class DNASequenceTests(TestCase):
def setUp(self):
self.empty = DNASequence('')
self.b1 = DNASequence('GATTACA')
self.b2 = DNASequence(
'ACCGGTACC', id="test-seq-2",
description="A test sequence")
self.b3 = DNASequence(
'ACCGGUACC', id="bad-seq-1",
description="Not a DNA sequence")
self.b4 = DNASequence(
'MRWSYKVHDBN', id="degen",
description="All of the degenerate bases")
self.b5 = DNASequence('.G--ATTAC-A...')
def test_alphabet(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'T', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
't', 'w', 'v', 'y'
}
self.assertEqual(self.b1.alphabet(), exp)
self.assertEqual(DNASequence.alphabet(), exp)
def test_gap_alphabet(self):
self.assertEqual(self.b1.gap_alphabet(), set('-.'))
def test_complement_map(self):
exp = {
'-': '-', '.': '.', 'A': 'T', 'C': 'G', 'B': 'V', 'D': 'H',
'G': 'C', 'H': 'D', 'K': 'M', 'M': 'K', 'N': 'N', 'S': 'S',
'R': 'Y', 'T': 'A', 'W': 'W', 'V': 'B', 'Y': 'R', 'a': 't',
'c': 'g', 'b': 'v', 'd': 'h', 'g': 'c', 'h': 'd', 'k': 'm',
'm': 'k', 'n': 'n', 's': 's', 'r': 'y', 't': 'a', 'w': 'w',
'v': 'b', 'y': 'r'
}
self.assertEqual(self.b1.complement_map(), exp)
self.assertEqual(DNASequence.complement_map(), exp)
def test_iupac_standard_characters(self):
exp = set("ACGTacgt")
self.assertEqual(self.b1.iupac_standard_characters(), exp)
self.assertEqual(DNASequence.iupac_standard_characters(), exp)
def test_iupac_degeneracies(self):
exp = {
'B': set(['C', 'T', 'G']), 'D': set(['A', 'T', 'G']),
'H': set(['A', 'C', 'T']), 'K': set(['T', 'G']),
'M': set(['A', 'C']), 'N': set(['A', 'C', 'T', 'G']),
'S': set(['C', 'G']), 'R': set(['A', 'G']), 'W': set(['A', 'T']),
'V': set(['A', 'C', 'G']), 'Y': set(['C', 'T']),
'b': set(['c', 't', 'g']), 'd': set(['a', 't', 'g']),
'h': set(['a', 'c', 't']), 'k': set(['t', 'g']),
'm': set(['a', 'c']), 'n': set(['a', 'c', 't', 'g']),
's': set(['c', 'g']), 'r': set(['a', 'g']), 'w': set(['a', 't']),
'v': set(['a', 'c', 'g']), 'y': set(['c', 't'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(DNASequence.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(DNASequence.iupac_degenerate_characters(), exp)
def test_iupac_characters(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'T', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
't', 'w', 'v', 'y'
}
self.assertEqual(self.b1.iupac_characters(), exp)
self.assertEqual(DNASequence.iupac_characters(), exp)
def test_complement(self):
self.assertEqual(self.b1.complement(), DNASequence("CTAATGT"))
self.assertEqual(self.b2.complement(), DNASequence("TGGCCATGG"))
self.assertRaises(BiologicalSequenceError, self.b3.complement)
self.assertEqual(self.b4.complement(), DNASequence("KYWSRMBDHVN"))
self.assertEqual(self.b5.complement(), DNASequence(".C--TAATG-T..."))
def test_reverse_complement(self):
self.assertEqual(self.b1.reverse_complement(), DNASequence("TGTAATC"))
self.assertEqual(self.b2.reverse_complement(),
DNASequence("GGTACCGGT"))
self.assertRaises(BiologicalSequenceError, self.b3.reverse_complement)
self.assertEqual(self.b4.reverse_complement(),
DNASequence("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('U'))
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(DNASequence('TGTAATC')))
self.assertTrue(
self.b4.is_reverse_complement(DNASequence('NVHDBMRSWYK')))
def test_nondegenerates_invalid(self):
with self.assertRaises(BiologicalSequenceError):
list(DNASequence('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 = [DNASequence('CC'), DNASequence('CG'), DNASequence('GC'),
DNASequence('GG')]
# Sort based on sequence string, as order is not guaranteed.
obs = sorted(DNASequence('SS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Different chars.
exp = [DNASequence('AC'), DNASequence('AG'), DNASequence('GC'),
DNASequence('GG')]
obs = sorted(DNASequence('RS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Odd number of chars.
obs = list(DNASequence('NNN').nondegenerates())
self.assertEqual(len(obs), 4**3)
def test_nondegenerates_mixed_degens(self):
exp = [DNASequence('AGC'), DNASequence('AGT'), DNASequence('GGC'),
DNASequence('GGT')]
obs = sorted(DNASequence('RGY').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_nondegenerates_gap_mixed_case(self):
exp = [DNASequence('-A.a'), DNASequence('-A.c'),
DNASequence('-C.a'), DNASequence('-C.c')]
obs = sorted(DNASequence('-M.m').nondegenerates(), key=str)
self.assertEqual(obs, exp)
class DNASequenceTests(TestCase):
def setUp(self):
self.empty = DNASequence('')
self.b1 = DNASequence('GATTACA')
self.b2 = DNASequence('ACCGGTACC',
id="test-seq-2",
description="A test sequence")
self.b3 = DNASequence('ACCGGUACC',
id="bad-seq-1",
description="Not a DNA sequence")
self.b4 = DNASequence('MRWSYKVHDBN',
id="degen",
description="All of the degenerate bases")
self.b5 = DNASequence('.G--ATTAC-A...')
