def run_and_get_vcf_rows(self):
outVcf = util.file.mkstempfname('.vcf.gz')
intrahost.merge_to_vcf(self.ref, outVcf,
self.sample_order,
list(self.dump_isnv_tmp_file(s) for s in self.sample_order),
list(self.genomeFastas[s] for s in self.sample_order))
with util.vcf.VcfReader(outVcf) as vcf:
rows = list(vcf.get())
return rows
def test_headers_with_two_samps(self):
ref = makeTempFasta([('ref1', 'ATCGTTCA'), ('ref2', 'GGCCC')])
s1 = makeTempFasta([('s1_1', 'ATCGCA'), ('s1_2', 'GGCCC')])
s2 = makeTempFasta([('s2_1', 'ATCGTTCA'), ('s2_2', 'GGCCC')])
emptyfile = util.file.mkstempfname('.txt')
outVcf = util.file.mkstempfname('.vcf.gz')
intrahost.merge_to_vcf(ref, outVcf, ['s1', 's2'], [emptyfile, emptyfile], [s1, s2])
with util.vcf.VcfReader(outVcf) as vcf:
self.assertEqual(vcf.samples(), ['s1', 's2'])
self.assertEqual(vcf.chrlens(), {'ref1':8, 'ref2':5})
def run_and_get_vcf_rows(self, retree=1):
outVcf = util.file.mkstempfname('.vcf.gz')
self.multi_align_samples(retree=retree)
seqIds = list(itertools.chain.from_iterable(self.sequence_order.values()))
intrahost.merge_to_vcf(self.ref, outVcf, seqIds, list(self.dump_isnv_tmp_file(s) for s in self.sample_order),
self.alignedFastas)
with util.vcf.VcfReader(outVcf) as vcf:
rows = list(vcf.get())
return rows
def run_and_get_vcf_rows(self, retree=1):
outVcf = util.file.mkstempfname('.vcf.gz')
self.multi_align_samples(retree=retree)
seqIds = list(
itertools.chain.from_iterable(self.sequence_order.values()))
intrahost.merge_to_vcf(
self.ref, outVcf, seqIds,
list(self.dump_isnv_tmp_file(s) for s in self.sample_order),
self.alignedFastas)
with util.vcf.VcfReader(outVcf) as vcf:
rows = list(vcf.get())
return rows
def test_empty_output(self):
ref = makeTempFasta([('ref1', 'ATCGCA')])
s1 = makeTempFasta([('s1_1', 'ATCGCA')])
emptyfile = util.file.mkstempfname('.txt')
outVcf = util.file.mkstempfname('.vcf')
intrahost.merge_to_vcf(ref, outVcf, ['s1'], [emptyfile], [s1])
self.assertGreater(os.path.getsize(outVcf), 0)
with util.file.open_or_gzopen(outVcf, 'rt') as inf:
for line in inf:
self.assertTrue(line.startswith('#'))
outVcf = util.file.mkstempfname('.vcf.gz')
intrahost.merge_to_vcf(ref, outVcf, ['s1'], [emptyfile], [s1])
self.assertGreater(os.path.getsize(outVcf), 0)
with util.file.open_or_gzopen(outVcf, 'rt') as inf:
for line in inf:
self.assertTrue(line.startswith('#'))
def run_and_get_vcf_rows(self, retree=1, omit_samplenames=False):
outVcf = util.file.mkstempfname('.vcf.gz')
self.multi_align_samples(retree=retree)
if not omit_samplenames:
intrahost.merge_to_vcf(self.ref, outVcf, self.sample_order, list(self.dump_isnv_tmp_file(s) for s in self.sample_order),
self.alignedFastas)
else:
intrahost.merge_to_vcf(self.ref, outVcf, [], list(self.dump_isnv_tmp_file(s) for s in self.sample_order),
self.alignedFastas)
with util.vcf.VcfReader(outVcf) as vcf:
rows = list(vcf.get())
return rows
def run_and_get_vcf_rows(self, retree=1, omit_samplenames=False):
outVcf = util.file.mkstempfname('.vcf.gz')
self.multi_align_samples(retree=retree)
if not omit_samplenames:
intrahost.merge_to_vcf(
self.ref, outVcf, self.sample_order,
list(self.dump_isnv_tmp_file(s) for s in self.sample_order),
self.alignedFastas)
else:
intrahost.merge_to_vcf(
self.ref, outVcf, [],
list(self.dump_isnv_tmp_file(s) for s in self.sample_order),
self.alignedFastas)
with phylo.vcf.VcfReader(outVcf) as vcf:
rows = list(vcf.get())
return rows