def get_response_content(fs):
# get the mutation process nucleotide distribution
nt_distribution = SnippetUtil.get_distribution(fs.nucleotides,
'nucleotide', nt_ordered)
# get the selection process amino acid energies
aa_to_energy = SnippetUtil.get_dictionary(fs.aminoacids,
'amino acid', 'energy', aa_ordered)
# create the direct protein rate matrix object
nt_distribution_list = [nt_distribution[nt] for nt in nt_ordered]
aa_energy_list = [aa_to_energy[aa] for aa in aa_ordered]
rate_matrix_object = DirectProtein.DirectProteinRateMatrix(fs.kappa,
nt_distribution_list, aa_energy_list)
# write the response
out = StringIO()
if fs.srm:
# write the scaled rate matrix
rate_matrix_object.normalize()
row_major_rate_matrix = rate_matrix_object.get_row_major_rate_matrix()
print >> out, MatrixUtil.m_to_string(row_major_rate_matrix)
elif fs.urm:
# write the unscaled rate matrix
row_major_rate_matrix = rate_matrix_object.get_row_major_rate_matrix()
print >> out, MatrixUtil.m_to_string(row_major_rate_matrix)
elif fs.cstat:
# write the codon stationary distribution
codon_distribution = rate_matrix_object.get_codon_distribution()
for codon in codons_ordered:
print >> out, codon, ':', codon_distribution[codon]
elif fs.astat:
# write the amino acid stationary distribution
aa_distribution = rate_matrix_object.get_aa_distribution()
for aa in aa_ordered:
print >> out, aa, ':', aa_distribution[aa]
elif fs.nstat:
# write the nucleotide stationary distribution
nt_distribution = rate_matrix_object.get_nt_distribution()
for nt in nt_ordered:
print >> out, nt, ':', nt_distribution[nt]
elif fs.sf:
# write the rate matrix scaling factor
print >> out, rate_matrix_object.get_expected_rate()
# return the response
return out.getvalue() + '\n'
def get_response_content(fs):
# get the nucleotide distribution
nt_to_weight = SnippetUtil.get_distribution(fs.nucleotides, 'nucleotide',
nt_letters)
# get the amino acid distribution
aa_to_weight = SnippetUtil.get_distribution(fs.aminoacids, 'amino acid',
aa_letters)
# get distributions in convenient list form
stationary_nt_distribution = [nt_to_weight[nt] for nt in nt_letters]
aa_distribution = [aa_to_weight[aa] for aa in aa_letters]
codon_distribution = []
implied_stationary_nt_distribution = []
if fs.corrected:
# define the objective function
objective_function = MyObjective(aa_distribution,
stationary_nt_distribution)
initial_guess = (0, 0, 0)
iterations = 20
best = scipy.optimize.nonlin.broyden2(objective_function,
initial_guess, iterations)
x, y, z = best
best_mutation_weights = (1, math.exp(x), math.exp(y), math.exp(z))
best_mutation_distribution = normalized(best_mutation_weights)
# Given the mutation distribution and the amino acid distribution,
# get the stationary distribution.
result = DirectProtein.get_nt_distribution_and_aa_energies(
best_mutation_distribution, aa_distribution)
implied_stationary_nt_distribution, result_aa_energies = result
# Get the codon distribution;
# kappa doesn't matter because we are only concerned
# with stationary distributions
kappa = 1.0
dpm = DirectProtein.DirectProteinRateMatrix(
kappa, best_mutation_distribution, result_aa_energies)
codon_distribution = dpm.get_stationary_distribution()
elif fs.hb:
# get the codon distribution
unnormalized_codon_distribution = []
for codon in codons:
aa = Codon.g_codon_to_aa_letter[codon]
sibling_codons = Codon.g_aa_letter_to_codons[aa]
codon_aa_weight = aa_to_weight[aa]
codon_nt_weight = np.prod([nt_to_weight[nt] for nt in codon])
sibling_nt_weight_sum = sum(
np.prod([nt_to_weight[nt] for nt in sibling])
for sibling in sibling_codons)
weight = codon_aa_weight * codon_nt_weight
weight /= sibling_nt_weight_sum
unnormalized_codon_distribution.append(weight)
codon_distribution = normalized(unnormalized_codon_distribution)
nt_to_weight = dict(zip(nt_letters, [0] * 4))
for codon, p in zip(codons, codon_distribution):
for nt in codon:
nt_to_weight[nt] += p
implied_stationary_nt_distribution = normalized(nt_to_weight[nt]
for nt in nt_letters)
# start the output text string
out = StringIO()
# write the codon stationary distribution
print >> out, 'estimated codon stationary distribution:'
for codon, p in zip(codons, codon_distribution):
print >> out, '%s : %s' % (codon, p)
print >> out, ''
# write the nucleotide stationary distribution
print >> out, 'implied nucleotide stationary distribution:'
for nt, p in zip(nt_letters, implied_stationary_nt_distribution):
print >> out, '%s : %s' % (nt, p)
# return the response
return out.getvalue()