def setUp(self):
"""Initialize values to be used in tests
"""
self.d1 = DNASequence('GATTACA', id="d1")
self.d2 = DNASequence('TTG', id="d2")
self.d1_lower = DNASequence('gattaca', id="d1")
self.d2_lower = DNASequence('ttg', id="d2")
self.r1 = RNASequence('GAUUACA', id="r1")
self.r2 = RNASequence('UUG', id="r2")
self.r3 = RNASequence('U-----UGCC--', id="r3")
self.i1 = DNASequence('GATXACA', id="i1")
self.seqs1 = [self.d1, self.d2]
self.seqs1_lower = [self.d1_lower, self.d2_lower]
self.seqs2 = [self.r1, self.r2, self.r3]
self.seqs3 = self.seqs1 + self.seqs2
self.seqs1_t = [('d1', 'GATTACA'), ('d2', 'TTG')]
self.seqs2_t = [('r1', 'GAUUACA'), ('r2', 'UUG'),
('r3', 'U-----UGCC--')]
self.seqs3_t = self.seqs1_t + self.seqs2_t
self.s1 = SequenceCollection(self.seqs1)
self.s1_lower = SequenceCollection(self.seqs1_lower)
self.s2 = SequenceCollection(self.seqs2)
self.s3 = SequenceCollection(self.seqs3)
self.empty = SequenceCollection([])
self.invalid_s1 = SequenceCollection([self.i1])
def setUp(self):
self.d1 = DNASequence('..ACC-GTTGG..', id="d1")
self.d2 = DNASequence('TTACCGGT-GGCC', id="d2")
self.d3 = DNASequence('.-ACC-GTTGC--', id="d3")
self.r1 = RNASequence('UUAU-', id="r1")
self.r2 = RNASequence('ACGUU', id="r2")
self.seqs1 = [self.d1, self.d2, self.d3]
self.seqs2 = [self.r1, self.r2]
self.seqs1_t = [('d1', '..ACC-GTTGG..'), ('d2', 'TTACCGGT-GGCC'),
('d3', '.-ACC-GTTGC--')]
self.seqs2_t = [('r1', 'UUAU-'), ('r2', 'ACGUU')]
self.a1 = Alignment(self.seqs1)
self.a2 = Alignment(self.seqs2)
self.a3 = Alignment(self.seqs2,
score=42.0,
start_end_positions=[(0, 3), (5, 9)])
self.a4 = Alignment(self.seqs2,
score=-42.0,
start_end_positions=[(1, 4), (6, 10)])
# no sequences
self.empty = Alignment([])
# sequences, but no positions
self.no_positions = Alignment([RNA('', id='a'), RNA('', id='b')])
def test_omit_gap_positions(self):
expected = self.a2
self.assertEqual(self.a2.omit_gap_positions(1.0), expected)
self.assertEqual(self.a2.omit_gap_positions(0.51), expected)
r1 = RNASequence('UUAU', id="r1")
r2 = RNASequence('ACGU', id="r2")
expected = Alignment([r1, r2])
self.assertEqual(self.a2.omit_gap_positions(0.49), expected)
r1 = RNASequence('UUAU', id="r1")
r2 = RNASequence('ACGU', id="r2")
expected = Alignment([r1, r2])
self.assertEqual(self.a2.omit_gap_positions(0.0), expected)
self.assertEqual(self.empty.omit_gap_positions(0.0), self.empty)
self.assertEqual(self.empty.omit_gap_positions(0.49), self.empty)
self.assertEqual(self.empty.omit_gap_positions(1.0), self.empty)
