def test_contains(self):
"""MolType contains should return correct result"""
for i in 'UCAGWSMKRYBDHVN-' + 'UCAGWSMKRYBDHVN-'.lower():
self.assertContains(RnaMolType, i)
for i in 'x!@#$%^&ZzQq':
self.assertNotContains(RnaMolType, i)
a = MolType(dict.fromkeys('ABC'), add_lower=True)
for i in 'abcABC':
self.assertContains(a, i)
self.assertNotContains(a, 'x')
b = MolType(dict.fromkeys('ABC'), add_lower=False)
for i in 'ABC':
self.assertContains(b, i)
for i in 'abc':
self.assertNotContains(b, i)
def test_init_minimal(self):
"""MolType should init OK with just monomers"""
a = MolType('Abc')
self.assertContains(a.Alphabet, 'A')
self.assertNotContains(a.Alphabet, 'a') # case-sensitive
self.assertContains(a.Alphabet, 'b')
self.assertNotContains(a.Alphabet, 'B')
self.assertNotContains(a.Alphabet, 'x')
def test_init_everything(self):
"""MolType should init OK with all parameters set"""
k = dict.fromkeys
a = MolType(k('Abc'), Ambiguities={'d':'bc'}, Gaps=k('~'), \
Complements={'b':'c','c':'b'}, Pairs={}, add_lower=False)
for i in 'Abcd~':
self.assertContains(a, i)
self.assertEqual(a.complement('b'), 'c')
self.assertEqual(a.complement('AbcAA'), 'AcbAA')
self.assertEqual(a.firstDegenerate('AbcdA'), 3)
self.assertEqual(a.firstGap('a~c'), 1)
self.assertEqual(a.firstInvalid('Abcx'), 3)
def test_countGaps(self):
"""MolType countGaps should return correct gap count"""
c = RnaMolType.countGaps
self.assertEqual(c(''), 0)
self.assertEqual(c('ACUGUCAGUACGHFSDKJCUICDNINS'), 0)
self.assertEqual(c('GUACGUIACAKJDC-SDFHJDSFK'), 1)
self.assertEqual(c('-DSHFUHDSF'), 1)
self.assertEqual(c('UACHASJAIDS-'), 1)
self.assertEqual(c('---CGAUgCAU---ACGHc---ACGUCAGU---'), 12)
a = MolType({'A': 1}, Gaps=dict.fromkeys('!@#$%'))
c = a.countGaps
self.assertEqual(c(''), 0)
self.assertEqual(c('!!!'), 3)
self.assertEqual(c('!@#$!@#$!@#$'), 12)
self.assertEqual(c('cguua!cgcuagua@cguasguadc#'), 3)
def test_gapList(self):
"""MolType gapList should return correct gap positions"""
g = RnaMolType.gapList
self.assertEqual(g(''), [])
self.assertEqual(g('ACUGUCAGUACGHFSDKJCUICDNINS'), [])
self.assertEqual(g('GUACGUIACAKJDC-SDFHJDSFK'), [14])
self.assertEqual(g('-DSHFUHDSF'), [0])
self.assertEqual(g('UACHASJAIDS-'), [11])
self.assertEqual(g('---CGAUgCAU---ACGHc---ACGUCAGU---'), \
[0,1,2,11,12,13,19,20,21,30,31,32])
a = MolType({'A': 1}, Gaps=dict.fromkeys('!@#$%'))
g = a.gapList
self.assertEqual(g(''), [])
self.assertEqual(g('!!!'), [0, 1, 2])
self.assertEqual(g('!@#$!@#$!@#$'), list(range(12)))
self.assertEqual(g('cguua!cgcuagua@cguasguadc#'), [5, 14, 25])
def test_init_everything(self):
"""MolType should init OK with all parameters set"""
k = dict.fromkeys
a = MolType(k('Abc'), Ambiguities={'d':'bc'}, Gaps=k('~'), \
Complements={'b':'c','c':'b'}, Pairs={}, add_lower=False)
for i in 'Abcd~':
