def test_variant_equal_throws_below_reference():
ref_id = chrom_ref['13'].keys()[0]
v1 = ('13', chrom_ref['13'][ref_id]['start'], 'A', 'C')
v2 = ('13', chrom_ref['13'][ref_id]['start'] + 10, 'A', 'C')
with pytest.raises(AssertionError):
variant_equal(v1, v2, ref_id, seq_provider)
with pytest.raises(AssertionError):
variant_equal(v2, v1, ref_id, seq_provider)
def test_variant_equal_throws_below_reference():
ref_id = chrom_ref['13'].keys()[0]
v1 = ('13', chrom_ref['13'][ref_id]['start'], 'A', 'C')
v2 = ('13', chrom_ref['13'][ref_id]['start'] + 10, 'A', 'C')
with pytest.raises(AssertionError):
variant_equal(v1, v2, ref_id, seq_provider)
with pytest.raises(AssertionError):
variant_equal(v2, v1, ref_id, seq_provider)
def test_variant_equal_throws_above_reference():
ref_id = chrom_ref['13'].keys()[0]
start = chrom_ref['13'][ref_id]['start']
v1 = ('13', start + reference_length + 2, 'A', 'C')
v2 = ('13', start + 10, 'A', 'C')
with pytest.raises(AssertionError):
variant_equal(v1, v2, ref_id, seq_provider)
with pytest.raises(AssertionError):
variant_equal(v2, v1, ref_id, seq_provider)
def test_variant_equal_throws_above_reference():
ref_id = chrom_ref['13'].keys()[0]
start = chrom_ref['13'][ref_id]['start']
v1 = ('13', start + reference_length + 2, 'A', 'C')
v2 = ('13', start + 10, 'A', 'C')
with pytest.raises(AssertionError):
variant_equal(v1, v2, ref_id, seq_provider)
with pytest.raises(AssertionError):
variant_equal(v2, v1, ref_id, seq_provider)
def test_variant_equal_commutative(v1, v2, ref_id):
"Comparing x, y should be the same as comparing y, x"
(_, pos1, ref1, _) = v1
(_, pos2, ref2, _) = v2
assume(pos1 + len(ref1) <= reference_length)
assume(pos2 + len(ref2) <= reference_length)
v1 = add_start(v1, ref_id)
v2 = add_start(v2, ref_id)
assert variant_equal(v1, v2, ref_id, seq_provider) == variant_equal(v2, v1, ref_id, seq_provider)
def test_variant_equal_commutative(v1, v2, ref_id):
"Comparing x, y should be the same as comparing y, x"
(_, pos1, ref1, _) = v1
(_, pos2, ref2, _) = v2
assume(pos1 + len(ref1) <= reference_length)
assume(pos2 + len(ref2) <= reference_length)
v1 = add_start(v1, ref_id)
v2 = add_start(v2, ref_id)
assert variant_equal(v1, v2, ref_id, seq_provider) == variant_equal(
v2, v1, ref_id, seq_provider)
def test_variant_equal_not_equiv(v1, v2, ref_id):
(chrom1, pos1, reflen1, alt1) = v1
(chrom2, pos2, reflen2, alt2) = v2
assume(pos1 + reflen1 <= reference_length)
assume(pos2 + reflen2 <= reference_length)
assume(not alt1 == '' and reflen1 == 0)
assume(not alt2 == '' and reflen2 == 0)
refsequence1 = chrom_ref[chrom1][ref_id]["sequence"]
refsequence2 = chrom_ref[chrom2][ref_id]["sequence"]
v1 = inject_ref(refsequence1, v1)
v2 = inject_ref(refsequence2, v2)
eq1 = equiv_set(refsequence1, v1)
eq2 = equiv_set(refsequence2, v2)
if len(eq1.intersection(eq2)) == 0: # should test not-equal
assert not variant_equal(add_start(v1, ref_id), add_start(v2, ref_id), ref_id, seq_provider)
else:
assert variant_equal(add_start(v1, ref_id), add_start(v2, ref_id), ref_id, seq_provider)
def test_variant_equal_equiv(v, ref_id):
(chrom, pos, reflen, alt) = v
refsequence = chrom_ref[chrom][ref_id]["sequence"]
assume(pos + reflen <= len(refsequence))
v = inject_ref(refsequence, v)
equivs = all_norm_equiv(refsequence, v)
for veq in equivs:
if is_in_bounds(veq):
assert variant_equal(add_start(v, ref_id), add_start(veq, ref_id), ref_id, seq_provider)
def test_variant_equal_equiv(v, ref_id):
(chrom, pos, reflen, alt) = v
