mutcleaner.cleaners.rbd_antibody_cleaner#

Functions

clean_rbd_antibody_dataset(pipeline)

Execute the RBD antibody cleaning pipeline.

create_rbd_antibody_cleaner([...])

Create the RBD antibody cleaning pipeline.

Classes

RBDAntibodyCleanerConfig([pipeline_name, ...])

Configuration for the RBD antibody cleaner.

class mutcleaner.cleaners.rbd_antibody_cleaner.RBDAntibodyCleanerConfig(pipeline_name='RBDAntibody pipeline', num_workers=16, validate_config=True, reference_sequences=<factory>, target_name_aliases=<factory>, column_mapping=<factory>, filters=<factory>, drop_na_columns=<factory>, type_conversions=<factory>, fallback_reference_sequence=None, require_known_reference_sequence=True, validate_mut_workers=16, process_workers=16, label_columns=<factory>, primary_label_column='label')[source]#

Bases: BaseCleanerConfig

Configuration for the RBD antibody cleaner.

Attributes:
reference_sequencesDict[str, str]

Canonical RBD reference sequences keyed by target/reference name.

target_name_aliasesDict[str, str]

RBD target alias-to-canonical-name mapping.

column_mappingDict[str, str]

Mapping from raw source column names to standardized column names consumed by the RBD antibody cleaner.

filtersDict[str, Any]

Filter conditions applied before mutation processing.

drop_na_columnsList[str]

Columns that must be present after filtering.

type_conversionsDict[str, str]

Data type conversion specifications for label columns.

fallback_reference_sequenceOptional[str]

Reference sequence used when a row has an unknown reference name.

require_known_reference_sequencebool

Whether reference names must be found in reference_sequences.

validate_mut_workersint

Worker count for mutation validation.

process_workersint

Worker count for sequence materialization.

label_columnsList[str]

Label columns retained through the pipeline.

primary_label_columnstr

Label column written into the final MutationDataset.

pipeline_namestr

Pipeline name.

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 the configuration

column_mapping: Dict[str, str]#
drop_na_columns: List[str]#
fallback_reference_sequence: str | None = None#
filters: Dict[str, Any]#
label_columns: List[str]#
pipeline_name: str = 'RBDAntibody pipeline'#
primary_label_column: str = 'label'#
process_workers: int = 16#
reference_sequences: Dict[str, str]#
require_known_reference_sequence: bool = True#
target_name_aliases: Dict[str, str]#
type_conversions: Dict[str, str]#
validate()[source]#

Validate the configuration

This method should be implemented by subclasses to perform specific validation logic.

Raises:

ValueError – If configuration is invalid

Return type:

None

validate_mut_workers: int = 16#
mutcleaner.cleaners.rbd_antibody_cleaner.clean_rbd_antibody_dataset(pipeline)[source]#

Execute the RBD antibody cleaning pipeline.

Return type:

Tuple[Pipeline, MutationDataset]

mutcleaner.cleaners.rbd_antibody_cleaner.create_rbd_antibody_cleaner(dataset_or_path=None, config=None)[source]#

Create the RBD antibody cleaning pipeline.

Return type:

Pipeline