def main(argv):
with errors.clean_commandline_error_exit():
if len(argv) > 1:
errors.log_and_raise(
'Command line parsing failure: vcf_stats_report does not accept '
'positional arguments but some are present on the command line: '
'"{}".'.format(str(argv[1:])), errors.CommandLineError)
with vcf.VcfReader(FLAGS.input_vcf) as reader:
sample_names = reader.header.sample_names
if len(sample_names) != 1:
raise ValueError(
'There must be exactly one sample in VCF: {}'.format(
FLAGS.input_vcf))
sample_name = sample_names[0]
# Missing GT causes error later while reading, so throw a clearer error here
vcf_columns = [col.id for col in reader.header.formats]
if 'GT' not in vcf_columns:
errors.log_and_raise('ERROR: No GT sub-column in VCF.')
if FLAGS.num_records == -1:
variants = reader.iterate()
else:
variants = itertools.islice(reader.iterate(), FLAGS.num_records)
vcf_stats.create_vcf_report(variants,
output_basename=FLAGS.outfile_base,
sample_name=sample_name,
vcf_reader=reader)
def test_create_vcf_report(self):
base_dir = tempfile.mkdtemp()
outfile_base = os.path.join(base_dir, 'stats_test')
sample_name = 'test_sample_name'
with vcf.VcfReader(testdata.GOLDEN_POSTPROCESS_OUTPUT) as reader:
vcf_stats.create_vcf_report(variants=reader.iterate(),
output_basename=outfile_base,
sample_name=sample_name,
vcf_reader=reader)
self.assertTrue(
tf.io.gfile.exists(outfile_base + '.visual_report.html'))
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:
logging.info('call_variants_output is empty. Writing out empty VCF.')
sample_name = dv_constants.DEFAULT_SAMPLE_NAME
if FLAGS.sample_name:
logging.info(
'--sample_name is set in postprocess_variant. Using %s as the '
'sample name.', FLAGS.sample_name)
sample_name = FLAGS.sample_name
variant_generator = iter([])
else:
sample_name = _extract_single_sample_name(record)
temp = tempfile.NamedTemporaryFile()
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.')
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,
group_variants=FLAGS.group_variants,
use_multiallelic_model=FLAGS.use_multiallelic_model)
variant_generator = haplotypes.maybe_resolve_conflicting_variants(
independent_variants)
header = dv_vcf_constants.deepvariant_header(
contigs=contigs, sample_names=[sample_name])
use_csi = _decide_to_use_csi(contigs)
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'):
build_index(FLAGS.outfile, use_csi)
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'):
build_index(FLAGS.outfile, use_csi)
if FLAGS.gvcf_outfile.endswith('.gz'):
build_index(FLAGS.gvcf_outfile, use_csi)
logging.info('Finished writing VCF and gVCF in %s minutes.',
(time.time() - start_time) / 60)
if FLAGS.vcf_stats_report:
outfile_base = _get_base_path(FLAGS.outfile)
with vcf.VcfReader(FLAGS.outfile) as reader:
vcf_stats.create_vcf_report(
variants=reader.iterate(),
output_basename=outfile_base,
sample_name=sample_name,
vcf_reader=reader)
if record:
temp.close()