def process_dataset(self,
dataset: RepertoireDataset,
result_path: Path = None):
self.check_dataset_type(dataset, [RepertoireDataset],
"ClonesPerRepertoireFilter")
self.result_path = result_path if result_path is not None else self.result_path
processed_dataset = dataset.clone()
repertoires, indices = [], []
for index, repertoire in enumerate(dataset.get_data()):
if self.lower_limit != -1 and len(
repertoire.sequences) < self.lower_limit:
continue
if self.upper_limit != -1 and len(
repertoire.sequences) > self.upper_limit:
continue
repertoires.append(dataset.repertoires[index])
indices.append(index)
processed_dataset.repertoires = repertoires
processed_dataset.metadata_file = self._build_new_metadata(
dataset, indices)
self.check_dataset_not_empty(processed_dataset,
"ClonesPerRepertoireFilter")
return processed_dataset
def _merge_repertoires(self, dataset: RepertoireDataset):
rep_map = {}
repertoires, indices_to_keep = [], []
processed_dataset = dataset.clone()
for index, repertoire in enumerate(processed_dataset.get_data()):
if repertoire.metadata["subject_id"] in rep_map.keys():
sequences = np.append(
repertoire.sequences,
rep_map[repertoire.metadata["subject_id"]].sequences)
del rep_map[repertoire.metadata["subject_id"]]
repertoires.append(
self._store_repertoire(repertoire, sequences))
else:
rep_map[repertoire.metadata["subject_id"]] = repertoire
indices_to_keep.append(index)
for key in rep_map.keys():
repertoires.append(
self._store_repertoire(rep_map[key], rep_map[key].sequences))
processed_dataset.repertoires = repertoires
processed_dataset.metadata_file = self._build_new_metadata(
dataset, indices_to_keep)
return processed_dataset
def process(dataset: RepertoireDataset, params: dict) -> RepertoireDataset:
SubjectRepertoireCollector.check_dataset_type(dataset, [RepertoireDataset], "SubjectRepertoireCollector")
rep_map = {}
repertoires = []
indices_to_keep = []
processed_dataset = dataset.clone()
PathBuilder.build(params["result_path"])
for index, repertoire in enumerate(processed_dataset.get_data()):
if repertoire.metadata["subject_id"] in rep_map.keys():
sequences = np.append(repertoire.sequences, rep_map[repertoire.metadata["subject_id"]].sequences)
del rep_map[repertoire.metadata["subject_id"]]
repertoires.append(SubjectRepertoireCollector.store_repertoire(
params["result_path"], repertoire, sequences))
else:
rep_map[repertoire.metadata["subject_id"]] = repertoire
indices_to_keep.append(index)
for key in rep_map.keys():
repertoires.append(SubjectRepertoireCollector.store_repertoire(params["result_path"], rep_map[key], rep_map[key].sequences))
processed_dataset.repertoires = repertoires
processed_dataset.metadata_file = SubjectRepertoireCollector.build_new_metadata(dataset, indices_to_keep, params["result_path"])
return processed_dataset
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(self, dataset: RepertoireDataset, result_path: Path):
self.check_dataset_type(dataset, [RepertoireDataset],
"MetadataRepertoireFilter")
self.result_path = result_path if result_path is not None else self.result_path
processed_dataset = dataset.clone()
original_repertoires = processed_dataset.get_data()
indices = self._get_matching_indices(processed_dataset)
processed_dataset.repertoires = [
original_repertoires[i] for i in indices
]
processed_dataset.metadata_file = self._build_new_metadata(
dataset, indices)
self.check_dataset_not_empty(processed_dataset,
"MetadataRepertoireFilter")
return processed_dataset
def encode(self, dataset: RepertoireDataset,
params: EncoderParams) -> RepertoireDataset:
train_repertoire_ids = EncoderHelper.prepare_training_ids(
dataset, params)
labels = self.build_labels(dataset,
params) if params.encode_labels else None
distance_matrix = self.build_distance_matrix(dataset, params,
train_repertoire_ids)
encoded_dataset = dataset.clone()
encoded_dataset.encoded_data = EncodedData(
examples=distance_matrix.to_numpy(),
labels=labels,
feature_names=distance_matrix.columns.values,
example_ids=distance_matrix.index.values,
encoding=CompAIRRDistanceEncoder.__name__)
return encoded_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
def process_dataset(self, dataset: RepertoireDataset, result_path: Path):
self.check_dataset_type(dataset, [RepertoireDataset],
"ChainRepertoireFilter")
processed_dataset = dataset.clone()
self.result_path = result_path if result_path is not None else self.result_path
repertoires = []
indices = []
for index, repertoire in enumerate(dataset.get_data()):
if all(sequence.metadata.chain == self.keep_chain
for sequence in repertoire.sequences):
repertoires.append(repertoire)
indices.append(index)
processed_dataset.repertoires = repertoires
processed_dataset.metadata_file = self._build_new_metadata(
processed_dataset, indices)
self.check_dataset_not_empty(processed_dataset,
"ChainRepertoireFilter")
return processed_dataset