def test_cli(self):
oxo_vcf = get_test_data_path(
"test_input_for_add_oxog_filters_from_maf.vcf.gz")
vcf_file = get_test_data_path("test_input_for_add_oxog_filters.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
with captured_output() as (_, stderr):
main(args=["add-oxog-filters", vcf_file, oxo_vcf, fn])
vcf = pysam.VariantFile(fn)
self.assertEqual(vcf.header.filters.keys(), ["PASS", "oxog"])
for record in vcf:
if (record.contig == "chr1" and record.pos == 10
and record.alleles == (
"A",
"T",
)):
self.assertEqual(record.filter.keys(), ["oxog"])
else:
self.assertEqual(record.filter.keys(), ["PASS"])
vcf.close()
serr = stderr.getvalue()
self.assertTrue(
"[gdc_filtration_tools.add_oxog_filters] - Creating tabix index"
in serr)
self.assertTrue(
"[gdc_filtration_tools.add_oxog_filters] - Processed 4 records - Tagged 1; Wrote 4"
in serr)
self.assertTrue("[gdc_filtration_tools.main] - Finished!" in serr)
finally:
cleanup_files(fn)
def test_cli(self):
ifa = get_test_data_path("test_oxog_ref.fa")
imaf = get_test_data_path("test_oxog_annotated.maf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
with captured_output() as (_, stderr):
main(["dtoxog-maf-to-vcf", imaf, ifa, fn])
vout = pysam.VariantFile(fn)
for record in vout:
self.assertEqual(record.chrom, "chr1")
self.assertEqual(record.pos, 10)
self.assertEqual(record.alleles, (
"A",
"T",
))
self.assertEqual(record.filter.keys(), ["oxog"])
vout.close()
serr = stderr.getvalue()
self.assertTrue(
"[gdc_filtration_tools.dtoxog_maf_to_vcf] - Creating tabix index..."
in serr)
self.assertTrue(
"[gdc_filtration_tools.dtoxog_maf_to_vcf] - Processed 2 records - Wrote 1"
in serr)
self.assertTrue("[gdc_filtration_tools.main] - Finished!" in serr)
finally:
cleanup_files([fn, fn + ".tbi"])
def test_cli(self):
imets = get_test_data_path("test_oxog_metrics.txt")
vcf_file = get_test_data_path("test_input_for_dtoxog.vcf")
fa_file = get_test_data_path("test_oxog_ref.fa")
(fd, fn) = tempfile.mkstemp()
try:
with captured_output() as (_, stderr):
main(args=[
"create-dtoxog-maf", vcf_file, fn, fa_file, imets, "32.0"
])
with open(fn, "rt") as fh:
self.assertEqual(fh.readline(), "#version 2.4.1\n")
header = fh.readline().rstrip("\r\n").split("\t")
self.assertEqual(header, MAF_COLUMNS)
count = 0
for line in fh:
dat = dict(zip(header,
line.rstrip("\r\n").split("\t")))
self.assertEqual(dat,
TestCreatedToxoGMaf.exp_maf[count])
count += 1
self.assertEqual(count, 3)
serr = stderr.getvalue()
self.assertTrue("Converts a SNP VCF to dToxoG MAF format." in serr)
self.assertTrue("Processed 3 records" in serr)
serr = [i for i in serr.split("\n") if i.rstrip("\r\n")]
self.assertTrue(
"gdc_filtration_tools.create_dtoxog_maf" in serr[0])
self.assertTrue("gdc_filtration_tools.main" in serr[-1])
finally:
cleanup_files(fn)
def test_get_header(self):
ivcf = get_test_data_path("pindel_test.vcf")
vcf = pysam.VariantFile(ivcf)
found_svtype = False
found_fhet = False
found_center = False
try:
res = get_header(vcf.header)
for record in res.records:
if record.type == "INFO":
if record.get("ID", "") == "TYPEOFSV":
self.assertFalse(found_svtype)
found_svtype = True
elif record.get("ID", "") == "forcedHet":
self.assertFalse(found_fhet)
found_fhet = True
elif record.type == "GENERIC" and record.key == "center":
found_center = True
self.assertEqual(list(res.samples), ["NORMAL", "TUMOR"])
