def _encode_examples(self, dataset: ReceptorDataset,
params: EncoderParams):
encoded_receptors_counts, encoded_receptors = [], []
receptor_ids = []
label_config = params.label_config
labels = {label: []
for label in label_config.get_labels_by_name()
} if params.encode_labels else None
chains = []
sequence_encoder = self._prepare_sequence_encoder()
feature_names = sequence_encoder.get_feature_names(params)
for receptor in dataset.get_data(params.pool_size):
counts = {chain: Counter() for chain in receptor.get_chains()}
chains = receptor.get_chains()
for chain in receptor.get_chains():
counts[chain] = self._encode_sequence(
receptor.get_chain(chain), params, sequence_encoder,
counts[chain])
encoded_receptors_counts.append(counts)
receptor_ids.append(receptor.identifier)
if params.encode_labels:
for label_name in label_config.get_labels_by_name():
label = receptor.metadata[label_name]
labels[label_name].append(label)
for encoded_receptor_count in encoded_receptors_counts:
counts = [
self._add_chain_to_name(encoded_receptor_count[chain], chain)
for chain in chains
]
encoded_receptors.append(counts[0] + counts[1])
return encoded_receptors, receptor_ids, labels, feature_names
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 _build_labels(self, dataset: ReceptorDataset,
params: EncoderParams) -> dict:
labels = {
label: []
for label in params.label_config.get_labels_by_name()
}
for receptor in dataset.get_data():
for label in labels.keys():
labels[label].append(receptor.metadata[label])
return labels
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
def prepare_tcr_dist_dataframe(dataset: ReceptorDataset,
label_names: list) -> pd.DataFrame:
if len(label_names) > 1:
raise NotImplementedError(
f"TCRdist: multiple labels specified ({str(label_names)[1:-1]}), but only single label binary class "
f"is currently supported in immuneML.")
label_name = label_names[0]
subject, epitope, count, v_a_gene, j_a_gene, cdr3_a_aa, v_b_gene, j_b_gene, cdr3_b_aa, clone_id, cdr3_b_nucseq, cdr3_a_nucseq = \
[], [], [], [], [], [], [], [], [], [], [], []
for receptor in dataset.get_data():
subject.append(receptor.metadata["subject"] if "subject" in
receptor.metadata else "sub" + receptor.identifier)
epitope.append(receptor.metadata[label_name])
count.append(
receptor.get_chain("alpha").metadata.
count if receptor.get_chain("alpha").metadata.count ==
receptor.get_chain("beta").metadata.count and receptor.
get_chain("beta").metadata.count is not None else 1)
v_a_gene.append(
TCRdistHelper.add_default_allele_to_v_gene(
receptor.get_chain('alpha').metadata.v_allele))
j_a_gene.append(receptor.get_chain('alpha').metadata.j_allele)
cdr3_a_aa.append(receptor.get_chain('alpha').amino_acid_sequence)
cdr3_a_nucseq.append(
receptor.get_chain("alpha").nucleotide_sequence)
v_b_gene.append(
TCRdistHelper.add_default_allele_to_v_gene(
receptor.get_chain('beta').metadata.v_allele))
j_b_gene.append(receptor.get_chain('beta').metadata.j_allele)
cdr3_b_aa.append(receptor.get_chain('beta').amino_acid_sequence)
cdr3_b_nucseq.append(
receptor.get_chain("beta").nucleotide_sequence)
clone_id.append(receptor.identifier)
if all(item is not None
for item in cdr3_a_nucseq) and all(item is not None
for item in cdr3_b_nucseq):
return pd.DataFrame({
"subject": subject,
"epitope": epitope,
"count": count,
"v_a_gene": v_a_gene,
"j_a_gene": j_a_gene,
"cdr3_a_aa": cdr3_a_aa,
"v_b_gene": v_b_gene,
"j_b_gene": j_b_gene,
"cdr3_b_aa": cdr3_b_aa,
"clone_id": clone_id,
"cdr3_b_nucseq": cdr3_b_nucseq,
"cdr3_a_nucseq": cdr3_a_nucseq
})
else:
return pd.DataFrame({
"subject": subject,
"epitope": epitope,
"count": count,
"v_a_gene": v_a_gene,
"j_a_gene": j_a_gene,
"cdr3_a_aa": cdr3_a_aa,
"v_b_gene": v_b_gene,
"j_b_gene": j_b_gene,
"cdr3_b_aa": cdr3_b_aa,
"clone_id": clone_id
})