def test_aminoAcids(self):
"""PositionalBaseUsage aminoAcids should return correct amino acids"""
#check hand-calculated values on a particular sequence
orig = CodonUsage('UCGAGUUCGUCG')
final = orig.positionalBases().aminoAcids()
exp = {
'S': 0.75 * 0.75 * 0.75 + 0.75 * 0.75 * 0.25 + 0.25*0.25*0.25,
'W': 0.75 * 0.25 * 0.75,
'C': 0.75 * 0.25 * 0.25,
'T': 0.25 * 0.75 * 0.75 + 0.25 * 0.75 * 0.25,
'R': 0.25 * 0.25 * 0.75,
}
for f in final:
if f in exp:
self.assertFloatEqual(final[f], exp[f])
else:
self.assertEqual(final[f], 0)
#test for unbiased freqs on a couple of different genetic codes
orig = CodonUsage('UUUCCCAAAGGG')
final = orig.positionalBases().aminoAcids()
SGC = GeneticCodes[1]
for aa in final:
self.assertEqual(final[aa], len(SGC[aa])/64.0)
mt = GeneticCodes[2]
final_mt = orig.positionalBases().aminoAcids(mt)
self.assertNotEqual(final, final_mt)
for aa in final_mt:
self.assertEqual(final_mt[aa], len(mt[aa])/64.0)
def test_codons(self):
"""PositionalBaseUsage codons should give expected codon freqs"""
#one of each base should give freqs if 1/64 for everything
orig = CodonUsage('UUUCCCAAAGGG')
b = orig.positionalBases()
final = b.codons()
self.assertEqual(len(final), 64)
for i in final:
self.assertFloatEqual(final[i], 1.0/64)
#two bases at each position should give correct freqs
orig = CodonUsage('UCGAGUUCGUCG')
final = orig.positionalBases().codons()
exp = {
'UCG': 0.75 * 0.75 * 0.75,
'UCU': 0.75 * 0.75 * 0.25,
'UGG': 0.75 * 0.25 * 0.75,
'UGU': 0.75 * 0.25 * 0.25,
'ACG': 0.25 * 0.75 * 0.75,
'ACU': 0.25 * 0.75 * 0.25,
'AGG': 0.25 * 0.25 * 0.75,
'AGU': 0.25 * 0.25 * 0.25,
}
for f in final:
if f in exp:
self.assertFloatEqual(final[f], exp[f])
else:
self.assertEqual(final[f], 0)
def test_positionalBases(self):
"""CodonUsage bases should count bases at each position correctly"""
freqs = {'UUC':5, 'AUA':10, 'AUG':10, 'CGC':3, 'AGG':2, 'XYZ':8,
'UAA':2, 'UGA':1}
u = CodonUsage(freqs)
b = u.positionalBases()
assert isinstance(b, PositionalBaseUsage)
first, second, third = b
self.assertEqual(first, BaseUsage({'U':8,'C':3,'A':22,'X':8}))
self.assertEqual(second, BaseUsage({'U':25,'C':0,'A':2,'G':6,'Y':8}))
self.assertEqual(third, BaseUsage({'C':8,'A':13,'G':12,'Z':8}))
#check that it also works when we purge
p = u.positionalBases(purge_unwanted=True)
first, second, third = p
self.assertEqual(first, BaseUsage({'U':5,'C':3,'A':2}))
self.assertEqual(second, BaseUsage({'U':5,'G':5}))
self.assertEqual(third, BaseUsage({'C':8,'G':2}))
#check that it also works with a different genetic code, and,
#incidentally, that the purging didn't affect the original object
u.GeneticCode = GeneticCodes[2] #mt code: different stop codons
p = u.positionalBases(purge_unwanted=True)
first, second, third = p
self.assertEqual(first, BaseUsage({'U':6,'C':3,'A':20}))
self.assertEqual(second, BaseUsage({'U':25,'G':4}))
self.assertEqual(third, BaseUsage({'C':8,'A':11,'G':10}))
def test_aminoAcids(self):
