def test_report_dnds_values(self):
valid_dnds_report = TEST_PATH + "/data/output/dnds_report.csv"
csv = TEST_PATH + "/data/output/mutant_types.csv"
ref_seq = self.references[0].seq
codon_variants = parse_codon_variants(csv, self.references)
# Read from file and make sure there are no empty lines
with open(valid_dnds_report, "r") as input:
valid_report = input.read()
# Sort and filter for comparison
valid_dnds_values = sorted(filter(None, valid_report.split("\n")))
# Create the report string
test_report = codon_variants.report_dnds_values(ref_seq, self.offset)
# Split into lines and sort
test_values = sorted(test_report.split("\n"))
assert len(valid_dnds_values) == len(test_values)
# Compare each line in the test report to the valid report
for pos in range(0, len(valid_dnds_values)):
if valid_dnds_values[pos][0:1] != "#":
assert valid_dnds_values[pos] == \
test_values[pos]
def setup(self):
csv = TEST_PATH + "/data/output/mutant_types.csv"
reference = TEST_PATH + "/data/hxb2_pol.fas"
self.offset = 1269
rs = parse_references_from_fasta(reference)
self.ref_seq = rs[0].seq
self.codon_variants = parse_codon_variants(csv, rs)
def cli(ctx, csv, reference, offset, output):
rs = parse_references_from_fasta(reference)
ref_seq = rs[0].seq
codon_variants = parse_codon_variants(csv, rs)
if output:
output.write(codon_variants.report_dnds_values(ref_seq, offset))
else:
click.echo(codon_variants.report_dnds_values(ref_seq, offset))
def test_valid_csv_file(self):
"""Tests to make sure that a valid codon variant csv file is properly
parsed into a CodonVariantCollection object.
"""
reference = TEST_PATH + "/data/hxb2_pol.fas"
rs = parse_references_from_fasta(reference)
var_obj = CodonVariantCollection(rs)
for i in range(0, 30):
variant = CodonVariant(chrom="hxb2_pol",
pos=i,
gene="gag",
nt_start_gene=1309 + i,
nt_end_gene=2841 + i,
nt_start=2077 + i,
nt_end=2079 + i,
ref_codon="ata",
mutant_codon="aAa",
ref_aa="I",
mutant_aa="K",
coverage=563 + i,
mutant_freq=1.60 + i,
mutant_type="S",
ns_count=1.0000,
s_count=1.5000)
pos = int(variant.nt_start) - int(variant.nt_start_gene)
var_obj.variants["gag"][pos]["aAa"] = variant
valid_csv = TEST_PATH + "/data/valid_csv.csv"
with open(valid_csv, "w+") as f:
f.write("#gene,nt position (gene),nt start position,"
"nt end position,ref codon,mutant codon,ref AA,mutant AA,"
"coverage,mutant frequency,mutant type,NS count,S count")
for gene in var_obj.variants:
for pos in var_obj.variants[gene]:
for codon in var_obj.variants[gene][pos]:
variant = var_obj.variants[gene][pos][codon]
f.write(
"%s,%i-%i,%i,%i,%s,%s,%s,%s,%i,%.2f,%s,%0.4f,%0.4f\n"
% (variant.gene, variant.nt_start_gene,
variant.nt_end_gene, variant.nt_start,
variant.nt_end, variant.ref_codon,
variant.mutant_codon, variant.ref_aa,
variant.mutant_aa, variant.coverage,
variant.mutant_freq, variant.mutant_type,
variant.ns_count, variant.s_count))
parsed_codon_variants = parse_codon_variants(valid_csv, rs)
for gene in parsed_codon_variants.variants:
for pos in parsed_codon_variants.variants[gene]:
for codon in parsed_codon_variants.variants[gene][pos]:
parsed_variant = parsed_codon_variants.variants[gene][pos][
codon]
variant = var_obj.variants[gene][pos][codon]
assert parsed_variant.chrom == variant.chrom
assert parsed_variant.nt_start_gene == variant.nt_start_gene
assert parsed_variant.nt_end_gene == variant.nt_end_gene
assert parsed_variant.nt_start == variant.nt_start
assert parsed_variant.nt_end == variant.nt_end
assert parsed_variant.ref_codon == variant.ref_codon
assert parsed_variant.mutant_codon == variant.mutant_codon
assert parsed_variant.ref_aa == variant.ref_aa
assert parsed_variant.mutant_aa == variant.mutant_aa
assert parsed_variant.coverage == variant.coverage
assert parsed_variant.mutant_freq == variant.mutant_freq
assert parsed_variant.mutant_type == variant.mutant_type
assert parsed_variant.ns_count == variant.ns_count
assert parsed_variant.s_count == variant.s_count
os.remove(valid_csv)