def test_issue_80():
# This issue turned out to not be an actual issue with the alignment
# algorithm. The following alignment is found because it has more matches
# than the 'obvious' one:
#
# TCGTATGCCGTCTTC
# =========X==XX=
# TCGTATGCCCTC--C
#
# This is correct, albeit a little surprising, since an alignment without
# indels would have only two errors.
adapter = Adapter(
sequence="TCGTATGCCGTCTTC",
where=BACK,
max_error_rate=0.2,
min_overlap=3,
read_wildcards=False,
adapter_wildcards=False)
read = Sequence(name="seq2", sequence="TCGTATGCCCTCC")
result = adapter.match_to(read)
assert read.original_length == 13, result
assert result.errors == 3, result
assert result.astart == 0, result
assert result.astop == 15, result
def test_random_match_probabilities():
a = Adapter('A', BACK)
rmp = a.random_match_probabilities()
assert rmp == [1.0, 0.25]
a = Adapter('AC', BACK, gc_content=0.4)
rmp = a.random_match_probabilities()
assert rmp == [1.0, 0.3, 0.06]
def test_statistics():
read = Sequence('name', 'AAAACCCCAAAA')
adapters = [Adapter('CCCC', BACK, 0.1)]
cutter = AdapterCutter(adapters, times=3)
trimmed_read = cutter(read)
# TODO make this a lot simpler
trimmed_bp = 0
for adapter in adapters:
for d in (adapter.lengths_front, adapter.lengths_back):
trimmed_bp += sum(seqlen * count for (seqlen, count) in d.items())
assert trimmed_bp <= len(read), trimmed_bp
def test_issue_52():
adapter = Adapter(
sequence='GAACTCCAGTCACNNNNN',
where=BACK,
max_error_rate=0.12,
min_overlap=5,
read_wildcards=False,
adapter_wildcards=True)
read = Sequence(name="abc", sequence='CCCCAGAACTACAGTCCCGGC')
am = Match(astart=0, astop=17, rstart=5, rstop=21, matches=15, errors=2, front=None, adapter=adapter, read=read)
assert am.wildcards() == 'GGC'
"""
def test_random_match_probabilities():
a = Adapter('A', BACK)
rmp = a.random_match_probabilities()
assert rmp == [1.0, 0.25]
a = Adapter('AC', BACK, gc_content=0.4)
rmp = a.random_match_probabilities()
assert rmp == [1.0, 0.3, 0.06]
def test_str():
a = Adapter('ACGT', where=BACK, max_error_rate=0.1)
str(a)
str(a.match_to(Sequence(name='seq', sequence='TTACGT')))
ca = ColorspaceAdapter('0123', where=BACK, max_error_rate=0.1)
str(ca)
