masster 0.2.5__py3-none-any.whl → 0.3.0__py3-none-any.whl

masster/sample/sample.py

@@ -1,387 +1,391 @@
-"""
-sample.py
-
-This module provides tools for processing and analyzing Data-Dependent Acquisition (DDA) mass spectrometry data.
-It defines the `Sample` class, which offers methods to load, process, analyze, and visualize mass spectrometry data
-from various file formats, including mzML, Thermo RAW, and Sciex WIFF formats.
-
-Key Features:
-- **File Handling**: Load and save data in multiple formats.
-- **Feature Detection**: Detect and process mass spectrometry features.
-- **Spectrum Analysis**: Retrieve and analyze MS1/MS2 spectra.
-- **Visualization**: Generate interactive and static plots for spectra and chromatograms.
-- **Statistics**: Compute and export detailed DDA run statistics.
-
-Dependencies:
-- `pyopenms`: For file handling and feature detection.
-- `polars` and `pandas`: For data manipulation.
-- `numpy`: For numerical computations.
-- `bokeh`, `panel`, `holoviews`, `datashader`: For interactive visualizations.
-
-Classes:
-- `Sample`: Main class for handling DDA data, providing methods for data import, processing, and visualization.
-
-Example Usage:
-```python
-from masster.sample import Sample
-
-sample = Sample(file="example.mzML")
-sample.find_features()
-sample.plot_2d()
-```
-
-"""
-
-import importlib
-import os
-import sys
-
-import polars as pl
-
-from masster._version import get_version
-
-from masster.sample.defaults.sample_def import sample_defaults
-
-# Sample-specific imports
-from masster.sample.h5 import _load_sample5
-from masster.sample.h5 import _save_sample5
-from masster.sample.helpers import _delete_ms2
-from masster.sample.helpers import _get_scan_uids
-from masster.sample.helpers import _get_feature_uids
-from masster.sample.helpers import filter_features
-from masster.sample.helpers import find_closest_scan
-from masster.sample.helpers import get_dda_stats
-from masster.sample.helpers import get_feature
-from masster.sample.helpers import get_scan
-from masster.sample.load import _load_featureXML
-from masster.sample.load import _load_ms2data
-from masster.sample.load import _load_mzML
-from masster.sample.load import _load_raw
-from masster.sample.load import _load_wiff
-from masster.sample.load import chrom_extract
-from masster.sample.load import index_file
-from masster.sample.load import load
-from masster.sample.load import sanitize
-from masster.logger import MassterLogger
-from masster.sample.plot import plot_2d
-from masster.sample.plot import plot_2d_oracle
-from masster.sample.plot import plot_dda_stats
-from masster.sample.plot import plot_eic
-from masster.sample.plot import plot_feature_stats
-from masster.sample.plot import plot_ms2_cycle
-from masster.sample.plot import plot_ms2_eic
-from masster.sample.plot import plot_ms2_q1
-from masster.sample.processing import _clean_features_df
-from masster.sample.processing import _features_deisotope
-from masster.sample.processing import _get_ztscan_stats
-from masster.sample.processing import _spec_to_mat
-from masster.sample.processing import analyze_dda
-from masster.sample.processing import find_adducts
-from masster.sample.processing import find_features
-from masster.sample.processing import find_ms2
-from masster.sample.processing import get_spectrum
-from masster.sample.parameters import store_history
-from masster.sample.parameters import get_parameters
-from masster.sample.parameters import update_parameters
-from masster.sample.parameters import get_parameters_property
-from masster.sample.parameters import set_parameters_property
-from masster.sample.defaults.find_features_def import find_features_defaults
-from masster.sample.defaults.find_adducts_def import find_adducts_defaults
-from masster.sample.defaults.find_ms2_def import find_ms2_defaults
-from masster.sample.defaults.get_spectrum_def import get_spectrum_defaults
-from masster.sample.save import _save_featureXML
-from masster.sample.save import export_chrom
-from masster.sample.save import export_dda_stats
-from masster.sample.save import export_features
-from masster.sample.save import export_mgf
-from masster.sample.save import save
-
-
-class Sample:
-    """
-    Main class for handling mass spectrometry sample data analysis.