# Test to ensure floating point precision bug isn't present. See the
# tests for Alignment.position_frequencies for more details.
seqs = []
for i in range(33):
seqs.append(DNA('-.', id=str(i)))
aln = Alignment(seqs)
self.assertEqual(aln.omit_gap_positions(1 - np.finfo(float).eps),
Alignment([DNA('', id=str(i)) for i in range(33)]))
def test_reverse_complement(self):
self.assertEqual(self.b1.reverse_complement(), RNASequence("UGUAAUC"))
self.assertEqual(self.b2.reverse_complement(),
RNASequence("GGUACCGGU"))
self.assertRaises(BiologicalSequenceError, self.b3.reverse_complement)
self.assertEqual(self.b4.reverse_complement(),
RNASequence("NVHDBMRSWYK"))
def test_nondegenerates_mixed_degens(self):
exp = [
RNASequence('AGC'),
RNASequence('AGU'),
RNASequence('GGC'),
RNASequence('GGU')
]
obs = sorted(RNASequence('RGY').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_nondegenerates_gap_mixed_case(self):
exp = [
RNASequence('-A.a'),
RNASequence('-A.c'),
RNASequence('-C.a'),
RNASequence('-C.c')
]
obs = sorted(RNASequence('-M.m').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_iupac_degenerate_characters(self):
exp = set([
'B', 'D', 'H', 'K', 'M', 'N', 'S', 'R', 'W', 'V', 'Y', 'b', 'd',
'h', 'k', 'm', 'n', 's', 'r', 'w', 'v', 'y'
])
self.assertEqual(self.b1.iupac_degenerate_characters(), exp)
self.assertEqual(RNASequence.iupac_degenerate_characters(), exp)
def test_iupac_degeneracies(self):
exp = {
'B': set(['C', 'U', 'G']),
'D': set(['A', 'U', 'G']),
'H': set(['A', 'C', 'U']),
'K': set(['U', 'G']),
'M': set(['A', 'C']),
'N': set(['A', 'C', 'U', 'G']),
'S': set(['C', 'G']),
'R': set(['A', 'G']),
'W': set(['A', 'U']),
'V': set(['A', 'C', 'G']),
'Y': set(['C', 'U']),
'b': set(['c', 'u', 'g']),
'd': set(['a', 'u', 'g']),
'h': set(['a', 'c', 'u']),
'k': set(['u', 'g']),
'm': set(['a', 'c']),
'n': set(['a', 'c', 'u', 'g']),
's': set(['c', 'g']),
'r': set(['a', 'g']),
'w': set(['a', 'u']),
'v': set(['a', 'c', 'g']),
'y': set(['c', 'u'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(RNASequence.iupac_degeneracies(), exp)
def test_iupac_characters(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
'u', 'w', 'v', 'y'
}
self.assertEqual(self.b1.iupac_characters(), exp)
self.assertEqual(RNASequence.iupac_characters(), exp)
def test_iupac_characters(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
'u', 'w', 'v', 'y'
}
self.assertEqual(self.b1.iupac_characters(), exp)
self.assertEqual(RNASequence.iupac_characters(), exp)
def generator():
yield BiologicalSequence('ACGT',
id='',
description='',
quality=range(4))
yield RNASequence('GAU', id=' foo \t\t bar ', description='')
yield DNASequence('TAG', id='', description='foo\n\n bar\n')
yield BiologicalSequence('A',
id='foo',
description='bar baz',
quality=[42])
def test_complement_map(self):
exp = {
'-': '-', '.': '.', 'A': 'U', 'C': 'G', 'B': 'V', 'D': 'H',
'G': 'C', 'H': 'D', 'K': 'M', 'M': 'K', 'N': 'N', 'S': 'S',
'R': 'Y', 'U': 'A', 'W': 'W', 'V': 'B', 'Y': 'R', 'a': 'u',
'c': 'g', 'b': 'v', 'd': 'h', 'g': 'c', 'h': 'd', 'k': 'm',
'm': 'k', 'n': 'n', 's': 's', 'r': 'y', 'u': 'a', 'w': 'w',
'v': 'b', 'y': 'r'
}
self.assertEqual(self.b1.complement_map(), exp)
self.assertEqual(RNASequence.complement_map(), exp)
def test_omit_gap_positions(self):
"""omitting gap positions functions as expected
"""
expected = self.a2
self.assertEqual(self.a2.omit_gap_positions(1.0), expected)
