class TestCodonVariant:
@classmethod
def setup_class(self):
self.offset = 1269
self.variant = CodonVariant(chrom="hxb2_pol",
pos=1,
gene="gag",
nt_start_gene=1309,
nt_end_gene=2841,
nt_start=2077,
nt_end=2079,
ref_codon="ata",
mutant_codon="aAa",
ref_aa="I",
mutant_aa="K",
coverage=563,
mutant_freq=1.60,
mutant_type="S",
ns_count=1.0000,
s_count=1.5000)
def test_to_csv_entry(self):
assert self.variant.to_csv_entry(self.offset) == (
"gag,%i-%i,%i,%i,ata,aAa,I,K,563,1.60,S,1.0000,1.5000\n" %
(1309 + self.offset, 2841 + self.offset, 2077 + self.offset,
2079 + self.offset))
def setup_class(self):
self.offset = 1269
self.variant = CodonVariant(chrom="hxb2_pol",
pos=1,
gene="gag",
nt_start_gene=1309,
nt_end_gene=2841,
nt_start=2077,
nt_end=2079,
ref_codon="ata",
mutant_codon="aAa",
ref_aa="I",
mutant_aa="K",
coverage=563,
mutant_freq=1.60,
mutant_type="S",
ns_count=1.0000,
s_count=1.5000)
def setup_class(self):
self.reference = TEST_PATH + "/data/hxb2_pol.fas"
self.references = parse_references_from_fasta(self.reference)
self.variant_collection = CodonVariantCollection(self.references)
self.offset = 1269
self.variant_collection.variants['gag']['3']['aTa'] = CodonVariant(
chrom="hxb2_pol",
pos=1,
gene="gag",
nt_start_gene=1309,
nt_end_gene=2841,
nt_start=2077,
nt_end=2079,
ref_codon="ata",
mutant_codon="aTa",
ref_aa="I",
mutant_aa="K",
coverage=563,
mutant_freq=1.60,
mutant_type="S",
ns_count=1.0000,
s_count=1.5000)
self.variant_collection.variants['tat']['10']['aAa'] = CodonVariant(
chrom="hxb2_pol",
pos=2,
gene="tat",
nt_start_gene=3309,
nt_end_gene=4841,
nt_start=4000,
nt_end=4002,
ref_codon="ata",
mutant_codon="aAa",
ref_aa="I",
mutant_aa="K",
coverage=563,
mutant_freq=1.60,
mutant_type="S",
ns_count=1.0000,
s_count=1.5000)
def parse_codon_variants(csv, references):
"""Parse a codon variants csv and build a codon variants object"""
variant_collect = CodonVariantCollection(references)
with open(csv, "r") as f:
for line in f:
if line[0] != "#":
(
gene, gene_start_end, nt_start,
nt_end, ref_codon, mutant_codon,
ref_aa, mutant_aa, coverage,
mutant_freq, mutant_type,
ns_count, s_count
) = line.rstrip().split(",")
gene_start, gene_end = gene_start_end.split('-')
pos = int(nt_start)-int(gene_start)
variant = CodonVariant(
chrom=gene,
pos=pos,
gene=gene,
nt_start_gene=int(gene_start),
nt_end_gene=int(gene_end),
nt_start=int(nt_start),
nt_end=int(nt_end),
ref_codon=ref_codon,
mutant_codon=mutant_codon,
ref_aa=ref_aa,
mutant_aa=mutant_aa,
coverage=int(coverage),
mutant_freq=float(mutant_freq),
mutant_type=mutant_type,
ns_count=float(ns_count),
s_count=float(s_count))
variant_collect.variants[gene][
pos][mutant_codon] = variant
f.close()
return variant_collect
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)