-    
-    This class provides comprehensive functionality for loading, processing,
-    and analyzing DDA (data-dependent acquisition) mass spectrometry data.
-    """
-
-    def __init__(
-        self,
-        **kwargs,
-    ):
-        """
-        Initialize a DDA (data-dependent acquisition) instance.
-
-        This constructor initializes various attributes related to file handling,
-        data storage, and processing parameters used for mass spectrometry data analysis.
-
-        Parameters:
-            **kwargs: Keyword arguments for setting sample parameters. Can include:
-                     - A sample_defaults instance to set all parameters at once (pass as params=sample_defaults(...))
-                     - Individual parameter names and values (see sample_defaults for available parameters)
-
-                     Core initialization parameters:
-                     - file (str, optional): The file path or file object to be loaded
-                     - ondisk (bool): Whether to keep data on disk or load into memory. Default is False
-                     - label (str, optional): An optional label to identify the file or dataset
-                     - log_level (str): The logging level to be set for the logger. Defaults to 'INFO'
-                     - log_label (str, optional): Optional label for the logger
-
-                     Processing parameters:
-                     - All parameters from sample_defaults class (see class documentation)
-
-                     For backward compatibility, original signature is supported:
-                     Sample(file=..., ondisk=..., label=..., log_level=..., log_label=...)
-        """
-        # Initialize default parameters
-
-        # Check if a sample_defaults instance was passed
-        if "params" in kwargs and isinstance(kwargs["params"], sample_defaults):
-            params = kwargs.pop("params")
-        else:
-            # Create default parameters and update with provided values
-            params = sample_defaults()
-
-            # Update with any provided parameters
-            for key, value in kwargs.items():
-                if hasattr(params, key):
-                    params.set(key, value, validate=True)
-
-        # Store parameter instance for method access
-        self.parameters = params
-
-        # Set instance attributes for logger
-        self.log_level = params.log_level
-        self.log_label = (params.log_label + " | " if params.log_label else "")
-        self.log_sink = params.log_sink
-
-        # Initialize independent logger
-        from masster.logger import MassterLogger
-        self.logger = MassterLogger(
-            instance_type="sample",
-            level=params.log_level,
-            label=params.log_label if params.log_label else "",
-            sink=params.log_sink
-        )
-
-        # Initialize history as dict to keep track of processing parameters
-        self.history = {}
-        self.store_history(["sample"], params.to_dict())
-
-        # these are sample attributes
-        self.file_path = None  # Path to the file
-        # 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
-        self.file_obj = None
-
-        self.features = None  # the feature map as obtained by openMS
-        self.features_df = None  # the polars data frame with features
-        # the polars data frame with metadata of all scans in the file
-        self.scans_df = pl.DataFrame()
-        # the polars data frame with MS1 level data
-        self.ms1_df = pl.DataFrame()  
-
-        # lightweight lib data for matching, targeted analyses, etc. > superseded by study methods
-        self.lib = None
-        self.lib_match = None
-        self.chrom_df = None
-
-        if params.filename is not None:
-            self.load(params.filename, ondisk=params.ondisk)
-
-        
-    # Attach module functions as class methods
-    load = load
-    save = save
-    find_features = find_features
-    find_adducts = find_adducts
-    find_ms2 = find_ms2
-    get_spectrum = get_spectrum
-    filter_features = filter_features
-    analyze_dda = analyze_dda
-    store_history = store_history
-    get_parameters = get_parameters
-    update_parameters = update_parameters
-    get_parameters_property = get_parameters_property
