def _encode_data(self, dataset: ReceptorDataset, params: EncoderParams):
receptor_objs = [receptor for receptor in dataset.get_data()]
sequences = [[
getattr(obj, chain).get_sequence(self.sequence_type)
for chain in obj.get_chains()
] for obj in receptor_objs]
first_chain_seqs, second_chain_seqs = zip(*sequences)
if any(seq is None for seq in first_chain_seqs) or any(
seq is None for seq in second_chain_seqs):
raise ValueError(
f"{OneHotEncoder.__name__}: receptor dataset {dataset.name} (id: {dataset.identifier}) contains empty sequences for the "
f"specified sequence type {self.sequence_type.name.lower()}. Please check that the dataset is imported correctly."
)
max_seq_len = max(max([len(seq) for seq in first_chain_seqs]),
max([len(seq) for seq in second_chain_seqs]))
example_ids = dataset.get_example_ids()
labels = self._get_labels(receptor_objs,
params) if params.encode_labels else None
examples_first_chain = self._encode_sequence_list(
first_chain_seqs,
pad_n_sequences=len(receptor_objs),
pad_sequence_len=max_seq_len)
examples_second_chain = self._encode_sequence_list(
second_chain_seqs,
pad_n_sequences=len(receptor_objs),
pad_sequence_len=max_seq_len)
examples = np.stack((examples_first_chain, examples_second_chain),
axis=1)
feature_names = self._get_feature_names(max_seq_len,
receptor_objs[0].get_chains())
if self.flatten:
examples = examples.reshape(
(len(receptor_objs),
2 * max_seq_len * len(self.onehot_dimensions)))
feature_names = [
item for sublist in feature_names for subsublist in sublist
for item in subsublist
]
encoded_data = EncodedData(
examples=examples,
labels=labels,
example_ids=example_ids,
feature_names=feature_names,
encoding=OneHotEncoder.__name__,
info={
"chain_names":
receptor_objs[0].get_chains() if all(
receptor_obj.get_chains() == receptor_objs[0].get_chains()
for receptor_obj in receptor_objs) else None
})
return encoded_data
def _encode_data(self, dataset: ReceptorDataset, params: EncoderParams):
receptor_objs = [receptor for receptor in dataset.get_data()]
sequences = [[
getattr(obj, chain).get_sequence() for chain in obj.get_chains()
] for obj in receptor_objs]
first_chain_seqs, second_chain_seqs = zip(*sequences)
max_seq_len = max(max([len(seq) for seq in first_chain_seqs]),
max([len(seq) for seq in second_chain_seqs]))
example_ids = dataset.get_example_ids()
labels = self._get_labels(receptor_objs,
params) if params.encode_labels else None
examples_first_chain = self._encode_sequence_list(
first_chain_seqs,
pad_n_sequences=len(receptor_objs),
pad_sequence_len=max_seq_len)
examples_second_chain = self._encode_sequence_list(
second_chain_seqs,
pad_n_sequences=len(receptor_objs),
pad_sequence_len=max_seq_len)
examples = np.stack((examples_first_chain, examples_second_chain),
axis=1)
feature_names = self._get_feature_names(max_seq_len,
receptor_objs[0].get_chains())
if self.flatten:
examples = examples.reshape(
(len(receptor_objs),
2 * max_seq_len * len(self.onehot_dimensions)))
feature_names = [
item for sublist in feature_names for subsublist in sublist
for item in subsublist
]
encoded_data = EncodedData(
examples=examples,
labels=labels,
example_ids=example_ids,
feature_names=feature_names,
encoding=OneHotEncoder.__name__,
info={
"chain_names":
receptor_objs[0].get_chains() if all(
receptor_obj.get_chains() == receptor_objs[0].get_chains()
for receptor_obj in receptor_objs) else None
})
return encoded_data