def _encode_new_dataset(self, dataset, params: EncoderParams):
encoded_dataset = RepertoireDataset(
repertoires=dataset.repertoires,
labels=dataset.labels,
metadata_file=dataset.metadata_file)
feature_annotations = self._get_feature_info()
encoded_repertoires, labels, example_ids = self._encode_repertoires(
dataset, params)
encoded_dataset.add_encoded_data(
EncodedData(
# examples contains a np.ndarray with counts
examples=encoded_repertoires,
# example_ids contains a list of repertoire identifiers
example_ids=example_ids,
# feature_names contains a list of reference receptor identifiers
feature_names=[
"{receptor_id}.{chain}".format(
receptor_id=row["receptor_id"], chain=row["chain"])
for index, row in feature_annotations.iterrows()
],
# feature_annotations contains a PD dataframe with sequence and VDJ gene usage per reference receptor
feature_annotations=feature_annotations,
labels=labels,
encoding=MatchedReceptorsEncoder.__name__))
return encoded_dataset
def _encode_new_dataset(self, dataset, params: EncoderParams):
self._load_regex_df()
encoded_dataset = RepertoireDataset(repertoires=dataset.repertoires, labels=dataset.labels,
metadata_file=dataset.metadata_file)
feature_annotations = self._get_feature_info()
encoded_repertoires, labels = self._encode_repertoires(dataset, params)
encoded_dataset.add_encoded_data(EncodedData(
examples=encoded_repertoires,
example_ids=list(dataset.get_metadata(["subject_id"]).values())[0],
feature_names=list(feature_annotations["chain_id"]),
feature_annotations=feature_annotations,
labels=labels,
encoding=MatchedRegexEncoder.__name__
))
return encoded_dataset
def _encode_new_dataset(self, dataset, params: EncoderParams):
encoded_dataset = RepertoireDataset(
repertoires=dataset.repertoires,
labels=dataset.labels,
metadata_file=dataset.metadata_file)
encoded_repertoires, labels = self._encode_repertoires(dataset, params)
feature_annotations = self._get_feature_info()
encoded_dataset.add_encoded_data(
EncodedData(examples=encoded_repertoires,
labels=labels,
feature_names=list(feature_annotations["sequence_id"]),
feature_annotations=feature_annotations,
example_ids=[
repertoire.identifier
for repertoire in dataset.get_data()
],
encoding=MatchedSequencesEncoder.__name__))
return encoded_dataset