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 _create_new_sequences(self, sequences, new_sequence_count,
signal) -> List[ReceptorSequence]:
new_sequences = sequences[:-new_sequence_count]
for _ in range(new_sequence_count):
motif = random.choice(signal.motifs)
motif_instance = motif.instantiate_motif()
annotation = SequenceAnnotation([
ImplantAnnotation(signal_id=signal.id,
motif_id=motif.identifier,
motif_instance=motif_instance.instance,
position=0)
])
metadata = SequenceMetadata(v_gene="TRBV6-1",
j_gene="TRBJ2-7",
count=1,
chain="B")
new_sequences.append(
ReceptorSequence(amino_acid_sequence=motif_instance.instance,
annotation=annotation,
metadata=metadata))
return new_sequences
def _make_sequence_object(self, row, load_implants: bool = False):
fields = row.dtype.names
implants = []
if load_implants:
keys = [
key for key in row.dtype.names if key not in Repertoire.FIELDS
]
for key in keys:
value_dict = row[key]
if value_dict:
try:
implants.append(
ImplantAnnotation(**ast.literal_eval(value_dict)))
except (SyntaxError, ValueError, TypeError) as e:
pass
seq = ReceptorSequence(
amino_acid_sequence=row["sequence_aas"]
if "sequence_aas" in fields else None,
nucleotide_sequence=row["sequences"]
if "sequences" in fields else None,
identifier=row["sequence_identifiers"]
if "sequence_identifiers" in fields else None,
metadata=SequenceMetadata(
v_gene=row["v_genes"] if "v_genes" in fields else None,
j_gene=row["j_genes"] if "j_genes" in fields else None,
v_subgroup=row["v_subgroups"]
if "v_subgroups" in fields else None,
j_subgroup=row["j_subgroups"]
if "j_subgroups" in fields else None,
v_allele=row["v_alleles"] if "v_alleles" in fields else None,
j_allele=row["j_alleles"] if "j_alleles" in fields else None,
chain=row["chains"] if "chains" in fields else None,
count=row["counts"] if "counts" in fields
and not NumpyHelper.is_nan_or_empty(row['counts']) else None,
region_type=row["region_types"]
if "region_types" in fields else None,
frame_type=row["frame_types"]
if "frame_types" in fields else "IN",
cell_id=row["cell_ids"] if "cell_ids" in fields else None,
custom_params={
key: row[key] if key in fields else None
for key in set(self.fields) - set(Repertoire.FIELDS)
}),
annotation=SequenceAnnotation(implants=implants))
return seq
def create_from_record(cls, record: np.void):
if 'version' in record.dtype.names and record['version'] == cls.version:
return ReceptorSequence(
**{
**{
key: record[key]
for key, val_type in ReceptorSequence.FIELDS.items() if val_type == str and key != 'version'
},
**{
'metadata':
SequenceMetadata(**json.loads(record['metadata'])),
'annotation':
SequenceAnnotation(**json.loads(record['annotation']))
}
})
else:
raise NotImplementedError
def _make_sequence_object(self, row):
fields = row.dtype.names
keys = [key for key in row.dtype.names if "signal" in key]
implants = []
for key in keys:
value_dict = row[key]
if value_dict:
implants.append(
ImplantAnnotation(**ast.literal_eval(value_dict)))
seq = ReceptorSequence(
amino_acid_sequence=row["sequence_aas"]
if "sequence_aas" in fields else None,
nucleotide_sequence=row["sequences"]
if "sequences" in fields else None,
identifier=row["sequence_identifiers"]
if "sequence_identifiers" in fields else None,
metadata=SequenceMetadata(
v_gene=row["v_genes"] if "v_genes" in fields else None,
j_gene=row["j_genes"] if "j_genes" in fields else None,
v_subgroup=row["v_subgroups"]
if "v_subgroups" in fields else None,
j_subgroup=row["j_subgroups"]
if "j_subgroups" in fields else None,
v_allele=row["v_alleles"] if "v_alleles" in fields else None,
j_allele=row["j_alleles"] if "j_alleles" in fields else None,
chain=row["chains"] if "chains" in fields else None,
count=row["counts"] if "counts" in fields else None,
region_type=row["region_types"]
if "region_types" in fields else None,
frame_type=row["frame_types"]
if "frame_types" in fields else "IN",
cell_id=row["cell_ids"] if "cell_ids" in fields else None,
custom_params={
key: row[key] if key in fields else None
for key in set(self.fields) - set(Repertoire.FIELDS)
}),
annotation=SequenceAnnotation(implants=implants))
return seq