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 bipartition(reads):
positions = reads.get_positions()
# create genotypes over your variants: all heterozygous (=1)
genotypes = canonic_index_list_to_biallelic_gt_list([1] * len(positions))
# genotype likelihoods are None
genotype_likelihoods = [None] * len(positions)
# create empty pedigree
pedigree = Pedigree(NumericSampleIds())
# add one individual to pedigree
pedigree.add_individual('individual0', genotypes, genotype_likelihoods)
# recombination cost vector, irrelevant if one using one individual
recombcost = [1] * len(positions)
# run the core phasing algorithm, creating a DP table
dp_table = PedigreeDPTable(reads,
recombcost,
pedigree,
distrust_genotypes=False)
phasing, transmission_vector = dp_table.get_super_reads()
#print('PHASING')
#print(phasing[0])
#print(phasing[0][0])
#print(phasing[0][1])
mec_score = dp_table.get_optimal_cost()
eprint("MEC Score:", mec_score)
eprint("MEC Score / readset length:",
float(mec_score) / float(readset_length))
# In case the bi-partition of reads is of interest:
partition = dp_table.get_optimal_partitioning()
#print(partition)
eprint("partition fraction:", sum(partition) / float(len(partition)))
return phasing, partition
def test_genotyping_trio13():
reads = """
A 1111
A 0000
B 1111
B 0000
"""
expected_genotypes = [
canonic_index_list_to_biallelic_gt_list([1, 1, 1, 1, 1, 1]),
canonic_index_list_to_biallelic_gt_list([1, 1, 1, 1, 1, 1]),
canonic_index_list_to_biallelic_gt_list([1, 1, 1, 1, 1, 1]),
]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual(
"individual0",
canonic_index_list_to_biallelic_gt_list([0, 0, 0, 0, 0, 0]),
[PhredGenotypeLikelihoods([0, 1, 0])] * 6,
)
pedigree.add_individual(
"individual1",
canonic_index_list_to_biallelic_gt_list([0, 0, 0, 0, 0, 0]),
[PhredGenotypeLikelihoods([0, 1, 0])] * 6,
)
pedigree.add_individual(
"individual2",
canonic_index_list_to_biallelic_gt_list([0, 0, 0, 0, 0, 0]),
[PhredGenotypeLikelihoods([0.25, 0.5, 0.25])] * 6,
)
pedigree.add_relationship("individual0", "individual1", "individual2")
recombcost = [1000000, 1000000, 1000000, 1000000, 1000000, 1000000]
genotype_pedigree(
numeric_sample_ids, reads, recombcost, pedigree, expected_genotypes, scaling=1000,
)
def test_genotyping_trio3():
reads = """
A 1111
B 1010
C 111000
C 010101
C 010101
B 0101
A 0000
B 1010
C 1010
C 1100
A 0000
A 1111
B 1010
B 010
"""
expected_genotypes = [[1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1],
[1, 2, 1, 1, 0, 1]]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual(
'individual0', [0, 0, 0, 0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 6)
pedigree.add_individual(
'individual1', [0, 0, 0, 0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 6)
pedigree.add_individual(
'individual2', [0, 0, 0, 0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 6)
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [3, 3, 3, 4, 3, 3]
genotype_pedigree(numeric_sample_ids, reads, recombcost, pedigree,
expected_genotypes)
def test_genotyping_trio14():
reads = """
A 111111
A 111111
B 111111
B 000000
C 000000
"""
expected_genotypes = [[2, 2, 2, 2, 2, 2], [1, 1, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 1]]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual(
'individual0', [0, 0, 0, 0, 0, 0],
[PhredGenotypeLikelihoods(1 / 3.0, 1 / 3.0, 1 / 3.0)] * 6)
pedigree.add_individual(
'individual1', [0, 0, 0, 0, 0, 0],
[PhredGenotypeLikelihoods(1 / 3.0, 1 / 3.0, 1 / 3.0)] * 6)
pedigree.add_individual(
'individual2', [0, 0, 0, 0, 0, 0],
[PhredGenotypeLikelihoods(1 / 3.0, 1 / 3.0, 1 / 3.0)] * 6)
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [1000000, 1000000, 1000000, 1000000, 1000000, 1000000]
genotype_pedigree(numeric_sample_ids,
reads,
recombcost,
pedigree,
expected_genotypes,
scaling=1000)
def test_pedigree_with_gls():
ped = Pedigree(NumericSampleIds())
genotypes1 = [0, 1, 0, 2]
gls1 = [
PhredGenotypeLikelihoods(0, 1, 2),
PhredGenotypeLikelihoods(215, 81, 147),
PhredGenotypeLikelihoods(199, 49, 253),
PhredGenotypeLikelihoods(167, 200, 163),
