def test_save_snps_vcf_discrepant_pos(self):
s = SNPs("tests/input/testvcf.vcf")
r = Resources()
r._reference_sequences["GRCh37"] = {}
with tempfile.TemporaryDirectory() as tmpdir:
dest = os.path.join(tmpdir, "generic.fa.gz")
gzip_file("tests/input/generic.fa", dest)
seq = ReferenceSequence(ID="1", path=dest)
r._reference_sequences["GRCh37"]["1"] = seq
# create discrepant SNPs by setting positions outside reference sequence
s._snps.loc["rs1", "pos"] = 0
s._snps.loc["rs17", "pos"] = 118
self.assertEqual(os.path.relpath(s.save(vcf=True)),
f"output{os.sep}vcf_GRCh37.vcf")
pd.testing.assert_frame_equal(
s.discrepant_vcf_position,
self.create_snp_df(
rsid=["rs1", "rs17"],
chrom=["1", "1"],
pos=[0, 118],
genotype=["AA", np.nan],
),
check_exact=True,
)
expected = self.generic_snps_vcf().drop(["rs1", "rs17"])
self.run_parsing_tests_vcf("output/vcf_GRCh37.vcf", snps_df=expected)
def test_save_snps_phased(self):
# read phased data
s = SNPs("tests/input/testvcf_phased.vcf")
# save phased data to TSV
self.assertEqual(os.path.relpath(s.save()), "output/vcf_GRCh37.txt")
# read saved TSV
self.run_parsing_tests_vcf("output/vcf_GRCh37.txt", phased=True)
def test_save_snps_csv_filename(self):
snps = SNPs("tests/input/generic.csv")
self.assertEqual(
os.path.relpath(snps.save("generic.csv", sep=",")),
f"output{os.sep}generic.csv",
)
self.run_parsing_tests("output/generic.csv", "generic")
def test_save_snps_vcf_false_positive_build(self):
with tempfile.TemporaryDirectory() as tmpdir1:
snps = SNPs("tests/input/testvcf.vcf", output_dir=tmpdir1)
r = Resources()
r._reference_sequences["GRCh37"] = {}
output = os.path.join(tmpdir1, "vcf_GRCh37.vcf")
with tempfile.TemporaryDirectory() as tmpdir2:
dest = os.path.join(tmpdir2, "generic.fa.gz")
gzip_file("tests/input/generic.fa", dest)
seq = ReferenceSequence(ID="1", path=dest)
r._reference_sequences["GRCh37"]["1"] = seq
self.assertEqual(snps.save(vcf=True), output)
s = ""
with open(output, "r") as f:
for line in f.readlines():
if "snps v" in line:
s += '##source="vcf; snps v1.2.3.post85.dev0+gb386302; https://pypi.org/project/snps/"\n'
else:
s += line
with open(output, "w") as f:
f.write(s)
self.run_parsing_tests_vcf(output)
def test_save_snps_tsv_filename(self):
with tempfile.TemporaryDirectory() as tmpdir:
snps = SNPs("tests/input/generic.tsv", output_dir=tmpdir)
dest = os.path.join(tmpdir, "generic.tsv")
self.assertEqual(
snps.save("generic.tsv", sep="\t"), dest,
)
self.run_parsing_tests(dest, "generic")
def test_save_snps_phased(self):
with tempfile.TemporaryDirectory() as tmpdir:
# read phased data
s = SNPs("tests/input/testvcf_phased.vcf", output_dir=tmpdir)
dest = os.path.join(tmpdir, "vcf_GRCh37.txt")
# save phased data to TSV
self.assertEqual(s.save(), dest)
# read saved TSV
self.run_parsing_tests_vcf(dest, phased=True)
def test_save_source(self):
s = SNPs("tests/input/GRCh38.csv")
self.assertEqual(os.path.relpath(s.save()), f"output{os.sep}generic_GRCh38.txt")
snps = SNPs("output/generic_GRCh38.txt")
self.assertEqual(snps.build, 38)
self.assertTrue(snps.build_detected)
self.assertEqual(snps.source, "generic")
self.assertListEqual(snps._source, ["generic"])
pd.testing.assert_frame_equal(snps.snps, self.snps_GRCh38(), check_exact=True)
def test_save_source(self):
with tempfile.TemporaryDirectory() as tmpdir:
s = SNPs("tests/input/GRCh38.csv", output_dir=tmpdir)
dest = os.path.join(tmpdir, "generic_GRCh38.txt")
self.assertEqual(s.save(), dest)
snps = SNPs(dest)
self.assertEqual(snps.build, 38)
self.assertTrue(snps.build_detected)
self.assertEqual(snps.source, "generic")
self.assertListEqual(snps._source, ["generic"])
pd.testing.assert_frame_equal(snps.snps,
self.snps_GRCh38(),
check_exact=True)
def test_source_snps(self):
with tempfile.TemporaryDirectory() as tmpdir:
s = SNPs("tests/input/GRCh37.csv", output_dir=tmpdir)
self.assertEqual(s.source, "generic")
results = s.merge((SNPs("tests/input/23andme.txt"), ))
self.assertEqual(s.source, "generic, 23andMe")
self.assertListEqual(s._source, ["generic", "23andMe"])
dest = os.path.join(tmpdir, "generic__23andMe_GRCh37.txt")
self.assertEqual(s.save(), dest)
s = SNPs(dest)
self.assertEqual(s.source, "generic, 23andMe")
self.assertListEqual(s._source, ["generic", "23andMe"])
pd.testing.assert_frame_equal(s.snps, s.snps, check_exact=True)
self.assert_results(results, [{"merged": True}])
def test_source_snps(self):
s = SNPs("tests/input/GRCh37.csv")
self.assertEqual(s.source, "generic")
results = s.merge((SNPs("tests/input/23andme.txt"),))
self.assertEqual(s.source, "generic, 23andMe")
self.assertListEqual(s._source, ["generic", "23andMe"])
self.assertEqual(
os.path.relpath(s.save()), f"output{os.sep}generic__23andMe_GRCh37.txt"
)
s = SNPs("output/generic__23andMe_GRCh37.txt")
self.assertEqual(s.source, "generic, 23andMe")
self.assertListEqual(s._source, ["generic", "23andMe"])
pd.testing.assert_frame_equal(s.snps, s.snps, check_exact=True)
self.assert_results(results, [{"merged": True}])
def test_save_snps_false_positive_build(self):
snps = SNPs("tests/input/generic.csv")
output = "output/generic_GRCh37.txt"
self.assertEqual(os.path.relpath(snps.save()), output)
s = ""
with open(output, "r") as f:
for line in f.readlines():
if "snps v" in line:
s += "# Generated by snps v1.2.3.post85.dev0+gb386302, https://pypi.org/project/snps/\n"
else:
s += line
with open(output, "w") as f:
f.write(s)
self.run_parsing_tests(output, "generic")
def test_save_snps_vcf(self):
s = SNPs("tests/input/testvcf.vcf")
r = Resources()
r._reference_sequences["GRCh37"] = {}
with tempfile.TemporaryDirectory() as tmpdir:
dest = os.path.join(tmpdir, "generic.fa.gz")
gzip_file("tests/input/generic.fa", dest)
seq = ReferenceSequence(ID="1", path=dest)
r._reference_sequences["GRCh37"]["1"] = seq
self.assertEqual(os.path.relpath(s.save(vcf=True)),
f"output{os.sep}vcf_GRCh37.vcf")
self.run_parsing_tests_vcf("output/vcf_GRCh37.vcf")
def test_save_snps_false_positive_build(self):
with tempfile.TemporaryDirectory() as tmpdir:
snps = SNPs("tests/input/generic.csv", output_dir=tmpdir)
output = os.path.join(tmpdir, "generic_GRCh37.txt")
self.assertEqual(snps.save(), output)
s = ""
with open(output, "r") as f:
for line in f.readlines():
if "snps v" in line:
s += "# Generated by snps v1.2.3.post85.dev0+gb386302, https://pypi.org/project/snps/\n"
else:
s += line
with open(output, "w") as f:
f.write(s)
self.run_parsing_tests(output, "generic")
def test_save_snps_vcf(self):
with tempfile.TemporaryDirectory() as tmpdir1:
s = SNPs("tests/input/testvcf.vcf", output_dir=tmpdir1)
r = Resources()
r._reference_sequences["GRCh37"] = {}
output = os.path.join(tmpdir1, "vcf_GRCh37.vcf")