def test_alphabet(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'T', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
't', 'w', 'v', 'y'
}
self.assertEqual(self.b1.alphabet(), exp)
self.assertEqual(DNASequence.alphabet(), exp)
def test_gap_alphabet(self):
self.assertEqual(self.b1.gap_alphabet(), set('-.'))
def test_complement_map(self):
exp = {
'-': '-',
'.': '.',
'A': 'T',
'C': 'G',
'B': 'V',
'D': 'H',
'G': 'C',
'H': 'D',
'K': 'M',
'M': 'K',
'N': 'N',
'S': 'S',
'R': 'Y',
'T': 'A',
'W': 'W',
'V': 'B',
'Y': 'R',
'a': 't',
'c': 'g',
'b': 'v',
'd': 'h',
'g': 'c',
'h': 'd',
'k': 'm',
'm': 'k',
'n': 'n',
's': 's',
'r': 'y',
't': 'a',
'w': 'w',
'v': 'b',
'y': 'r'
}
self.assertEqual(self.b1.complement_map(), exp)
self.assertEqual(DNASequence.complement_map(), exp)
def test_iupac_standard_characters(self):
exp = set("ACGTacgt")
self.assertEqual(self.b1.iupac_standard_characters(), exp)
self.assertEqual(DNASequence.iupac_standard_characters(), exp)
def test_iupac_degeneracies(self):
exp = {
'B': set(['C', 'T', 'G']),
'D': set(['A', 'T', 'G']),
'H': set(['A', 'C', 'T']),
'K': set(['T', 'G']),
'M': set(['A', 'C']),
'N': set(['A', 'C', 'T', 'G']),
'S': set(['C', 'G']),
'R': set(['A', 'G']),
'W': set(['A', 'T']),
'V': set(['A', 'C', 'G']),
'Y': set(['C', 'T']),
'b': set(['c', 't', 'g']),
'd': set(['a', 't', 'g']),
'h': set(['a', 'c', 't']),
'k': set(['t', 'g']),
'm': set(['a', 'c']),
'n': set(['a', 'c', 't', 'g']),
's': set(['c', 'g']),
'r': set(['a', 'g']),
'w': set(['a', 't']),
'v': set(['a', 'c', 'g']),
'y': set(['c', 't'])
}
self.assertEqual(self.b1.iupac_degeneracies(), exp)
self.assertEqual(DNASequence.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(DNASequence.iupac_degenerate_characters(), exp)
def test_iupac_characters(self):
exp = {
'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'T', 'W',
'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r',
't', 'w', 'v', 'y'
}
self.assertEqual(self.b1.iupac_characters(), exp)
self.assertEqual(DNASequence.iupac_characters(), exp)
def test_complement(self):
self.assertEqual(self.b1.complement(), DNASequence("CTAATGT"))
self.assertEqual(self.b2.complement(), DNASequence("TGGCCATGG"))
self.assertRaises(BiologicalSequenceError, self.b3.complement)
self.assertEqual(self.b4.complement(), DNASequence("KYWSRMBDHVN"))
self.assertEqual(self.b5.complement(), DNASequence(".C--TAATG-T..."))
def test_reverse_complement(self):
self.assertEqual(self.b1.reverse_complement(), DNASequence("TGTAATC"))
self.assertEqual(self.b2.reverse_complement(),
DNASequence("GGTACCGGT"))
self.assertRaises(BiologicalSequenceError, self.b3.reverse_complement)
self.assertEqual(self.b4.reverse_complement(),
DNASequence("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('U'))
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(DNASequence('TGTAATC')))
self.assertTrue(
self.b4.is_reverse_complement(DNASequence('NVHDBMRSWYK')))
def test_nondegenerates_invalid(self):
with self.assertRaises(BiologicalSequenceError):
list(DNASequence('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 = [
DNASequence('CC'),
DNASequence('CG'),
DNASequence('GC'),
DNASequence('GG')
]
# Sort based on sequence string, as order is not guaranteed.
obs = sorted(DNASequence('SS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Different chars.
exp = [
DNASequence('AC'),
DNASequence('AG'),
DNASequence('GC'),
DNASequence('GG')
]
obs = sorted(DNASequence('RS').nondegenerates(), key=str)
self.assertEqual(obs, exp)
# Odd number of chars.
obs = list(DNASequence('NNN').nondegenerates())
self.assertEqual(len(obs), 4**3)
def test_nondegenerates_mixed_degens(self):
exp = [
DNASequence('AGC'),
DNASequence('AGT'),
DNASequence('GGC'),
DNASequence('GGT')
]
obs = sorted(DNASequence('RGY').nondegenerates(), key=str)
self.assertEqual(obs, exp)
def test_nondegenerates_gap_mixed_case(self):
exp = [
DNASequence('-A.a'),
DNASequence('-A.c'),
DNASequence('-C.a'),
DNASequence('-C.c')
]
obs = sorted(DNASequence('-M.m').nondegenerates(), key=str)
self.assertEqual(obs, exp)