self.assertContains(a, i)
self.assertEqual(a.complement('b'), 'c')
self.assertEqual(a.complement('AbcAA'), 'AcbAA')
self.assertEqual(a.firstDegenerate('AbcdA'), 3)
self.assertEqual(a.firstGap('a~c'), 1)
self.assertEqual(a.firstInvalid('Abcx'), 3)
def test_gapVector(self):
"""MolType gapVector should return correct gap positions"""
g = RnaMolType.gapVector
self.assertEqual(g(''), [])
self.assertEqual(g('ACUGUCAGUACGHFSDKJCUICDNINS'), [False] * 27)
self.assertEqual(g('GUACGUIACAKJDC-SDFHJDSFK'),
map(bool, map(int, '000000000000001000000000')))
self.assertEqual(g('-DSHFUHDSF'), map(bool, map(int, '1000000000')))
self.assertEqual(g('UACHASJAIDS-'), map(bool, map(int,
'000000000001')))
self.assertEqual(g('---CGAUgCAU---ACGHc---ACGUCAGU---'), \
map(bool, map(int,'111000000001110000011100000000111')))
a = MolType({'A': 1}, Gaps=dict.fromkeys('!@#$%'))
g = a.gapVector
self.assertEqual(g(''), [])
self.assertEqual(g('!!!'), map(bool, [1, 1, 1]))
self.assertEqual(g('!@#$!@#$!@#$'), [True] * 12)
self.assertEqual(g('cguua!cgcuagua@cguasguadc#'),
map(bool, map(int, '00000100000000100000000001')))
def test_iter(self):
"""MolType iter should iterate over monomer order"""
self.assertEqual(list(RnaMolType),
['U', 'C', 'A', 'G', 'u', 'c', 'a', 'g'])
a = MolType('ZXCV')
self.assertEqual(list(a), ['Z', 'X', 'C', 'V'])
__email__ = "*****@*****.**"
__status__ = "Production"
#ind some of the standard alphabets to reduce typing
RnaBases = RNA.Alphabets.Base
DnaBases = DNA.Alphabets.Base
AminoAcids = PROTEIN.Alphabets.Base
#the following classes are to preserve compatibility for older test code
#that assumes mixed-case is OK.
RnaMolType = MolType(
Sequence=sequence.RnaSequence,
motifset=IUPAC_RNA_chars,
Ambiguities=IUPAC_RNA_ambiguities,
label="rna_with_lowercase",
MWCalculator=RnaMW,
Complements=IUPAC_RNA_ambiguities_complements,
Pairs=RnaStandardPairs,
add_lower=True,
preserve_existing_moltypes=True,
make_alphabet_group=True,
)
DnaMolType = MolType(
Sequence=sequence.DnaSequence,
motifset=IUPAC_DNA_chars,
Ambiguities=IUPAC_DNA_ambiguities,
label="dna_with_lowercase",
MWCalculator=DnaMW,
Complements=IUPAC_DNA_ambiguities_complements,
Pairs=DnaStandardPairs,
add_lower=True,
preserve_existing_moltypes=True,
"""
try:
validity = isinstance(a, ndarray)
except:
validity = False
return validity
#make an alphabet that allows '.' as additional gaps
DNA_with_more_gaps = MolType(
Sequence=DnaSequence,
motifset=IUPAC_DNA_chars,
Ambiguities=IUPAC_DNA_ambiguities,
label="dna",
Gaps=".",
MWCalculator=DnaMW,
Complements=IUPAC_DNA_ambiguities_complements,
Pairs=DnaStandardPairs,
make_alphabet_group=True,
ModelSeq=ModelDnaSequence,
)
def degap_fasta_aln(seqs):
"""degap a Fasta aligment.
seqs: list of label,seq pairs
"""
for (label, seq) in seqs:
degapped_seq = Sequence(moltype=DNA_with_more_gaps,
