def experiment2_():
L = 10
sigma = 1
code = sample_code(L, 1)
mu = -10
Ne = 2
sites = [random_site(L) for i in xrange(10000)]
apw_eps = [score(code, site) for site in sites]
site_sigma = sd(apw_eps)
pssm = sample_matrix(L, sqrt(site_sigma**2 / L))
#linear_eps = [score_seq(pssm, site) for site in sites]
def apw_phat(site):
ep = score(code, site)
return 1 / (1 + exp(ep - mu))**(Ne - 1)
def linear_phat(site):
ep = score_seq(pssm, site)
return 1 / (1 + exp(ep - mu))**(Ne - 1)
def sample_apw_site():
return mh(apw_phat, proposal=mutate_site, x0=random_site(L))
apw_chain = mh(apw_phat, proposal=mutate_site, x0=random_site(L))
linear_chain = mh(linear_phat, proposal=mutate_site, x0=random_site(L))
apw_fits = map(apw_phat, apw_chain)
linear_fits = map(linear_phat, linear_chain)
return apw_fits, linear_fits
def experiment3(trials=10):
mu = -10
Ne = 5
L = 10
sigma = 1
codes = [sample_code(L, sigma) for i in range(trials)]
pssms = [sample_matrix(L, sigma) for i in range(trials)]
sites = [random_site(L) for i in xrange(10000)]
apw_site_sigmas = [
sd([score(code, site) for site in sites]) for code in codes
]
linear_site_sigmas = [
sd([score_seq(pssm, site) for site in sites]) for pssm in pssms
]
def apw_phat(code, site):
ep = score(code, site)
return 1 / (1 + exp(ep - mu))**(Ne - 1)
def apw_occ(code, site):
ep = score(code, site)
return 1 / (1 + exp(ep - mu))
def linear_phat(pssm, site):
ep = score_seq(pssm, site)
return 1 / (1 + exp(ep - mu))**(Ne - 1)
def linear_occ(pssm, site):
ep = score_seq(pssm, site)
return 1 / (1 + exp(ep - mu))
apw_mean_fits = [
exp(
mean(
map(
log10,
mh(lambda s: apw_phat(code, s),
proposal=mutate_site,
x0=random_site(L),
capture_state=lambda s: apw_occ(code, s))[1:])))
for code in tqdm(codes)
]
linear_mean_fits = [
exp(
mean(
map(
log10,
mh(lambda s: linear_phat(pssm, s),
proposal=mutate_site,
x0=random_site(L),
capture_state=lambda s: linear_occ(pssm, s))[1:])))
for pssm in tqdm(pssms)
]
plt.scatter(apw_site_sigmas, apw_mean_fits, label='apw')
plt.scatter(linear_site_sigmas,
linear_mean_fits,
color='g',
label='linear')
plt.semilogy()
plt.legend(loc='lower right')
def sample_model(model, iterations=50000,x0=None):
k = len(model)
L = int(1 + sqrt(1+8*k)/2)
if x0 is None:
x0 = random_site(L)
chain = mh(lambda s:score(model,s),
proposal=mutate_site,
x0=random_site(L),
use_log=True, iterations=iterations)
return chain
def sample_model(model, iterations=50000, x0=None):
k = len(model)
L = int(1 + sqrt(1 + 8 * k) / 2)
if x0 is None:
x0 = random_site(L)
chain = mh(lambda s: score(model, s),
proposal=mutate_site,
x0=random_site(L),
use_log=True,
iterations=iterations)
return chain
def sample_site_cftp_dep(matrix, mu, Ne):
L = len(matrix)
def log_phat(s):
ep = score_seq(matrix,s)
nu = Ne - 1
return -nu*log(1 + exp(ep - mu))
first_site = "A"*L
last_site = "T"*L
best_site = "".join(["ACGT"[argmin(row)] for row in matrix])
worst_site = "".join(["ACGT"[argmax(row)] for row in matrix])
trajs = [[best_site],[random_site(L)],[random_site(L)],[random_site(L)], [worst_site]]
