def update_Estep(self, cascade, scores, alpha, beta, tau, pi, gamma, mu=None, B=None, omega=None, omegao=None):
footprint_logodds = np.zeros((self.N,1),dtype=float)
if gamma.model=='modelA':
lhoodA, lhoodB = likelihoodAB(cascade, B=B, model=gamma.model)
elif gamma.model=='modelB':
lhoodA, lhoodB = likelihoodAB(cascade, mu=mu, model=gamma.model)
elif gamma.model=='modelC':
lhoodA, lhoodB, lhoodC = likelihoodAB(cascade, B=B, omega=omega, omegao=omegao, model=gamma.model)
for j in xrange(pi.J):
footprint_logodds += insum((1-gamma.value[j])*(lhoodB.value[j]-lhoodA.value[j]) \
+ gamma.value[j]*(nplog(pi.estim[j])-nplog(gamma.value[j])) \
+ (1-gamma.value[j])*(nplog(1-pi.estim[j])-nplog(1-gamma.value[j])),[1])
self.estim[:,1:] = beta.estim[0] + beta.estim[1]*scores + footprint_logodds \
+ gammaln(self.total+alpha.estim[1]) - gammaln(self.total+alpha.estim[0]) \
+ gammaln(alpha.estim[0]) - gammaln(alpha.estim[1]) \
+ alpha.estim[1]*nplog(tau.estim[1]) - alpha.estim[0]*nplog(tau.estim[0]) \
+ self.total*(nplog(1-tau.estim[1])-nplog(1-tau.estim[0]))
self.estim[:,0] = 0.
self.estim[self.estim==np.inf] = MAX
self.estim = np.exp(self.estim-np.max(self.estim,1).reshape(self.N,1))
self.estim = self.estim/insum(self.estim,[1])
if np.isnan(self.estim).any():
print "Nan in Eta"
raise ValueError
if np.isinf(self.estim).any():
print "Inf in Eta"
raise ValueError
def __init__(self, cascade, totalreads, scores, gamma=None, beta=None, \
pi=None, mu=None, B=None, omega=None, omegao=None, alpha=None, tau=None):
self.N = cascade.N
self.total = totalreads.reshape(self.N, 1)
self.estim = np.zeros((self.N, 2), dtype=float)
if alpha is None:
indices = np.argsort(self.total.ravel())[:self.N / 2]
self.estim[indices, 1:] = -MAX
indices = np.argsort(self.total.ravel())[self.N / 2:]
self.estim[indices, 1:] = MAX
else:
footprint_logodds = np.zeros((self.N, 1), dtype=float)
if gamma.model == 'modelA':
lhoodA, lhoodB = likelihoodAB(cascade, B=B, model=gamma.model)
elif gamma.model == 'modelB':
lhoodA, lhoodB = likelihoodAB(cascade,
mu=mu,
model=gamma.model)
elif gamma.model == 'modelC':
lhoodA, lhoodB, lhoodC = likelihoodAB(cascade,
B=B,
omega=omega,
omegao=omegao,
model=gamma.model)
for j in xrange(pi.J):
if model == 'modelC':
footprint_logodds += insum(
gamma.value[j] * lhoodA.value[j] - lhoodC.value[j] +
(1 - gamma.value[j]) * lhoodB.value[j], [1])
else:
footprint_logodds += insum(
(1 - gamma.value[j]) *
(lhoodB.value[j] - lhoodA.value[j]), [1])
footprint_logodds += insum(gamma.value[j]*(nplog(pi.estim[j])-nplog(gamma.value[j])) \
+ (1-gamma.value[j])*(nplog(1-pi.estim[j])-nplog(1-gamma.value[j])),[1])
self.estim[:,1:] = beta.estim[0] + beta.estim[1]*scores + footprint_logodds \
+ gammaln(self.total+alpha.estim[1]) - gammaln(self.total+alpha.estim[0]) \
+ gammaln(alpha.estim[0]) - gammaln(alpha.estim[1]) \
+ alpha.estim[1]*nplog(tau.estim[1]) - alpha.estim[0]*nplog(tau.estim[0]) \
+ self.total*(nplog(1-tau.estim[1])-nplog(1-tau.estim[0]))
if alpha is None:
self.estim[self.estim == np.inf] = MAX
self.estim = np.exp(self.estim -
np.max(self.estim, 1).reshape(self.N, 1))
self.estim = self.estim / insum(self.estim, [1])
else:
self.estim[:, 1:] = self.estim[:, 1:] / np.log(10)
def update_Estep(self,
cascade,
scores,
alpha,
beta,
tau,
pi,
gamma,
mu=None,
B=None,
omega=None,
omegao=None):
footprint_logodds = np.zeros((self.N, 1), dtype=float)