with tempfile.TemporaryDirectory() as tmpdir2:
dest = os.path.join(tmpdir2, "generic.fa.gz")
gzip_file("tests/input/generic.fa", dest)
seq = ReferenceSequence(ID="1", path=dest)
r._reference_sequences["GRCh37"]["1"] = seq
self.assertEqual(s.save(vcf=True), output)
self.run_parsing_tests_vcf(output)
def test_save_snps_vcf_phased(self):
# read phased data
s = SNPs("tests/input/testvcf_phased.vcf")
# setup resource to use test FASTA reference sequence
r = Resources()
r._reference_sequences["GRCh37"] = {}
with tempfile.TemporaryDirectory() as tmpdir:
dest = os.path.join(tmpdir, "generic.fa.gz")
gzip_file("tests/input/generic.fa", dest)
seq = ReferenceSequence(ID="1", path=dest)
r._reference_sequences["GRCh37"]["1"] = seq
# save phased data to VCF
self.assertEqual(os.path.relpath(s.save(vcf=True)),
f"output{os.sep}vcf_GRCh37.vcf")
# read saved VCF
self.run_parsing_tests_vcf("output/vcf_GRCh37.vcf", phased=True)
def test_save_snps_vcf_discrepant_pos(self):
with tempfile.TemporaryDirectory() as tmpdir1:
s = SNPs("tests/input/testvcf.vcf", output_dir=tmpdir1)
r = Resources()
r._reference_sequences["GRCh37"] = {}
output = os.path.join(tmpdir1, "vcf_GRCh37.vcf")
with tempfile.TemporaryDirectory() as tmpdir2:
dest = os.path.join(tmpdir2, "generic.fa.gz")
gzip_file("tests/input/generic.fa", dest)
seq = ReferenceSequence(ID="1", path=dest)
r._reference_sequences["GRCh37"]["1"] = seq
# create discrepant SNPs by setting positions outside reference sequence
s._snps.loc["rs1", "pos"] = 0
s._snps.loc["rs17", "pos"] = 118
# esnure this is the right type after manual tweaking
s._snps = s._snps.astype({"pos": np.uint32})
self.assertEqual(s.save(vcf=True), output)
pd.testing.assert_frame_equal(
s.discrepant_vcf_position,
self.create_snp_df(
rsid=["rs1", "rs17"],
chrom=["1", "1"],
pos=[0, 118],
genotype=["AA", np.nan],
),
check_exact=True,
)
expected = self.generic_snps_vcf().drop(["rs1", "rs17"])
self.run_parsing_tests_vcf(output, snps_df=expected)
def test_save_buffer_binary(self):
s = SNPs("tests/input/generic.csv")
out = io.BytesIO()
s.save(out)
self.assertTrue(out.read().startswith(b"# Generated by snps"))
def test_save_snps_csv(self):
snps = SNPs("tests/input/generic.csv")
self.assertEqual(os.path.relpath(snps.save(sep=",")),
"output/generic_GRCh37.csv")
self.run_parsing_tests("output/generic_GRCh37.csv", "generic")
def test_save_buffer(self):
s = SNPs("tests/input/generic.csv")
out = io.StringIO()
s.save(out)
self.assertTrue(out.read().startswith("# Generated by snps"))
def test_save_snps(self):
with tempfile.TemporaryDirectory() as tmpdir:
snps = SNPs("tests/input/generic.csv", output_dir=tmpdir)
dest = os.path.join(tmpdir, "generic_GRCh37.txt")
self.assertEqual(snps.save(), dest)
self.run_parsing_tests(dest, "generic")
def test_save_no_snps(self):
s = SNPs()
self.assertFalse(s.save())
def test_save_no_snps_vcf(self):
s = SNPs()
self.assertFalse(s.save(vcf=True))
def test_save_snps_specify_file(self):
s = SNPs("tests/input/generic.csv")
self.assertEqual(os.path.relpath(s.save("snps.csv")),
f"output{os.sep}snps.csv")
self.run_parsing_tests("output/snps.csv", "generic")
def test_save_snps(self):
snps = SNPs("tests/input/generic.csv")
self.assertEqual(os.path.relpath(snps.save()),
f"output{os.sep}generic_GRCh37.txt")
self.run_parsing_tests("output/generic_GRCh37.txt", "generic")