def mutate_site(site,(ri,rb)):
return subst(site,"ACGT"[rb],ri)
def sample_motif_ar_tilted(matrix, mu, Ne, N):
nu = Ne - 1
L = len(matrix)
ep_min, ep_max, L = sum(map(min,matrix)), sum(map(max,matrix)), len(matrix)
site_sigma = site_sigma_from_matrix(matrix)
density = lambda ep:(1/(1+exp(ep-mu)))**(Ne-1) * dnorm(ep,0,site_sigma)*(ep_min <= ep <= ep_max)
d_density = lambda ep:ep/site_sigma**2 + nu/(1+exp(mu-ep))
phat = lambda ep:(1/(1+exp(ep-mu)))**(Ne-1)
mode = bisect_interval(d_density, -100, 100)
if mode < ep_min:
mode = ep_min + 1 # don't want mode right on the nose of ep_min for sampling purposes, so offset it a bit
dmode = density(mode)
# calculate mean epsilon via rejection sampling
motif = []
def mean_ep(lamb):
psfm = psfm_from_matrix(matrix, lamb=lamb)
return sum([ep * p for (mat_row, psfm_row) in zip(matrix, psfm)
for (ep, p) in zip(mat_row, psfm_row)])
lamb = bisect_interval(lambda l:mean_ep(l) - mode, -20, 20)
tilted_psfm = psfm_from_matrix(matrix, lamb=lamb)
log_tilted_psfm = [map(log,row) for row in tilted_psfm]
while len(motif) < N:
site = random_site(L)
ep = score_seq(matrix, site)
if random.random() < phat(ep)/pmode:
motif.append(site)
return motif
def experiment3(trials=10):
mu = -10
Ne = 5
L = 10
sigma = 1
codes = [sample_code(L, sigma) for i in range(trials)]
pssms = [sample_matrix(L, sigma) for i in range(trials)]
sites = [random_site(L) for i in xrange(10000)]
apw_site_sigmas = [sd([score(code,site) for site in sites]) for code in codes]
linear_site_sigmas = [sd([score_seq(pssm,site) for site in sites]) for pssm in pssms]
def apw_phat(code, site):
ep = score(code, site)
return 1/(1+exp(ep-mu))**(Ne-1)
def apw_occ(code, site):
ep = score(code, site)
return 1/(1+exp(ep-mu))
def linear_phat(pssm, site):
ep = score_seq(pssm, site)
return 1/(1+exp(ep-mu))**(Ne-1)
def linear_occ(pssm, site):
ep = score_seq(pssm, site)
return 1/(1+exp(ep-mu))
apw_mean_fits = [exp(mean(map(log10, mh(lambda s:apw_phat(code, s), proposal=mutate_site, x0=random_site(L),
capture_state = lambda s:apw_occ(code, s))[1:])))
for code in tqdm(codes)]
linear_mean_fits = [exp(mean(map(log10, mh(lambda s:linear_phat(pssm, s), proposal=mutate_site, x0=random_site(L),
capture_state = lambda s:linear_occ(pssm, s))[1:])))
for pssm in tqdm(pssms)]
plt.scatter(apw_site_sigmas, apw_mean_fits, label='apw')
plt.scatter(linear_site_sigmas, linear_mean_fits, color='g',label='linear')
plt.semilogy()
plt.legend(loc='lower right')
def sample_motif_ar_tilted(matrix, mu, Ne, N):
nu = Ne - 1
L = len(matrix)
ep_min, ep_max, L = sum(map(min, matrix)), sum(map(max,
matrix)), len(matrix)
site_sigma = site_sigma_from_matrix(matrix)
density = lambda ep: (1 / (1 + exp(ep - mu)))**(Ne - 1) * dnorm(
ep, 0, site_sigma) * (ep_min <= ep <= ep_max)
d_density = lambda ep: ep / site_sigma**2 + nu / (1 + exp(mu - ep))
phat = lambda ep: (1 / (1 + exp(ep - mu)))**(Ne - 1)
mode = bisect_interval(d_density, -100, 100)
if mode < ep_min:
mode = ep_min + 1 # don't want mode right on the nose of ep_min for sampling purposes, so offset it a bit
dmode = density(mode)
# calculate mean epsilon via rejection sampling
motif = []
def mean_ep(lamb):
psfm = psfm_from_matrix(matrix, lamb=lamb)
return sum([
ep * p for (mat_row, psfm_row) in zip(matrix, psfm)
for (ep, p) in zip(mat_row, psfm_row)
])
lamb = bisect_interval(lambda l: mean_ep(l) - mode, -20, 20)
tilted_psfm = psfm_from_matrix(matrix, lamb=lamb)
log_tilted_psfm = [map(log, row) for row in tilted_psfm]
while len(motif) < N:
site = random_site(L)
ep = score_seq(matrix, site)
if random.random() < phat(ep) / pmode:
motif.append(site)
return motif
def apw_fit(sigma, mu, Ne):
code = sample_code(L, sigma)
def apw_phat(site):
ep = score(code, site)
return 1/(1+exp(ep-mu))**(Ne-1)
chain = mh(lambda s:apw_phat(s), proposal=mutate_site, x0=random_site(L),
capture_state = lambda s:apw_occ(code, mu, s))[25000:]
return mean(chain)
def linear_fit(sigma, mu, Ne):
pssm = sample_matrix(L, sigma)
def linear_phat(site):
ep = score_seq(pssm, site)
return 1/(1+exp(ep-mu))**(Ne-1)
chain = mh(lambda s:linear_phat(s), proposal=mutate_site, x0=random_site(L),
capture_state = lambda s:linear_occ(pssm, mu, s))[25000:]
return mean(chain)
def select_sites_by_occupancy(matrix, mu, n):
L = len(matrix)
motif = []
while len(motif) < n:
site = random_site(L)
if random.random() < 1 / (1 + exp(score_seq(matrix, site) - mu)):
motif.append(site)
print len(motif)
return motif
def alignment_simulation():
ell = 100
L = 10
N = 50
trials = 100000
seqs = [random_site(ell) for i in range(N)]
def random_alignment():
rs = [random.randrange(ell-L+1) for _ in range(N)]
return [seq[r:r+L] for seq, r in zip(seqs,rs)]
ics = [motif_ic(random_alignment()) for _ in trange(trials)]
def mr_system_mh(alphas,G=100000.0,n=16,L=10):
scale = 10000 #lower means less stringent
matrix = [[0,0,0,0] for i in range(L)]
motif = [random_site(L) for i in range(n)]
scaled_sse = lambda matrix,motif:(sse(matrix,motif,alphas,G,n))*scale
return mh(lambda (matrix,motif):exp(-scaled_sse(matrix,motif)),
lambda (matrix,motif):propose(matrix,motif),
(matrix,motif),
iterations=100000,
every=1000,verbose=True)
def experiment1_():
L = 10
sigma = 1
code = sample_code(L, 1)
mu = -10
Ne = 2
pssm = linearize(code)
def apw_phat(site):
ep = score(code, site)
return 1/(1+exp(ep-mu))**(Ne-1)
def linear_phat(site):
ep = score_seq(pssm, site)
return 1/(1+exp(ep-mu))**(Ne-1)
def sample_apw_site():
return mh(apw_phat, proposal=mutate_site, x0=random_site(L))
apw_chain = mh(apw_phat, proposal=mutate_site, x0=random_site(L))
linear_chain = mh(linear_phat, proposal=mutate_site, x0=random_site(L))
apw_fits = map(apw_phat, apw_chain)
linear_fits = map(linear_phat, linear_chain)
return apw_fits, linear_fits
def sample_site_ar(matrix, mu, Ne, lamb=None, modulus=10**6, return_ar=False):
nu = Ne - 1
if nu == 0:
return random_site(len(matrix))
if lamb is None:
lamb = nu/2.0
L = len(matrix)
def rQ():
return sample_from_matrix(matrix, lamb)
