def build_receptor_from_rows(first_row, second_row, identifier, chain_pair, metadata_columns):
first_sequence = ImportHelper.import_sequence(first_row, metadata_columns=metadata_columns)
second_sequence = ImportHelper.import_sequence(second_row, metadata_columns=metadata_columns)
if chain_pair == ChainPair.TRA_TRB:
receptor = TCABReceptor(alpha=first_sequence,
beta=second_sequence,
identifier=identifier,
metadata={**second_sequence.metadata.custom_params})
elif chain_pair == ChainPair.TRG_TRD:
receptor = TCGDReceptor(gamma=first_sequence,
delta=second_sequence,
identifier=identifier,
metadata={**second_sequence.metadata.custom_params})
elif chain_pair == ChainPair.IGH_IGL:
receptor = BCReceptor(heavy=first_sequence,
light=second_sequence,
identifier=identifier,
metadata={**first_sequence.metadata.custom_params})
elif chain_pair == ChainPair.IGH_IGK:
receptor = BCKReceptor(heavy=first_sequence,
kappa=second_sequence,
identifier=identifier,
metadata={**first_sequence.metadata.custom_params})
else:
raise NotImplementedError(f"ImportHelper: {chain_pair} chain pair is not supported.")
return receptor
def _prepare_parameters(reference: dict,
max_edit_distances: dict,
name: str = None):
location = "MatchedReceptorsEncoder"
legal_chains = [
chain
for receptor in (TCABReceptor(), TCGDReceptor(), BCReceptor())
for chain in receptor.get_chains()
]
if type(max_edit_distances) is int:
max_edit_distances = {
chain: max_edit_distances
for chain in legal_chains
}
elif type(max_edit_distances) is dict:
ParameterValidator.assert_keys(max_edit_distances.keys(),
legal_chains,
location,
"max_edit_distances",
exclusive=False)
else:
ParameterValidator.assert_type_and_value(max_edit_distances, dict,
location,
'max_edit_distances')
reference_receptors = MatchedReferenceUtil.prepare_reference(
reference, location=location, paired=True)
return {
"reference_receptors": reference_receptors,
"max_edit_distances": max_edit_distances,
"name": name
}
def build_object(cls,
sequences: dict,
identifier: str = None,
metadata: dict = None) -> Receptor:
if all(chain in ChainPair.TRA_TRB.value for chain in sequences.keys()):
return TCABReceptor(alpha=sequences[Chain.ALPHA.value],
beta=sequences[Chain.BETA.value],
identifier=identifier,
metadata=metadata)
elif all(chain in ChainPair.TRG_TRD.value
for chain in sequences.keys()):
return TCGDReceptor(gamma=sequences[Chain.GAMMA.value],
delta=sequences[Chain.DELTA.value],
identifier=identifier,
metadata=metadata)
elif all(chain in ChainPair.IGH_IGL.value
for chain in sequences.keys()):
return BCReceptor(heavy=sequences[Chain.HEAVY.value],
light=sequences[Chain.LIGHT.value],
identifier=identifier,
metadata=metadata)
elif all(chain in ChainPair.IGH_IGK.value
for chain in sequences.keys()):
return BCKReceptor(heavy=sequences[Chain.HEAVY.value],
kappa=sequences[Chain.KAPPA.value],
identifier=identifier,
metadata=metadata)
else:
warnings.warn(
f"ReceptorBuilder: attempt to build_from_objects receptor with chains {sequences.keys()}, returning None..."
)
return None
def test_build_batch_generator(self):
path = EnvironmentSettings.tmp_test_path / "element_batch_generator/"
PathBuilder.build(path)
receptors = [BCReceptor(identifier=str(i), heavy=ReceptorSequence('A'), light=ReceptorSequence('C')) for i in range(307)]
file_list = [path / f"batch{i}.npy" for i in range(4)]
for i in range(4):
matrix = np.core.records.fromrecords([r.get_record() for r in receptors[i * 100: (i+1) * 100]], names=BCReceptor.get_record_names())
np.save(str(file_list[i]), matrix, allow_pickle=False)
receptor_generator = ElementGenerator(file_list, element_class_name=BCReceptor.__name__)
generator = receptor_generator.build_batch_generator()
counter = 0
for batch in generator:
for receptor in batch:
self.assertEqual(counter, int(receptor.identifier))
self.assertTrue(isinstance(receptor, BCReceptor))
counter += 1
self.assertEqual(307, counter)
generator = receptor_generator.build_batch_generator()
counter = 0
for batch in generator:
for receptor in batch:
self.assertEqual(counter, int(receptor.identifier))
self.assertTrue(isinstance(receptor, BCReceptor))
counter += 1
self.assertEqual(307, counter)
shutil.rmtree(path)
def test_build_batch_generator(self):
path = EnvironmentSettings.tmp_test_path / "element_batch_generator/"
PathBuilder.build(path)
receptors = [BCReceptor(identifier=str(i)) for i in range(307)]
file_list = [path / f"batch{i}.pkl" for i in range(4)]
for i in range(4):
with file_list[i].open("wb") as file:
pickle.dump(receptors[i * 100:(i + 1) * 100], file)
receptor_generator = ElementGenerator(file_list)
generator = receptor_generator.build_batch_generator()
counter = 0
for batch in generator:
for receptor in batch:
self.assertEqual(counter, int(receptor.identifier))
self.assertTrue(isinstance(receptor, BCReceptor))
counter += 1
self.assertEqual(307, counter)
generator = receptor_generator.build_batch_generator()
counter = 0
for batch in generator:
for receptor in batch:
self.assertEqual(counter, int(receptor.identifier))
self.assertTrue(isinstance(receptor, BCReceptor))
counter += 1
self.assertEqual(307, counter)
shutil.rmtree(path)