def set_fwr4_columns(record, database):
j_call = record["j_call"]
if not j_call or record["locus"] not in ALLOWED_LOCI:
return
cdr3_ref_end = database.j_cdr3_end(record["j_call"], record["locus"])
cdr3_query_end = record["cdr3_end"]
if cdr3_ref_end is None or not cdr3_query_end:
return
fwr4_nt = record["sequence"][cdr3_query_end : record["j_sequence_end"]]
# This overwrites some existing columns
record["fwr4_start"] = cdr3_query_end + 1
record["fwr4_end"] = record["j_sequence_end"]
record["fwr4"] = fwr4_nt
record["fwr4_aa"] = nt_to_aa(fwr4_nt)
# Compute FR4 mutation rate on nucleotide level
germline = database.j[record["j_call"]][
record["j_germline_start"] - 1 : record["j_germline_end"]
]
dist = edit_distance(germline, fwr4_nt)
record["FR4_SHM"] = 100.0 * dist / len(germline)
# Compute FR4 amino acid mutation rate
sequence_aa = record["fwr4_aa"]
germline_aa = nt_to_aa(germline)
dist = edit_distance(germline_aa, sequence_aa)
record["J_aa_mut"] = 100.0 * dist / len(germline_aa)
def assert_cdr3_detection(chain, s):
for amino_acids, sequence in split(s):
for offset in range(3):
target = sequence[offset:]
match = find_cdr3(target, chain)
assert match is not None
assert nt_to_aa(
target[match[0]:match[1]]) == amino_acids, (chain, amino_acids,
offset)
def set_aa_mut_columns(record, database):
"""
Compute amino acid mutation rate for all regions on V and also for V
itself as the sum of the regions (that is, excluding the CDR3)
"""
total_length = 0
total_dist = 0
n_regions = 0
for airr_col, region in (
("fwr1", "FR1"),
("cdr1", "CDR1"),
("fwr2", "FR2"),
("cdr2", "CDR2"),
("fwr3", "FR3"),
):
record[region + "_aa_mut"] = None
start = record[airr_col + "_start"]
end = record[airr_col + "_end"]
if start is None or end is None:
continue
sequence_aa = nt_to_aa(record["sequence"][start - 1 : end])
germline_aa = database.v_regions_aa[record["v_call"]].get(region)
if germline_aa is None:
continue
# Some FR1 alignments are reported with a frameshift by IgBLAST. By requiring that
# reference and query lengths are identical, we can filter out these cases (and use
# Hamming distance to get some speedup)
if len(germline_aa) != len(sequence_aa):
continue
dist = hamming_distance(germline_aa, sequence_aa)
mut_aa = dist / len(germline_aa)
if mut_aa >= 0.8:
# assume something went wrong
continue
total_dist += dist
n_regions += 1
total_length += len(germline_aa)
record[region + "_aa_mut"] = 100.0 * mut_aa
if n_regions == 5:
record["V_aa_mut"] = 100.0 * total_dist / total_length
else:
record["V_aa_mut"] = None
def set_cdr3_columns(record, database):
if (
not record["v_call"]
or not record["j_call"]
or record["locus"] not in ALLOWED_LOCI
):
return
# CDR3 start
cdr3_ref_start = database.v_cdr3_start(
record["v_call"], record["locus"]
)
if cdr3_ref_start is None:
return
cdr3_query_start = query_position(record, "v", reference_position=cdr3_ref_start)
if cdr3_query_start is None:
# Alignment is not long enough to cover CDR3 start position; try to rescue it
# by assuming that the alignment would continue without indels.
cdr3_query_start = record["v_sequence_end"] + (
cdr3_ref_start - record["v_germline_end"]
)
# CDR3 end
cdr3_ref_end = database.j_cdr3_end(record["j_call"], record["locus"])
if cdr3_ref_end is None:
return
cdr3_query_end = query_position(record, "j", reference_position=cdr3_ref_end)
if cdr3_query_end is None:
return
cdr3_nt = record["sequence"][cdr3_query_start:cdr3_query_end]
record["cdr3_start"] = cdr3_query_start + 1
record["cdr3_end"] = cdr3_query_end
record["cdr3"] = cdr3_nt
record["cdr3_aa"] = nt_to_aa(cdr3_nt)