-    set_parameters_property = set_parameters_property
-    export_features = export_features
-    export_mgf = export_mgf
-    export_chrom = export_chrom
-    export_dda_stats = export_dda_stats
-    plot_2d = plot_2d
-    plot_2d_oracle = plot_2d_oracle
-    plot_dda_stats = plot_dda_stats
-    plot_eic = plot_eic
-    plot_feature_stats = plot_feature_stats
-    plot_ms2_cycle = plot_ms2_cycle
-    plot_ms2_eic = plot_ms2_eic
-    plot_ms2_q1 = plot_ms2_q1
-    get_feature = get_feature
-    get_scan = get_scan
-    get_dda_stats = get_dda_stats
-    find_closest_scan = find_closest_scan
-    
-    # Additional method assignments for all imported functions
-    _load_sample5 = _load_sample5
-    _save_sample5 = _save_sample5
-    _delete_ms2 = _delete_ms2
-    _get_scan_uids = _get_scan_uids
-    _get_feature_uids = _get_feature_uids
-    _load_featureXML = _load_featureXML
-    _load_ms2data = _load_ms2data
-    _load_mzML = _load_mzML
-    _load_raw = _load_raw
-    _load_wiff = _load_wiff
-    chrom_extract = chrom_extract
-    index_file = index_file
-    sanitize = sanitize
-    _clean_features_df = _clean_features_df
-    _features_deisotope = _features_deisotope
-    _get_ztscan_stats = _get_ztscan_stats
-    _spec_to_mat = _spec_to_mat
-    _save_featureXML = _save_featureXML
-
-
-    def logger_update(self, level: str | None = None, label: str | None = None, sink: str | None = None):
-        """Update the logging configuration for this Sample instance.
-        
-        Args:
-            level: New logging level ("DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL")
-            label: New label for log messages
-            sink: New output sink (file path, file object, or "sys.stdout")
-        """
-        if level is not None:
-            self.log_level = level.upper()
-            self.logger.update_level(level)
-        
-        if label is not None:
-            self.log_label = label + " | " if len(label) > 0 else ""
-            self.logger.update_label(self.log_label)
-        
-        if sink is not None:
-            if sink == "sys.stdout":
-                self.log_sink = sys.stdout
-            else:
-                self.log_sink = sink
-            self.logger.update_sink(self.log_sink)
-
-    def reload(self):
-        """
-        Reloads all masster modules to pick up any changes to their source code,
-        and updates the instance's class reference to the newly reloaded class version.
-        This ensures that the instance uses the latest implementation without restarting the interpreter.
-        """
-        # Reset logger configuration flags to allow proper reconfiguration after reload
-        try:
-            import masster.sample.logger as logger_module
-
-            if hasattr(logger_module, "_SAMPLE_LOGGER_CONFIGURED"):
-                logger_module._SAMPLE_LOGGER_CONFIGURED = False
-        except Exception:
-            pass
-
-        # Get the base module name (masster)
-        base_modname = self.__class__.__module__.split(".")[0]
-        current_module = self.__class__.__module__
-
-        # Dynamically find all sample submodules
-        sample_modules = []
-        sample_module_prefix = f"{base_modname}.sample."
-
-        # Get all currently loaded modules that are part of the sample package
-        for module_name in sys.modules:
-            if (
-                module_name.startswith(sample_module_prefix)
-                and module_name != current_module
-            ):
-                sample_modules.append(module_name)
-
-        # Add core masster modules
-        core_modules = [
-            f"{base_modname}._version",
-            f"{base_modname}.chromatogram",
-            f"{base_modname}.spectrum",
-        ]
-
-        # Add study submodules
-        study_modules = []
-        study_module_prefix = f"{base_modname}.study."
-        for module_name in sys.modules:
-            if (
-                module_name.startswith(study_module_prefix)
-                and module_name != current_module
-            ):
-                study_modules.append(module_name)
-
-        # Add parameters submodules
-        parameters_modules = []
-        parameters_module_prefix = f"{base_modname}.parameters."
