def create_dummy_receptordataset(self, path):
receptors = [
TCABReceptor(identifier="1",
alpha=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"
})),
beta=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",
"custom1": "cust1"
}))),
TCABReceptor(identifier="2",
alpha=ReceptorSequence(amino_acid_sequence="AAAAAA",
identifier="2a",
metadata=SequenceMetadata(
v_gene="TRAV1",
j_gene="TRAJ1",
chain=Chain.ALPHA,
frame_type="IN",
custom_params={
"d_call": "TRAD1",
"custom2": "cust1"
})),
beta=ReceptorSequence(amino_acid_sequence="AAAAAA",
identifier="2b",
metadata=SequenceMetadata(
v_gene="TRBV1",
j_gene="TRBJ1",
chain=Chain.BETA,
frame_type="IN",
custom_params={
"d_call": "TRBD1",
"custom2": "cust1"
})))
]
receptors_path = path / "receptors"
PathBuilder.build(receptors_path)
return ReceptorDataset.build(receptors, 2, receptors_path)
def _implant_signals_in_receptors(
simulation_state: SimulationState) -> Dataset:
processed_receptors = SignalImplanter._implant_signals(
simulation_state, SignalImplanter._process_receptor)
processed_dataset = ReceptorDataset.build(
receptors=processed_receptors,
file_size=simulation_state.dataset.file_size,
name=simulation_state.dataset.name,
path=simulation_state.result_path)
processed_dataset.labels = {**(simulation_state.dataset.labels if simulation_state.dataset.labels is not None else {}),
**{signal: [True, False] for signal in simulation_state.signals}}
return processed_dataset
def _construct_test_dataset(self, path, dataset_size: int = 50):
receptors = [
TCABReceptor(alpha=ReceptorSequence(amino_acid_sequence="AAAA"),
beta=ReceptorSequence(amino_acid_sequence="ATA"),
metadata={"l1": 1},
identifier=str("1")),
TCABReceptor(alpha=ReceptorSequence(amino_acid_sequence="ATA"),
beta=ReceptorSequence(amino_acid_sequence="ATT"),
metadata={"l1": 2},
identifier=str("2"))
]
PathBuilder.build(path)
lc = LabelConfiguration()
lc.add_label("l1", [1, 2])
dataset = ReceptorDataset.build(receptors, 2, path)
return dataset, lc
def _import_from_files(filenames: List[str], generic_params: DatasetImportParams) -> ReceptorDataset:
elements = []
for file in filenames:
df = pd.read_csv(file, sep=generic_params.separator, usecols=generic_params.columns_to_load)
df.dropna()
df.drop_duplicates()
df.rename(columns=generic_params.column_mapping, inplace=True)
if "alpha_amino_acid_sequence" in df:
df["alpha_amino_acid_sequence"] = df["alpha_amino_acid_sequence"].str[1:-1]
if "beta_amino_acid_sequence" in df:
df["beta_amino_acid_sequence"] = df["beta_amino_acid_sequence"].str[1:-1]
if "alpha_nucleotide_sequence" in df:
df["alpha_nucleotide_sequence"] = df["alpha_nucleotide_sequence"].str[3:-3]
if "beta_nucleotide_sequence" in df:
df["beta_nucleotide_sequence"] = df["beta_nucleotide_sequence"].str[3:-3]
chain_vals = [ch for ch in generic_params.receptor_chains.value]
chain_names = [Chain.get_chain(ch).name.lower() for ch in generic_params.receptor_chains.value]
for chain_name in chain_names:
df = SingleLineReceptorImport.make_gene_columns(df, ["v", "j"], chain_name)
for index, row in df.iterrows():
sequences = {chain_vals[i]: ReceptorSequence(amino_acid_sequence=row[
chain_name + "_amino_acid_sequence"] if chain_name + "_amino_acid_sequence" in row else None,
nucleotide_sequence=row[
chain_name + "_nucleotide_sequence"] if chain_name + "_nucleotide_sequence" in row else None,
metadata=SequenceMetadata(
v_gene=row[f"{chain_name}_v_gene"], v_allele=row[f"{chain_name}_v_allele"],
v_subgroup=row[f'{chain_name}_v_subgroup'],
j_gene=row[f"{chain_name}_j_gene"], j_allele=row[f"{chain_name}_j_allele"],
j_subgroup=row[f'{chain_name}_j_subgroup'],
chain=chain_name, count=row["count"], region_type=generic_params.region_type.value))
for i, chain_name in enumerate(chain_names)}
elements.append(ReceptorBuilder.build_object(sequences, row["identifier"],
{key: row[key] for key in row.keys()
if all(item not in key for item in
["v_gene", 'j_gene', "count", "identifier"] + chain_names)}))
return ReceptorDataset.build(elements, generic_params.sequence_file_size, generic_params.result_path)
def construct_test_flatten_dataset(self, path):
receptors = [
TCABReceptor(alpha=ReceptorSequence(amino_acid_sequence="AAATTT",
identifier="1a"),
beta=ReceptorSequence(amino_acid_sequence="ATATAT",
identifier="1b"),
metadata={"l1": 1},
identifier="1"),
TCABReceptor(alpha=ReceptorSequence(amino_acid_sequence="AAAAAA",
identifier="2a"),
beta=ReceptorSequence(amino_acid_sequence="AAAAAA",
identifier="2b"),
metadata={"l1": 2},
identifier="2"),
TCABReceptor(alpha=ReceptorSequence(amino_acid_sequence="AAAAAA",
identifier="2a"),
beta=ReceptorSequence(amino_acid_sequence="AAAAAA",
identifier="2b"),
metadata={"l1": 2},
identifier="2")
]
return ReceptorDataset.build(receptors, 10, path)