def test_extract_sequence_vcf_plus(interval_plus, fasta, vcf):
mutator = VCFMutator(True, False, vcf, None)
res = mutator.mutate_sequence(interval_plus, fasta, None)
assert res == [("CCCTGAGGCGTCCTTGC", (12, 14)),
("CCCCAAGGCGTCCTTGC", (12, 14, 8)),
("CCCTGAAGCGTCCTTGC", (12, 14, 11)),
("CCCTGAGGCGTCTTTGC", (12, 14, 17)),
("CCCCAAAGCGTCCTTGC", (12, 14, 8, 11)),
("CCCCAAGGCGTCTTTGC", (12, 14, 8, 17)),
("CCCTGAAGCGTCTTTGC", (12, 14, 11, 17)),
("CCCCAAAGCGTCTTTGC", (12, 14, 8, 11, 17))]
def test_extract_sequence_vcf_minus(interval_minus, fasta, vcf):
mutator = VCFMutator(True, False, vcf, None)
res = mutator.mutate_sequence(interval_minus, fasta, None)
assert res == [("GCAAGGACGCCTCAGGG", (12, 14)),
("GCAAGGACGCCTTGGGG", (12, 14, 8)),
("GCAAGGACGCTTCAGGG", (12, 14, 11)),
("GCAAAGACGCCTCAGGG", (12, 14, 17)),
("GCAAGGACGCTTTGGGG", (12, 14, 8, 11)),
("GCAAAGACGCCTTGGGG", (12, 14, 8, 17)),
("GCAAAGACGCTTCAGGG", (12, 14, 11, 17)),
("GCAAAGACGCTTTGGGG", (12, 14, 8, 11, 17))]
def test_extract_sequence_no_vcf(interval_plus, fasta):
mutator = VCFMutator(True, False, None, None)
res = mutator.mutate_sequence(interval_plus, fasta, None)
assert res == [("CCCTGAGTCATCCTTGC", )]
def get_nucleobase_mutation_table(self, vcf):
"""
Get a table which shows whether a certain nucleobase in Kozak sequence or stop codon context was mutated or not.
:param vcf: path to the vcf.gz or file opened using cyvcf2
:type vcf: string or an "opened" file
:return: pd.DataFrame,
column names – K_i – where i shows position in Kozak sequence;
S_i – where i shows position in stop codon context; gene_id; transcript_id
rows – NaN – no variant, 1 – heterozygous variant, 2 – homozygous variant
"""
# only for Kozak sequence and stop codon context + transcript_id column
columns = [
"K_0", "K_1", "K_2", "K_3", "K_4", "K_5", "K_6", "K_7", "K_8",
"K_9", "K_10", "K_11", "K_12", "K_13", "K_14", "S_0", "S_1", "S_2",
"S_3", "S_4", "S_5", "S_6", "S_7", "S_8", "S_9", "S_10", "S_11",
"S_12", "S_13", "S_14", "transcript_id", "gene_id", "name"
]
df_nucleobases = pd.DataFrame(columns=columns)
nucleobases_lines = []
mutator = VCFMutator(False, True, vcf, True)
contigs = [
'1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12',
'13', '14', '15', '16', '17', '18', '19', '20', '21', '22', 'X',
'Y'
]
for contig in contigs:
for transcript in self.transcripts(contig, '+'):
if transcript.contains_stop_codon and transcript.contains_start_codon:
Kozak_seq = transcript.get_Kozak_seq()
Interval_Kozak = Interval(
"chr" + transcript.contig,
transcript.start_codon_positions[0] - 6,
transcript.start_codon_positions[0] + 9, "NA", 0, "+")
stop_codon_context = transcript.get_stop_codon_context()
Interval_stop = Interval(
"chr" + transcript.contig,
transcript.stop_codon_positions[0] - 6,
transcript.stop_codon_positions[0] + 9, "NA", 0, "+")
df_nucleobases_line = mutator.mutate_codon_context(
[Interval_Kozak, Interval_stop],
[Kozak_seq, stop_codon_context], ["K_", "S_"])
if len(Kozak_seq) < 15:
new_columns = []
for column in df_nucleobases_line:
if column.find("K_") != -1:
new_columns.append("K_" + str(
int(column[2:]) + (15 - len(Kozak_seq))))
else:
new_columns.append(column)
df_nucleobases_line.columns = new_columns
df_nucleobases_line["transcript_id"] = transcript.id
df_nucleobases_line["gene_id"] = transcript.gene_id
nucleobases_lines.append(df_nucleobases_line)
for transcript in self.transcripts(contig, '-'):
if transcript.contains_stop_codon and transcript.contains_start_codon:
Kozak_seq = reverse_complement(transcript.get_Kozak_seq())
Interval_Kozak = Interval(
"chr" + transcript.contig,
transcript.start_codon_positions[0] - 6,
transcript.start_codon_positions[0] + 9, "NA", 0, "-")
stop_codon_context = reverse_complement(
transcript.get_stop_codon_context())
Interval_stop = Interval(
"chr" + transcript.contig,
transcript.stop_codon_positions[0] - 6,
transcript.stop_codon_positions[0] + 9, "NA", 0, "-")
df_nucleobases_line = mutator.mutate_codon_context(
[Interval_Kozak, Interval_stop],
[Kozak_seq, stop_codon_context], ["K_", "S_"])
if len(Kozak_seq) < 15:
new_columns = []
for column in df_nucleobases_line:
if column.find("K_") != -1:
new_columns.append("K_" + str(
int(column[2:]) + (15 - len(Kozak_seq))))
else:
new_columns.append(column)
df_nucleobases_line.columns = new_columns
df_nucleobases_line["transcript_id"] = transcript.id
df_nucleobases_line["gene_id"] = transcript.gene_id
nucleobases_lines.append(df_nucleobases_line)
df_nucleobases = pd.concat(nucleobases_lines, ignore_index=True)
df_nucleobases = df_nucleobases.drop(['name'], axis=1)
return df_nucleobases