-        for module_name in sys.modules:
-            if (
-                module_name.startswith(parameters_module_prefix)
-                and module_name != current_module
-            ):
-                parameters_modules.append(module_name)
-
-        all_modules_to_reload = (
-            core_modules + sample_modules + study_modules + parameters_modules
-        )
-
-        # Reload all discovered modules
-        for full_module_name in all_modules_to_reload:
-            try:
-                if full_module_name in sys.modules:
-                    mod = sys.modules[full_module_name]
-                    importlib.reload(mod)
-                    self.logger.debug(f"Reloaded module: {full_module_name}")
-            except Exception as e:
-                self.logger.warning(f"Failed to reload module {full_module_name}: {e}")
-
-        # Finally, reload the current module (sample.py)
-        try:
-            mod = __import__(current_module, fromlist=[current_module.split(".")[0]])
-            importlib.reload(mod)
-
-            # Get the updated class reference from the reloaded module
-            new = getattr(mod, self.__class__.__name__)
-            # Update the class reference of the instance
-            self.__class__ = new
-
-            self.logger.debug("Module reload completed")
-        except Exception as e:
-            self.logger.error(f"Failed to reload current module {current_module}: {e}")
-
-    def get_version(self):
-        return get_version()
-
-    def info(self):
-        # show the key attributes of the object
-        str = f"File: {os.path.basename(self.file_path)}\n"
-        str += f"Path: {os.path.dirname(self.file_path)}\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:
-            str += f"Features: {len(self.features_df) if self.features_df is not None else 0}\n"
-            str += f"Features with MS2 spectra: {len(self.features_df.filter(pl.col('ms2_scans').is_not_null()))}\n"
-        else:
-            str += "Features: 0\n"
-            str += "Features with MS2 spectra: 0\n"
-
-        print(str)
-
-    def __str__(self):
-        if self.features_df is None:
-            str = f"masster Sample, source: {os.path.basename(self.file_path)}, features: 0"
-        else:
-            str = f"masster Sample, source: {os.path.basename(self.file_path)}, features: {len(self.features_df)}"
-        return str
-
-
-if __name__ == "__main__":
-    print(
-        "This module is not meant to be run directly. Please import it in your script.",
-    )
-
+"""
+sample.py
+
+This module provides tools for processing and analyzing Data-Dependent Acquisition (DDA) mass spectrometry data.
+It defines the `Sample` class, which offers methods to load, process, analyze, and visualize mass spectrometry data
+from various file formats, including mzML, Thermo RAW, and Sciex WIFF formats.
+
+Key Features:
+- **File Handling**: Load and save data in multiple formats.
+- **Feature Detection**: Detect and process mass spectrometry features.
+- **Spectrum Analysis**: Retrieve and analyze MS1/MS2 spectra.
+- **Visualization**: Generate interactive and static plots for spectra and chromatograms.
+- **Statistics**: Compute and export detailed DDA run statistics.
+
+Dependencies:
+- `pyopenms`: For file handling and feature detection.
+- `polars` and `pandas`: For data manipulation.
+- `numpy`: For numerical computations.
+- `bokeh`, `panel`, `holoviews`, `datashader`: For interactive visualizations.
+
+Classes:
+- `Sample`: Main class for handling DDA data, providing methods for data import, processing, and visualization.
