def add_call_to_variant(variant, predictions, qual_filter=0, sample_name=None):
"""Fills in Variant record using the prediction probabilities.
This functions sets the call[0].genotype, call[0].info['GQ'],
call[0].genotype_probabilities, variant.filter, and variant.quality fields of
variant based on the genotype likelihoods in predictions.
Args:
variant: third_party.nucleus.protos.Variant protobuf
to be filled in with info derived from predictions.
predictions: N element array-like. The real-space probabilities of each
genotype state for this variant.
qual_filter: float. If predictions implies that this isn't a reference call
and the QUAL of the prediction isn't larger than qual_filter variant will
be marked as FILTERed.
sample_name: str. The name of the sample to assign to the Variant proto
call_set_name field.
Returns:
A Variant record.
Raises:
ValueError: If variant doesn't have exactly one variant.call record.
"""
call = variant_utils.only_call(variant)
n_alleles = len(variant.alternate_bases) + 1
index, genotype = most_likely_genotype(predictions, n_alleles=n_alleles)
gq, variant.quality = compute_quals(predictions, index)
call.call_set_name = sample_name
variantcall_utils.set_gt(call, genotype)
variantcall_utils.set_gq(call, gq)
gls = [genomics_math.perror_to_bounded_log10_perror(gp) for gp in predictions]
variantcall_utils.set_gl(call, gls)
variant.filter[:] = compute_filter_fields(variant, qual_filter)
return variant
def add_call_to_variant(variant, predictions, qual_filter=0, sample_name=None):
"""Fills in Variant record using the prediction probabilities.
This functions sets the call[0].genotype, call[0].info['GQ'],
call[0].genotype_probabilities, variant.filter, and variant.quality fields of
variant based on the genotype likelihoods in predictions.
Args:
variant: third_party.nucleus.protos.Variant protobuf
to be filled in with info derived from predictions.
predictions: N element array-like. The real-space probabilities of each
genotype state for this variant.
qual_filter: float. If predictions implies that this isn't a reference call
and the QUAL of the prediction isn't larger than qual_filter variant will
be marked as FILTERed.
sample_name: str. The name of the sample to assign to the Variant proto
call_set_name field.
Returns:
A Variant record.
Raises:
ValueError: If variant doesn't have exactly one variant.call record.
"""
call = variant_utils.only_call(variant)
n_alleles = len(variant.alternate_bases) + 1
index, genotype = most_likely_genotype(predictions, n_alleles=n_alleles)
gq, variant.quality = compute_quals(predictions, index)
call.call_set_name = sample_name
variantcall_utils.set_gt(call, genotype)
variantcall_utils.set_gq(call, gq)
gls = [
genomics_math.perror_to_bounded_log10_perror(gp) for gp in predictions
]
variantcall_utils.set_gl(call, gls)
variant.filter[:] = compute_filter_fields(variant, qual_filter)
uncall_homref_gt_if_lowqual(variant, FLAGS.cnn_homref_call_min_gq)
return variant
def test_log10_prob(self, prob, bound, expected):
if bound:
actual = genomics_math.perror_to_bounded_log10_perror(prob, bound)
else:
actual = genomics_math.perror_to_bounded_log10_perror(prob)
self.assertAlmostEqual(actual, expected, places=6)
def test_log10_prob(self, prob, bound, expected):
if bound:
actual = genomics_math.perror_to_bounded_log10_perror(prob, bound)
else:
actual = genomics_math.perror_to_bounded_log10_perror(prob)
self.assertAlmostEqual(actual, expected, places=6)