finally:
vcf.close()
self.assertTrue(found_svtype)
self.assertTrue(found_fhet)
self.assertFalse(found_center)
def test_filter_contigs(self):
ivcf = get_test_data_path("filter_contigs.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf")
with captured_output() as (_, stderr):
filter_contigs(ivcf, fn)
found = 0
exp_chroms = ["chr1", "chr2"]
rdr = pysam.VariantFile(fn)
try:
for record in rdr:
self.assertTrue(record.chrom in exp_chroms)
found += 1
finally:
rdr.close()
self.assertEqual(found, 2)
cleanup_files(fn)
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
with captured_output() as (_, stderr):
filter_contigs(ivcf, fn)
found = 0
rdr = pysam.VariantFile(fn)
try:
for record in rdr:
self.assertTrue(record.chrom in exp_chroms)
found += 1
finally:
rdr.close()
self.assertEqual(found, 2)
cleanup_files(fn)
def test_build_new_record(self):
ifa = get_test_data_path("test_oxog_ref.fa")
header = generate_header(ifa, "oxog")
maf = {
"Chromosome": "chr1",
"Start_position": "10",
"Reference_Allele": "A",
"Tumor_Seq_Allele1": "T",
}
(fd, fn) = tempfile.mkstemp(suffix=".vcf")
vcf = None
try:
vcf = pysam.VariantFile(fn, mode="w", header=header)
record = build_new_record(maf, vcf, "oxog")
self.assertEqual(record.pos, 10)
self.assertEqual(record.chrom, "chr1")
self.assertEqual(record.alleles, (
"A",
"T",
))
self.assertEqual(record.filter.keys(), ["oxog"])
finally:
if vcf is not None:
vcf.close()
cleanup_files(fn)
def test_cli(self):
ivcf = get_test_data_path("test_somatic_score.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
total = 0
tagged = 0
with captured_output() as (_, stderr):
main(args=["filter-somatic-score", ivcf, fn])
vcf = pysam.VariantFile(fn)
for record in vcf:
total += 1
self.assertTrue(record.pos != 1)
if "ssc40" in record.filter:
tagged += 1
self.assertTrue(record.samples["TUMOR"]["SSC"] == 25)
vcf.close()
self.assertEqual(total, 3)
self.assertEqual(tagged, 1)
serr = stderr.getvalue()
self.assertTrue(
"Filters SomaticSniper VCF files based on Somatic Score." in
serr)
self.assertTrue("Filter tag: ssc40" in serr)
self.assertTrue("Creating tabix index..." in serr)
self.assertTrue(
"Processed 4 records - Removed 1; Tagged 1; Wrote 3" in serr)
serr = [i for i in serr.split("\n") if i.rstrip("\r\n")]
self.assertTrue(
"gdc_filtration_tools.filter_somatic_score" in serr[0])
self.assertTrue("gdc_filtration_tools.main" in serr[-1])
finally:
cleanup_files(fn)
def test_get_context(self):
vcf_file = get_test_data_path("test_input_for_dtoxog.vcf")
fa_file = get_test_data_path("test_oxog_ref.fa")
fasta = pysam.FastaFile(fa_file)
vcf = pysam.VariantFile(vcf_file)
exp = ["CTTGGGGGGGG", "GGGGGGGGGGCGGGGGGGGGG", "GGGGGGGTTTACCGGGGGGGG"]
n = 0
try:
for rec in vcf:
res = get_context(rec, fasta)
self.assertEqual(res, exp[n])
n += 1
finally:
fasta.close()
vcf.close()
def test_cli(self):
ivcf = get_test_data_path("test.vcf")
(fd, fn) = tempfile.mkstemp()
try:
found = []
expected = ["chr1:1", "chr2:1"]
with captured_output() as (_, stderr):
main(args=["create-oxog-intervals", ivcf, fn])
with open(fn, "rt") as fh:
for line in fh:
found.append(line.rstrip("\r\n"))
self.assertEqual(len(found), 2)
self.assertEqual(found, expected)
serr = stderr.getvalue()
self.assertTrue(
"Extracts interval-file for Broad OxoG metrics from VCF." in serr
)
self.assertTrue("Processed 2 records" in serr)
