def test_AlignmentToProfile_weighted(self):
"""AlignmentToProfile: should work when sequences are weighted
"""
#Alignment: sequences are just strings and don't have an alphabet
#Weights: a normal dictionary (could be a real Weights object as well)
a = Alignment({'seq1':'TCAG','seq2':'TAR-','seq3':'YAG-'},\
Names=['seq1','seq2','seq3'])
w = {'seq1': 0.5, 'seq2': .25, 'seq3': .25}
#Basic situation in which all letters in the sequences occur in the
#CharOrder, None have to be ignored. In that case it doesn't matter
#whether we set split_degenerates to True or False, because if it's
#True it's overwritten by the fact that the char is in the CharOrder.
exp = array([[0.75, 0, 0, 0, 0, .25, 0], [0, 0.5, 0.5, 0, 0, 0, 0],
[0, 0.5, 0, 0.25, 0.25, 0, 0], [0, 0, 0, 0.5, 0, 0, 0.5]])
#split_degenerates = False
self.assertEqual(AlnToProfile(a,DNA, char_order="TACGRY-",\
weights=w, split_degenerates=False).Data.tolist(),exp.tolist())
#split_degenerates = True
self.assertEqual(AlnToProfile(a,DNA, char_order="TACGRY-",\
weights=w, split_degenerates=True).Data.tolist(),exp.tolist())
#Only non-degenerate symbols in the CharOrder. Degenerates are split.
#Gaps are ignored
exp = array([[0.875, 0, 0.125, 0], [0, 0.5, 0.5, 0],
[0, 0.625, 0, 0.375], [0, 0, 0, 1]])
self.assertEqual(AlnToProfile(a,DNA, char_order="TACG",\
weights=w, split_degenerates=True).Data.tolist(),exp.tolist())
#An Error is raised if all chars in an alignment column are ignored
#CharOrder=AT, degenerates are not split.
self.assertRaises(ValueError,AlnToProfile,a,DNA,\
char_order="AT",weights=w, split_degenerates=True)
def test_AlignmentToProfile_basic(self):
"""AlignmentToProfile: should work under basic conditions
"""
#sequences in the alignment are unweighted
#Alphabet is the alphabet of the sequences (RNA)
#CharOrder is set explicitly
#Degenerate bases are split up
#Gaps are ignored
#In all of the columns at least one character is in the CharOrder
a = Alignment({'a':RnaSequence('UCAGRYN-'),'b':RnaSequence('ACUGAAAA')})
exp =\
array([[.5,0,.5,0],
[0,1,0,0],
[.5,0,.5,0],
[0,0,0,1],
[0,0,.75,.25],
[.25,.25,.5,0],
[.125,.125,.625,.125],
[0,0,1,0]])
self.assertEqual(AlnToProfile(a,alphabet=RNA,\
split_degenerates=True).Data.tolist(),exp.tolist())