def test_nondegenerates_gap_mixed_case(self):
exp = [
NucleotideSequence('-A.a'),
NucleotideSequence('-A.c'),
NucleotideSequence('-C.a'),
NucleotideSequence('-C.c')
]
obs = sorted(NucleotideSequence('-M.m').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_eq(self):
self.assertTrue(self.b1 == self.b1)
self.assertTrue(self.b2 == self.b2)
self.assertTrue(self.b3 == self.b3)
self.assertTrue(self.b1 != self.b3)
self.assertTrue(self.b1 != self.b2)
self.assertTrue(self.b2 != self.b3)
# identicial sequences of the same type are equal, even if they have
# different ids and/or descriptions
self.assertTrue(
BiologicalSequence('ACGT') == BiologicalSequence('ACGT'))
self.assertTrue(
BiologicalSequence('ACGT', id='a') == BiologicalSequence('ACGT',
id='b'))
self.assertTrue(
BiologicalSequence('ACGT', description='c') == BiologicalSequence(
'ACGT', description='d'))
self.assertTrue(
BiologicalSequence('ACGT', id='a', description='c') ==
BiologicalSequence('ACGT', id='b', description='d'))
# different type causes sequences to not be equal
self.assertFalse(
BiologicalSequence('ACGT') == NucleotideSequence('ACGT'))
def test_nondegenerates_mixed_degens(self):
exp = [
NucleotideSequence('AGC'),
NucleotideSequence('AGT'),
NucleotideSequence('AGU'),
NucleotideSequence('GGC'),
NucleotideSequence('GGT'),
NucleotideSequence('GGU')
]
obs = sorted(NucleotideSequence('RGY').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_sequence_collection_to_fastq_kwargs_passed(self):
for components, kwargs_expected_fp in self.valid_files:
for kwargs, expected_fp in kwargs_expected_fp:
obj = SequenceCollection([
NucleotideSequence(c[2],
id=c[0],
description=c[1],
quality=c[3]) for c in components
])
fh = StringIO()
_sequence_collection_to_fastq(obj, fh, **kwargs)
observed = fh.getvalue()
fh.close()
with open(expected_fp, 'U') as f:
expected = f.read()
self.assertEqual(observed, expected)
def test_nondegenerates_all_degens(self):
# Same chars.
exp = [
NucleotideSequence('CC'),
NucleotideSequence('CG'),
NucleotideSequence('GC'),
NucleotideSequence('GG')
]
# Sort based on sequence string, as order is not guaranteed.
obs = sorted(NucleotideSequence('SS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Different chars.
exp = [
NucleotideSequence('AC'),
NucleotideSequence('AG'),
NucleotideSequence('GC'),
NucleotideSequence('GG')
]
obs = sorted(NucleotideSequence('RS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Odd number of chars.
obs = list(NucleotideSequence('NNN').nondegenerates())
self.assertEqual(len(obs), 5**3)
def test_nondegenerates_invalid(self):
with self.assertRaises(BiologicalSequenceError):
list(NucleotideSequence('AZA').nondegenerates())
def setUp(self):
self.empty = NucleotideSequence('')
self.b1 = NucleotideSequence('GATTACA')
self.b2 = NucleotideSequence('ACCGGUACC',
id="test-seq-2",
description="A test sequence")
def test_lower(self):
b = NucleotideSequence('GAt.ACa-', id='x', description='42')
expected = NucleotideSequence('gat.aca-', id='x', description='42')
self.assertEqual(b.lower(), expected)
def test_upper(self):
b = NucleotideSequence('GAt.ACa-', id='x', description='42')
expected = NucleotideSequence('GAT.ACA-', id='x', description='42')
self.assertEqual(b.upper(), expected)
