def update_gene_columns(df, allele_name, gene_name):
for index, row in df.iterrows():
for gene in ['v', 'j']:
if NumpyHelper.is_nan_or_empty(
row[f"{gene}_{allele_name}"]
) and not NumpyHelper.is_nan_or_empty(
row[f"{gene}_{gene_name}"]):
df[f"{gene}_{allele_name}"][index] = row[
f"{gene}_{gene_name}"]
def get_counts(self):
counts = self.get_attribute("counts")
if counts is not None:
counts = np.array([
int(count) if not NumpyHelper.is_nan_or_empty(count) else None
for count in counts
])
return counts
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