]
genotypes5 = [1, 2, 2, 0]
gls5 = [
PhredGenotypeLikelihoods(184, 71, 233),
PhredGenotypeLikelihoods(65, 32, 87),
PhredGenotypeLikelihoods(28, 215, 131),
PhredGenotypeLikelihoods(98, 250, 137),
]
ped.add_individual('sample1', genotypes1, gls1)
assert len(ped) == 1
assert ped.variant_count == 4, str(ped.variant_count)
ped.add_individual('sample5', genotypes5, gls5)
assert len(ped) == 2
assert ped.variant_count == 4, str(ped.variant_count)
for i in range(ped.variant_count):
assert ped.genotype('sample1', i) == genotypes1[i]
assert list(ped.genotype_likelihoods('sample1', i)) == list(gls1[i])
assert ped.genotype('sample5', i) == genotypes5[i]
assert list(ped.genotype_likelihoods('sample5', i)) == list(gls5[i])
def test_genotyping_trio5():
reads = """
B 101
B 101
B 101
A 111
A 111
A 111
C 111
C 111
C 101
C 101
"""
expected_genotypes = [[2, 2, 2], [2, 0, 2], [2, 1, 2]]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual(
'individual0', [0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 3)
pedigree.add_individual(
'individual1', [0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 3)
pedigree.add_individual(
'individual2', [0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 3)
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [2, 2, 2]
genotype_pedigree(numeric_sample_ids, reads, recombcost, pedigree,
expected_genotypes)
def test_genotyping_trio1():
reads = """
A 00
A 00
B 11
B 11
C 11
C 00
"""
expected_genotypes = [[0, 0], [2, 2], [1, 1]]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual(
'individual0', [1, 1],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 2)
pedigree.add_individual(
'individual1', [1, 1],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 2)
pedigree.add_individual(
'individual2', [1, 1],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 2)
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [10, 10]
genotype_pedigree(numeric_sample_ids, reads, recombcost, pedigree,
expected_genotypes)
def test_phase_trio5():
reads = """
B 101
B 101
B 101
A 111
A 111
A 111
C 111
C 111
C 111
"""
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual("individual0",
canonic_index_list_to_biallelic_gt_list([1, 1, 1]))
pedigree.add_individual("individual1",
canonic_index_list_to_biallelic_gt_list([1, 1, 1]))
pedigree.add_individual("individual2",
canonic_index_list_to_biallelic_gt_list([1, 1, 1]))
pedigree.add_relationship("individual0", "individual1", "individual2")
recombcost = [2, 2, 2]
superreads_list, transmission_vector, cost = phase_pedigree(
reads, recombcost, pedigree)
assert cost == 3
assert len(set(transmission_vector)) == 1
all_expected_haplotypes = [("111", "000"), ("111", "000"), ("111", "000")]
assert_haplotypes(superreads_list, all_expected_haplotypes, 3)
assert_trio_allele_order(superreads_list, transmission_vector, 3)
def test_phase_doubletrio_pure_genetic():
reads = ""
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual('individualA', [1, 2, 1, 0])
pedigree.add_individual('individualB', [1, 0, 1, 1])
pedigree.add_individual('individualC', [2, 1, 1, 0])
pedigree.add_individual('individualD', [1, 2, 2, 1])
pedigree.add_individual('individualE', [1, 1, 1, 0])
pedigree.add_relationship('individualA', 'individualB', 'individualC')
pedigree.add_relationship('individualC', 'individualD', 'individualE')
recombcost = [2, 2, 2]
superreads_list, transmission_vector, cost = phase_pedigree(
reads, recombcost, pedigree, positions=[10, 20, 30, 40])
assert cost == 0
assert len(set(transmission_vector)) == 1
all_expected_haplotypes = [('0100', '1110'), ('0011', '1000'),
('1110', '1000'), ('1111', '0110'),
('1000', '0110')]
assert_haplotypes(superreads_list, all_expected_haplotypes, 4)
trio_transmission_vectors = get_trio_transmission_vectors(
transmission_vector, 4)
assert_trio_allele_order(superreads_list[:3], trio_transmission_vectors[0],
4)
assert_trio_allele_order(superreads_list[2:], trio_transmission_vectors[1],
4)
def test_genotyping_trio1():
reads = """
A 00
A 00
B 11
B 11
C 11
C 00
"""
