIsolationWindowUpperMZ = None
-            prec_intyensity = None
+            prec_inty = None
             energy = None
         else:
-            prec_mz = s.getPrecursors()[0].getMZ()
+            prec_mz = s.getPrecursors()
+            if len(prec_mz) == 0:
+                continue
+            prec_mz = prec_mz[0].getMZ()
             precursorIsolationWindowLowerMZ = s.getPrecursors()[
                 0
             ].getIsolationWindowLowerOffset()
             precursorIsolationWindowUpperMZ = s.getPrecursors()[
                 0
             ].getIsolationWindowUpperOffset()
-            prec_intyensity = s.getPrecursors()[0].getIntensity()
+            prec_inty = s.getPrecursors()[0].getIntensity()
             # Try to get collision energy from meta values first, fallback to getActivationEnergy()
             try:
                 energy = s.getPrecursors()[0].getMetaValue("collision energy")
@@ -321,7 +335,7 @@ def _load_mzML(
             "prec_mz": prec_mz,
             "prec_mz_min": precursorIsolationWindowLowerMZ,
             "prec_mz_max": precursorIsolationWindowUpperMZ,
-            "prec_inty": prec_intyensity,
+            "prec_inty": prec_inty,
             "energy": energy,
             "feature_uid": -1,
         }
@@ -367,10 +381,11 @@ def _load_mzML(
         },
         infer_schema_length=None,
     )
+    self.polarity = polarity
     self.file_interface = "oms"
     self.ms1_df = ms1_df
     self.label = os.path.basename(filename)
-    if self.file_type != "ztscan":
+    if self.type != "ztscan":
         self.analyze_dda()
 
 
@@ -401,7 +416,8 @@ 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:
         raise ValueError("Filename must be provided.")
@@ -464,6 +480,13 @@ def _load_raw(
             prec_intyensity = None
             energy = s["nce"]
 
+        # try to get polarity
+        if self.polarity is None:
+            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]
@@ -564,16 +587,10 @@ def _load_wiff(
     self,
     filename=None,
 ):
-    try:
-        # Use masster's own implementation first
-        from masster.sample.sciex import SciexWiffData as MassterSciexWiffData
+    # Use masster's own implementation first
+    from masster.sample.sciex import SciexWiffData as MassterSciexWiffData
 
-        SciexWiffDataClass = MassterSciexWiffData
-    except ImportError:
-        # Fallback to alpharaw if masster implementation fails
-        from alpharaw.sciex import SciexWiffData as AlpharawSciexWiffData
-
-        SciexWiffDataClass = AlpharawSciexWiffData
+    SciexWiffDataClass = MassterSciexWiffData
 
     if not filename:
         raise ValueError("Filename must be provided.")
@@ -610,7 +627,7 @@ def _load_wiff(
         "mz": pl.Float64,
         "inty": pl.Float64,
     }
-
+    polarity = None
     # iterate over rows of specs
     tdqm_disable = self.log_level not in ["TRACE", "DEBUG", "INFO"]
     for i, s in tqdm(
@@ -620,6 +637,13 @@ def _load_wiff(
         disable=tdqm_disable,
     ):
         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 ms_level == 1:
             cycle += 1
             prec_mz = None
@@ -723,7 +747,7 @@ def _load_wiff(
     self.file_interface = "alpharaw"
     self.label = os.path.basename(filename)
     self.ms1_df = pl.DataFrame(ms1_df_records, schema=schema)
-    if self.file_type != "ztscan":
+    if self.type != "ztscan":
         self.analyze_dda()
 
