mutcleaner.cleaners.ddg_dtm_cleaners#

Functions

clean_ddg_dtm_dataset(pipeline)

Clean ddG-dTm dataset using configurable pipeline

create_ddg_dtm_cleaner([dataset_or_path, config])

Create ddG-dTm dataset cleaning pipeline

Classes

DdgDtmCleanerConfig([pipeline_name, ...])

Configuration class for ddG-dTm dataset cleaner.
class mutcleaner.cleaners.ddg_dtm_cleaners.DdgDtmCleanerConfig(pipeline_name='ddG-dTm', num_workers=16, validate_config=True, column_mapping=<factory>, type_conversions=<factory>, infer_mut_workers=16, aggregation_strategy='nearest', nearest_by=<factory>, label_columns=<factory>, primary_label_column='label')[source]#

Bases: BaseCleanerConfig

Configuration class for ddG-dTm dataset cleaner. Inherits from BaseCleanerConfig and adds ddG-dTm-specific configuration options.

Simply run mutcleaner.download_ddg_dtm_source_file() to download the dataset.

Alternatively, the raw ddG-dTm files can be obtained from:

Attributes:
column_mappingDict[str, str]

Mapping from source to target column names

type_conversionsDict[str, str]

Data type conversion specifications

infer_mut_workersint

Number of workers for mutation inference, set to -1 to use all available CPUs

aggregation_strategyLiteral[“mean”, “first”, “nearest”]

Aggregate labels by name, see aggregate_labels_by_name for details

nearest_byList[Tuple[str, float]]

Keep mutation by distance, see aggregate_labels_by_name for details

label_columnsList[str]

List of score columns to process

primary_label_columnstr

Primary score column for the dataset

Methods

from_dict(config_dict)

Create configuration object from dictionary

from_json(json_path)

Load configuration from JSON file

get_summary()

Get a human-readable summary of the configuration

merge(partial_config)

Merge partial configuration with current configuration

to_dict([exclude_callables])

Convert configuration to dictionary

to_json(json_path, **json_kwargs)

Save configuration to JSON file

validate()

Validate ddG-dTm-specific configuration parameters
aggregation_strategy: Literal['mean', 'first', 'nearest'] = 'nearest'#
column_mapping: Dict[str, str]#
infer_mut_workers: int = 16#
label_columns: List[str]#
nearest_by: List[Tuple[str, float]]#
pipeline_name: str = 'ddG-dTm'#
primary_label_column: str = 'label'#
type_conversions: Dict[str, str]#
validate()[source]#

Validate ddG-dTm-specific configuration parameters

Raises:

ValueError – If configuration is invalid

Return type:

None

mutcleaner.cleaners.ddg_dtm_cleaners.clean_ddg_dtm_dataset(pipeline)[source]#

Clean ddG-dTm dataset using configurable pipeline

Parameters:

pipeline (Pipeline) – ddG-dTm dataset cleaning pipeline

Return type:

Tuple[Pipeline, MutationDataset]

Returns:

  • Pipeline: The cleaned pipeline - MutationDataset: The cleaned ddG-dTm dataset

Examples

>>> pipeline = create_ddg_dtm_cleaner(df)  # df is raw ddG-dTm dataset file

Use default configuration:

>>> pipeline, dataset = clean_ddg_dtm_dataset(pipeline)

Use partial configuration:

>>> pipeline, dataset = clean_ddg_dtm_dataset(df, config={
...     "infer_mut_workers": 8,
... })

Load configuration from file:

>>> pipeline, dataset = clean_ddg_dtm_dataset(df, config="config.json")
mutcleaner.cleaners.ddg_dtm_cleaners.create_ddg_dtm_cleaner(dataset_or_path=None, config=None)[source]#

Create ddG-dTm dataset cleaning pipeline

Parameters:

  • dataset_or_path (Union[DataFrame, str, Path, None]) – Raw dataset DataFrame or file path to ddG-dTm dataset.

  • config (Union[DdgDtmCleanerConfig, Dict[str, Any], str, Path, None]) – Configuration for the cleaning pipeline. Can be: - DdgDtmCleanerConfig object - Dictionary with configuration parameters (merged with defaults) - Path to JSON configuration file (str or Path) - None (uses default configuration)

Return type:

Pipeline

Returns:

Pipeline: The cleaning pipeline used

Raises:

  • TypeError – If config has invalid type

  • ValueError – If configuration validation fails

Notes

Label columns (dTm or ddG) are automatically detected and added to the pipeline.