+
+Example Usage:
+```python
+from masster.sample import Sample
+
+sample = Sample(file="example.mzML")
+sample.find_features()
+sample.plot_2d()
+```
+
+"""
+
+import importlib
+import os
+import sys
+
+import polars as pl
+
+from masster._version import get_version
+
+from masster.sample.defaults.sample_def import sample_defaults
+
+# Sample-specific imports
+from masster.sample.h5 import _load_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
+from masster.sample.helpers import _get_feature_uids
+from masster.sample.helpers import _features_sync
+from masster.sample.helpers import features_delete
+from masster.sample.helpers import features_filter
+from masster.sample.helpers import select
+from masster.sample.helpers import select_closest_scan
+from masster.sample.helpers import get_dda_stats
+from masster.sample.helpers import get_feature
+from masster.sample.helpers import get_scan
+from masster.sample.helpers import set_source
+from masster.sample.load import _load_featureXML
+from masster.sample.load import _load_ms2data
+from masster.sample.load import _load_mzML
+from masster.sample.load import _load_raw
+from masster.sample.load import _load_wiff
+from masster.sample.load import chrom_extract
+from masster.sample.load import index_file
+from masster.sample.load import load
+from masster.sample.load import sanitize
+from masster.logger import MassterLogger
+from masster.sample.plot import plot_2d
+from masster.sample.plot import plot_2d_oracle
+from masster.sample.plot import plot_dda_stats
+from masster.sample.plot import plot_eic
+from masster.sample.plot import plot_feature_stats
+from masster.sample.plot import plot_ms2_cycle
+from masster.sample.plot import plot_ms2_eic
+from masster.sample.plot import plot_ms2_q1
+from masster.sample.processing import _clean_features_df
+from masster.sample.processing import _features_deisotope
+from masster.sample.processing import _get_ztscan_stats
+from masster.sample.processing import _spec_to_mat
+from masster.sample.processing import analyze_dda
+from masster.sample.processing import find_adducts
+from masster.sample.processing import find_features
+from masster.sample.processing import find_ms2
+from masster.sample.processing import get_spectrum
+from masster.sample.parameters import store_history
+from masster.sample.parameters import get_parameters
+from masster.sample.parameters import update_parameters
+from masster.sample.parameters import get_parameters_property
+from masster.sample.parameters import set_parameters_property
+from masster.sample.save import _save_featureXML
+from masster.sample.save import export_chrom
+from masster.sample.save import export_dda_stats
+from masster.sample.save import export_features
+from masster.sample.save import export_mgf
+from masster.sample.save import save
+
+
+class Sample:
+    """
+    Main class for handling mass spectrometry sample data analysis.
+
+    This class provides comprehensive functionality for loading, processing,
+    and analyzing DDA (data-dependent acquisition) mass spectrometry data.
+    """
+
+    def __init__(
+        self,
+        **kwargs,
+    ):
+        """
+        Initialize a DDA (data-dependent acquisition) instance.
+
+        This constructor initializes various attributes related to file handling,
+        data storage, and processing parameters used for mass spectrometry data analysis.
+
+        Parameters:
+            **kwargs: Keyword arguments for setting sample parameters. Can include:
+                     - A sample_defaults instance to set all parameters at once (pass as params=sample_defaults(...))
+                     - Individual parameter names and values (see sample_defaults for available parameters)
+
+                     Core initialization parameters:
+                     - file (str, optional): The file path or file object to be loaded
+                     - ondisk (bool): Whether to keep data on disk or load into memory. Default is False
+                     - label (str, optional): An optional label to identify the file or dataset
+                     - log_level (str): The logging level to be set for the logger. Defaults to 'INFO'
+                     - log_label (str, optional): Optional label for the logger
+
+                     Processing parameters:
+                     - All parameters from sample_defaults class (see class documentation)
+
+                     For backward compatibility, original signature is supported:
+                     Sample(file=..., ondisk=..., label=..., log_level=..., log_label=...)