 
@@ -750,103 +774,6 @@ def _load_featureXML(
     fm = oms.FeatureMap()
     fh.load(filename, fm)
     self._oms_features_map = fm
-    """if self.features_df is None:
-        df = self._oms_features_map.get_df(export_peptide_identifications=False)
-        df = self._clean_features_df(df)
-
-        # desotope features
-        df = self._features_deisotope(df, mz_tol=0.02, rt_tol=0.5)
-
-        # update eic
-        df["chrom"] = None
-        mz_tol = 0.01
-        rt_tol = 10
-        # iterate over all rows in df
-        for i, row in df.iterrows():
-            # select data in ms1_df with mz in range [mz_start - mz_tol, mz_end + mz_tol] and rt in range [rt_start - rt_tol, rt_end + rt_tol]
-            d = self.ms1_df.filter(
-                (pl.col("rt") >= row["rt_start"] - rt_tol)
-                & (pl.col("rt") <= row["rt_end"] + rt_tol)
-                & (pl.col("mz") >= row["mz"] - mz_tol)
-                & (pl.col("mz") <= row["mz"] + mz_tol)
-            )
-            # for all unique rt values, find the maximum inty
-            eic_rt = d.group_by("rt").agg(pl.col("inty").max())
-            if len(eic_rt) < 4:
-                continue
-            eic = Chromatogram(
-                eic_rt["rt"].to_numpy(),
-                eic_rt["inty"].to_numpy(),
-                label=f"EIC mz={row['mz']:.4f}",
-                feature_start=row["rt_start"],
-                feature_end=row["rt_end"],
-                feature_apex=row["rt"],
-            ).find_peaks()
-            # set eic in df
-            df.at[i, "chrom"] = eic
-            if len(eic.peak_widths) > 0:
-                df.at[i, "chrom_coherence"] = round(eic.feature_coherence, 3)
-                df.at[i, "chrom_prominence"] = round(
-                    eic.peak_prominences[0], 3
-                )  # eic.peak_prominences[0]
-                df.at[i, "chrom_prominence_scaled"] = round(
-                    eic.peak_prominences[0] / (np.mean(eic.inty) + 1e-10), 3
-                )
-                df.at[i, "chrom_height_scaled"] = round(
-                    eic.peak_heights[0] / (np.mean(eic.inty) + 1e-10), 3
-                )
-
-        self.features_df = df"""
-
-
-'''
-def _load_mzpkl(
-    self,
-    filename="sample.mzpkl",
-    ondisk=False,
-):
-    """
-    Load the mzpkl data file, initialize the experiment attributes, and set up the file object.
-    Parameters:
-        filename (str, optional): The path to the .mzpkl file to be loaded. Defaults to "data.mzpkl".
-        ondisk (bool, optional): A flag indicating whether the data should be loaded for on-disk usage.
-                                    If True, self.ondisk is set to True and an OnDiscMSExperiment is used.
-                                    Otherwise, an MSExperiment is used.
-    Side Effects:
-        - Decompresses and unpickles the specified file.
-        - Sets attributes on self for each key in the loaded data dictionary, except for keys named 'format'.
-        - Renames the attribute 'spectra_df' to 'scans_df' if present.
-        - Initializes self.file_obj as either an OnDiscMSExperiment or MSExperiment based on the ondisk flag.
-        - Checks for an associated featureXML file (with the same base name as the input file) and loads it if found.
-    """
-
-    if ondisk is True:
-        self.ondisk = True
-
-    with bz2.BZ2File(filename, "rb") as f:
-        data = pickle.load(f)
-
-    for k, v in data.items():
-        if k in ["format"]:
-            continue
-        if k == "spectra_df":
-            k = "scans_df"
-    setattr(self, k, v)
-
-# Import and call internal sanitize function
-from masster.study.load import _sanitize
-_sanitize(self)    if self.ondisk:
-        self.file_obj = oms.OnDiscMSExperiment()
-    else:
-        self.file_obj = oms.MSExperiment()
-
-    # check if *.featureXML exists
-    featureXML = filename.replace(".mzpkl", ".featureXML")
-    if os.path.exists(featureXML):
-        self._load_featureXML(featureXML)
-
-'''
-
 
 def _wiff_to_dict(
     filename=None,

{masster-0.5.16 → masster-0.5.18}/src/masster/sample/processing.py

@@ -248,7 +248,7 @@ def get_spectrum(self, scan, **kwargs):
         spect = spect.keep_top(max_peaks)
 
     if dia_stats:
-        if self.file_type in ["ztscan", "dia"]:
+        if self.type in ["ztscan", "dia", "swath"]:
             spect = self._get_ztscan_stats(
                 spec=spect,
                 scan_uid=scan_uid,

{masster-0.5.16 → masster-0.5.18}/src/masster/sample/sample.py

@@ -240,12 +240,13 @@ class Sample:
         # Initialize label from parameters
         self.label = params.label
 
+        self.type = params.type  # dda, dia, ztscan
+        self.polarity = params.polarity  # Initialize from parameters, may be overridden during raw file loading
+
         # this is the path to the original file. It's never sample5
         self.file_source = None
         # this is the path to the object that was loaded. It could be sample5
         self.file_path = None
-        # Type of the file (e.g., mzML, RAW, WIFF, mzpkl)
-        self.file_type = None
         # Interface to handle the file operations (e.g., oms, alpharaw)
         self.file_interface = None
         # The file object once loaded, can be oms.MzMLFile or alpharaw.AlphaRawFile
@@ -327,7 +328,6 @@ class Sample:
     _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
@@ -503,6 +503,8 @@ class Sample:
         str = f"File: {os.path.basename(self.file_path)}\n"
         str += f"Path: {os.path.dirname(self.file_path)}\n"
         str += f"Source: {self.file_source}\n"
+        str += f"Type: {self.type}\n"
+        str += f"Polarity: {self.polarity}\n"
         str += f"MS1 scans: {len(self.scans_df.filter(pl.col('ms_level') == 1))}\n"
         str += f"MS2 scans: {len(self.scans_df.filter(pl.col('ms_level') == 2))}\n"
         if self.features_df is not None: