def check_genotyping_single_individual(
reads,
weights=None,
expected=None,
genotypes=None,
scaling=None,
genotype_priors=None,
):
# 0) set up read set
readset = string_to_readset(s=reads, w=weights, scale_quality=scaling)
positions = readset.get_positions()
# 1) Genotype using forward backward algorithm
recombcost = [1] * len(positions)
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
genotype_likelihoods = [
PhredGenotypeLikelihoods([1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0])
] * len(positions)
if genotype_priors is not None:
genotype_likelihoods = genotype_priors
pedigree.add_individual(
"individual0",
[canonic_index_to_biallelic_gt(1) for i in range(len(positions))],
genotype_likelihoods,
)
dp_forward_backward = GenotypeDPTable(numeric_sample_ids, readset,
recombcost, pedigree)
# check the results
compare_to_expected(dp_forward_backward, positions, expected, genotypes)
def test_read_phased():
tables = list(VcfReader("tests/data/phasedinput.vcf", phases=True))
assert len(tables) == 1
table = tables[0]
assert table.chromosome == "ref"
assert table.samples == ["sample"]
assert len(table.variants) == 2
assert table.variants[0].reference_allele == "A"
assert table.variants[0].alternative_allele == "C"
assert table.variants[1].reference_allele == "G"
assert table.variants[1].alternative_allele == "T"
assert table.genotypes[0][0] == table.genotypes[0][1] == canonic_index_to_biallelic_gt(1)
def verify(rs, all_heterozygous=False):
positions = rs.get_positions()
# recombination costs 1, should not occur
recombcost = [1] * len(positions)
pedigree = Pedigree(NumericSampleIds())
genotype_likelihoods = [
None if all_heterozygous else PhredGenotypeLikelihoods([0, 0, 0])
] * len(positions)
# all genotypes heterozygous
pedigree.add_individual(
"individual0",
[canonic_index_to_biallelic_gt(1) for _ in range(len(positions))],
genotype_likelihoods,
)
dp_table = PedigreeDPTable(rs, recombcost, pedigree, distrust_genotypes=not all_heterozygous)
verify_mec_score_and_partitioning(dp_table, rs)
def check_phasing_single_individual(reads, algorithm="whatshap", weights=None):
# 0) set up read set
readset = string_to_readset(reads, weights)
positions = readset.get_positions()
# for hapchat
if algorithm == "hapchat":
dp_table = HapChatCore(readset)
superreads = dp_table.get_super_reads()
cost = dp_table.get_optimal_cost()
partition = dp_table.get_optimal_partitioning()
compare_phasing_brute_force(superreads[0][0], cost, partition, readset,
True, weights, algorithm)
return
# 1) Phase using PedMEC code for single individual
for all_heterozygous in [False, True]:
recombcost = [1] * len(
positions) # recombination costs 1, should not occur
pedigree = Pedigree(NumericSampleIds())
genotype_likelihoods = [
None if all_heterozygous else PhredGenotypeLikelihoods([0, 0, 0])
] * len(positions)
pedigree.add_individual(
"individual0",
[canonic_index_to_biallelic_gt(1) for i in range(len(positions))],
genotype_likelihoods,
) # all genotypes heterozygous
dp_table = PedigreeDPTable(readset,
recombcost,
pedigree,
distrust_genotypes=not all_heterozygous)
superreads, transmission_vector = dp_table.get_super_reads()
cost = dp_table.get_optimal_cost()
# TODO: transmission vectors not returned properly, see issue 73
assert len(set(transmission_vector)) == 1
partition = dp_table.get_optimal_partitioning()
compare_phasing_brute_force(superreads[0], cost, partition, readset,
all_heterozygous, weights)
# 2) Phase using PedMEC code for trios with two "empty" individuals (i.e. having no reads)
for all_heterozygous in [False, True]:
recombcost = [1] * len(
positions) # recombination costs 1, should not occur
pedigree = Pedigree(NumericSampleIds())
genotype_likelihoods = [
None if all_heterozygous else PhredGenotypeLikelihoods([0, 0, 0])
] * len(positions)
pedigree.add_individual(
"individual0",
[canonic_index_to_biallelic_gt(1) for _ in range(len(positions))],
genotype_likelihoods,
) # all genotypes heterozygous
pedigree.add_individual(
"individual1",
[canonic_index_to_biallelic_gt(1) for _ in range(len(positions))],
genotype_likelihoods,
) # all genotypes heterozygous
pedigree.add_individual(
"individual2",
[canonic_index_to_biallelic_gt(1) for _ in range(len(positions))],
genotype_likelihoods,
) # all genotypes heterozygous
pedigree.add_relationship("individual0", "individual1", "individual2")
dp_table = PedigreeDPTable(readset,
recombcost,
pedigree,
distrust_genotypes=not all_heterozygous)
cost = dp_table.get_optimal_cost()
superreads, transmission_vector = dp_table.get_super_reads()
assert len(set(transmission_vector)) == 1
partition = dp_table.get_optimal_partitioning()
compare_phasing_brute_force(superreads[0], cost, partition, readset,
all_heterozygous, weights)