self.assertEqual(self.a2.omit_gap_positions(0.51), expected)
r1 = RNASequence('UUAU', id="r1")
r2 = RNASequence('ACGU', id="r2")
expected = Alignment([r1, r2])
self.assertEqual(self.a2.omit_gap_positions(0.49), expected)
r1 = RNASequence('UUAU', id="r1")
r2 = RNASequence('ACGU', id="r2")
expected = Alignment([r1, r2])
self.assertEqual(self.a2.omit_gap_positions(0.0), expected)
self.assertEqual(self.empty.omit_gap_positions(0.0), self.empty)
self.assertEqual(self.empty.omit_gap_positions(0.49), self.empty)
self.assertEqual(self.empty.omit_gap_positions(1.0), self.empty)
def test_iter_positions(self):
actual = list(self.a2.iter_positions())
expected = [[RNASequence(j) for j in i]
for i in ['UA', 'UC', 'AG', 'UU', '-U']]
self.seqs2_t = [('r1', 'UUAU-'), ('r2', 'ACGUU')]
self.assertEqual(actual, expected)
actual = list(self.a2.iter_positions(constructor=str))
expected = [list('UA'), list('UC'), list('AG'), list('UU'), list('-U')]
self.seqs2_t = [('r1', 'UUAU-'), ('r2', 'ACGUU')]
self.assertEqual(actual, expected)
def test_iupac_degeneracies(self):
exp = {
'B': set(['C', 'U', 'G']), 'D': set(['A', 'U', 'G']),
'H': set(['A', 'C', 'U']), 'K': set(['U', 'G']),
'M': set(['A', 'C']), 'N': set(['A', 'C', 'U', 'G']),
'S': set(['C', 'G']), 'R': set(['A', 'G']), 'W': set(['A', 'U']),
'V': set(['A', 'C', 'G']), 'Y': set(['C', 'U']),
'b': set(['c', 'u', 'g']), 'd': set(['a', 'u', 'g']),
'h': set(['a', 'c', 'u']), 'k': set(['u', 'g']),
'm': set(['a', 'c']), 'n': set(['a', 'c', 'u', 'g']),
's': set(['c', 'g']), 'r': set(['a', 'g']), 'w': set(['a', 'u']),
'v': set(['a', 'c', 'g']), 'y': set(['c', 'u'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(RNASequence.iupac_degeneracies(), exp)
def setUp(self):
self.empty = RNASequence('')
self.b1 = RNASequence('GAUUACA')
self.b2 = RNASequence('ACCGGUACC', id="test-seq-2",
description="A test sequence", quality=range(9))
self.b3 = RNASequence(
'ACCGGTACC', id="bad-seq-1",
description="Not a RNA sequence")
self.b4 = RNASequence(
'MRWSYKVHDBN', id="degen",
description="All of the degenerate bases")
self.b5 = RNASequence('.G--AUUAC-A...')
def test_complement_map(self):
exp = {
'-': '-',
'.': '.',
'A': 'U',
'C': 'G',
'B': 'V',
'D': 'H',
'G': 'C',
'H': 'D',
'K': 'M',
'M': 'K',
'N': 'N',
'S': 'S',
'R': 'Y',
'U': 'A',
'W': 'W',
'V': 'B',
'Y': 'R',
'a': 'u',
'c': 'g',
'b': 'v',
'd': 'h',
'g': 'c',
'h': 'd',
'k': 'm',
'm': 'k',
'n': 'n',
's': 's',
'r': 'y',
'u': 'a',
'w': 'w',
'v': 'b',
'y': 'r'
}
self.assertEqual(self.b1.complement_map(), exp)
self.assertEqual(RNASequence.complement_map(), exp)
def test_iupac_standard_characters(self):
exp = set("ACGUacgu")
self.assertEqual(self.b1.iupac_standard_characters(), exp)
self.assertEqual(RNASequence.iupac_standard_characters(), exp)
def test_iupac_degenerate_characters(self):
exp = set(['B', 'D', 'H', 'K', 'M', 'N', 'S', 'R', 'W', 'V', 'Y',
'b', 'd', 'h', 'k', 'm', 'n', 's', 'r', 'w', 'v', 'y'])
self.assertEqual(self.b1.iupac_degenerate_characters(), exp)
self.assertEqual(RNASequence.iupac_degenerate_characters(), exp)
def setUp(self):
self.empty = RNASequence('')
self.b1 = RNASequence('GAUUACA')
self.b2 = RNASequence('ACCGGUACC',
id="test-seq-2",
description="A test sequence")
self.b3 = RNASequence('ACCGGTACC',
id="bad-seq-1",
description="Not a RNA sequence")
self.b4 = RNASequence('MRWSYKVHDBN',
id="degen",
description="All of the degenerate bases")
self.b5 = RNASequence('.G--AUUAC-A...')