"""PositionalBaseUsage aminoAcids should return correct amino acids"""
#check hand-calculated values on a particular sequence
orig = CodonUsage('UCGAGUUCGUCG')
final = orig.positionalBases().aminoAcids()
exp = {
'S': 0.75 * 0.75 * 0.75 + 0.75 * 0.75 * 0.25 + 0.25 * 0.25 * 0.25,
'W': 0.75 * 0.25 * 0.75,
'C': 0.75 * 0.25 * 0.25,
'T': 0.25 * 0.75 * 0.75 + 0.25 * 0.75 * 0.25,
'R': 0.25 * 0.25 * 0.75,
}
for f in final:
if f in exp:
self.assertFloatEqual(final[f], exp[f])
else:
self.assertEqual(final[f], 0)
#test for unbiased freqs on a couple of different genetic codes
orig = CodonUsage('UUUCCCAAAGGG')
final = orig.positionalBases().aminoAcids()
SGC = GeneticCodes[1]
for aa in final:
self.assertEqual(final[aa], len(SGC[aa]) / 64.0)
mt = GeneticCodes[2]
final_mt = orig.positionalBases().aminoAcids(mt)
self.assertNotEqual(final, final_mt)
for aa in final_mt:
self.assertEqual(final_mt[aa], len(mt[aa]) / 64.0)
def test_codons(self):
"""PositionalBaseUsage codons should give expected codon freqs"""
#one of each base should give freqs if 1/64 for everything
orig = CodonUsage('UUUCCCAAAGGG')
b = orig.positionalBases()
final = b.codons()
self.assertEqual(len(final), 64)
for i in final:
self.assertFloatEqual(final[i], 1.0 / 64)
#two bases at each position should give correct freqs
orig = CodonUsage('UCGAGUUCGUCG')
final = orig.positionalBases().codons()
exp = {
'UCG': 0.75 * 0.75 * 0.75,
'UCU': 0.75 * 0.75 * 0.25,
'UGG': 0.75 * 0.25 * 0.75,
'UGU': 0.75 * 0.25 * 0.25,
'ACG': 0.25 * 0.75 * 0.75,
'ACU': 0.25 * 0.75 * 0.25,
'AGG': 0.25 * 0.25 * 0.75,
'AGU': 0.25 * 0.25 * 0.25,
}
for f in final:
if f in exp:
self.assertFloatEqual(final[f], exp[f])
else:
self.assertEqual(final[f], 0)
def test_positionalBases(self):
"""CodonUsage bases should count bases at each position correctly"""
freqs = {
'UUC': 5,
'AUA': 10,
'AUG': 10,
'CGC': 3,
'AGG': 2,
'XYZ': 8,
'UAA': 2,
'UGA': 1
}
u = CodonUsage(freqs)
b = u.positionalBases()
assert isinstance(b, PositionalBaseUsage)
first, second, third = b
self.assertEqual(first, BaseUsage({'U': 8, 'C': 3, 'A': 22, 'X': 8}))
self.assertEqual(second,
BaseUsage({
'U': 25,
'C': 0,
'A': 2,
'G': 6,
'Y': 8
}))
self.assertEqual(third, BaseUsage({'C': 8, 'A': 13, 'G': 12, 'Z': 8}))
#check that it also works when we purge
p = u.positionalBases(purge_unwanted=True)
first, second, third = p
self.assertEqual(first, BaseUsage({'U': 5, 'C': 3, 'A': 2}))
self.assertEqual(second, BaseUsage({'U': 5, 'G': 5}))
self.assertEqual(third, BaseUsage({'C': 8, 'G': 2}))
#check that it also works with a different genetic code, and,
#incidentally, that the purging didn't affect the original object
u.GeneticCode = GeneticCodes[2] #mt code: different stop codons
p = u.positionalBases(purge_unwanted=True)
first, second, third = p
self.assertEqual(first, BaseUsage({'U': 6, 'C': 3, 'A': 20}))
self.assertEqual(second, BaseUsage({'U': 25, 'G': 4}))
self.assertEqual(third, BaseUsage({'C': 8, 'A': 11, 'G': 10}))
