def test_merge_pair_without_shared_positions(merge):
empty1 = Read("Name1")
empty2 = Read("Name2")
assert merge(empty1, empty2).name == "Name1"
assert merge(empty2, empty1).name == "Name2"
# add_variant parameters are: (position, allele, quality)
left = Read("Name1")
left.add_variant(100, 0, 31)
left.add_variant(200, 0, 32)
right = Read("Name2")
right.add_variant(300, 1, 41)
right.add_variant(400, 1, 42)
expected = [
Variant(100, 0, 31),
Variant(200, 0, 32),
Variant(300, 1, 41),
Variant(400, 1, 42),
]
assert expected == list(merge(left, right))
assert expected == list(merge(right, left))
outer = Read("Name1")
outer.add_variant(100, 0, 31)
outer.add_variant(400, 1, 42)
inner = Read("Name2")
inner.add_variant(200, 0, 32)
inner.add_variant(300, 1, 41)
assert expected == list(merge(inner, outer))
assert expected == list(merge(outer, inner))
def test_read_iteration():
r = Read("name", 15)
r.add_variant(100, 1, 37)
r.add_variant(23, 0, 99)
v1 = Variant(position=100, allele=1, quality=37)
v2 = Variant(position=23, allele=0, quality=99)
variants = list(r)
assert variants == [v1, v2]
# negative indices
assert r[-1] == v2
assert r[-2] == v1
def test_readset():
rs = ReadSet()
r = Read('Read A', 56)
r.add_variant(100, 1, 37)
r.add_variant(101, 0, 18)
rs.add(r)
r = Read('Read B', 0)
r.add_variant(101, 0, 23)
rs.add(r)
r = Read('Read C', 17)
r.add_variant(99, 1, 27)
r.add_variant(80, 1, 17)
r[1] = Variant(position=105, allele=0, quality=14)
rs.add(r)
assert rs[0].name == 'Read A'
assert rs[1].name == 'Read B'
assert rs[2].name == 'Read C'
rs.sort()
# should be sorted after finalization
assert rs[0].name == 'Read C'
assert rs[1].name == 'Read A'
assert rs[2].name == 'Read B'
assert len(rs) == 3
assert rs.get_positions() == [99, 100, 101, 105]
r = rs[(0, 'Read A')]
assert r.name == 'Read A'
assert r.mapqs == (56, ), str(r.mapqs)
r = rs[(0, 'Read B')]
assert r.name == 'Read B'
assert r.mapqs == (0, )
r = rs[(0, 'Read C')]
assert r.name == 'Read C'
assert r.mapqs == (17, )
assert len(r) == 2
assert r[0] == Variant(position=99, allele=1, quality=27)
assert r[1] == Variant(position=105, allele=0, quality=14)
def test_merge_many_reads():
reads = [
Read("Name1"),
Read("Name2"),
Read("Name3"),
]
reads[0].add_variant(100, 0, 31)
reads[0].add_variant(200, 1, 32)
reads[0].add_variant(300, 0, 33)
reads[1].add_variant(200, 1, 41)
reads[1].add_variant(400, 0, 42)
reads[1].add_variant(500, 0, 43)
reads[2].add_variant(200, 0, 51)
reads[2].add_variant(500, 0, 52)
reads[2].add_variant(600, 0, 53)
expected = [
Variant(100, 0, 31),
Variant(200, 1, 73), # see note: this depends on order of reads
Variant(300, 0, 33),
Variant(400, 0, 42),
Variant(500, 0, 43 + 52),
Variant(600, 0, 53),
]
assert expected == list(merge_reads(*reads))
# TODO merging should not depend on the order of reads
expected[1] = Variant(200, 0, 51)
assert expected == list(merge_reads(*reads[::-1]))
def test_merge_pair_with_shared_positions(merge):
left = Read("Name1")
left.add_variant(100, 0, 31)
left.add_variant(200, 0, 32)
left.add_variant(300, 0, 33)
right = Read("Name2")
right.add_variant(200, 0, 41) # alleles disagree
right.add_variant(300, 1, 42) # alleles agree
right.add_variant(400, 1, 43)
expected = [
Variant(100, 0, 31),
Variant(200, 0, 32 + 41),
Variant(300, 1, 42),
Variant(400, 1, 43),
]
assert expected == list(merge(left, right))
assert expected == list(merge(right, left))