def test_expand_raises_with_missing_contig_in_map(self):
# Empty contig_map should raise.
with self.assertRaises(KeyError):
ranges.expand(ranges.make_range('1', 10, 20), 1, contig_map={})
# Missing '1' from the contig map should raise.
with self.assertRaises(KeyError):
ranges.expand(
ranges.make_range('1', 10, 20),
1,
contig_map={
'2': reference_pb2.ContigInfo(name='2', n_bases=50),
})
def _candidates_from_reads(config, ref_reader, reads, region):
"""Returns a list of candidate positions.
Args:
config: learning.genomics.deepvariant.realigner.WindowSelectorOptions
options determining the behavior of this window selector.
ref_reader: GenomeReference. Indexed reference genome to query bases.
reads: list[nucleus.protos.Read]. The reads we are processing into candidate
positions.
region: nucleus.protos.Range. The region we are processing.
Returns:
A list. The elements are reference positions within region.
Raises:
ValueError: if config.window_selector_model.model_type isn't a valid enum
name in realigner_pb2.WindowSelectorModel.ModelType.
"""
allele_counter_options = deepvariant_pb2.AlleleCounterOptions(
read_requirements=reads_pb2.ReadRequirements(
min_mapping_quality=config.min_mapq,
min_base_quality=config.min_base_quality),
keep_legacy_behavior=config.keep_legacy_behavior)
expanded_region = ranges.expand(region,
config.region_expansion_in_bp,
contig_map=ranges.contigs_dict(
ref_reader.header.contigs))
allele_counter = allelecounter.AlleleCounter(ref_reader.c_reader,
expanded_region, [],
allele_counter_options)
for read in reads:
allele_counter.add(read, 'placeholder_sample_id')
model_type = config.window_selector_model.model_type
if model_type == realigner_pb2.WindowSelectorModel.VARIANT_READS:
return _variant_reads_threshold_selector(
allele_counter, config.window_selector_model.variant_reads_model,
expanded_region)
elif model_type == realigner_pb2.WindowSelectorModel.ALLELE_COUNT_LINEAR:
return _allele_count_linear_selector(
allele_counter,
config.window_selector_model.allele_count_linear_model,
expanded_region)
else:
raise ValueError('Unknown enum option "{}" for '
'WindowSelectorModel.model_type'.format(
config.window_selector_model.model_type))
def _label_grouped_variants(self, variants):
# redacted
# redacted
# they should be computed in the grouping.
span = ranges.span([variant_utils.variant_range(v) for v in variants])
truths = list(
self._get_truth_variants(
ranges.expand(span,
_TRUTH_VARIANTS_QUERY_REGION_EXPANSION_IN_BP)))
if len(truths) > self.max_group_size:
logging.warning((
'Found a large number of variants to label (n_candidates=%d, '
'n_truth=%d) relative to candidate cap of %d. This may make the '
'algorithm very slow.'), len(variants), len(truths),
self.max_group_size)
# redacted
logging.warning(
'Returning all variants with not-confident markers.')
for variant in variants:
yield variant_labeler.VariantLabel(is_confident=False,
genotype=(-1, -1),
variant=variant)
return
ref = self.make_labeler_ref(variants, truths)
labeled_variants = label_variants(variants, truths, ref)
if not labeled_variants:
raise ValueError('Failed to assign labels for variants', variants)
else:
for labeled in labeled_variants:
yield variant_labeler.VariantLabel(
# redacted
# now. Rethink how we establish a variant is confident. Seems like
# it'd be confident if it has a non-ref genotype (as we only
# consider confident truth variants) or if it overlaps the confident
# regions.
is_confident=self._confident_regions.variant_overlaps(
labeled),
genotype=tuple(labeled.calls[0].genotype),
variant=labeled)
def _label_grouped_variants(self, variants):
# redacted
# redacted
# they should be computed in the grouping.
span = ranges.span([variant_utils.variant_range(v) for v in variants])
truths = list(
self._get_truth_variants(
ranges.expand(span, _TRUTH_VARIANTS_QUERY_REGION_EXPANSION_IN_BP)))
if len(truths) > self.max_group_size:
logging.warning(
('Found a large number of variants to label (n_candidates=%d, '
'n_truth=%d) relative to candidate cap of %d. This may make the '
'algorithm very slow.'), len(variants), len(truths),
self.max_group_size)
# redacted
logging.warning('Returning all variants with not-confident markers.')
for variant in variants:
yield variant_labeler.VariantLabel(
is_confident=False, genotype=(-1, -1), variant=variant)
return
ref = self.make_labeler_ref(variants, truths)
labeled_variants = label_variants(variants, truths, ref)
if not labeled_variants:
raise ValueError('Failed to assign labels for variants', variants)
else:
for labeled in labeled_variants:
yield variant_labeler.VariantLabel(
# redacted
# now. Rethink how we establish a variant is confident. Seems like
# it'd be confident if it has a non-ref genotype (as we only
# consider confident truth variants) or if it overlaps the confident
# regions.
is_confident=self._confident_regions.variant_overlaps(labeled),
genotype=tuple(labeled.calls[0].genotype),
variant=labeled)
def test_expand_raises_on_negative_n_bp(self):
with self.assertRaisesRegexp(ValueError, 'n_bp must be >= 0 but got -10'):
ranges.expand(ranges.make_range('1', 10, 20), -10)
def test_expand_handles_boundaries(self, region, n_bp, contig_map, expected): self.assertEqual(expected, ranges.expand(region, n_bp, contig_map))
def test_expand_is_correct(self, region, n_bp, contig_map, expected): self.assertEqual(expected, ranges.expand(region, n_bp, contig_map))
