def test_iupac_degeneracies(self):
exp = {
# upper
'B': set(['C', 'U', 'T', 'G']), 'D': set(['A', 'U', 'T', 'G']),
'H': set(['A', 'C', 'U', 'T']), 'K': set(['U', 'T', 'G']),
'M': set(['A', 'C']), 'N': set(['A', 'C', 'U', 'T', 'G']),
'S': set(['C', 'G']), 'R': set(['A', 'G']),
'W': set(['A', 'U', 'T']), 'V': set(['A', 'C', 'G']),
'Y': set(['C', 'U', 'T']),
# lower
'b': set(['c', 'u', 't', 'g']), 'd': set(['a', 'u', 't', 'g']),
'h': set(['a', 'c', 'u', 't']), 'k': set(['u', 't', 'g']),
'm': set(['a', 'c']), 'n': set(['a', 'c', 'u', 't', 'g']),
's': set(['c', 'g']), 'r': set(['a', 'g']),
'w': set(['a', 'u', 't']), 'v': set(['a', 'c', 'g']),
'y': set(['c', 'u', 't'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(NucleotideSequence.iupac_degeneracies(), exp)
# Test that we can modify a copy of the mapping without altering the
# canonical representation.
degen = NucleotideSequence.iupac_degeneracies()
degen.update({'V': set("BRO"), 'Z': set("ZORRO")})
self.assertNotEqual(degen, exp)
self.assertEqual(NucleotideSequence.iupac_degeneracies(), exp)
def test_iupac_degeneracies(self):
exp = {
# upper
'B': set(['C', 'U', 'T', 'G']),
'D': set(['A', 'U', 'T', 'G']),
'H': set(['A', 'C', 'U', 'T']),
'K': set(['U', 'T', 'G']),
'M': set(['A', 'C']),
'N': set(['A', 'C', 'U', 'T', 'G']),
'S': set(['C', 'G']),
'R': set(['A', 'G']),
'W': set(['A', 'U', 'T']),
'V': set(['A', 'C', 'G']),
'Y': set(['C', 'U', 'T']),
# lower
'b': set(['c', 'u', 't', 'g']),
'd': set(['a', 'u', 't', 'g']),
'h': set(['a', 'c', 'u', 't']),
'k': set(['u', 't', 'g']),
'm': set(['a', 'c']),
'n': set(['a', 'c', 'u', 't', 'g']),
's': set(['c', 'g']),
'r': set(['a', 'g']),
'w': set(['a', 'u', 't']),
'v': set(['a', 'c', 'g']),
'y': set(['c', 'u', 't'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(NucleotideSequence.iupac_degeneracies(), exp)
# Test that we can modify a copy of the mapping without altering the
# canonical representation.
degen = NucleotideSequence.iupac_degeneracies()
degen.update({'V': set("BRO"), 'Z': set("ZORRO")})
self.assertNotEqual(degen, exp)
self.assertEqual(NucleotideSequence.iupac_degeneracies(), exp)
class NucelotideSequenceTests(TestCase):
def setUp(self):
self.empty = NucleotideSequence('')
self.b1 = NucleotideSequence('GATTACA')
self.b2 = NucleotideSequence(
'ACCGGUACC', id="test-seq-2",
description="A test sequence")
def test_alphabet(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'T',
'W', 'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's',
'r', 'u', 't', 'w', 'v', 'y'
}
# Test calling from an instance and purely static context.
self.assertEqual(self.b1.alphabet(), exp)
self.assertEqual(NucleotideSequence.alphabet(), exp)
def test_gap_alphabet(self):
self.assertEqual(self.b1.gap_alphabet(), set('-.'))
def test_complement_map(self):
exp = {}
self.assertEqual(self.b1.complement_map(), exp)
self.assertEqual(NucleotideSequence.complement_map(), exp)
def test_iupac_standard_characters(self):
exp = set("ACGTUacgtu")
self.assertEqual(self.b1.iupac_standard_characters(), exp)
self.assertEqual(NucleotideSequence.iupac_standard_characters(), exp)
def test_iupac_degeneracies(self):
exp = {
# upper
'B': set(['C', 'U', 'T', 'G']), 'D': set(['A', 'U', 'T', 'G']),
'H': set(['A', 'C', 'U', 'T']), 'K': set(['U', 'T', 'G']),
'M': set(['A', 'C']), 'N': set(['A', 'C', 'U', 'T', 'G']),
'S': set(['C', 'G']), 'R': set(['A', 'G']),
'W': set(['A', 'U', 'T']), 'V': set(['A', 'C', 'G']),
'Y': set(['C', 'U', 'T']),
# lower
'b': set(['c', 'u', 't', 'g']), 'd': set(['a', 'u', 't', 'g']),
'h': set(['a', 'c', 'u', 't']), 'k': set(['u', 't', 'g']),
'm': set(['a', 'c']), 'n': set(['a', 'c', 'u', 't', 'g']),
's': set(['c', 'g']), 'r': set(['a', 'g']),
'w': set(['a', 'u', 't']), 'v': set(['a', 'c', 'g']),
'y': set(['c', 'u', 't'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(NucleotideSequence.iupac_degeneracies(), exp)
