def _construct_test_dataset(self, path):
sequences = [
ReceptorSequence(amino_acid_sequence="AAAA",
identifier="1",
metadata=SequenceMetadata(custom_params={
"l1": 1,
"l2": 1
})),
ReceptorSequence(amino_acid_sequence="ATA",
identifier="2",
metadata=SequenceMetadata(custom_params={
"l1": 2,
"l2": 1
})),
ReceptorSequence(amino_acid_sequence="ATT",
identifier="3",
metadata=SequenceMetadata(custom_params={
"l1": 1,
"l2": 2
}))
]
lc = LabelConfiguration()
lc.add_label("l1", [1, 2])
lc.add_label("l2", [1, 2])
dataset = SequenceDataset.build(sequences=sequences,
file_size=10,
path=path)
return dataset, lc
def construct_test_flatten_dataset(self, path):
sequences = [
ReceptorSequence(
amino_acid_sequence="AAATTT",
identifier="1",
metadata=SequenceMetadata(custom_params={"l1": 1})),
ReceptorSequence(
amino_acid_sequence="ATATAT",
identifier="2",
metadata=SequenceMetadata(custom_params={"l1": 2}))
]
PathBuilder.build(path)
return SequenceDataset.build(sequences=sequences,
file_size=10,
path=path)
def create_dummy_sequencedataset(self, path):
sequences = [
ReceptorSequence(amino_acid_sequence="AAATTT",
identifier="1a",
metadata=SequenceMetadata(v_gene="TRAV1",
j_gene="TRAJ1",
chain=Chain.ALPHA,
frame_type="IN",
custom_params={
"d_call": "TRAD1",
"custom1": "cust1"
})),
ReceptorSequence(amino_acid_sequence="ATATAT",
identifier="1b",
metadata=SequenceMetadata(v_gene="TRBV1",
j_gene="TRBJ1",
chain=Chain.BETA,
frame_type="IN",
custom_params={
"d_call": "TRBD1",
"custom2": "cust1"
})),
ReceptorSequence(amino_acid_sequence="ATATAT",
identifier="2b",
metadata=SequenceMetadata(v_gene="TRBV1",
j_gene="TRBJ1",
chain=Chain.BETA,
frame_type="IN",
custom_params={
"d_call": "TRBD1",
"custom2": "cust1"
}))
]
sequences_path = path / "sequences"
PathBuilder.build(sequences_path)
return SequenceDataset.build(sequences, 2, sequences_path)