serr = [i for i in serr.split("\n") if i.rstrip("\r\n")]
self.assertTrue("gdc_filtration_tools.create_oxog_intervals" in serr[0])
self.assertTrue("gdc_filtration_tools.main" in serr[-1])
finally:
cleanup_files(fn)
def test_filter_somatic_score_defaults(self):
ivcf = get_test_data_path("test_somatic_score.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
total = 0
tagged = 0
with captured_output() as (_, stderr):
filter_somatic_score(ivcf, fn)
vcf = pysam.VariantFile(fn)
for record in vcf:
total += 1
self.assertTrue(record.pos != 1)
if "ssc40" in record.filter:
tagged += 1
self.assertTrue(record.samples["TUMOR"]["SSC"] == 25)
vcf.close()
self.assertEqual(total, 3)
self.assertEqual(tagged, 1)
serr = stderr.getvalue()
self.assertTrue(
"Filters SomaticSniper VCF files based on Somatic Score." in
serr)
self.assertTrue("Filter tag: ssc40" in serr)
self.assertTrue("Creating tabix index..." in serr)
self.assertTrue(
"Processed 4 records - Removed 1; Tagged 1; Wrote 3" in serr)
finally:
cleanup_files(fn)
def test_cli(self):
ivcf = get_test_data_path("sanger_pindel_test.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
with captured_output() as (_, stderr):
main(["format-sanger-pindel-vcf", ivcf, fn])
vcf = pysam.VariantFile(fn)
self.assertEqual(list(vcf.header.samples), ["NORMAL", "TUMOR"])
rec = next(vcf)
self.assertEqual(rec.pos, 10)
self.assertEqual(rec.samples["TUMOR"]["GT"], (0, 1))
self.assertEqual(rec.samples["NORMAL"]["GT"], (0, 0))
rec = next(vcf)
self.assertEqual(rec.pos, 20)
self.assertEqual(rec.samples["TUMOR"]["GT"], (0, 1))
self.assertEqual(rec.samples["NORMAL"]["GT"], (0, 0))
with self.assertRaises(StopIteration):
rec = next(vcf)
vcf.close()
serr = stderr.getvalue()
self.assertTrue(
"[gdc_filtration_tools.format_sanger_pindel_vcf] - Creating tabix index..."
in serr
)
self.assertTrue(
"[gdc_filtration_tools.format_sanger_pindel_vcf] - Processed 2 records."
in serr
)
self.assertTrue("gdc_filtration_tools.main" in serr)
finally:
cleanup_files(fn)
def test_filter_nonstandard_variants(self):
ivcf = get_test_data_path("test_nonstandard_variants.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
with captured_output() as (_, stderr):
filter_nonstandard_variants(ivcf, fn)
vcf = pysam.VariantFile(fn)
record = next(vcf)
self.assertTrue(record.chrom == "chr1")
record = next(vcf)
self.assertTrue(record.chrom == "chr3")
with self.assertRaises(StopIteration):
record = next(vcf)
vcf.close()
serr = stderr.getvalue()
self.assertTrue("Drops non-ACTG loci from a VCF." in serr)
self.assertTrue("Removing chr2:1:A,R" in serr)
self.assertTrue("Creating tabix index..." in serr)
self.assertTrue("Processed 3 records - Removed 1; Wrote 2" in serr)
finally:
cleanup_files(fn)
def test_cli(self):
ivcf = get_test_data_path("test_nonstandard_variants.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
with captured_output() as (_, stderr):
main(args=["filter-nonstandard-variants", ivcf, fn])
vcf = pysam.VariantFile(fn)
record = next(vcf)
self.assertTrue(record.chrom == "chr1")
record = next(vcf)
self.assertTrue(record.chrom == "chr3")
with self.assertRaises(StopIteration):
record = next(vcf)
vcf.close()
serr = stderr.getvalue()
self.assertTrue("Drops non-ACTG loci from a VCF." in serr)
self.assertTrue("Removing chr2:1:A,R" in serr)
self.assertTrue("Creating tabix index..." in serr)