#log_Z = sum(log(sum(exp(-lamb*ep) for ep in col)) for col in matrix)
def log_dQ(site):
log_numer = -lamb*sum(row["ACGT".index(b)] for b,row in zip(site,matrix))
return log_numer# - log_Z
def log_fit(site):
return -nu*log(1+exp(score_seq(matrix,site)-mu))
ep_max = sum(max(row) for row in matrix)
ep_min = sum(min(row) for row in matrix)
alpha = lamb/float(nu)
def find_logM(ep):
return nu*log((exp(alpha*ep)/(1+exp(ep-mu))))
def log_M_p(ep):
term1 = alpha*exp(alpha*ep)/(exp(ep-mu)+1)
term2 = -exp(alpha*ep+ep-mu)/((exp(ep-mu)+1)**2)
return term1 + term2
if alpha != 1 and alpha/(1-alpha) > 0:
ep_crit = log(alpha/(1-alpha)) + mu
else:
deriv = log_M_p(0)
if deriv < 0:
ep_crit = ep_min
else:
ep_crit = ep_max
log_M = find_logM(ep_crit)
# print "choosing from:",find_logM(ep_min), find_logM(ep_max)
# print "log_M:",log_M
trials = 0
while True:
trials += 1
s = rQ()
log_f = log_fit(s)
log_prop = log_dQ(s) + log_M
log_ar = log_f - log_prop
log_r = log(random.random())
accept = log_r < log_ar
#print trials, s, "*" if accept else " ",log_r, log_ar, log_f, log_prop
assert log_f < 0
assert log_ar < 0
if trials % modulus == 0:
print trials, s, "*" if accept else " ",log_r, log_ar, log_f, log_prop
if accept:
if return_ar:
return trials
else:
return s
def roc_experiment(motif, trials=10**5):
pw_model = pairwise_model_from_motif(motif)
li_model = linear_model_from_motif(motif)
L = len(motif[0])
negatives = [random_site(L) for i in trange(trials)]
pw_pos = [pw_prob_site(site, pw_model) for site in motif]
pw_neg = [pw_prob_site(site, pw_model) for site in tqdm(negatives)]
li_pos = [linear_prob_site(site, li_model) for site in motif]
li_neg = [linear_prob_site(site, li_model) for site in tqdm(negatives)]
_, _, _, pw_auc = roc_curve(pw_pos, pw_neg)
_, _, _, li_auc = roc_curve(li_pos, li_neg, color='g')
return li_auc, pw_auc
def alignment_simulation():
ell = 100
L = 10
N = 50
trials = 100000
seqs = [random_site(ell) for i in range(N)]
def random_alignment():
rs = [random.randrange(ell - L + 1) for _ in range(N)]
return [seq[r:r + L] for seq, r in zip(seqs, rs)]
ics = [motif_ic(random_alignment()) for _ in trange(trials)]
def apw_fit(sigma, mu, Ne):
code = sample_code(L, sigma)
def apw_phat(site):
ep = score(code, site)
return 1 / (1 + exp(ep - mu))**(Ne - 1)
chain = mh(lambda s: apw_phat(s),
proposal=mutate_site,
x0=random_site(L),
capture_state=lambda s: apw_occ(code, mu, s))[25000:]
return mean(chain)
def linear_fit(sigma, mu, Ne):
pssm = sample_matrix(L, sigma)
def linear_phat(site):
ep = score_seq(pssm, site)
return 1 / (1 + exp(ep - mu))**(Ne - 1)
chain = mh(lambda s: linear_phat(s),
proposal=mutate_site,
x0=random_site(L),
capture_state=lambda s: linear_occ(pssm, mu, s))[25000:]
return mean(chain)
def train_pairwise_model(motif,
pc=1 / 16.0,
decay_timescale=10000,
take_stock=1000,
eta=0.01,
stop_crit=0.01):
L = len(motif[0])
N = len(motif)
fs = get_pairwise_freqs(motif, pc=pc)
ws = [{(b1, b2): 0
for (b1, b2) in dinucs} for _ in range(int(choose(L, 2)))]
x = random_site(L)
