def test_init_one_parameter(self):
"""PairFrequency should interpret single parameter as pair probs"""
obs = PairFrequency('UCCC')
exp = Freqs({('U','U'):0.0625, ('U','C'):0.1875,
('C','U'):0.1875, ('C','C'):0.5625})
for k, v in exp.items():
self.assertEqual(v, obs[k])
for k, v in obs.items():
if k not in exp:
self.assertEqual(v, 0)
self.assertEqual(PairFrequency('UCCC', [('U','U'),('C','C')]), \
Freqs({('U','U'):0.1, ('C','C'):0.9}))
#check that the alphabets are right: should not raise error on
#incrementing characters already there, but should raise KeyError
#on anything that's missing.
p = PairFrequency('UCCC')
p[('U','U')] += 1
try:
p[('X','U')] += 1
except KeyError:
pass
else:
raise AssertionError, "Expected KeyError."
p = PairFrequency('UCCC', (('C','C'),))
p[('C','C')] += 1
try:
p[('U','U')] += 1
except KeyError:
pass
else:
raise AssertionError, "Expected KeyError."
def codons(self, genetic_code=SGC, codon_usage=_equal_codons):
"""Predicts most likely set of codon frequencies.
Optionally uses genetic_code (to figure out which codons belong
with each amino acid), and codon_usage (to get most likely codons for
each amino acid). Defaults are the standard genetic code and unbiased
codon frequencies.
"""
result = {}
normalized = Freqs(self)
normalized.normalize()
for aa, aa_freq in list(normalized.items()):
curr_codons = [c.upper().replace('T','U') for c in genetic_code[aa]]
if not curr_codons:
continue #code might be missing some amino acids?
curr_codon_freqs = Numbers([codon_usage[c] for c in curr_codons])
curr_codon_freqs.normalize()
for codon, c_freq in zip(curr_codons, curr_codon_freqs):
result[codon] = c_freq * aa_freq
return CodonUsage(result, self.info, genetic_code)
def codons(self, genetic_code=SGC, codon_usage=_equal_codons):
"""Predicts most likely set of codon frequencies.
Optionally uses genetic_code (to figure out which codons belong
with each amino acid), and codon_usage (to get most likely codons for
each amino acid). Defaults are the standard genetic code and unbiased
codon frequencies.
"""
result = {}
normalized = Freqs(self)
normalized.normalize()
for aa, aa_freq in normalized.items():
curr_codons = [c.upper().replace('T','U') for c in genetic_code[aa]]
if not curr_codons:
continue #code might be missing some amino acids?
curr_codon_freqs = Numbers([codon_usage[c] for c in curr_codons])
curr_codon_freqs.normalize()
for codon, c_freq in zip(curr_codons, curr_codon_freqs):
result[codon] = c_freq * aa_freq
return CodonUsage(result, self.info, genetic_code)