if gamma.model == 'modelA':
lhoodA, lhoodB = likelihoodAB(cascade, B=B, model=gamma.model)
elif gamma.model == 'modelB':
lhoodA, lhoodB = likelihoodAB(cascade, mu=mu, model=gamma.model)
elif gamma.model == 'modelC':
lhoodA, lhoodB, lhoodC = likelihoodAB(cascade,
B=B,
omega=omega,
omegao=omegao,
model=gamma.model)
for j in xrange(pi.J):
footprint_logodds += insum((1-gamma.value[j])*(lhoodB.value[j]-lhoodA.value[j]) \
+ gamma.value[j]*(nplog(pi.estim[j])-nplog(gamma.value[j])) \
+ (1-gamma.value[j])*(nplog(1-pi.estim[j])-nplog(1-gamma.value[j])),[1])
self.estim[:,1:] = beta.estim[0] + beta.estim[1]*scores + footprint_logodds \
+ gammaln(self.total+alpha.estim[1]) - gammaln(self.total+alpha.estim[0]) \
+ gammaln(alpha.estim[0]) - gammaln(alpha.estim[1]) \
+ alpha.estim[1]*nplog(tau.estim[1]) - alpha.estim[0]*nplog(tau.estim[0]) \
+ self.total*(nplog(1-tau.estim[1])-nplog(1-tau.estim[0]))
self.estim[:, 0] = 0.
self.estim[self.estim == np.inf] = MAX
self.estim = np.exp(self.estim -
np.max(self.estim, 1).reshape(self.N, 1))
self.estim = self.estim / insum(self.estim, [1])
if np.isnan(self.estim).any():
print "Nan in Eta"
raise ValueError
if np.isinf(self.estim).any():
print "Inf in Eta"
raise ValueError
def likelihood(cascade, scores, eta, gamma, pi, alpha, beta, tau, mu=None, B=None, omega=None, omegao=None):
apriori = beta.estim[0] + beta.estim[1]*scores
if gamma.model=='modelA':
lhoodA, lhoodB = likelihoodAB(cascade, B=B, model=gamma.model)
elif gamma.model=='modelB':
lhoodA, lhoodB = likelihoodAB(cascade, mu=mu, model=gamma.model)
elif gamma.model=='modelC':
lhoodA, lhoodB, lhoodC = likelihoodAB(cascade, B=B, omega=omega, omegao=omegao, model=gamma.model)
footprint = np.zeros((cascade.N,1),dtype=float)
for j in xrange(pi.J):
footprint += insum(gamma.value[j]*lhoodA.value[j] + (1-gamma.value[j])*lhoodB.value[j] \
+ gamma.value[j]*(nplog(pi.estim[j])-nplog(gamma.value[j])) \
+ (1-gamma.value[j])*(nplog(1-pi.estim[j])-nplog(1-gamma.value[j])),[1])
P_1 = footprint + gammaln(eta.total+alpha.estim[1]) - gammaln(alpha.estim[1]) \
+ alpha.estim[1]*nplog(tau.estim[1]) + eta.total*nplog(1-tau.estim[1])
P_1[P_1==np.inf] = MAX
P_1[P_1==-np.inf] = -MAX
null = np.zeros((cascade.N,1),dtype=float)
for j in xrange(cascade.J):
if gamma.model=='modelC':
null = null + insum(lhoodC.value[j],[1])
else:
null = null + insum(lhoodA.value[j],[1])
P_0 = null + gammaln(eta.total+alpha.estim[0]) - gammaln(alpha.estim[0]) \
+ alpha.estim[0]*nplog(tau.estim[0]) + eta.total*nplog(1-tau.estim[0])
P_0[P_0==np.inf] = MAX
P_0[P_0==-np.inf] = -MAX
L = P_0*eta.estim[:,:1] + insum(P_1*eta.estim[:,1:],[1]) + apriori*(1-eta.estim[:,:1]) \
- nplog(1+np.exp(apriori)) - insum(eta.estim*nplog(eta.estim),[1])
L = L.sum()
if np.isnan(L):
print "Nan in LogLike"
raise ValueError
if np.isinf(L):
print "Inf in LogLike"
raise ValueError
return L
def F(x):
arg = x[0]+x[1]*scores
func = arg*insum(eta.estim[:,1:],1) - nplog(1+np.exp(arg))
f = -1.*func.sum()
if np.isnan(f) or np.isinf(f):
return np.inf
else:
return f
def F(x):
arg = x[0] + x[1] * scores
func = arg * insum(eta.estim[:, 1:], 1) - nplog(1 + np.exp(arg))
f = -1. * func.sum()
if np.isnan(f) or np.isinf(f):
return np.inf
else:
return f
def Fprime(x):
arg = x[0]+x[1]*scores
df1 = insum(eta.estim[:,1:],1) - logistic(-arg)
df2 = df1*scores
