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_from_objects(sequences=sequences,
file_size=10,
path=path)
return dataset, lc
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_from_objects(sequences, 2, sequences_path)
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_from_objects(sequences=sequences,
file_size=10,
path=path)
def test(self):
sequences = [
ReceptorSequence(
amino_acid_sequence="AAACCC",
nucleotide_sequence="AAACCC",
identifier="1",
metadata=SequenceMetadata(custom_params={"l1": 1})),
ReceptorSequence(
amino_acid_sequence="ACACAC",
nucleotide_sequence="ACACAC",
identifier="2",
metadata=SequenceMetadata(custom_params={"l1": 2})),
ReceptorSequence(
amino_acid_sequence="CCCAAA",
nucleotide_sequence="CCCAAA",
identifier="3",
metadata=SequenceMetadata(custom_params={"l1": 1})),
ReceptorSequence(
amino_acid_sequence="AAACCC",
nucleotide_sequence="AAACCC",
identifier="4",
metadata=SequenceMetadata(custom_params={"l1": 2})),
ReceptorSequence(
amino_acid_sequence="ACACAC",
nucleotide_sequence="ACACAC",
identifier="5",
metadata=SequenceMetadata(custom_params={"l1": 1})),
ReceptorSequence(
amino_acid_sequence="CCCAAA",
nucleotide_sequence="CCCAAA",
identifier="6",
metadata=SequenceMetadata(custom_params={"l1": 2})),
ReceptorSequence(
amino_acid_sequence="AAACCC",
nucleotide_sequence="AAACCC",
identifier="7",
metadata=SequenceMetadata(custom_params={"l1": 1})),
ReceptorSequence(
amino_acid_sequence="ACACAC",
nucleotide_sequence="ACACAC",
identifier="8",
metadata=SequenceMetadata(custom_params={"l1": 2})),
ReceptorSequence(
amino_acid_sequence="CCCAAA",
nucleotide_sequence="CCCAAA",
identifier="9",
metadata=SequenceMetadata(custom_params={"l1": 1}))
]
path = EnvironmentSettings.tmp_test_path / "kmrefreqseqfacencoder/"
PathBuilder.build(path)
dataset = SequenceDataset.build_from_objects(
sequences, 100, PathBuilder.build(path / 'data'), 'd2')
lc = LabelConfiguration()
lc.add_label("l1", [1, 2])
encoder = KmerFreqSequenceEncoder.build_object(
dataset, **{
"normalization_type":
NormalizationType.RELATIVE_FREQUENCY.name,
"reads": ReadsType.UNIQUE.name,
"sequence_encoding": SequenceEncodingType.CONTINUOUS_KMER.name,
"sequence_type": SequenceType.NUCLEOTIDE.name,
"k": 3
})
encoded_dataset = encoder.encode(
dataset,
EncoderParams(result_path=path / "2/",
label_config=lc,
pool_size=2,
learn_model=True,
model={},
filename="dataset.csv"))
self.assertEqual(9, encoded_dataset.encoded_data.examples.shape[0])
self.assertTrue(
all(identifier in encoded_dataset.encoded_data.example_ids for
identifier in ['1', '2', '3', '4', '5', '6', '7', '8', '9']))
self.assertTrue(
numpy.array_equal(encoded_dataset.encoded_data.examples[0].A,
encoded_dataset.encoded_data.examples[3].A))
shutil.rmtree(path)