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_span_raises_on_bad_input(self, regions, regexp):
with self.assertRaisesRegexp(ValueError, regexp):
ranges.span(regions)
def test_span_computes_span_correctly(self, regions, expected_span):
for permutation in itertools.permutations(regions, len(regions)):
self.assertEqual(expected_span, ranges.span(permutation))