Df = -1.*np.array([df1.sum(), df2.sum()])
if np.isnan(Df).any() or np.isinf(Df).any():
return np.inf
else:
return Df
def Fprime(x):
arg = x[0] + x[1] * scores
df1 = insum(eta.estim[:, 1:], 1) - logistic(-arg)
df2 = df1 * scores
Df = -1. * np.array([df1.sum(), df2.sum()])
if np.isnan(Df).any() or np.isinf(Df).any():
return np.inf
else:
return Df
def __init__(self, cascade, totalreads, scores, gamma=None, beta=None, \
pi=None, mu=None, B=None, omega=None, omegao=None, alpha=None, tau=None):
self.N = cascade.N
self.total = totalreads.reshape(self.N,1)
self.estim = np.zeros((self.N, 2),dtype=float)
if alpha is None:
indices = np.argsort(self.total.ravel())[:self.N/2]
self.estim[indices,1:] = -MAX
indices = np.argsort(self.total.ravel())[self.N/2:]
self.estim[indices,1:] = MAX
else:
footprint_logodds = np.zeros((self.N,1),dtype=float)
if gamma.model=='modelA':
lhoodA, lhoodB = likelihoodAB(cascade, B=B, model=gamma.model)
elif gamma.model=='modelB':
lhoodA, lhoodB = likelihoodAB(cascade, mu=mu, model=gamma.model)
elif gamma.model=='modelC':
lhoodA, lhoodB, lhoodC = likelihoodAB(cascade, B=B, omega=omega, omegao=omegao, model=gamma.model)
for j in xrange(pi.J):
if model=='modelC':
footprint_logodds += insum(gamma.value[j]*lhoodA.value[j]-lhoodC.value[j]+(1-gamma.value[j])*lhoodB.value[j],[1])
else:
footprint_logodds += insum((1-gamma.value[j])*(lhoodB.value[j]-lhoodA.value[j]),[1])
footprint_logodds += insum(gamma.value[j]*(nplog(pi.estim[j])-nplog(gamma.value[j])) \
+ (1-gamma.value[j])*(nplog(1-pi.estim[j])-nplog(1-gamma.value[j])),[1])
self.estim[:,1:] = beta.estim[0] + beta.estim[1]*scores + footprint_logodds \
+ gammaln(self.total+alpha.estim[1]) - gammaln(self.total+alpha.estim[0]) \
+ gammaln(alpha.estim[0]) - gammaln(alpha.estim[1]) \
+ alpha.estim[1]*nplog(tau.estim[1]) - alpha.estim[0]*nplog(tau.estim[0]) \
+ self.total*(nplog(1-tau.estim[1])-nplog(1-tau.estim[0]))
if alpha is None:
self.estim[self.estim==np.inf] = MAX
self.estim = np.exp(self.estim-np.max(self.estim,1).reshape(self.N,1))
self.estim = self.estim/insum(self.estim,[1])
else:
self.estim[:,1:] = self.estim[:,1:]/np.log(10)
def getnull(self, locations, sample='', width=200):
left = self.k/2
right = self.k/2-1
if sample=='':
cutrate = self.cutrate
else:
cutrate = self.cutrate[sample]
strand = np.array([1 if loc[3]=='+' else 0 for loc in locations])
# removed a +1 for the - strand
sequences = np.array([utils.makestr(self.genome[loc[0]][int(loc[1])-width/2-left:int(loc[1])+width/2+right]) if loc[3]=='+' \
else utils.makestr(self.genome[loc[0]][int(loc[2])-width/2-left:int(loc[2])+width/2+right]) \
for loc in locations])
null = sequence_null.getnull(sequences, strand, cutrate, width, self.k)
null[null==0] = 1e-8
null = null/utils.insum(null,[1])
return null
def getnull(self, locations, sample='', width=200):
left = self.k / 2
right = self.k / 2 - 1
if sample == '':
cutrate = self.cutrate
else:
cutrate = self.cutrate[sample]
strand = np.array([1 if loc[3] == '+' else 0 for loc in locations])
# removed a +1 for the - strand
sequences = np.array([utils.makestr(self.genome[loc[0]][int(loc[1])-width/2-left:int(loc[1])+width/2+right]) if loc[3]=='+' \
else utils.makestr(self.genome[loc[0]][int(loc[2])-width/2-left:int(loc[2])+width/2+right]) \
for loc in locations])
null = sequence_null.getnull(sequences, strand, cutrate, width, self.k)