self.assertTrue("Processed 3 records - Removed 1; Wrote 2" in serr)
serr = [i for i in serr.split("\n") if i.rstrip("\r\n")]
self.assertTrue(
"gdc_filtration_tools.filter_nonstandard_variants" in serr[0])
self.assertTrue("gdc_filtration_tools.main" in serr[-1])
finally:
cleanup_files(fn)
def test_build_header(self):
obj = FakeOpts()
ivcf = get_test_data_path("test.vcf")
vcf = pysam.VariantFile(ivcf)
opts = [vcf] + obj.to_build_header()
res = build_header(*opts)
vcf.close()
self.validate_header(obj, res)
def test_format_gdc_vcf(self):
ivcf = get_test_data_path("test.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
obj = FakeOpts(ivcf, fn)
opts = attr.asdict(obj)
format_gdc_vcf(**opts)
vcf = pysam.VariantFile(fn)
hdr = vcf.header.copy()
vcf.close()
cleanup_files(fn)
self.validate_header(obj, hdr)
def test_generate_maf_record(self):
from gdc_filtration_tools.logger import Logger
imets = get_test_data_path("test_oxog_metrics.txt")
mets = load_oxog(imets)
vcf_file = get_test_data_path("test_input_for_dtoxog.vcf")
fa_file = get_test_data_path("test_oxog_ref.fa")
fasta = pysam.FastaFile(fa_file)
vcf = pysam.VariantFile(vcf_file)
logger = Logger.get_logger("create_dtoxog_maf")
count = 0
try:
for record in vcf:
maf_record = generate_maf_record(record, fasta, mets, 32.0,
logger)
self.assertEqual(maf_record,
TestCreatedToxoGMaf.exp_maf[count])
count += 1
finally:
fasta.close()
vcf.close()
def test_create_dtoxog_maf(self):
imets = get_test_data_path("test_oxog_metrics.txt")
vcf_file = get_test_data_path("test_input_for_dtoxog.vcf")
fa_file = get_test_data_path("test_oxog_ref.fa")
(fd, fn) = tempfile.mkstemp()
try:
with captured_output() as (_, stderr):
create_dtoxog_maf(vcf_file, fn, fa_file, imets, 32.0)
with open(fn, "rt") as fh:
self.assertEqual(fh.readline(), "#version 2.4.1\n")
header = fh.readline().rstrip("\r\n").split("\t")
self.assertEqual(header, MAF_COLUMNS)
count = 0
for line in fh:
dat = dict(zip(header,
line.rstrip("\r\n").split("\t")))
self.assertEqual(dat,
TestCreatedToxoGMaf.exp_maf[count])
count += 1
serr = stderr.getvalue().split("\n")
self.assertTrue("Processed 3 records" in serr[2])
finally:
cleanup_files(fn)
def test_add_oxog_filters(self):
oxo_vcf = get_test_data_path(
"test_input_for_add_oxog_filters_from_maf.vcf.gz")
vcf_file = get_test_data_path("test_input_for_add_oxog_filters.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf")
try:
with captured_output() as (_, stderr):
add_oxog_filters(vcf_file, oxo_vcf, fn)
vcf = pysam.VariantFile(fn)
self.assertEqual(vcf.header.filters.keys(), ["PASS", "oxog"])
for record in vcf:
if (record.contig == "chr1" and record.pos == 10
and record.alleles == (
"A",
"T",
)):
self.assertEqual(record.filter.keys(), ["oxog"])
else:
self.assertEqual(record.filter.keys(), ["PASS"])
vcf.close()
serr = stderr.getvalue()
self.assertTrue("Processed 4 records - Tagged 1; Wrote 4" in serr)
finally:
cleanup_files(fn)
def test_cli(self):
ivcf = get_test_data_path("test.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
obj = FakeOpts(ivcf, fn)
params = obj.to_cli_list()
with captured_output() as (_, stderr):
main(args=params)
vcf = pysam.VariantFile(fn)
hdr = vcf.header.copy()
vcf.close()
cleanup_files(fn)
self.validate_header(obj, hdr)
serr = [i for i in stderr.getvalue().split("\n") if i.rstrip("\r\n")]
self.assertTrue("gdc_filtration_tools.format_gdc_vcf" in serr[0])