def test_iupac_standard_characters(self):
exp = set("ACGUacgu")
self.assertEqual(self.b1.iupac_standard_characters(), exp)
self.assertEqual(RNASequence.iupac_standard_characters(), exp)
def test_complement(self):
self.assertEqual(self.b1.complement(), RNASequence("CUAAUGU"))
self.assertEqual(self.b2.complement(), RNASequence("UGGCCAUGG"))
self.assertRaises(BiologicalSequenceError, self.b3.complement)
self.assertEqual(self.b4.complement(), RNASequence("KYWSRMBDHVN"))
self.assertEqual(self.b5.complement(), RNASequence(".C--UAAUG-U..."))
class RNASequenceTests(TestCase):
def setUp(self):
self.empty = RNASequence('')
self.b1 = RNASequence('GAUUACA')
self.b2 = RNASequence(
'ACCGGUACC', id="test-seq-2",
description="A test sequence")
self.b3 = RNASequence(
'ACCGGTACC', id="bad-seq-1",
description="Not a RNA sequence")
self.b4 = RNASequence(
'MRWSYKVHDBN', id="degen",
description="All of the degenerate bases")
self.b5 = RNASequence('.G--AUUAC-A...')
def test_alphabet(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
'u', 'w', 'v', 'y'
}
self.assertEqual(self.b1.alphabet(), exp)
self.assertEqual(RNASequence.alphabet(), exp)
def test_gap_alphabet(self):
self.assertEqual(self.b1.gap_alphabet(), set('-.'))
def test_complement_map(self):
exp = {
'-': '-', '.': '.', 'A': 'U', 'C': 'G', 'B': 'V', 'D': 'H',
'G': 'C', 'H': 'D', 'K': 'M', 'M': 'K', 'N': 'N', 'S': 'S',
'R': 'Y', 'U': 'A', 'W': 'W', 'V': 'B', 'Y': 'R', 'a': 'u',
'c': 'g', 'b': 'v', 'd': 'h', 'g': 'c', 'h': 'd', 'k': 'm',
'm': 'k', 'n': 'n', 's': 's', 'r': 'y', 'u': 'a', 'w': 'w',
'v': 'b', 'y': 'r'
}
self.assertEqual(self.b1.complement_map(), exp)
self.assertEqual(RNASequence.complement_map(), exp)
def test_iupac_standard_characters(self):
exp = set("ACGUacgu")
self.assertEqual(self.b1.iupac_standard_characters(), exp)
self.assertEqual(RNASequence.iupac_standard_characters(), exp)
def test_iupac_degeneracies(self):
exp = {
'B': set(['C', 'U', 'G']), 'D': set(['A', 'U', 'G']),
'H': set(['A', 'C', 'U']), 'K': set(['U', 'G']),
'M': set(['A', 'C']), 'N': set(['A', 'C', 'U', 'G']),
'S': set(['C', 'G']), 'R': set(['A', 'G']), 'W': set(['A', 'U']),
'V': set(['A', 'C', 'G']), 'Y': set(['C', 'U']),
'b': set(['c', 'u', 'g']), 'd': set(['a', 'u', 'g']),
'h': set(['a', 'c', 'u']), 'k': set(['u', 'g']),
'm': set(['a', 'c']), 'n': set(['a', 'c', 'u', 'g']),
's': set(['c', 'g']), 'r': set(['a', 'g']), 'w': set(['a', 'u']),
'v': set(['a', 'c', 'g']), 'y': set(['c', 'u'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(RNASequence.iupac_degeneracies(), exp)
def test_iupac_degenerate_characters(self):
exp = set(['B', 'D', 'H', 'K', 'M', 'N', 'S', 'R', 'W', 'V', 'Y',