+        """
+        # Initialize default parameters
+
+        # Check if a sample_defaults instance was passed
+        if "params" in kwargs and isinstance(kwargs["params"], sample_defaults):
+            params = kwargs.pop("params")
+        else:
+            # Create default parameters and update with provided values
+            params = sample_defaults()
+
+            # Update with any provided parameters
+            for key, value in kwargs.items():
+                if hasattr(params, key):
+                    params.set(key, value, validate=True)
+
+        # Store parameter instance for method access
+        self.parameters = params
+
+        # Set instance attributes for logger
+        self.log_level = params.log_level.upper()
+        self.log_label = params.log_label + " | " if params.log_label else ""
+        self.log_sink = params.log_sink
+
+        # Initialize independent logger
+        from masster.logger import MassterLogger
+        self.logger = MassterLogger(
+            instance_type="sample",
+            level=params.log_level.upper(),
+            label=params.log_label if params.log_label else "",
+            sink=params.log_sink,
+        )
+
+        # Initialize history as dict to keep track of processing parameters
+        self.history = {}
+        self.store_history(["sample"], params.to_dict())
+
+        # 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
+        self.file_obj = None
+
+        self.features = None  # the feature map as obtained by openMS
+        self.features_df = None  # the polars data frame with features
+        # the polars data frame with metadata of all scans in the file
+        self.scans_df = pl.DataFrame()
+        # the polars data frame with MS1 level data
+        self.ms1_df = pl.DataFrame()
+
+        # lightweight lib data for matching, targeted analyses, etc. > superseded by study methods
+        self.lib = None
+        self.lib_match = None
+        self.chrom_df = None
+
+        if params.filename is not None:
+            self.load(params.filename, ondisk=params.ondisk)
+
+    # Attach module functions as class methods
+    load = load
+    save = save
+    find_features = find_features
+    find_adducts = find_adducts
+    find_ms2 = find_ms2
+    get_spectrum = get_spectrum
+    filter = filter
+    select = select
+    features_filter = features_filter  # New function that keeps only specified features
+    filter_features = filter
+    features_select = select
+    select_features = select
+    analyze_dda = analyze_dda
+    store_history = store_history
+    get_parameters = get_parameters
+    update_parameters = update_parameters
+    get_parameters_property = get_parameters_property
+    set_parameters_property = set_parameters_property
+    export_features = export_features
+    export_mgf = export_mgf
+    export_chrom = export_chrom
+    export_dda_stats = export_dda_stats
+    plot_2d = plot_2d
+    plot_2d_oracle = plot_2d_oracle
+    plot_dda_stats = plot_dda_stats
+    plot_eic = plot_eic
+    plot_feature_stats = plot_feature_stats
+    plot_ms2_cycle = plot_ms2_cycle
+    plot_ms2_eic = plot_ms2_eic
+    plot_ms2_q1 = plot_ms2_q1
+    get_feature = get_feature
+    get_scan = get_scan
+    get_dda_stats = get_dda_stats
+    select_closest_scan = select_closest_scan
+    set_source = set_source
+
+    # Additional method assignments for all imported functions
+    _load_sample5 = _load_sample5
+    _save_sample5 = _save_sample5
+    _delete_ms2 = _delete_ms2
+    _estimate_memory_usage = _estimate_memory_usage
+    _get_scan_uids = _get_scan_uids
+    _get_feature_uids = _get_feature_uids
+    _features_sync = _features_sync
+    features_delete = features_delete
+    features_filter = features_filter
+    _load_featureXML = _load_featureXML
+    _load_ms2data = _load_ms2data
+    _load_mzML = _load_mzML
+    _load_raw = _load_raw
+    _load_wiff = _load_wiff
+    chrom_extract = chrom_extract
+    index_file = index_file
+    sanitize = sanitize
+    _clean_features_df = _clean_features_df
+    _features_deisotope = _features_deisotope
+    _get_ztscan_stats = _get_ztscan_stats
+    _spec_to_mat = _spec_to_mat
+    _save_featureXML = _save_featureXML
+
+    def logger_update(self, level: str | None = None, label: str | None = None, sink: str | None = None):
+        """Update the logging configuration for this Sample instance.
+
+        Args:
+            level: New logging level ("DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL")
+            label: New label for log messages
+            sink: New output sink (file path, file object, or "sys.stdout")
+        """
+        if level is not None:
+            self.log_level = level.upper()
+            self.logger.update_level(level)
+
+        if label is not None:
+            self.log_label = label + " | " if len(label) > 0 else ""
+            self.logger.update_label(self.log_label)
+
+        if sink is not None:
+            if sink == "sys.stdout":
+                self.log_sink = sys.stdout
+            else:
+                self.log_sink = sink
+            self.logger.update_sink(self.log_sink)
+
+    def _reload(self):
+        """
+        Reloads all masster modules to pick up any changes to their source code,
+        and updates the instance's class reference to the newly reloaded class version.
+        This ensures that the instance uses the latest implementation without restarting the interpreter.
+        """
+        # Reset logger configuration flags to allow proper reconfiguration after reload
+        try:
+            import masster.sample.logger as logger_module
+
+            if hasattr(logger_module, "_SAMPLE_LOGGER_CONFIGURED"):
+                logger_module._SAMPLE_LOGGER_CONFIGURED = False
+        except Exception:
+            pass
+
+        # Get the base module name (masster)
+        base_modname = self.__class__.__module__.split(".")[0]
+        current_module = self.__class__.__module__
+
+        # Dynamically find all sample submodules
+        sample_modules = []
+        sample_module_prefix = f"{base_modname}.sample."
+
+        # Get all currently loaded modules that are part of the sample package
+        for module_name in sys.modules:
+            if module_name.startswith(sample_module_prefix) and module_name != current_module:
+                sample_modules.append(module_name)
+
+        # Add core masster modules
+        core_modules = [
+            f"{base_modname}._version",
+            f"{base_modname}.chromatogram",
+            f"{base_modname}.spectrum",
+        ]
+
+        # Add study submodules
+        study_modules = []
+        study_module_prefix = f"{base_modname}.study."
+        for module_name in sys.modules:
+            if module_name.startswith(study_module_prefix) and module_name != current_module:
+                study_modules.append(module_name)
+
+        # Add parameters submodules
+        parameters_modules = []
+        parameters_module_prefix = f"{base_modname}.parameters."
+        for module_name in sys.modules:
+            if module_name.startswith(parameters_module_prefix) and module_name != current_module:
+                parameters_modules.append(module_name)
+
+        all_modules_to_reload = core_modules + sample_modules + study_modules + parameters_modules
+
+        # Reload all discovered modules
+        for full_module_name in all_modules_to_reload:
+            try:
+                if full_module_name in sys.modules:
+                    mod = sys.modules[full_module_name]
+                    importlib.reload(mod)
+                    self.logger.debug(f"Reloaded module: {full_module_name}")
+            except Exception as e:
+                self.logger.warning(f"Failed to reload module {full_module_name}: {e}")
+
+        # Finally, reload the current module (sample.py)
+        try:
+            mod = __import__(current_module, fromlist=[current_module.split(".")[0]])
+            importlib.reload(mod)
+
+            # Get the updated class reference from the reloaded module
+            new = getattr(mod, self.__class__.__name__)
+            # Update the class reference of the instance
+            self.__class__ = new
+
+            self.logger.debug("Module reload completed")
+        except Exception as e:
+            self.logger.error(f"Failed to reload current module {current_module}: {e}")
+
+    def get_version(self):
+        return get_version()
+
+    def info(self):
+        # show the key attributes of the object
+        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"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:
+            str += f"Features: {len(self.features_df) if self.features_df is not None else 0}\n"
+            str += f"Features with MS2 spectra: {len(self.features_df.filter(pl.col('ms2_scans').is_not_null()))}\n"
+        else:
+            str += "Features: 0\n"
+            str += "Features with MS2 spectra: 0\n"
+
+        # estimate memory usage
+        mem_usage = self._estimate_memory_usage()
+        str += f"Estimated memory usage: {mem_usage:.2f} MB\n"
+
+        print(str)
+
+    def __str__(self):
+        if self.features_df is None:
+            str = f"masster Sample, source: {os.path.basename(self.file_path)}, features: 0"
+        else:
+            str = f"masster Sample, source: {os.path.basename(self.file_path)}, features: {len(self.features_df)}"
+        return str
+
+
+if __name__ == "__main__":
+    print(
+        "This module is not meant to be run directly. Please import it in your script.",
+    )