self.assertTrue("gdc_filtration_tools.main" in serr[-1])
def test_position_filter_dkfz(self):
ivcf = get_test_data_path("test_dfkz.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
total = 0
with captured_output() as (_, stderr):
position_filter_dkfz(ivcf, fn)
vcf = pysam.VariantFile(fn)
for record in vcf:
total += 1
self.assertEqual(record.chrom, "chr2")
vcf.close()
self.assertEqual(total, 1)
serr = stderr.getvalue()
self.assertTrue("Position Filter for DKFZ." in serr)
self.assertTrue("Creating tabix index..." in serr)
self.assertTrue("Processed 2 records - Removed 1; Wrote 1" in serr)
finally:
cleanup_files(fn)
def test_create_oxog_intervals(self):
ivcf = get_test_data_path("test.vcf")
(fd, fn) = tempfile.mkstemp()
try:
found = []
expected = ["chr1:1", "chr2:1"]
with captured_output() as (_, stderr):
create_oxog_intervals(ivcf, fn)
with open(fn, "rt") as fh:
for line in fh:
found.append(line.rstrip("\r\n"))
self.assertEqual(len(found), 2)
self.assertEqual(found, expected)
serr = stderr.getvalue()
self.assertTrue(
"Extracts interval-file for Broad OxoG metrics from VCF." in serr
)
self.assertTrue("Processed 2 records" in serr)
finally:
cleanup_files(fn)
def test_cli(self):
ivcf = get_test_data_path("test_dfkz.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
total = 0
with captured_output() as (_, stderr):
main(args=["position-filter-dkfz", ivcf, fn])
vcf = pysam.VariantFile(fn)
for record in vcf:
total += 1
self.assertEqual(record.chrom, "chr2")
vcf.close()
self.assertEqual(total, 1)
serr = stderr.getvalue()
self.assertTrue("Position Filter for DKFZ." in serr)
self.assertTrue("Creating tabix index..." in serr)
self.assertTrue("Processed 2 records - Removed 1; Wrote 1" in serr)
serr = [i for i in serr.split("\n") if i.rstrip("\r\n")]
self.assertTrue(
"gdc_filtration_tools.position_filter_dkfz" in serr[0])
self.assertTrue("gdc_filtration_tools.main" in serr[-1])
finally:
cleanup_files(fn)
def test_format_pindel_vcf(self):
ivcf = get_test_data_path("pindel_test.vcf")
(fd, fn) = tempfile.mkstemp(suffix=".vcf.gz")
try:
with captured_output() as (_, stderr):
format_pindel_vcf(ivcf, fn)
vcf = pysam.VariantFile(fn)
self.assertEqual(list(vcf.header.samples), ["NORMAL", "TUMOR"])
rec = next(vcf)
self.assertEqual(rec.info.get("TYPEOFSV"), "INS")
with self.assertRaises(ValueError):
rec.info.get("SVTYPE")
self.assertFalse(rec.info.get("forcedHet"))
self.assertEqual(rec.samples["TUMOR"]["GT"], (0, 1))
rec = next(vcf)
self.assertEqual(rec.info.get("TYPEOFSV"), "INS")
self.assertTrue(rec.info.get("forcedHet"))
self.assertEqual(rec.samples["TUMOR"]["GT"], (0, 1))
with self.assertRaises(StopIteration):
rec = next(vcf)
vcf.close()
serr = stderr.getvalue()
self.assertTrue(
"[gdc_filtration_tools.format_pindel_vcf] - Creating tabix index..."
in serr
)
self.assertTrue(
"[gdc_filtration_tools.format_pindel_vcf] - Processed 2 records."
in serr
)
finally:
cleanup_files(fn)
def test_generate_header(self):
ifa = get_test_data_path("test_oxog_ref.fa")
header = generate_header(ifa, "TEST")
self.assertEqual(header.filters.keys(), ["PASS", "TEST"])
self.assertEqual(list(header.contigs), ["chr1"])
self.assertEqual(header.contigs.get("chr1").length, 100)
def test_load_oxog(self):
imets = get_test_data_path("test_oxog_metrics.txt")
res = load_oxog(imets)
self.assertEqual(res, TestCreatedToxoGMaf.exp_oxog)