'b', 'd', 'h', 'k', 'm', 'n', 's', 'r', 'w', 'v', 'y'])
self.assertEqual(self.b1.iupac_degenerate_characters(), exp)
self.assertEqual(RNASequence.iupac_degenerate_characters(), exp)
def test_iupac_characters(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
'u', 'w', 'v', 'y'
}
self.assertEqual(self.b1.iupac_characters(), exp)
self.assertEqual(RNASequence.iupac_characters(), exp)
def test_complement(self):
self.assertEqual(self.b1.complement(), RNASequence("CUAAUGU"))
self.assertEqual(self.b2.complement(), RNASequence("UGGCCAUGG"))
self.assertRaises(BiologicalSequenceError, self.b3.complement)
self.assertEqual(self.b4.complement(), RNASequence("KYWSRMBDHVN"))
self.assertEqual(self.b5.complement(), RNASequence(".C--UAAUG-U..."))
def test_reverse_complement(self):
self.assertEqual(self.b1.reverse_complement(), RNASequence("UGUAAUC"))
self.assertEqual(self.b2.reverse_complement(),
RNASequence("GGUACCGGU"))
self.assertRaises(BiologicalSequenceError, self.b3.reverse_complement)
self.assertEqual(self.b4.reverse_complement(),
RNASequence("NVHDBMRSWYK"))
def test_unsupported_characters(self):
self.assertEqual(self.b1.unsupported_characters(), set())
self.assertEqual(self.b2.unsupported_characters(), set())
self.assertEqual(self.b3.unsupported_characters(), set('T'))
self.assertEqual(self.b4.unsupported_characters(), set())
def test_has_unsupported_characters(self):
self.assertFalse(self.b1.has_unsupported_characters())
self.assertFalse(self.b2.has_unsupported_characters())
self.assertTrue(self.b3.has_unsupported_characters())
self.assertFalse(self.b4.has_unsupported_characters())
def test_is_reverse_complement(self):
self.assertFalse(self.b1.is_reverse_complement(self.b1))
self.assertTrue(
self.b1.is_reverse_complement(RNASequence('UGUAAUC')))
self.assertTrue(
self.b4.is_reverse_complement(RNASequence('NVHDBMRSWYK')))
def test_nondegenerates_invalid(self):
with self.assertRaises(BiologicalSequenceError):
list(RNASequence('AZA').nondegenerates())
def test_nondegenerates_empty(self):
self.assertEqual(list(self.empty.nondegenerates()), [self.empty])
def test_nondegenerates_no_degens(self):
self.assertEqual(list(self.b1.nondegenerates()), [self.b1])
def test_nondegenerates_all_degens(self):
# Same chars.
exp = [RNASequence('CC'), RNASequence('CG'), RNASequence('GC'),
RNASequence('GG')]
# Sort based on sequence string, as order is not guaranteed.
obs = sorted(RNASequence('SS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Different chars.
exp = [RNASequence('AC'), RNASequence('AG'), RNASequence('GC'),
RNASequence('GG')]
obs = sorted(RNASequence('RS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Odd number of chars.
