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 make_gvcfs(self, allele_count_summaries):
"""Primary interface function for computing gVCF confidence at a site.
Looks at the counts in the provided list of AlleleCountSummary protos and
returns properly-formatted Variant protos containing gVCF reference
blocks for all sites in allele_count_summaries. The returned Variant has
reference_name, start, end are set and contains a single VariantCall in the
calls field with call_set_name of options.sample_name, genotypes set to 0/0
(diploid reference), a GQ value bound in the info field appropriate to the
data in allele_count, and a MIN_DP value which is the minimum read coverage
seen in the block.
The provided allele count must have either a canonical DNA sequence base (
A, C, G, T) or be "N".
Args:
allele_count_summaries: iterable of AlleleCountSummary protos in
coordinate-sorted order. Each proto is used to get the read counts for
reference and alternate alleles, the reference position, and reference
base.
Yields:
third_party.nucleus.protos.Variant proto in
coordinate-sorted order containing gVCF records.
"""
def with_gq_and_likelihoods(summary_counts):
"""Returns summary_counts along with GQ and genotype likelihoods.
If the reference base is not in CANONICAL_DNA_BASES, both GQ and genotype
likelihoods are set to None.
Args:
summary_counts: A single AlleleCountSummary.
Returns:
A tuple of summary_counts, quantized GQ, raw GQ, and genotype
likelihoods for summary_counts where raw GQ and genotype_likelihood are
calculated by self.reference_confidence.
Raises:
ValueError: The reference base is not a valid DNA or IUPAC base.
"""
if summary_counts.ref_base not in CANONICAL_DNA_BASES:
if summary_counts.ref_base in EXTENDED_IUPAC_CODES:
# Skip calculating gq and likelihoods, since this is an ambiguous
# reference base.
quantized_gq, raw_gq, likelihoods = None, None, None
n_total = summary_counts.total_read_count
else:
raise ValueError(
'Invalid reference base={} found during gvcf '
'calculation'.format(summary_counts.ref_base))
else:
n_ref = summary_counts.ref_supporting_read_count
n_total = summary_counts.total_read_count
raw_gq, likelihoods = self.reference_confidence(n_ref, n_total)
quantized_gq = _quantize_gq(raw_gq, self.options.gq_resolution)
return _GVCF(summary_counts=summary_counts,
quantized_gq=quantized_gq,
raw_gq=raw_gq,
likelihoods=likelihoods,
read_depth=n_total)
# Combines contiguous, compatible single-bp blocks into larger gVCF blocks,
# respecting non-reference variants interspersed among them. Yields each
# combined gVCF Variant proto, in order. Compatible right now means that the
# blocks to be merged have the same non-None GQ value.
for key, combinable in itertools.groupby(
(with_gq_and_likelihoods(sc) for sc in allele_count_summaries),
key=operator.attrgetter('quantized_gq')):
if key is None:
# A None key indicates that a non-DNA reference base was encountered, so
# skip this group.
continue
combinable = list(combinable)
min_gq = min(elt.raw_gq for elt in combinable)
min_dp = min(elt.read_depth for elt in combinable)
first_record, last_record = combinable[0], combinable[-1]
call = variants_pb2.VariantCall(
call_set_name=self.options.sample_name,
genotype=[0, 0],
genotype_likelihood=first_record.likelihoods)
variantcall_utils.set_gq(call, min_gq)
variantcall_utils.set_min_dp(call, min_dp)
yield variants_pb2.Variant(
reference_name=first_record.summary_counts.reference_name,
reference_bases=first_record.summary_counts.ref_base,
alternate_bases=[vcf_constants.GVCF_ALT_ALLELE],
start=first_record.summary_counts.position,
end=last_record.summary_counts.position + 1,
calls=[call])
def make_gvcfs(self, allele_count_summaries):
"""Primary interface function for computing gVCF confidence at a site.
Looks at the counts in the provided list of AlleleCountSummary protos and
returns properly-formatted Variant protos containing gVCF reference
blocks for all sites in allele_count_summaries. The returned Variant has
reference_name, start, end are set and contains a single VariantCall in the
calls field with call_set_name of options.sample_name, genotypes set to 0/0
(diploid reference), a GQ value bound in the info field appropriate to the
data in allele_count, and a MIN_DP value which is the minimum read coverage
seen in the block.
The provided allele count must have either a canonical DNA sequence base (
A, C, G, T) or be "N".
Args:
allele_count_summaries: iterable of AlleleCountSummary protos in
coordinate-sorted order. Each proto is used to get the read counts for
reference and alternate alleles, the reference position, and reference
base.
Yields:
third_party.nucleus.protos.Variant proto in
coordinate-sorted order containing gVCF records.
"""
def with_gq_and_likelihoods(summary_counts):
"""Returns summary_counts along with GQ and genotype likelihoods.
If the reference base is not in CANONICAL_DNA_BASES, both GQ and genotype
likelihoods are set to None.
Args:
summary_counts: A single AlleleCountSummary.
Returns:
A tuple of summary_counts, quantized GQ, raw GQ, and genotype
likelihoods for summary_counts where raw GQ and genotype_likelihood are
calculated by self.reference_confidence.
Raises:
ValueError: The reference base is not a valid DNA or IUPAC base.
"""
if summary_counts.ref_base not in CANONICAL_DNA_BASES:
if summary_counts.ref_base in EXTENDED_IUPAC_CODES:
# Skip calculating gq and likelihoods, since this is an ambiguous
# reference base.
quantized_gq, raw_gq, likelihoods = None, None, None
n_total = summary_counts.total_read_count
else:
raise ValueError('Invalid reference base={} found during gvcf '
'calculation'.format(summary_counts.ref_base))
else:
n_ref = summary_counts.ref_supporting_read_count
n_total = summary_counts.total_read_count
raw_gq, likelihoods = self.reference_confidence(n_ref, n_total)
quantized_gq = _quantize_gq(raw_gq, self.options.gq_resolution)
return _GVCF(
summary_counts=summary_counts,
quantized_gq=quantized_gq,
raw_gq=raw_gq,
likelihoods=likelihoods,
read_depth=n_total)
# Combines contiguous, compatible single-bp blocks into larger gVCF blocks,
# respecting non-reference variants interspersed among them. Yields each
# combined gVCF Variant proto, in order. Compatible right now means that the
# blocks to be merged have the same non-None GQ value.
for key, combinable in itertools.groupby(
(with_gq_and_likelihoods(sc) for sc in allele_count_summaries),
key=operator.attrgetter('quantized_gq')):
if key is None:
# A None key indicates that a non-DNA reference base was encountered, so
# skip this group.
continue
combinable = list(combinable)
min_gq = min(elt.raw_gq for elt in combinable)
min_dp = min(elt.read_depth for elt in combinable)
first_record, last_record = combinable[0], combinable[-1]
call = variants_pb2.VariantCall(
call_set_name=self.options.sample_name,
genotype=[0, 0],
genotype_likelihood=first_record.likelihoods)
variantcall_utils.set_gq(call, min_gq)
variantcall_utils.set_min_dp(call, min_dp)
yield variants_pb2.Variant(
reference_name=first_record.summary_counts.reference_name,
reference_bases=first_record.summary_counts.ref_base,
alternate_bases=[vcf_constants.GVCF_ALT_ALLELE],
start=first_record.summary_counts.position,
end=last_record.summary_counts.position + 1,
calls=[call])