expected_genotypes = [
canonic_index_list_to_biallelic_gt_list([0, 0]),
canonic_index_list_to_biallelic_gt_list([2, 2]),
canonic_index_list_to_biallelic_gt_list([1, 1]),
]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual(
"individual0",
canonic_index_list_to_biallelic_gt_list([1, 1]),
[PhredGenotypeLikelihoods([1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0])] * 2,
)
pedigree.add_individual(
"individual1",
canonic_index_list_to_biallelic_gt_list([1, 1]),
[PhredGenotypeLikelihoods([1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0])] * 2,
)
pedigree.add_individual(
"individual2",
canonic_index_list_to_biallelic_gt_list([1, 1]),
[PhredGenotypeLikelihoods([1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0])] * 2,
)
pedigree.add_relationship("individual0", "individual1", "individual2")
recombcost = [10, 10]
genotype_pedigree(numeric_sample_ids, reads, recombcost, pedigree, expected_genotypes)
def test_genotyping_trio10():
reads = """
B 0000
B 0000
B 0000
B 0000
B 0000
B 0000
A 1111
A 1111
A 1111
A 1111
A 1111
A 1111
"""
# no reads for child, but genotype must be 1/0 for each pos. (due to inheritance)
expected_genotypes = [[2, 2, 2, 2], [0, 0, 0, 0], [1, 1, 1, 1]]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual(
'individual0', [0, 0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 4)
pedigree.add_individual(
'individual1', [0, 0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 4)
pedigree.add_individual(
'individual2', [0, 0, 0, 0],
[PhredGenotypeLikelihoods(1.0 / 3.0, 1.0 / 3.0, 1.0 / 3.0)] * 4)
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [10, 10, 10, 10]
genotype_pedigree(numeric_sample_ids, reads, recombcost, pedigree,
expected_genotypes)
def test_weighted_genotyping():
reads = """
B 00
B 11
A 11
A 00
C 11
C 11
"""
weights = """
99
99
99
99
99
99
"""
expected_genotypes = [
canonic_index_list_to_biallelic_gt_list([1, 1]),
canonic_index_list_to_biallelic_gt_list([1, 1]),
canonic_index_list_to_biallelic_gt_list([2, 2]),
]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual(
"individual0",
canonic_index_list_to_biallelic_gt_list([0, 0, 0, 0]),
[PhredGenotypeLikelihoods([0.25, 0.5, 0.25])] * 4,
)
pedigree.add_individual(
"individual1",
canonic_index_list_to_biallelic_gt_list([0, 0, 0, 0]),
[PhredGenotypeLikelihoods([0.25, 0.5, 0.25])] * 4,
)
pedigree.add_individual(
"individual2",
canonic_index_list_to_biallelic_gt_list([0, 0, 0, 0]),
[PhredGenotypeLikelihoods([0.25, 0.5, 0.25])] * 4,
)
pedigree.add_relationship("individual0", "individual1", "individual2")
# recombination is extremely unlikely
recombcost = [1000, 1000, 1000, 1000]
expected = {
0: [[0, 1, 0], [0, 1, 0]],
1: [[0, 1, 0], [0, 1, 0]],
2: [[0, 1.0 / 3.0, 2 / 3.0], [0, 1.0 / 3.0, 2 / 3.0]],
}
genotype_pedigree(
numeric_sample_ids,
reads,
recombcost,
pedigree,
expected_genotypes,
weights,
expected,
scaling=500,
)
def test_genotyping_empty_readset():
rs = ReadSet()
genotypes = canonic_index_list_to_biallelic_gt_list([1, 1])
recombcost = [1, 1]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
genotype_likelihoods = [None, None]
pedigree.add_individual("individual0", genotypes, genotype_likelihoods)
_ = GenotypeDPTable(numeric_sample_ids, rs, recombcost, pedigree)
def test_genotyping_empty_readset():
rs = ReadSet()
genotypes = [1,1]
recombcost = [1,1]
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
genotype_likelihoods = [None, None]
pedigree.add_individual('individual0', genotypes, genotype_likelihoods)
dp_forward_backward = GenotypeDPTable(numeric_sample_ids,rs, recombcost, pedigree)
def test_phase_trio5():
reads = """
B 101
B 101
B 101
A 111
A 111
A 111
C 111
C 111
C 111
"""
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual('individual0', [1,1,1])
pedigree.add_individual('individual1', [1,1,1])
pedigree.add_individual('individual2', [1,1,1])
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [2,2,2]
superreads_list, transmission_vector, cost = phase_pedigree(reads, recombcost, pedigree)
assert cost == 3
assert len(set(transmission_vector)) == 1
