def test_snpeff(self):
temp_dir = tempfile.gettempdir()
input_dir = util.file.get_test_input_path(self)
ref_fasta = os.path.join(input_dir,"ref-rabies-JQ685920.fasta")
assembly_fasta = os.path.join(input_dir,"RBV16.fasta")
isnv_calls = os.path.join(input_dir,"vphaser2.RBV16.mapped.txt.gz")
# align sample to reference to create MSA
msa_fasta = util.file.mkstempfname('.fasta')
expected_msa_fasta = os.path.join(input_dir,"msa.fasta")
args = [ref_fasta, assembly_fasta, msa_fasta, "--localpair", "--preservecase"]
args = interhost.parser_align_mafft(argparse.ArgumentParser()).parse_args(args)
args.func_main(args)
test.assert_equal_contents(self, msa_fasta, expected_msa_fasta)
# merge (one) VCF to merged vcf
merged_vcf = os.path.join(temp_dir,"merged.vcf.gz")
expected_merged_vcf = os.path.join(input_dir,"merged.vcf.gz")
args = [ref_fasta, merged_vcf, "--isnvs", isnv_calls, "--alignments", msa_fasta, "--strip_chr_version", "--parse_accession"]
args = intrahost.parser_merge_to_vcf(argparse.ArgumentParser()).parse_args(args)
args.func_main(args)
vcf = util.vcf.VcfReader(merged_vcf)
expected_vcf = util.vcf.VcfReader(expected_merged_vcf)
rows = list(vcf.get())
expected_rows = list(expected_vcf.get())
#self.assertEqual(rows, expected_rows)
# run snpEff against merged VCF to predict SNP effects
eff_vcf = os.path.join(temp_dir,"ann_eff.vcf.gz")
expected_eff_vcf = os.path.join(input_dir,"ann_eff.vcf.gz")
args = [merged_vcf, "JQ685920", eff_vcf, "[email protected]"]
with self.capsys.disabled():
args = interhost.parser_snpEff(argparse.ArgumentParser()).parse_args(args)
args.func_main(args)
vcf = util.vcf.VcfReader(eff_vcf)
expected_vcf = util.vcf.VcfReader(expected_eff_vcf)
rows = list(vcf.get())
expected_rows = list(expected_vcf.get())
#self.assertEqual(rows, expected_rows)
# create tabular iSNV output
eff_txt = os.path.join(temp_dir,"ann_eff.txt.gz")
expected_eff_txt = os.path.join(input_dir,"ann_eff.txt.gz")
args = [eff_vcf, eff_txt]
args = intrahost.parser_iSNV_table(argparse.ArgumentParser()).parse_args(args)
args.func_main(args)
for outrow, expectedrow in zip(util.file.read_tabfile(eff_txt),util.file.read_tabfile(expected_eff_txt)):
for colout, colexpected in zip(outrow, expectedrow):
# if it casts to float, perform approx comparison
try:
f1=float(colout)
f2=float(colexpected)
self.assertAlmostEqual(f1, f1)
except ValueError:
self.assertEqual(sorted(sorted(colout.split(","))), sorted(sorted(colexpected.split(","))))
def test_snpeff(self):
temp_dir = tempfile.gettempdir()
input_dir = util.file.get_test_input_path(self)
ref_fasta = os.path.join(input_dir,"ref-rabies-JQ685920.fasta")
assembly_fasta = os.path.join(input_dir,"RBV16.fasta")
isnv_calls = os.path.join(input_dir,"vphaser2.RBV16.mapped.txt.gz")
# align sample to reference to create MSA
msa_fasta = util.file.mkstempfname('.fasta')
expected_msa_fasta = os.path.join(input_dir,"msa.fasta")
args = [ref_fasta, assembly_fasta, msa_fasta, "--localpair", "--preservecase"]
args = interhost.parser_align_mafft(argparse.ArgumentParser()).parse_args(args)
args.func_main(args)
test.assert_equal_contents(self, msa_fasta, expected_msa_fasta)
# merge (one) VCF to merged vcf
merged_vcf = os.path.join(temp_dir,"merged.vcf.gz")
expected_merged_vcf = os.path.join(input_dir,"merged.vcf.gz")
args = [ref_fasta, merged_vcf, "--isnvs", isnv_calls, "--alignments", msa_fasta, "--strip_chr_version", "--parse_accession"]
args = intrahost.parser_merge_to_vcf(argparse.ArgumentParser()).parse_args(args)
args.func_main(args)
vcf = util.vcf.VcfReader(merged_vcf)
expected_vcf = util.vcf.VcfReader(expected_merged_vcf)
rows = list(vcf.get())
expected_rows = list(expected_vcf.get())
#self.assertEqual(rows, expected_rows)
# run snpEff against merged VCF to predict SNP effects
eff_vcf = os.path.join(temp_dir,"ann_eff.vcf.gz")
expected_eff_vcf = os.path.join(input_dir,"ann_eff.vcf.gz")
args = [merged_vcf, "JQ685920", eff_vcf, "[email protected]"]
args = interhost.parser_snpEff(argparse.ArgumentParser()).parse_args(args)
args.func_main(args)
vcf = util.vcf.VcfReader(eff_vcf)
expected_vcf = util.vcf.VcfReader(expected_eff_vcf)
rows = list(vcf.get())
expected_rows = list(expected_vcf.get())
#self.assertEqual(rows, expected_rows)
# create tabular iSNV output
eff_txt = os.path.join(temp_dir,"ann_eff.txt.gz")
expected_eff_txt = os.path.join(input_dir,"ann_eff.txt.gz")
args = [eff_vcf, eff_txt]
args = intrahost.parser_iSNV_table(argparse.ArgumentParser()).parse_args(args)
args.func_main(args)
for outrow, expectedrow in zip(util.file.read_tabfile(eff_txt),util.file.read_tabfile(expected_eff_txt)):
for colout, colexpected in zip(outrow, expectedrow):
# if it casts to float, perform approx comparison
try:
f1=float(colout)
f2=float(colexpected)
self.assertAlmostEqual(f1, f1)
except ValueError:
self.assertEqual(sorted(sorted(colout.split(","))), sorted(sorted(colexpected.split(","))))
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 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 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 util.vcf.VcfReader(outVcf) as vcf:
rows = list(vcf.get())
return rows
