def process(dataset: RepertoireDataset, params: dict) -> RepertoireDataset:
processed_dataset = dataset.clone()
original_repertoires = processed_dataset.get_data()
indices = MetadataRepertoireFilter.get_matching_indices(
processed_dataset, params["criteria"])
processed_dataset.repertoires = [
original_repertoires[i] for i in indices
]
processed_dataset.metadata_file = MetadataRepertoireFilter.build_new_metadata(
dataset, indices, params["result_path"])
Filter.check_dataset_not_empty(processed_dataset,
"MetadataRepertoireFilter")
return processed_dataset
def process(dataset: RepertoireDataset, params: dict) -> RepertoireDataset:
Preprocessor.check_dataset_type(dataset, [RepertoireDataset], "ClonesPerRepertoireFilter")
processed_dataset = dataset.clone()
repertoires = []
indices = []
for index, repertoire in enumerate(dataset.get_data()):
if "lower_limit" in params.keys() and len(repertoire.sequences) >= params["lower_limit"] or \
"upper_limit" in params.keys() and len(repertoire.sequences) <= params["upper_limit"]:
repertoires.append(dataset.repertoires[index])
indices.append(index)
processed_dataset.repertoires = repertoires
processed_dataset.metadata_file = ClonesPerRepertoireFilter.build_new_metadata(dataset, indices, params["result_path"])
Filter.check_dataset_not_empty(processed_dataset, "ClonesPerRepertoireFilter")
return processed_dataset
def process(dataset: RepertoireDataset, params: dict) -> RepertoireDataset:
processed_dataset = copy.deepcopy(dataset)
with Pool(params["batch_size"]) as pool:
repertoires = pool.starmap(
CountPerSequenceFilter.process_repertoire,
[(repertoire, params) for repertoire in dataset.repertoires])
if params["remove_empty_repertoires"]:
repertoires = Filter.remove_empty_repertoires(repertoires)
processed_dataset.repertoires = repertoires
Filter.check_dataset_not_empty(processed_dataset,
"CountPerSequenceFilter")
return processed_dataset
def process(dataset: RepertoireDataset, params: dict) -> RepertoireDataset:
processed_dataset = dataset.clone()
PathBuilder.build(params["result_path"])
repertoires = []
indices = []
for index, repertoire in enumerate(dataset.get_data()):
if all(sequence.metadata.chain == Chain.get_chain(
params["keep_chain"])
for sequence in repertoire.sequences):
repertoires.append(repertoire)
indices.append(index)
processed_dataset.repertoires = repertoires
processed_dataset.metadata_file = ChainRepertoireFilter.build_new_metadata(
processed_dataset, indices, params["result_path"])
Filter.check_dataset_not_empty(processed_dataset,
"ChainRepertoireFilter")
return processed_dataset