all_expected_haplotypes = [
('111','000'),
('111','000'),
('111','000')
]
assert_haplotypes(superreads_list, all_expected_haplotypes, 3)
def test_phase_trio_genotype_likelihoods():
reads = """
A 111
A 010
A 110
B 001
B 110
B 101
C 001
C 010
C 010
"""
pedigree = Pedigree(NumericSampleIds())
genotype_likelihoods_mother = [
PhredGenotypeLikelihoods(0,0,0),
PhredGenotypeLikelihoods(0,0,1),
PhredGenotypeLikelihoods(5,0,5)
]
genotype_likelihoods0 = [PhredGenotypeLikelihoods(0,0,0)] * 3
pedigree.add_individual('individual0', [0,0,0], genotype_likelihoods_mother)
pedigree.add_individual('individual1', [0,0,0], genotype_likelihoods0)
pedigree.add_individual('individual2', [0,0,0], genotype_likelihoods0)
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [10,10,10]
superreads_list, transmission_vector, cost = phase_pedigree(reads, recombcost, pedigree, True)
assert cost == 3
assert len(set(transmission_vector)) == 1
all_expected_haplotypes = [
('111','010'),
('001','110'),
('001','010')
]
assert_haplotypes(superreads_list, all_expected_haplotypes, 3)
def test_phase_trio4():
reads = """
B 101
B 101
B 101
A 111
A 111
A 111
C 111
C 111
C 111
"""
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual('individual0', [1,1,1])
pedigree.add_individual('individual1', [1,1,1])
pedigree.add_individual('individual2', [1,1,1])
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [1,1,1]
superreads_list, transmission_vector, cost = phase_pedigree(reads, recombcost, pedigree)
assert cost == 2
assert transmission_vector in ([0,2,0], [2,0,2], [1,3,1], [3,1,3])
all_expected_haplotypes = [
('111','000'),
('101','010'),
('111','000')
]
assert_haplotypes(superreads_list, all_expected_haplotypes, 3)
def test_phase_trio1():
reads = """
A 111
A 010
A 110
B 001
B 110
B 101
C 001
C 010
C 010
"""
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual('individual0', [1,2,1])
pedigree.add_individual('individual1', [1,1,1])
pedigree.add_individual('individual2', [0,1,1])
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [10,10,10]
superreads_list, transmission_vector, cost = phase_pedigree(reads, recombcost, pedigree)
assert cost == 2
assert len(set(transmission_vector)) == 1
all_expected_haplotypes = [
('111','010'),
('001','110'),
('001','010')
]
assert_haplotypes(superreads_list, all_expected_haplotypes, 3)
def test_phase_empty_readset(algorithm):
rs = ReadSet()
recombcost = [1, 1]
genotypes = canonic_index_list_to_biallelic_gt_list([1, 1])
pedigree = Pedigree(NumericSampleIds())
genotype_likelihoods = [None, None]
pedigree.add_individual("individual0", genotypes, genotype_likelihoods)
if algorithm == "hapchat":
dp_table = HapChatCore(rs)
else:
dp_table = PedigreeDPTable(rs, recombcost, pedigree)
_ = dp_table.get_super_reads()
def test_phase_quartet2():
reads = """
A 111111
A 000000
B 010101
B 101010
C 000000
C 010101
D 000000
D 010101
"""
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual('individual0', [1,1,1,1,1,1])
pedigree.add_individual('individual1', [1,1,1,1,1,1])
pedigree.add_individual('individual2', [0,1,0,1,0,1])
pedigree.add_individual('individual3', [0,1,0,1,0,1])
pedigree.add_relationship('individual0', 'individual1', 'individual2')
pedigree.add_relationship('individual0', 'individual1', 'individual3')
recombcost =[3,3,3,3,3,3]
superreads_list, transmission_vector, cost = phase_pedigree(reads, recombcost, pedigree)
assert cost == 0
assert len(set(transmission_vector)) == 1
all_expected_haplotypes = [
('111111','000000'),
('010101','101010'),
('000000','010101'),
('000000','010101')
]
assert_haplotypes(superreads_list, all_expected_haplotypes, 6)
def test_phase_trio3():
reads = """
A 1111
B 1010
C 111000
C 010101
B 0101
A 0000
B 1010
C 1010
C 1100
A 0000
A 1111
B 1010
B 010
"""
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual('individual0', [1,1,1,1,1,1])
pedigree.add_individual('individual1', [1,1,1,1,1,1])
pedigree.add_individual('individual2', [1,2,1,1,0,1])
pedigree.add_relationship('individual0', 'individual1', 'individual2')
recombcost = [3,3,3,4,3,3]
