def test_vcf_query(self):
tabix.build_index(self.output_file)
self.input_reader = vcf.VcfReader(self.input_file)
self.output_reader = vcf.VcfReader(self.output_file)
range1 = ranges.parse_literal('chr3:100,000-500,000')
self.assertEqual(
list(self.input_reader.query(range1)),
list(self.output_reader.query(range1)))
def build_index(vcf_file, csi=False):
"""A helper function for indexing VCF files.
Args:
vcf_file: string. Path to the VCF file to be indexed.
csi: bool. If true, index using the CSI format.
"""
if csi:
tabix.build_csi_index(vcf_file, min_shift=14)
else:
tabix.build_index(vcf_file)
def test_build_index(self): self.assertFalse(gfile.Exists(self.tbx_index_file)) tabix.build_index(self.output_file) self.assertTrue(gfile.Exists(self.tbx_index_file))
def main(argv=()):
with errors.clean_commandline_error_exit():
if len(argv) > 1:
errors.log_and_raise(
'Command line parsing failure: postprocess_variants does not accept '
'positional arguments but some are present on the command line: '
'"{}".'.format(str(argv)), errors.CommandLineError)
del argv # Unused.
if (not FLAGS.nonvariant_site_tfrecord_path) != (
not FLAGS.gvcf_outfile):
errors.log_and_raise(
'gVCF creation requires both nonvariant_site_tfrecord_path and '
'gvcf_outfile flags to be set.', errors.CommandLineError)
proto_utils.uses_fast_cpp_protos_or_die()
logging_level.set_from_flag()
fasta_reader = fasta.IndexedFastaReader(FLAGS.ref,
cache_size=_FASTA_CACHE_SIZE)
contigs = fasta_reader.header.contigs
paths = sharded_file_utils.maybe_generate_sharded_filenames(
FLAGS.infile)
# Read one CallVariantsOutput record and extract the sample name from it.
# Note that this assumes that all CallVariantsOutput protos in the infile
# contain a single VariantCall within their constituent Variant proto, and
# that the call_set_name is identical in each of the records.
record = tf_utils.get_one_example_from_examples_path(
','.join(paths), proto=deepvariant_pb2.CallVariantsOutput)
if record is None:
raise ValueError('Cannot find any records in {}'.format(
','.join(paths)))
sample_name = _extract_single_sample_name(record)
header = dv_vcf_constants.deepvariant_header(
contigs=contigs, sample_names=[sample_name])
with tempfile.NamedTemporaryFile() as temp:
start_time = time.time()
postprocess_variants_lib.process_single_sites_tfrecords(
contigs, paths, temp.name)
logging.info('CVO sorting took %s minutes',
(time.time() - start_time) / 60)
logging.info('Transforming call_variants_output to variants.')
start_time = time.time()
independent_variants = _transform_call_variants_output_to_variants(
input_sorted_tfrecord_path=temp.name,
qual_filter=FLAGS.qual_filter,
multi_allelic_qual_filter=FLAGS.multi_allelic_qual_filter,
sample_name=sample_name)
variant_generator = haplotypes.maybe_resolve_conflicting_variants(
independent_variants)
start_time = time.time()
if not FLAGS.nonvariant_site_tfrecord_path:
logging.info('Writing variants to VCF.')
write_variants_to_vcf(variant_iterable=variant_generator,
output_vcf_path=FLAGS.outfile,
header=header)
if FLAGS.outfile.endswith('.gz'):
tabix.build_index(FLAGS.outfile)
logging.info('VCF creation took %s minutes',
(time.time() - start_time) / 60)
else:
logging.info('Merging and writing variants to VCF and gVCF.')
lessthanfn = _get_contig_based_lessthan(contigs)
with vcf.VcfWriter(
FLAGS.outfile, header=header, round_qualities=True) as vcf_writer, \
vcf.VcfWriter(
FLAGS.gvcf_outfile, header=header, round_qualities=True) \
as gvcf_writer:
nonvariant_generator = tfrecord.read_shard_sorted_tfrecords(
FLAGS.nonvariant_site_tfrecord_path,
key=_get_contig_based_variant_sort_keyfn(contigs),
proto=variants_pb2.Variant)
merge_and_write_variants_and_nonvariants(
variant_generator, nonvariant_generator, lessthanfn,
fasta_reader, vcf_writer, gvcf_writer)
if FLAGS.outfile.endswith('.gz'):
tabix.build_index(FLAGS.outfile)
if FLAGS.gvcf_outfile.endswith('.gz'):
tabix.build_index(FLAGS.gvcf_outfile)
logging.info('Finished writing VCF and gVCF in %s minutes.',
(time.time() - start_time) / 60)