null[null == 0] = 1e-8
null = null / utils.insum(null, [1])
return null
def logposteriorodds_multinomial(reads, footprint, null):
logodds = insum(reads*nplog(footprint.ravel()),[1]) - insum(reads*nplog(null),[1])
return logodds.ravel()
import numpy as np
import scipy.optimize as opt
from scipy.special import digamma, gammaln
from utils import insum, outsum, nplog, EPS, MAX
import cPickle, time, math, pdb
logistic = lambda x: 1./(1+insum(np.exp(x),[1]))
newlogistic = lambda x: 1./(1+np.exp(x))
class Cascade:
def __init__(self, L):
self.L = L
if math.frexp(self.L)[0]!=0.5:
print "profile size is not a power of 2"
pdb.set_trace()
self.J = math.frexp(self.L)[1]-1
self.data = False
self.value = dict()
def setreads(self, reads):
self.data = True
N,L = reads.shape
self.N = N
if L!=self.L:
print "data dimensions do not match"
pdb.set_trace()
self.transform(reads)
def likelihood(cascade,
scores,
eta,
gamma,
pi,
alpha,
beta,
tau,
mu=None,
B=None,
omega=None,
omegao=None):
apriori = beta.estim[0] + beta.estim[1] * scores
if gamma.model == 'modelA':
lhoodA, lhoodB = likelihoodAB(cascade, B=B, model=gamma.model)
elif gamma.model == 'modelB':
lhoodA, lhoodB = likelihoodAB(cascade, mu=mu, model=gamma.model)
elif gamma.model == 'modelC':
lhoodA, lhoodB, lhoodC = likelihoodAB(cascade,
B=B,
omega=omega,
omegao=omegao,
model=gamma.model)
footprint = np.zeros((cascade.N, 1), dtype=float)
for j in xrange(pi.J):
footprint += insum(gamma.value[j]*lhoodA.value[j] + (1-gamma.value[j])*lhoodB.value[j] \
+ gamma.value[j]*(nplog(pi.estim[j])-nplog(gamma.value[j])) \
+ (1-gamma.value[j])*(nplog(1-pi.estim[j])-nplog(1-gamma.value[j])),[1])
P_1 = footprint + gammaln(eta.total+alpha.estim[1]) - gammaln(alpha.estim[1]) \
+ alpha.estim[1]*nplog(tau.estim[1]) + eta.total*nplog(1-tau.estim[1])
P_1[P_1 == np.inf] = MAX
P_1[P_1 == -np.inf] = -MAX
null = np.zeros((cascade.N, 1), dtype=float)
for j in xrange(cascade.J):
if gamma.model == 'modelC':
null = null + insum(lhoodC.value[j], [1])
else:
null = null + insum(lhoodA.value[j], [1])
P_0 = null + gammaln(eta.total+alpha.estim[0]) - gammaln(alpha.estim[0]) \
+ alpha.estim[0]*nplog(tau.estim[0]) + eta.total*nplog(1-tau.estim[0])
P_0[P_0 == np.inf] = MAX
P_0[P_0 == -np.inf] = -MAX
L = P_0*eta.estim[:,:1] + insum(P_1*eta.estim[:,1:],[1]) + apriori*(1-eta.estim[:,:1]) \
- nplog(1+np.exp(apriori)) - insum(eta.estim*nplog(eta.estim),[1])
L = L.sum()
if np.isnan(L):
print "Nan in LogLike"
raise ValueError
if np.isinf(L):
print "Inf in LogLike"
raise ValueError
return L
import numpy as np
import scipy.optimize as opt
from scipy.special import digamma, gammaln
from utils import insum, outsum, nplog, EPS, MAX
import cPickle, time, math, pdb
logistic = lambda x: 1. / (1 + insum(np.exp(x), [1]))
newlogistic = lambda x: 1. / (1 + np.exp(x))
class Cascade:
def __init__(self, L):
self.L = L
if math.frexp(self.L)[0] != 0.5:
print "profile size is not a power of 2"
pdb.set_trace()
self.J = math.frexp(self.L)[1] - 1
self.data = False
self.value = dict()
def setreads(self, reads):
self.data = True
N, L = reads.shape
self.N = N
if L != self.L:
print "data dimensions do not match"
pdb.set_trace()
self.transform(reads)
def logposteriorodds_multinomial(reads, footprint, null):
logodds = insum(reads * nplog(footprint.ravel()), [1]) - insum(reads * nplog(null), [1])
return logodds.ravel()
