def generate_positions(vcf_reader, ref_reader, baseline_contig):
"""Gets all INDELs position and an equal amount of SNPs and random positions.
Args:
vcf_reader: a nucleus.io.VcfReader.
ref_reader: a nucleus.io.IndexedFastaReader.
baseline_contig: contig from which to sample baseline positions.
Returns:
A list of PositionWrapper.
"""
variants = [variant for variant in vcf_reader]
indels_positions = [
PositionWrapper(var.reference_name, var.start, _INDEL_LABEL)
for var in variants if variant_utils.is_indel(var)
]
n_indels = len(indels_positions)
# We sort by position for better data locality.
snps = [var for var in variants if variant_utils.is_snp(var)]
snps_positions = [
PositionWrapper(var.reference_name, var.start, _SNP_LABEL)
for var in random.sample(snps, min(len(snps), n_indels))
]
contig_size = ref_reader.contig(baseline_contig).n_bases
# NOTE: Though unlikely, these random positions can end up on actual
# variants.
baseline_positions = [
PositionWrapper(baseline_contig, pos, _REF_LABEL)
for pos in random.sample(xrange(contig_size), min(
contig_size, n_indels))
]
return sorted(indels_positions + snps_positions + baseline_positions)
def model_evaluation_runner(truth_variants, reads, ref, input_model_pckl,
eval_region, output_report_csv):
"""Outputs precision-recall for a sklearn model using AlleleCount features.
Args:
truth_variants: path to the VCF.
reads: path to the reads BAM.
ref: path to the reference FASTA.
input_model_pckl: path to read the LogisticRegression pickle from.
eval_region: str, region to evaluate on in the 'chr:start-end',
'chr:position' or 'chr' format.
output_report_csv: path to the output report csv.
Raises:
ValueError: if eval_region cannot be parsed.
"""
sam_reader = sam.SamReader(reads)
ref_reader = fasta.IndexedFastaReader(ref)
read_reqs = reads_pb2.ReadRequirements(
min_base_quality=10,
min_mapping_quality=10,
min_base_quality_mode=reads_pb2.ReadRequirements.ENFORCED_BY_CLIENT)
allele_counter_options = deepvariant_pb2.AlleleCounterOptions(
partition_size=1, read_requirements=read_reqs)
model = joblib.load(input_model_pckl)
with vcf.VcfReader(truth_variants) as vcf_reader:
region = ranges.parse_literal(eval_region,
contig_map=ranges.contigs_dict(
ref_reader.header.contigs))
true_indels = [
var for var in vcf_reader.query(region)
if (variant_utils.is_indel(var))
]
precisions = compute_precision(model, true_indels, sam_reader, ref_reader,
allele_counter_options, _THRESHOLDS, region)
recalls = compute_effective_recall(model, true_indels, sam_reader,
ref_reader, allele_counter_options,
_THRESHOLDS)
with tf.gfile.GFile(output_report_csv, 'w') as csvfile:
fieldnames = ['threshold', 'precision', 'recall']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for threshold in _THRESHOLDS:
writer.writerow({
'threshold': threshold,
'precision': precisions[threshold],
'recall': recalls[threshold]
})
def encoded_variant_type(variant):
"""Gets the EncodedVariantType for variant.
This function examines variant and returns the EncodedVariantType that best
describes the variation type of variant. For example, if variant has
`reference_bases = "A"` and `alternative_bases = ["C"]` this function would
return EncodedVariantType.SNP.
Args:
variant: nucleus.Variant proto. The variant whose EncodedVariantType we want
to get.
Returns:
EncodedVariantType enum value.
"""
if variant_utils.is_snp(variant):
return EncodedVariantType.SNP
elif variant_utils.is_indel(variant):
return EncodedVariantType.INDEL
else:
return EncodedVariantType.UNKNOWN
def test_is_indel(self, variant, expected): self.assertEqual(variant_utils.is_indel(variant), expected)
def test_is_indel_symbolic_allele(self, variant, exclude_alleles, expected):
self.assertEqual(
variant_utils.is_indel(variant, exclude_alleles=exclude_alleles),
expected)
def test_is_indel(self, variant, expected): self.assertEqual(variant_utils.is_indel(variant), expected)