superreads_list, transmission_vector, cost = phase_pedigree(reads, recombcost, pedigree)
assert cost == 4
assert transmission_vector in ([0,0,0,1,1,1], [1,1,1,0,0,0], [2,2,2,3,3,3], [3,3,3,2,2,2])
all_expected_haplotypes = [
('111111','000000'),
('010101','101010'),
('111000','010101')
]
assert_haplotypes(superreads_list, all_expected_haplotypes, 6)
def verify(rs, all_heterozygous=False):
positions = rs.get_positions()
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', [1] * len(positions),
genotype_likelihoods) # all genotypes heterozygous
dp_table = PedigreeDPTable(rs,
recombcost,
pedigree,
distrust_genotypes=not all_heterozygous)
verify_mec_score_and_partitioning(dp_table, rs)
def test_pedigree_no_gls():
ped = Pedigree(NumericSampleIds())
genotypes1 = [0, 1, 0, 2]
genotypes5 = [1, 2, 2, 0]
ped.add_individual('sample1', genotypes1)
assert len(ped) == 1
assert ped.variant_count == 4, str(ped.variant_count)
ped.add_individual('sample5', genotypes5)
assert len(ped) == 2
assert ped.variant_count == 4, str(ped.variant_count)
for i in range(ped.variant_count):
assert ped.genotype('sample1', i) == genotypes1[i]
assert ped.genotype_likelihoods('sample1', i) is None
assert ped.genotype('sample5', i) == genotypes5[i]
assert ped.genotype_likelihoods('sample5', i) is None
def test_phase_empty_readset(algorithm):
rs = ReadSet()
recombcost = [1, 1]
genotypes = [1, 1]
pedigree = Pedigree(NumericSampleIds())
genotype_likelihoods = [None, None]
pedigree.add_individual('individual0', genotypes, genotype_likelihoods)
dp_table = None
if algorithm == 'hapchat':
dp_table = HapChatCore(rs)
else:
dp_table = PedigreeDPTable(rs, recombcost, pedigree)
superreads = dp_table.get_super_reads()
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 test_genotyping_empty_trio():
rs = ReadSet()
recombcost = []
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual("individual0", [], [])
pedigree.add_individual("individual1", [], [])
pedigree.add_individual("individual2", [], [])
pedigree.add_relationship("individual0", "individual1", "individual2")
_ = GenotypeDPTable(numeric_sample_ids, rs, recombcost, pedigree)
def test_phase_empty_trio():
rs = ReadSet()
recombcost = []
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual('individual0', [])
pedigree.add_individual('individual1', [])
pedigree.add_individual('individual2', [])
pedigree.add_relationship('individual0', 'individual1', 'individual2')
dp_table = PedigreeDPTable(rs, recombcost, pedigree)
(superreadsm, superreadsf, superreadsc), transmission_vector = dp_table.get_super_reads()
def test_phase_trio3():
reads = """
A 1111
B 1010
C 111000
C 010101
B 0101
A 0000
B 1010
C 1010
C 1100
A 0000
A 1111
B 1010
B 010
"""
pedigree = Pedigree(NumericSampleIds())
pedigree.add_individual(
"individual0",
canonic_index_list_to_biallelic_gt_list([1, 1, 1, 1, 1, 1]))
pedigree.add_individual(
"individual1",
canonic_index_list_to_biallelic_gt_list([1, 1, 1, 1, 1, 1]))
pedigree.add_individual(
"individual2",
canonic_index_list_to_biallelic_gt_list([1, 2, 1, 1, 0, 1]))
pedigree.add_relationship("individual0", "individual1", "individual2")
recombcost = [3, 3, 3, 4, 3, 3]
superreads_list, transmission_vector, cost = phase_pedigree(
reads, recombcost, pedigree)
assert cost == 4
assert transmission_vector in (
[0, 0, 0, 1, 1, 1],
[1, 1, 1, 0, 0, 0],
[2, 2, 2, 3, 3, 3],
[3, 3, 3, 2, 2, 2],
)
all_expected_haplotypes = [
("111111", "000000"),
("010101", "101010"),
("111000", "010101"),
]
assert_haplotypes(superreads_list, all_expected_haplotypes, 6)
assert_trio_allele_order(superreads_list, transmission_vector, 6)
def test_genotyping_empty_trio():
rs = ReadSet()
recombcost = []
numeric_sample_ids = NumericSampleIds()
pedigree = Pedigree(numeric_sample_ids)
pedigree.add_individual('individual0', [], [])
pedigree.add_individual('individual1', [], [])
pedigree.add_individual('individual2', [], [])
pedigree.add_relationship('individual0', 'individual1', 'individual2')
dp_forward_backward = GenotypeDPTable(numeric_sample_ids, rs, recombcost,
pedigree)