obs = list(RNASequence('NNN').nondegenerates())
self.assertEqual(len(obs), 4**3)
def test_nondegenerates_mixed_degens(self):
exp = [RNASequence('AGC'), RNASequence('AGU'), RNASequence('GGC'),
RNASequence('GGU')]
obs = sorted(RNASequence('RGY').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_nondegenerates_gap_mixed_case(self):
exp = [RNASequence('-A.a'), RNASequence('-A.c'),
RNASequence('-C.a'), RNASequence('-C.c')]
obs = sorted(RNASequence('-M.m').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def missing_qual_gen():
for seq in (RNASequence('A',
quality=[42]), BiologicalSequence('AG'),
DNASequence('GG', quality=[41, 40])):
yield seq
def blank_seq_gen():
for seq in (DNASequence('A'), BiologicalSequence(''),
RNASequence('GG')):
yield seq
class RNASequenceTests(TestCase):
def setUp(self):
self.empty = RNASequence('')
self.b1 = RNASequence('GAUUACA')
self.b2 = RNASequence('ACCGGUACC',
id="test-seq-2",
description="A test sequence")
self.b3 = RNASequence('ACCGGTACC',
id="bad-seq-1",
description="Not a RNA sequence")
self.b4 = RNASequence('MRWSYKVHDBN',
id="degen",
description="All of the degenerate bases")
self.b5 = RNASequence('.G--AUUAC-A...')
def test_alphabet(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
'u', 'w', 'v', 'y'
}
self.assertEqual(self.b1.alphabet(), exp)
self.assertEqual(RNASequence.alphabet(), exp)
def test_gap_alphabet(self):
self.assertEqual(self.b1.gap_alphabet(), set('-.'))
def test_complement_map(self):
exp = {
'-': '-',
'.': '.',
'A': 'U',
'C': 'G',
'B': 'V',
'D': 'H',
'G': 'C',
'H': 'D',
'K': 'M',
'M': 'K',
'N': 'N',
'S': 'S',
'R': 'Y',
'U': 'A',
'W': 'W',
'V': 'B',
'Y': 'R',
'a': 'u',
'c': 'g',
'b': 'v',
'd': 'h',
'g': 'c',
'h': 'd',
'k': 'm',
'm': 'k',
'n': 'n',
's': 's',
'r': 'y',
'u': 'a',
'w': 'w',
'v': 'b',
'y': 'r'
}
self.assertEqual(self.b1.complement_map(), exp)
self.assertEqual(RNASequence.complement_map(), exp)
def test_iupac_standard_characters(self):
exp = set("ACGUacgu")
self.assertEqual(self.b1.iupac_standard_characters(), exp)
self.assertEqual(RNASequence.iupac_standard_characters(), exp)
def test_iupac_degeneracies(self):
exp = {
'B': set(['C', 'U', 'G']),
'D': set(['A', 'U', 'G']),
'H': set(['A', 'C', 'U']),
'K': set(['U', 'G']),
'M': set(['A', 'C']),
'N': set(['A', 'C', 'U', 'G']),
'S': set(['C', 'G']),
'R': set(['A', 'G']),
'W': set(['A', 'U']),
'V': set(['A', 'C', 'G']),
'Y': set(['C', 'U']),
'b': set(['c', 'u', 'g']),
'd': set(['a', 'u', 'g']),
'h': set(['a', 'c', 'u']),
'k': set(['u', 'g']),
'm': set(['a', 'c']),
'n': set(['a', 'c', 'u', 'g']),
's': set(['c', 'g']),
'r': set(['a', 'g']),
'w': set(['a', 'u']),
'v': set(['a', 'c', 'g']),
'y': set(['c', 'u'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(RNASequence.iupac_degeneracies(), exp)
def test_iupac_degenerate_characters(self):
exp = set([
'B', 'D', 'H', 'K', 'M', 'N', 'S', 'R', 'W', 'V', 'Y', 'b', 'd',
'h', 'k', 'm', 'n', 's', 'r', 'w', 'v', 'y'
])
self.assertEqual(self.b1.iupac_degenerate_characters(), exp)
self.assertEqual(RNASequence.iupac_degenerate_characters(), exp)
def test_iupac_characters(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
'u', 'w', 'v', 'y'
}
self.assertEqual(self.b1.iupac_characters(), exp)
self.assertEqual(RNASequence.iupac_characters(), exp)
def test_complement(self):
self.assertEqual(self.b1.complement(), RNASequence("CUAAUGU"))
self.assertEqual(self.b2.complement(), RNASequence("UGGCCAUGG"))
self.assertRaises(BiologicalSequenceError, self.b3.complement)
self.assertEqual(self.b4.complement(), RNASequence("KYWSRMBDHVN"))
self.assertEqual(self.b5.complement(), RNASequence(".C--UAAUG-U..."))
