def test_vcf_variant_hashability():
v = [
VcfVariant(10, 'A', 'TC'),
VcfVariant(10, 'A', 'TCA'),
VcfVariant(10, 'C', 'TC'),
VcfVariant(20, 'A', 'TC'),
VcfVariant(10, 'A', 'TCA'),
VcfVariant(20, 'A', 'TC')
]
assert len(set(v)) == 4
def test_vcf_variant_hashability():
v = [
VcfVariant(10, "A", "TC"),
VcfVariant(10, "A", "TCA"),
VcfVariant(10, "C", "TC"),
VcfVariant(20, "A", "TC"),
VcfVariant(10, "A", "TCA"),
VcfVariant(20, "A", "TC"),
]
assert len(set(v)) == 4
def test_normalize():
assert VcfVariant(100, 'A', 'C').normalized() == VcfVariant(100, 'A', 'C')
assert VcfVariant(100, '', 'A').normalized() == VcfVariant(100, '', 'A')
assert VcfVariant(100, 'A', '').normalized() == VcfVariant(100, 'A', '')
assert VcfVariant(100, 'A', 'AC').normalized() == VcfVariant(101, '', 'C')
assert VcfVariant(100, 'AC', 'A').normalized() == VcfVariant(101, 'C', '')
assert VcfVariant(100, 'ACAGACC',
'ACAGACT').normalized() == VcfVariant(106, 'C', 'T')
assert VcfVariant(100, 'GCTG',
'GCTAAA').normalized() == VcfVariant(103, 'G', 'AAA')
assert VcfVariant(100, 'ATTA',
'ATA').normalized() == VcfVariant(101, 'T', '')
assert VcfVariant(100, 'ATTTC',
'ATTTTTTC').normalized() == VcfVariant(101, '', 'TTT')
assert VcfVariant(100, 'GCTGTT',
'GCTAAATT').normalized() == VcfVariant(103, 'G', 'AAA')
def test_phasing_to_reads():
for filename in [
'tests/data/phased-via-HP.vcf', 'tests/data/phased-via-PS.vcf'
]:
tables = list(VcfReader(filename, phases=True))
assert len(tables) == 2
table_a, table_b = tables
phase_reads_sample1 = list(
table_a.phased_blocks_as_reads('sample1',
table_a.variants,
17,
18,
default_quality=90,
mapq=101))
print(phase_reads_sample1)
assert len(phase_reads_sample1) == 1
read = phase_reads_sample1[0]
assert len(read) == 2
assert read.name == 'sample1_block_300'
assert read.source_id == 17
assert read.mapqs == (101, )
assert read[0].position == 300 - 1
assert read[0].allele == 1
assert read[0].quality == 23
assert read[1].position == 350 - 1
assert read[1].allele == 0
assert read[1].quality == 42
phase_reads_sample2 = list(
table_a.phased_blocks_as_reads('sample2',
table_a.variants,
11,
12,
default_quality=91,
mapq=102))
print(phase_reads_sample2)
assert len(phase_reads_sample2) == 2
read1, read2 = phase_reads_sample2
assert len(read1) == len(read2) == 2
if read1[0].position > read2[0].position:
read1, read2 = read2, read1
assert read1.name == 'sample2_block_100'
assert read1.source_id == 11
assert read1.mapqs == (102, )
assert read1[0].position == 100 - 1
assert read1[0].allele == 0
assert read1[0].quality == 10
assert read1[1].position == 150 - 1
assert read1[1].allele == 1
assert read1[1].quality == 20
assert read2.name == 'sample2_block_300'
assert read2.source_id == 11
assert read2.mapqs == (102, )
assert read2[0].position == 300 - 1
assert read2[0].allele == 0
assert read2[0].quality == 30
assert read2[1].position == 350 - 1
assert read2[1].allele == 0
assert read2[1].quality == 91
variants = [
VcfVariant(350 - 1, 'G', 'T'),
VcfVariant(300 - 1, 'G', 'T'),
VcfVariant(17, 'A', 'TTC'),
VcfVariant(1000, 'C', 'G')
]
phase_reads_sample2 = list(
table_a.phased_blocks_as_reads('sample2',
variants,
11,
12,
default_quality=91,
mapq=102))
print(phase_reads_sample2)
assert len(phase_reads_sample2) == 1
read = phase_reads_sample2[0]
assert len(read) == 2
assert read.name == 'sample2_block_300'
assert read.source_id == 11
assert read.mapqs == (102, )
assert read[0].position == 300 - 1
assert read[0].allele == 0
assert read[0].quality == 30
assert read[1].position == 350 - 1
assert read[1].allele == 0
assert read[1].quality == 91
def test_normalize():
assert VcfVariant(100, "A", "C").normalized() == VcfVariant(100, "A", "C")
assert VcfVariant(100, "", "A").normalized() == VcfVariant(100, "", "A")
assert VcfVariant(100, "A", "").normalized() == VcfVariant(100, "A", "")
assert VcfVariant(100, "A", "AC").normalized() == VcfVariant(101, "", "C")
assert VcfVariant(100, "AC", "A").normalized() == VcfVariant(101, "C", "")
assert VcfVariant(100, "ACAGACC", "ACAGACT").normalized() == VcfVariant(106, "C", "T")
assert VcfVariant(100, "GCTG", "GCTAAA").normalized() == VcfVariant(103, "G", "AAA")
assert VcfVariant(100, "ATTA", "ATA").normalized() == VcfVariant(101, "T", "")
assert VcfVariant(100, "ATTTC", "ATTTTTTC").normalized() == VcfVariant(101, "", "TTT")
assert VcfVariant(100, "GCTGTT", "GCTAAATT").normalized() == VcfVariant(103, "G", "AAA")