def get_encoded_repertoire(self, repertoire, params: EncoderParams):
params.model = vars(self)
return CacheHandler.memo_by_params((("encoding_model", params.model), ("type", "kmer_encoding"),
("labels", params.label_config.get_labels_by_name()),
("repertoire_id", repertoire.identifier)),
lambda: self.encode_repertoire(repertoire, params), CacheObjectType.ENCODING_STEP)
def _get_encoded_repertoire(self, repertoire, params: EncoderParams):
params.model = vars(self)
return CacheHandler.memo_by_params((("encoding_model", params.model),
("labels", params.label_config.get_labels_by_name()),
("repertoire_id", repertoire.identifier),
("repertoire_data", hashlib.sha256(np.ascontiguousarray(repertoire.get_attribute(self.sequence_type.value))).hexdigest())),
lambda: self._encode_repertoire(repertoire, params), CacheObjectType.ENCODING)
def _encode_sequence(self, sequence: ReceptorSequence, params: EncoderParams, sequence_encoder, counts):
params.model = vars(self)
features = sequence_encoder.encode_sequence(sequence, params)
if features is not None:
for i in features:
if self.reads == ReadsType.UNIQUE:
counts[i] += 1
elif self.reads == ReadsType.ALL:
counts[i] += sequence.metadata.count
return counts