def test_reverse_complement(self):
self.assertEqual(self.b1.reverse_complement(), RNASequence("UGUAAUC"))
self.assertEqual(self.b2.reverse_complement(),
RNASequence("GGUACCGGU"))
self.assertRaises(BiologicalSequenceError, self.b3.reverse_complement)
self.assertEqual(self.b4.reverse_complement(),
RNASequence("NVHDBMRSWYK"))
def test_unsupported_characters(self):
self.assertEqual(self.b1.unsupported_characters(), set())
self.assertEqual(self.b2.unsupported_characters(), set())
self.assertEqual(self.b3.unsupported_characters(), set('T'))
self.assertEqual(self.b4.unsupported_characters(), set())
def test_has_unsupported_characters(self):
self.assertFalse(self.b1.has_unsupported_characters())
self.assertFalse(self.b2.has_unsupported_characters())
self.assertTrue(self.b3.has_unsupported_characters())
self.assertFalse(self.b4.has_unsupported_characters())
def test_is_reverse_complement(self):
self.assertFalse(self.b1.is_reverse_complement(self.b1))
self.assertTrue(self.b1.is_reverse_complement(RNASequence('UGUAAUC')))
self.assertTrue(
self.b4.is_reverse_complement(RNASequence('NVHDBMRSWYK')))
def test_nondegenerates_invalid(self):
with self.assertRaises(BiologicalSequenceError):
list(RNASequence('AZA').nondegenerates())
def test_nondegenerates_empty(self):
self.assertEqual(list(self.empty.nondegenerates()), [self.empty])
def test_nondegenerates_no_degens(self):
self.assertEqual(list(self.b1.nondegenerates()), [self.b1])
def test_nondegenerates_all_degens(self):
# Same chars.
exp = [
RNASequence('CC'),
RNASequence('CG'),
RNASequence('GC'),
RNASequence('GG')
]
# Sort based on sequence string, as order is not guaranteed.
obs = sorted(RNASequence('SS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Different chars.
exp = [
RNASequence('AC'),
RNASequence('AG'),
RNASequence('GC'),
RNASequence('GG')
]
obs = sorted(RNASequence('RS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Odd number of chars.
obs = list(RNASequence('NNN').nondegenerates())
self.assertEqual(len(obs), 4**3)
def test_nondegenerates_mixed_degens(self):
exp = [
RNASequence('AGC'),
RNASequence('AGU'),
RNASequence('GGC'),
RNASequence('GGU')
]
obs = sorted(RNASequence('RGY').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_nondegenerates_gap_mixed_case(self):
exp = [
RNASequence('-A.a'),
RNASequence('-A.c'),
RNASequence('-C.a'),
RNASequence('-C.c')
]
obs = sorted(RNASequence('-M.m').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_is_reverse_complement(self):
self.assertFalse(self.b1.is_reverse_complement(self.b1))
self.assertTrue(self.b1.is_reverse_complement(RNASequence('UGUAAUC')))
self.assertTrue(
self.b4.is_reverse_complement(RNASequence('NVHDBMRSWYK')))
def test_nondegenerates_all_degens(self):
# Same chars.
exp = [
RNASequence('CC'),
RNASequence('CG'),
RNASequence('GC'),
RNASequence('GG')
]
# Sort based on sequence string, as order is not guaranteed.
obs = sorted(RNASequence('SS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Different chars.
exp = [
RNASequence('AC'),
RNASequence('AG'),
RNASequence('GC'),
RNASequence('GG')
]
obs = sorted(RNASequence('RS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Odd number of chars.
obs = list(RNASequence('NNN').nondegenerates())
self.assertEqual(len(obs), 4**3)
def test_nondegenerates_invalid(self):
with self.assertRaises(BiologicalSequenceError):
list(RNASequence('AZA').nondegenerates())