# Test that we can modify a copy of the mapping without altering the
# canonical representation.
degen = NucleotideSequence.iupac_degeneracies()
degen.update({'V': set("BRO"), 'Z': set("ZORRO")})
self.assertNotEqual(degen, exp)
self.assertEqual(NucleotideSequence.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(NucleotideSequence.iupac_degenerate_characters(), exp)
def test_iupac_characters(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'T',
'W', 'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's',
'r', 'u', 't', 'w', 'v', 'y'
}
self.assertEqual(self.b1.iupac_characters(), exp)
self.assertEqual(NucleotideSequence.iupac_characters(), exp)
def test_complement(self):
self.assertRaises(BiologicalSequenceError,
self.b1.complement)
def test_reverse_complement(self):
self.assertRaises(BiologicalSequenceError,
self.b1.reverse_complement)
def test_is_reverse_complement(self):
self.assertRaises(BiologicalSequenceError,
self.b1.is_reverse_complement, self.b1)
def test_nondegenerates_invalid(self):
with self.assertRaises(BiologicalSequenceError):
list(NucleotideSequence('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 = [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_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_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)
class NucelotideSequenceTests(TestCase):
def setUp(self):
self.empty = NucleotideSequence('')
self.b1 = NucleotideSequence('GATTACA')
self.b2 = NucleotideSequence('ACCGGUACC',
id="test-seq-2",
description="A test sequence")
def test_alphabet(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'T',
'W', 'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's',
'r', 'u', 't', 'w', 'v', 'y'
}
# Test calling from an instance and purely static context.
self.assertEqual(self.b1.alphabet(), exp)
self.assertEqual(NucleotideSequence.alphabet(), exp)
def test_gap_alphabet(self):
self.assertEqual(self.b1.gap_alphabet(), set('-.'))
def test_complement_map(self):
exp = {}
self.assertEqual(self.b1.complement_map(), exp)
self.assertEqual(NucleotideSequence.complement_map(), exp)
def test_iupac_standard_characters(self):
exp = set("ACGTUacgtu")
self.assertEqual(self.b1.iupac_standard_characters(), exp)
self.assertEqual(NucleotideSequence.iupac_standard_characters(), exp)
def test_iupac_degeneracies(self):
exp = {
# upper
'B': set(['C', 'U', 'T', 'G']),
'D': set(['A', 'U', 'T', 'G']),
'H': set(['A', 'C', 'U', 'T']),
'K': set(['U', 'T', 'G']),
'M': set(['A', 'C']),
'N': set(['A', 'C', 'U', 'T', 'G']),
'S': set(['C', 'G']),
'R': set(['A', 'G']),
'W': set(['A', 'U', 'T']),
'V': set(['A', 'C', 'G']),
'Y': set(['C', 'U', 'T']),
# lower
'b': set(['c', 'u', 't', 'g']),
'd': set(['a', 'u', 't', 'g']),
'h': set(['a', 'c', 'u', 't']),
'k': set(['u', 't', 'g']),
'm': set(['a', 'c']),
'n': set(['a', 'c', 'u', 't', 'g']),
's': set(['c', 'g']),
'r': set(['a', 'g']),
'w': set(['a', 'u', 't']),
'v': set(['a', 'c', 'g']),
'y': set(['c', 'u', 't'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(NucleotideSequence.iupac_degeneracies(), exp)
# Test that we can modify a copy of the mapping without altering the
# canonical representation.
degen = NucleotideSequence.iupac_degeneracies()
degen.update({'V': set("BRO"), 'Z': set("ZORRO")})
self.assertNotEqual(degen, exp)
self.assertEqual(NucleotideSequence.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(NucleotideSequence.iupac_degenerate_characters(), exp)
def test_iupac_characters(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'U', 'T',
'W', 'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's',
'r', 'u', 't', 'w', 'v', 'y'
}
self.assertEqual(self.b1.iupac_characters(), exp)
self.assertEqual(NucleotideSequence.iupac_characters(), exp)
def test_complement(self):
self.assertRaises(BiologicalSequenceError, self.b1.complement)
def test_reverse_complement(self):
self.assertRaises(BiologicalSequenceError, self.b1.reverse_complement)
def test_is_reverse_complement(self):
self.assertRaises(BiologicalSequenceError,
self.b1.is_reverse_complement, self.b1)
def test_nondegenerates_invalid(self):
with self.assertRaises(BiologicalSequenceError):
list(NucleotideSequence('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 = [
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_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_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)
