def test_variant_position_and_range(self):
v1 = test_utils.make_variant(chrom='1', alleles=['A', 'C'], start=10)
v2 = test_utils.make_variant(chrom='1',
alleles=['AGCT', 'C'],
start=10)
pos = ranges.make_range('1', 10, 11)
range_ = ranges.make_range('1', 10, 14)
self.assertEqual(pos, variantutils.variant_position(v1))
self.assertEqual(pos, variantutils.variant_position(v2))
self.assertEqual(pos, variantutils.variant_range(v1))
self.assertEqual(range_, variantutils.variant_range(v2))
def _transform_call_variants_output_to_variants(input_sorted_tfrecord_path,
qual_filter,
multi_allelic_qual_filter,
sample_name):
"""Yields Variant protos in sorted order from CallVariantsOutput protos.
Variants present in the input TFRecord are converted to Variant protos, with
the following filters applied: 1) variants are omitted if their quality is
lower than the `qual_filter` threshold. 2) multi-allelic variants omit
individual alleles whose qualities are lower than the
`multi_allelic_qual_filter` threshold.
Args:
input_sorted_tfrecord_path: str. TFRecord format file containing sorted
CallVariantsOutput protos.
qual_filter: double. The qual value below which to filter variants.
multi_allelic_qual_filter: double. The qual value below which to filter
multi-allelic variants.
sample_name: str. Sample name to write to VCF file.
Yields:
Variant protos in sorted order representing the CallVariantsOutput calls.
"""
for _, group in itertools.groupby(
io_utils.read_tfrecords(input_sorted_tfrecord_path,
proto=deepvariant_pb2.CallVariantsOutput),
lambda x: variantutils.variant_range(x.variant)):
outputs = list(group)
canonical_variant, predictions = merge_predictions(
outputs, multi_allelic_qual_filter)
variant = add_call_to_variant(canonical_variant,
predictions,
qual_filter=qual_filter,
sample_name=sample_name)
yield variant
def write_call_variants_output_to_vcf(contigs, input_sorted_tfrecord_path,
output_vcf_path, qual_filter,
multi_allelic_qual_filter, sample_name):
"""Reads CallVariantsOutput protos and writes to a VCF file.
Variants present in the input TFRecord are converted to VCF format, with the
following filters applied: 1) variants are omitted if their quality is lower
than the `qual_filter` threshold. 2) multi-allelic variants omit individual
alleles whose qualities are lower than the `multi_allelic_qual_filter`
threshold.
Args:
contigs: list(ContigInfo). A list of the reference genome contigs for
writers that need contig information.
input_sorted_tfrecord_path: str. TFRecord format file containing sorted
CallVariantsOutput protos.
output_vcf_path: str. Output file in VCF format.
qual_filter: double. The qual value below which to filter variants.
multi_allelic_qual_filter: double. The qual value below which to filter
multi-allelic variants.
sample_name: str. Sample name to write to VCF file.
"""
logging.info('Writing calls to VCF file: %s', output_vcf_path)
sync_writer, writer_fn = genomics_io.make_variant_writer(
output_vcf_path, contigs, samples=[sample_name], filters=FILTERS)
with sync_writer, io_utils.AsyncWriter(writer_fn) as writer:
for _, group in itertools.groupby(
io_utils.read_tfrecords(
input_sorted_tfrecord_path,
proto=deepvariant_pb2.CallVariantsOutput),
lambda x: variantutils.variant_range(x.variant)):
outputs = list(group)
canonical_variant, predictions = merge_predictions(
outputs, multi_allelic_qual_filter)
variant = add_call_to_variant(canonical_variant,
predictions,
qual_filter=qual_filter,
sample_name=sample_name)
writer.write(variant)
def _fake_query(region):
return [
variant for variant in variants if ranges.ranges_overlap(
variantutils.variant_range(variant), region)
]