def _build_new_sequence(self, sequence: ReceptorSequence, position, signal: dict) -> ReceptorSequence:
gap_length = signal["motif_instance"].gap
if "/" in signal["motif_instance"].instance:
motif_left, motif_right = signal["motif_instance"].instance.split("/")
else:
motif_left = signal["motif_instance"].instance
motif_right = ""
gap_start = position+len(motif_left)
gap_end = gap_start+gap_length
part1 = sequence.get_sequence()[:position]
part2 = sequence.get_sequence()[gap_start:gap_end]
part3 = sequence.get_sequence()[gap_end+len(motif_right):]
new_sequence_string = part1 + motif_left + part2 + motif_right + part3
annotation = SequenceAnnotation()
implant = ImplantAnnotation(signal_id=signal["signal_id"],
motif_id=signal["motif_id"],
motif_instance=signal["motif_instance"],
position=position)
annotation.add_implant(implant)
new_sequence = ReceptorSequence()
new_sequence.set_annotation(annotation)
new_sequence.set_metadata(copy.deepcopy(sequence.metadata))
new_sequence.set_sequence(new_sequence_string, EnvironmentSettings.get_sequence_type())
return new_sequence
def get_sequence(self):
"""
:return: receptor_sequence (nucleotide/amino acid) that corresponds to preset
receptor_sequence type from EnvironmentSettings class
"""
if EnvironmentSettings.get_sequence_type() == SequenceType.AMINO_ACID:
return self.amino_acid_sequence
else:
return self.nucleotide_sequence
def _set_max_dims(self, dataset):
max_rep_len = 0
max_seq_len = 0
for repertoire in dataset.repertoires:
sequences = repertoire.get_attribute(
EnvironmentSettings.get_sequence_type().value)
max_rep_len = max(len(sequences), max_rep_len)
max_seq_len = max(max([len(seq) for seq in sequences]),
max_seq_len)
self.max_rep_len = max_rep_len
self.max_seq_len = max_seq_len
def _encode_repertoire(self, repertoire, params: EncoderParams):
sequences = repertoire.get_attribute(
EnvironmentSettings.get_sequence_type().value)
onehot_encoded = self._encode_sequence_list(
sequences,
pad_n_sequences=self.max_rep_len,
pad_sequence_len=self.max_seq_len)
example_id = repertoire.identifier
labels = self._get_repertoire_labels(
repertoire, params) if params.encode_labels else None
return onehot_encoded, example_id, labels
def drop_illegal_character_sequences(dataframe: pd.DataFrame, import_illegal_characters: bool) -> pd.DataFrame:
if not import_illegal_characters:
sequence_type = EnvironmentSettings.get_sequence_type()
sequence_name = sequence_type.name.lower().replace("_", " ")
legal_alphabet = EnvironmentSettings.get_sequence_alphabet(sequence_type)
if sequence_type == SequenceType.AMINO_ACID:
legal_alphabet.append(Constants.STOP_CODON)
is_illegal_seq = [ImportHelper.is_illegal_sequence(sequence, legal_alphabet) for
sequence in dataframe[sequence_type.value]]
n_illegal = sum(is_illegal_seq)
if n_illegal > 0:
dataframe.drop(dataframe.loc[is_illegal_seq].index, inplace=True)
warnings.warn(
f"{ImportHelper.__name__}: {n_illegal} sequences were removed from the dataset because their {sequence_name} sequence contained illegal characters. ")
return dataframe