def test_roundtrip(self,
expected_infos,
expected_fmt,
expected_fmt1,
expected_fmt2,
reader_excluded_info=None,
reader_excluded_format=None,
writer_excluded_info=None,
writer_excluded_format=None):
expected_records = [
record.format(info=info, fmt=expected_fmt, efmts1=e1,
efmts2=e2) for record, info, e1, e2 in zip(
self.record_format_strings, expected_infos,
expected_fmt1, expected_fmt2)
]
expected = self.header + ''.join(expected_records)
with vcf.VcfReader(
test_utils.genomics_core_testdata('test_py_roundtrip.vcf'),
excluded_info_fields=reader_excluded_info,
excluded_format_fields=reader_excluded_format) as reader:
records = list(reader.iterate())
output_path = test_utils.test_tmpfile('test_roundtrip_tmpfile.vcf')
with vcf.VcfWriter(
output_path,
header=reader.header,
excluded_info_fields=writer_excluded_info,
excluded_format_fields=writer_excluded_format) as writer:
for record in records:
writer.write(record)
with open(output_path) as f:
actual = f.read()
self.assertEqual(actual, expected)
def main(argv):
del argv
priors = map(float, FLAGS.genotype_priors)
sump = sum(priors)
log_priors = [math.log10(x / sump) for x in priors]
with vcf.VcfReader(FLAGS.input_vcf) as reader:
with vcf.VcfWriter(FLAGS.output_vcf, header=reader.header) as writer:
for variant in reader:
recall_variant(log_priors, variant)
# TODO(thomaswc): Also update the variant's quality.
writer.write(variant)
def test_headerless_vcf(self):
"""Writes a headerless vcf and reads it back out."""
test_vcf = test_utils.genomics_core_testdata('test_sites.vcf')
output_vcf = test_utils.test_tmpfile('output.vcf')
expected_variants = []
with vcf.VcfReader(test_vcf) as reader:
with vcf.VcfWriter(
output_vcf, header=reader.header, exclude_header=True) as writer:
for record in reader:
expected_variants.append(record)
writer.write(record)
with vcf.VcfReader(output_vcf, header=reader.header) as actual_reader:
self.assertEqual(expected_variants, list(actual_reader))
def main(argv):
if len(argv) != 3:
print('Usage: {} <input_vcf> <output_vcf>'.format(argv[0]))
sys.exit(-1)
in_vcf = argv[1]
out_vcf = argv[2]
# Please try to keep the following part in sync with the documenation in
# g3doc/overview.md.
with vcf.VcfReader(in_vcf, use_index=False) as reader:
print('Sample names in VCF: ', ' '.join(reader.header.sample_names))
with vcf.VcfWriter(out_vcf, header=reader.header) as writer:
for variant in reader:
if variant.quality > 3.01:
writer.write(variant)
def write_variant_to_tempfile(self, variant):
output_path = test_utils.test_tmpfile('test.vcf')
header = variants_pb2.VcfHeader(
contigs=[reference_pb2.ContigInfo(name='20')],
sample_names=[call.call_set_name for call in variant.calls],
formats=[
variants_pb2.VcfFormatInfo(
id='DP', number='1', type='Integer', description='Read depth'),
variants_pb2.VcfFormatInfo(
id='AD',
number='R',
type='Integer',
description='Read depth for each allele')
])
writer = vcf.VcfWriter(output_path, header=header)
with writer:
writer.write(variant)
return output_path
def main(argv):
if len(argv) != 3:
print('Usage: %s <input_vcf> <output_vcf>' % argv[0])
sys.exit(-1)
in_vcf = argv[1]
out_vcf = argv[2]
with vcf.VcfReader(in_vcf) as reader:
if 'AD' in [info.id for info in reader.header.infos]:
print('%s already contains AD field.' % in_vcf)
sys.exit(-1)
out_header = reader.header
out_header.infos.extend([vcf_constants.reserved_info_field('AD')])
with vcf.VcfWriter(out_vcf, header=out_header) as writer:
for variant in reader:
variant_utils.set_info(variant, 'AD', get_variant_ad(variant),
writer)
writer.write(variant)