refsequence = chrom_ref[chrom][ref_id]["sequence"]
assume(pos + reflen <= len(refsequence))
v = inject_ref(refsequence, v)
equivs = all_norm_equiv(refsequence, v)
for veq in equivs:
if is_in_bounds(veq):
assert variant_equal(add_start(v, ref_id), add_start(veq, ref_id),
ref_id, seq_provider)
def test_variant_equal_not_equiv(v1, v2, ref_id):
(chrom1, pos1, reflen1, alt1) = v1
(chrom2, pos2, reflen2, alt2) = v2
assume(pos1 + reflen1 <= reference_length)
assume(pos2 + reflen2 <= reference_length)
assume(not alt1 == '' and reflen1 == 0)
assume(not alt2 == '' and reflen2 == 0)
refsequence1 = chrom_ref[chrom1][ref_id]["sequence"]
refsequence2 = chrom_ref[chrom2][ref_id]["sequence"]
v1 = inject_ref(refsequence1, v1)
v2 = inject_ref(refsequence2, v2)
eq1 = equiv_set(refsequence1, v1)
eq2 = equiv_set(refsequence2, v2)
if len(eq1.intersection(eq2)) == 0: # should test not-equal
assert not variant_equal(add_start(v1, ref_id), add_start(v2, ref_id),
ref_id, seq_provider)
else:
assert variant_equal(add_start(v1, ref_id), add_start(v2, ref_id),
ref_id, seq_provider)
def test_variant_equal_identity(v, ref_id):
"A variant should be equal to itself"
(_, pos, ref, _) = v
assume(pos + len(ref) <= reference_length)
v = add_start(v, ref_id)
assert variant_equal(v, v, ref_id, seq_provider)
assert frozenset(example_variants) == frozenset(
find_equivalent_variants_whole_seq(variant_dict,
whole_seq_provider))
def test_chunking():
def chunker(vars, margin):
return seq_utils.ChunkBasedSeqProvider.generate_chunks(vars, margin)
margin = 2
assert chunker([], margin) == []
some_chr = 7
v1 = VCFVariant(some_chr, 10, 'AGAGT', 'G')
assert chunker([v1], margin) == [(some_chr, 10 - margin, 10 + 5 + margin)]
# merging intervals of v1 and v2 together
v2 = VCFVariant(some_chr, 11, 'GAGT', 'G')
assert chunker([v1, v2],
margin) == [(some_chr, min(10 - margin, 11 - margin),
max(10 + 5 + margin, 11 + 4 + margin))]
if __name__ == "__main__":
# To reproduce failure conditions, paste them in here and run as
# python ./test_variant_merging.py
# print variant_equal(v1 = ('17', 41100001, 'gcttccca', ''), v2 = ('17', 41100002, 'cttcccag', ''), version = 'hg38')
print variant_equal(('13', 32800003, '', 'A'), ('13', 32800005, '', 'A'),
'hg19')
pass
def test_variant_equal_identity(v, ref_id):
"A variant should be equal to itself"
(_, pos, ref, _) = v
assume(pos + len(ref) <= reference_length)
v = add_start(v, ref_id)
assert variant_equal(v, v, ref_id, seq_provider)
# empty case
assert [] == find_equivalent_variant({}, seq_provider)
# a bunch of variants. If they appear in the same set, they are considered equivalent
example_variants = [
frozenset({'chr13:g.32355030:A>AA'}),
frozenset({'chr13:g.32339774:GAT>G', 'chr13:g.32339776:TAT>T'}),
frozenset({'chr17:g.43090921:G>GCA', 'chr17:g.43090921:GCA>GCACA'})
]
# construct variant dict (flattening example_variants!)
variant_dict = {v: [None, None, None,
v.split(':')[0].lstrip('chr'),
v.split(':')[1].lstrip('g.'),
v.split(':')[2].split('>')[0],
v.split(':')[2].split('>')[1],
] for eq_variants in example_variants for v in
eq_variants
}
assert frozenset(example_variants) == frozenset(find_equivalent_variant(variant_dict,
seq_provider))
if __name__ == "__main__":
# To reproduce failure conditions, paste them in here and run as
# python ./test_variant_merging.py
# print variant_equal(v1 = ('17', 41100001, 'gcttccca', ''), v2 = ('17', 41100002, 'cttcccag', ''), version = 'hg38')
print variant_equal(('13', 32800003, '', 'A'), ('13', 32800005, '', 'A'), 'hg19')
pass