def test_vcf_caller_end2end_outputs(self):
# Confirming that the proposed VCF (input) has the same variants
# as the VCF output converted from the output of make_examples.
variants = list(
labeled_examples_to_vcf.examples_to_variants(
testdata.GOLDEN_VCF_CALLER_TRAINING_EXAMPLES))
with vcf.VcfReader(testdata.TRUTH_VARIANTS_VCF) as proposed_vcf_reader:
# This checks the keys (like chr20:10099832:A->G) are the same.
self.assertEqual([variant_utils.variant_key(v1) for v1 in variants], [
variant_utils.variant_key(v2) for v2 in proposed_vcf_reader.iterate()
])
with vcf.VcfReader(testdata.TRUTH_VARIANTS_VCF) as proposed_vcf_reader:
self.assertEqual(
[variant_utils.genotype_as_alleles(v1) for v1 in variants], [
variant_utils.genotype_as_alleles(
variant_utils.unphase_all_genotypes(v2))
for v2 in proposed_vcf_reader.iterate()
])
def test_genotype_as_alleles_raises_with_bad_inputs(self):
with self.assertRaises(Exception):
variant_utils.genotype_as_alleles(None)
with self.assertRaises(Exception):
variant_utils.genotype_as_alleles(test_utils.make_variant(gt=None))
with self.assertRaises(Exception):
variant_utils.genotype_as_alleles(
test_utils.make_variant(alleles=['A', 'C'], gt=[0, 0]), call_ix=1)
with self.assertRaises(Exception):
variant_utils.genotype_type(None)
def test_genotype_as_alleles_raises_with_bad_inputs(self):
with self.assertRaises(Exception):
variant_utils.genotype_as_alleles(None)
with self.assertRaises(Exception):
variant_utils.genotype_as_alleles(test_utils.make_variant(gt=None))
with self.assertRaises(Exception):
variant_utils.genotype_as_alleles(
test_utils.make_variant(alleles=['A', 'C'], gt=[0, 0]), call_ix=1)
with self.assertRaises(Exception):
variant_utils.genotype_type(None)
def test_genotype_as_alleles(self, variant, expected): self.assertEqual(variant_utils.genotype_as_alleles(variant), expected)
def test_genotype_as_alleles(self, variant, expected): self.assertEqual(variant_utils.genotype_as_alleles(variant), expected)
def _genotype_from_matched_truth(candidate_variant, truth_variant):
"""Gets the diploid genotype for candidate_variant from matched truth_variant.
This method figures out the genotype for candidate_variant by matching alleles
in candidate_variant with those used by the genotype assigned to
truth_variant. For example, if candidate is A/C and truth is A/C with a 0/1
genotype, then this function would return (0, 1) indicating that there's one
copy of the A allele and one of C in truth. If the true genotype is 1/1, then
this routine would return (1, 1).
The routine allows candidate_variant and truth_variant to differ in both
the number of alternate alleles, and even in the representation of the same
alleles due to those differences. For example, candidate could be:
AGT/A/AGTGT => 2 bp deletion and 2 bp insertion
and truth could have:
A/AGT => just the simplified 2 bp insertion
And this routine will correctly equate the AGT/AGTGT allele in candidate
with the A/AGT in truth and use the number of copies of AGT in truth to
compute the number of copies of AGTGT when determining the returned genotype.
Args:
candidate_variant: Our candidate third_party.nucleus.protos.Variant variant.
truth_variant: Our third_party.nucleus.protos.Variant truth variant
containing true alleles and genotypes.
Returns:
A tuple genotypes with the same semantics at the genotype field of the
VariantCall proto.
Raises:
ValueError: If candidate_variant is None, truth_variant is None, or
truth_variant doesn't have genotypes.
"""
if candidate_variant is None:
raise ValueError('candidate_variant cannot be None')
if truth_variant is None:
raise ValueError('truth_variant cannot be None')
if not variantcall_utils.has_genotypes(
variant_utils.only_call(truth_variant)):
raise ValueError(
'truth_variant needs genotypes to be used for labeling',
truth_variant)
def _match_one_allele(true_allele):
if true_allele == truth_variant.reference_bases:
return 0
else:
simplified_true_allele = variant_utils.simplify_alleles(
truth_variant.reference_bases, true_allele)
for alt_index, alt_allele in enumerate(
candidate_variant.alternate_bases):
simplified_alt_allele = variant_utils.simplify_alleles(
candidate_variant.reference_bases, alt_allele)
if simplified_true_allele == simplified_alt_allele:
return alt_index + 1
# If nothing matched, we don't have this alt, so the alt allele index for
# should be 0 (i.e., not any alt).
return 0
# If our candidate_variant is a reference call, return a (0, 0) genotype.
if variant_utils.is_ref(candidate_variant):
return (0, 0)
else:
return tuple(
sorted(
_match_one_allele(true_allele) for true_allele in
variant_utils.genotype_as_alleles(truth_variant)))
def _genotype_from_matched_truth(candidate_variant, truth_variant):
"""Gets the diploid genotype for candidate_variant from matched truth_variant.
This method figures out the genotype for candidate_variant by matching alleles
in candidate_variant with those used by the genotype assigned to
truth_variant. For example, if candidate is A/C and truth is A/C with a 0/1
genotype, then this function would return (0, 1) indicating that there's one
copy of the A allele and one of C in truth. If the true genotype is 1/1, then
this routine would return (1, 1).
The routine allows candidate_variant and truth_variant to differ in both
the number of alternate alleles, and even in the representation of the same
alleles due to those differences. For example, candidate could be:
AGT/A/AGTGT => 2 bp deletion and 2 bp insertion
and truth could have:
A/AGT => just the simplified 2 bp insertion
And this routine will correctly equate the AGT/AGTGT allele in candidate
with the A/AGT in truth and use the number of copies of AGT in truth to
compute the number of copies of AGTGT when determining the returned genotype.
Args:
candidate_variant: Our candidate third_party.nucleus.protos.Variant variant.
truth_variant: Our third_party.nucleus.protos.Variant truth variant
containing true alleles and genotypes.
Returns:
A tuple genotypes with the same semantics at the genotype field of the
VariantCall proto.
Raises:
ValueError: If candidate_variant is None, truth_variant is None, or
truth_variant doesn't have genotypes.
"""
if candidate_variant is None:
raise ValueError('candidate_variant cannot be None')
if truth_variant is None:
raise ValueError('truth_variant cannot be None')
if not variantcall_utils.has_genotypes(
variant_utils.only_call(truth_variant)):
raise ValueError('truth_variant needs genotypes to be used for labeling',
truth_variant)
def _match_one_allele(true_allele):
if true_allele == truth_variant.reference_bases:
return 0
else:
simplifed_true_allele = variant_utils.simplify_alleles(
truth_variant.reference_bases, true_allele)
for alt_index, alt_allele in enumerate(candidate_variant.alternate_bases):
simplifed_alt_allele = variant_utils.simplify_alleles(
candidate_variant.reference_bases, alt_allele)
if simplifed_true_allele == simplifed_alt_allele:
return alt_index + 1
# If nothing matched, we don't have this alt, so the alt allele index for
# should be 0 (i.e., not any alt).
return 0
# If our candidate_variant is a reference call, return a (0, 0) genotype.
if variant_utils.is_ref(candidate_variant):
return (0, 0)
else:
return tuple(
sorted(
_match_one_allele(true_allele) for true_allele in
variant_utils.genotype_as_alleles(truth_variant)))
