mutcleaner.cleaners.human_domainome_sup2_cleaner

Functions

clean_human_domainome_sup2_dataset(pipeline)	Clean HumanDomainome dataset using configurable pipeline - SupplementaryTable2
create_human_domainome_sup2_cleaner(...[, ...])	Create HumanDomainome ledataset cleaning pipeline - SupplementaryTable2

Classes

HumanDomainomeSup2CleanerConfig([...])

Configuration class for HumanDomainome dataset cleaner - SupplementaryTable2.

class mutcleaner.cleaners.human_domainome_sup2_cleaner.HumanDomainomeSup2CleanerConfig(num_workers=16, validate_config=True, *, pipeline_name='human_domainome_cleaner', column_mapping=<factory>, filters=<factory>, drop_na_columns=<factory>, type_conversions=<factory>, validation_workers=16, infer_wt_workers=16, handle_multiple_wt='error', label_columns=<factory>, primary_label_column='label_humanDomainome')

Bases: BaseCleanerConfig

Configuration class for HumanDomainome dataset cleaner - SupplementaryTable2. Inherits from BaseCleanerConfig and adds HumanDomainome-specific configuration options.

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

Alternatively, the raw HumanDomainome file and the wild type fasta file can be obtained from:

• Hugging Face: https://huggingface.co/datasets/xulab-research/MutCleaner/blob/main/Human_Domainome_Dataset/SupplementaryTable2.txt

• Hugging Face: https://huggingface.co/datasets/xulab-research/MutCleaner/blob/main/Human_Domainome_Dataset/wild_type.fasta

Attributes:

column_mappingDict[str, str]

Mapping from source to target column names

filtersDict[str, Callable]

Filter conditions for data cleaning

type_conversionsDict[str, str]

Data type conversion specifications

drop_na_columns: List[str]

List of column names where null values should be dropped

validation_workersint

Number of workers for mutations validation, set to -1 to use all available CPUs

infer_wt_workersint

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

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 HumanDomainome-specific configuration parameters

column_mapping: Dict[str, str]

drop_na_columns: List

filters: Dict[str, Callable]

handle_multiple_wt: Literal['error', 'first', 'separate'] = 'error'

infer_wt_workers: int = 16

label_columns: List[str]

pipeline_name: str = 'human_domainome_cleaner'

primary_label_column: str = 'label_humanDomainome'

type_conversions: Dict[str, str]

validate()

Validate HumanDomainome-specific configuration parameters

Raises:

ValueError – If configuration is invalid

Return type:

None

validation_workers: int = 16

mutcleaner.cleaners.human_domainome_sup2_cleaner.clean_human_domainome_sup2_dataset(pipeline)

Clean HumanDomainome dataset using configurable pipeline - SupplementaryTable2

Parameters:

pipeline (Pipeline) – HumanDomainome dataset cleaning pipeline

Return type:

Tuple[Pipeline, MutationDataset]

Returns:

• Pipeline: The cleaned pipeline - MutationDataset: The cleaned HumanDomainome dataset

Raises:

RuntimeError – If pipeline execution fails

mutcleaner.cleaners.human_domainome_sup2_cleaner.create_human_domainome_sup2_cleaner(dataset_or_path, config=None)

Create HumanDomainome ledataset cleaning pipeline - SupplementaryTable2

Parameters:

• dataset_or_path (Union[str, Path, DataFrame]) – Raw HumanDomainome dataset DataFrame or file path to HumanDomainome - File: SupplementaryTable2.txt from the article ‘Site-saturation mutagenesis of 500 human protein domains’

• config (Union[HumanDomainomeSup2CleanerConfig, Dict[str, Any], str, Path, None]) – Configuration for the cleaning pipeline. Can be: - HumanDomainomeCleanerConfig object - Dictionary with configuration parameters (merged with defaults) - Path to JSON configuration file (str or Path) - None (uses default configuration)

Return type:

Pipeline

Returns:

The cleaning pipeline

Raises:

• FileNotFoundError – If data file or sequence dictionary file not found

• TypeError – If config has invalid type

• ValueError – If configuration validation fails

Examples

Basic usage:

>>> pipeline = create_human_domainome_sup2_cleaner(
...     "human_domainome.csv"
... )
>>> pipeline, dataset = clean_human_domainome_dataset(pipeline)

Custom configuration:

>>> config = {
...     "process_workers": 8,
...     "type_conversions": {"label_humanDomainome": "float32"}
... }
>>> pipeline = create_human_domainome_sup2_cleaner(
...     "human_domainome.csv"
...     config=config
... )

Load configuration from file:

>>> pipeline = create_human_domainome_sup2_cleaner(
...     "data.csv",
...     config="config.json"
... )