def opt_drate_fix_drate_times_b(multiAlign, dRate, tree, qMat, piProb, cList, qRates=[1.]):
"""
optimization function for rate = (iRate, dRate) based on PIP
"""
dRateTimesTreeTotalBranchLength = dRate * tree.length()
res = minimize_scalar(nllk_drate_fix_drate_times_b, args=(multiAlign, dRateTimesTreeTotalBranchLength, tree, qMat, piProb, cList, qRates))
dRate = res.x
treeNew = copy.deepcopy(tree)
treeNew.scale_edges(dRateTimesTreeTotalBranchLength / (dRate * treeNew.length()))
seqNames = multiAlign.keys()
nLeaf = len(seqNames)
cPhi = '-' * nLeaf
tau = tree.length()
cListExt = cList + ['-']
piProbExt = np.append(piProb, 0)
pc0 = 0
for qRate in qRates:
qMatExt = q_to_qext(qMat*qRate, dRate)
pc0 += prob_msa_one_site(cPhi, seqNames, tree, qMatExt, piProbExt, dRate, cListExt)
pc0 = pc0 / len(qRates)
mlen = len(multiAlign.values()[0])
nu = mlen / (1. - pc0)
# logPsi = -np.sum(np.log(np.arange(1, mlen+1))) + mlen * np.log(nu) + (pc0 - 1) * nu
# nu = iRate * (tau + 1. / dRate)
iRate = nu / (tau + 1. / dRate)
rate = (iRate, dRate)
return rate, treeNew
def opt_drate(multiAlign, tree, qMat, piProb, cList, qRates=[1.]):
"""
optimization function for rate = (iRate, dRate) based on PIP
"""
res = minimize_scalar(nllk_drate,
args=(multiAlign, tree, qMat, piProb, cList, qRates))
dRate = res.x
seqNames = multiAlign.keys()
nLeaf = len(seqNames)
cPhi = '-' * nLeaf
tau = tree.length()
cListExt = cList + ['-']
piProbExt = np.append(piProb, 0)
pc0 = 0
for qRate in qRates:
qMatExt = q_to_qext(qMat * qRate, dRate)
pc0 += prob_msa_one_site(cPhi, seqNames, tree, qMatExt, piProbExt,
dRate, cListExt)
pc0 = pc0 / len(qRates)
mlen = len(multiAlign.values()[0])
nu = mlen / (1. - pc0)
# logPsi = -np.sum(np.log(np.arange(1, mlen+1))) + mlen * np.log(nu) + (pc0 - 1) * nu
# nu = iRate * (tau + 1. / dRate)
iRate = nu / (tau + 1. / dRate)
rate = (iRate, dRate)
return rate
def pc0_from_dRate_and_tree(dRate, seqNames, tree, qMat, piProb, cList, qRates=[1.]):
"""
calculate P(cPhi) under PIP
"""
nLeaf = len(seqNames)
cPhi = '-' * nLeaf
cListExt = cList + ['-']
pc0 = 0
for qRate in qRates:
qMatExt = q_to_qext(qMat*qRate, dRate)
piProbExt = np.append(piProb, 0)
pc0 += prob_msa_one_site(cPhi, seqNames, tree, qMatExt, piProbExt, dRate, cListExt)
pc0 = pc0 / len(qRates)
return pc0
def pc0_from_dRate_and_tree(dRate,
seqNames,
tree,
qMat,
piProb,
cList,
qRates=[1.]):
"""
calculate P(cPhi) under PIP
"""
nLeaf = len(seqNames)
cPhi = '-' * nLeaf
cListExt = cList + ['-']
pc0 = 0
for qRate in qRates:
qMatExt = q_to_qext(qMat * qRate, dRate)
piProbExt = np.append(piProb, 0)
pc0 += prob_msa_one_site(cPhi, seqNames, tree, qMatExt, piProbExt,
dRate, cListExt)
pc0 = pc0 / len(qRates)
return pc0
