def test_DnaSequence(self):
"""DnaSequence should behave as expected"""
x = DnaSequence('tcag')
#note: no longer preserves case
self.assertEqual(x, 'TCAG')
x = DnaSequence('aaa') + DnaSequence('ccc')
#note: doesn't preserve case
self.assertEqual(x, 'AAACCC')
assert x.MolType is DNA
self.assertRaises(AlphabetError, x.__add__, 'z')
self.assertEqual(DnaSequence('TTTAc').rc(), 'GTAAA')
def test_single_constructor(self):
"""RdbParser should use constructors if supplied"""
to_dna = lambda x, Info: DnaSequence(str(x).replace('U','T'), \
Info=Info)
f = list(RdbParser(self.oneseq, to_dna))
self.assertEqual(len(f), 1)
a = f[0]
self.assertEqual(a, 'AGTCATCTAGATHCATHC')
self.assertEqual(a.Info, Info({'Species':'H.Sapiens',\
'OriginalSeq':'AGUCAUCUAGAUHCAUHC'}))
def alternativeConstr(header_lines):
info = Info()
for line in header_lines:
all = line.strip().split(':', 1)
#strip out empty lines, lines without name, lines without colon
if not all[0] or len(all) != 2:
continue
name = all[0].upper()
value = all[1].strip().upper()
info[name] = value
return info
f = list(RdbParser(self.oneseq, to_dna, alternativeConstr))
self.assertEqual(len(f), 1)
a = f[0]
self.assertEqual(a, 'AGTCATCTAGATHCATHC')
exp_info = Info({'OriginalSeq':'AGUCAUCUAGAUHCAUHC',\
'Refs':{}, 'SEQ':'H.SAPIENS'})
self.assertEqual(a.Info, Info({'OriginalSeq':'AGUCAUCUAGAUHCAUHC',\
'Refs':{}, 'SEQ':'H.SAPIENS'}))
def test_SeqToProfile(self):
"""SequenceToProfile: should work with different parameter settings
"""
seq = DnaSequence("ATCGRYN-")
#Only non-degenerate bases in the char order, all other
#characters are ignored. In a sequence this means that
#several positions will contain only zeros in the profile.
exp = zeros([len(seq), 4], Float64)
for x, y in zip(range(len(seq)), [2, 0, 1, 3]):
exp[x, y] = 1
self.assertEqual(SeqToProfile(seq,char_order="TCAG",\
split_degenerates=False).Data.tolist(),exp.tolist())
#Same thing should work as well when the char order is not passed in
exp = zeros([len(seq), 4], Float64)
for x, y in zip(range(len(seq)), [2, 0, 1, 3]):
exp[x, y] = 1
self.assertEqual(SeqToProfile(seq, split_degenerates=False)\
.Data.tolist(),exp.tolist())
#All symbols in the sequence are in the char order, no row
#should contain only zeros. Degenerate symbols are not split.
exp = zeros([len(seq), 8], Float64)
for x, y in zip(range(len(seq)), [2, 0, 1, 3, 4, 5, 6, 7]):
exp[x, y] = 1
self.assertEqual(SeqToProfile(seq,char_order="TCAGRYN-",\
split_degenerates=False).Data.tolist(), exp.tolist())
#splitting all degenerate symbols, having only non-degenerate symbols
#in the character order (and -)
exp = array([[0, 0, 1, 0, 0], [1, 0, 0, 0, 0], [0, 1, 0, 0, 0],
[0, 0, 0, 1, 0], [0, 0, .5, .5, 0], [.5, .5, 0, 0, 0],
[.25, .25, .25, .25, 0], [0, 0, 0, 0, 1]])
self.assertEqual(SeqToProfile(seq,char_order="TCAG-",\
split_degenerates=True).Data.tolist(),exp.tolist())
#splitting degenerates, but having one of the degenerate
#symbols in the character order. In that case the degenerate symbol
#is not split.
exp = array([[0, 0, 1, 0, 0, 0], [1, 0, 0, 0, 0, 0],
[0, 1, 0, 0, 0, 0], [0, 0, 0, 1, 0, 0],
[0, 0, .5, .5, 0, 0], [.5, .5, 0, 0, 0, 0],
[0, 0, 0, 0, 1, 0], [0, 0, 0, 0, 0, 1]])
self.assertEqual(SeqToProfile(seq,char_order="TCAGN-",\
split_degenerates=True).Data.tolist(),exp.tolist())
def dnastrict(x, **kwargs):
try:
return DnaSequence(x, **kwargs)
except Exception:
raise RecordError, "Could not convert sequence"
def Dna(seq, *args, **kwargs):
seq = seq.replace('u', 't')
seq = seq.replace('U', 'T')
d = DnaSequence(seq, *args, **kwargs)
return d
def default_distance_function(first, second):
first = DnaSequence(first)
return first.fracDiff(second)