log_y = score(ws, x)
chain = []
# sses = [0.0] * (int(iterations/take_stock) + 1)
#chain = []
#for iteration in xrange(iterations):
iteration = 0
stock_counter = take_stock
while True:
xp = mutate_site(x)
log_yp = score(ws, xp)
if log(random.random()) < log_yp - log_y:
x = xp
log_y = log_yp
chain.append(x)
if iteration > 0 and iteration % stock_counter == 0:
current_fs = get_pairwise_freqs(
sample(N,
chain[iteration - stock_counter:iteration],
replace=False))
sse = 0
for w, f, cur_f in zip(ws, fs, current_fs):
for b1, b2 in dinucs:
delta = f[b1, b2] - cur_f[b1, b2]
sse += delta**2
w[b1, b2] += eta * (
delta) #* exp(-iteration/float(decay_timescale))
#sses[iteration/take_stock] = sse
sse_per_col_pair = sse / choose(L, 2)
print iteration, stock_counter, sse_per_col_pair, exp(
-iteration / float(decay_timescale)), ws[0]['A', 'A']
stock_counter += random.randrange(2)
#print "motif_ic:", motif_ic(chain[iteration-stock_counter : iteration])
if iteration > 0 and sse_per_col_pair < stop_crit:
print "breaking:", sse, sse_per_col_pair
break
log_y = score(ws, x) # recalculate this because weights change
#stock_counter += take_stock * (iteration > take_stock)
iteration += 1
return ws
def site_mh(matrix, mu, Ne, iterations=50000):
site_mu, site_sigma = site_mu_from_matrix(matrix), site_sigma_from_matrix(
matrix)
L = len(matrix)
nu = Ne - 1
log_f = lambda site: log_Pe(score_seq(matrix, site), site_mu, site_sigma,
mu, Ne)
#prop = lambda site:random_site(L)
prop = lambda site: mutate_site(site)
return mh(log_f,
prop,
x0=random_site(L),
use_log=True,
iterations=iterations)
def mr_system_sa(alphas,init_system=None,G=100000.0,n=16,L=10,
sse_epsilon=0.0001,proposal=propose,scale=1000,
iterations=10000,return_trajectory=False):
if init_system is None:
matrix = [[0,0,0,0] for i in range(L)]
motif = [random_site(L) for i in range(n)]
else:
matrix,motif = init_system
scaled_sse = lambda(matrix,motif):sse(matrix,motif,alphas,G,n)*scale
return anneal(scaled_sse,
lambda(matrix,motif):proposal(matrix,motif),
(matrix,motif),
iterations=iterations,
stopping_crit = sse_epsilon*scale,
return_trajectory=return_trajectory)
def experiment2_():
L = 10
sigma = 1
code = sample_code(L, 1)
mu = -10
Ne = 2
sites = [random_site(L) for i in xrange(10000)]
apw_eps = [score(code, site) for site in sites]
site_sigma = sd(apw_eps)
pssm = sample_matrix(L, sqrt(site_sigma**2/L))
#linear_eps = [score_seq(pssm, site) for site in sites]
def apw_phat(site):
ep = score(code, site)
return 1/(1+exp(ep-mu))**(Ne-1)
def linear_phat(site):
ep = score_seq(pssm, site)
return 1/(1+exp(ep-mu))**(Ne-1)
def sample_apw_site():
return mh(apw_phat, proposal=mutate_site, x0=random_site(L))
apw_chain = mh(apw_phat, proposal=mutate_site, x0=random_site(L))
linear_chain = mh(linear_phat, proposal=mutate_site, x0=random_site(L))
apw_fits = map(apw_phat, apw_chain)
linear_fits = map(linear_phat, linear_chain)
return apw_fits, linear_fits
def experiment1_():
L = 10
sigma = 1
code = sample_code(L, 1)
mu = -10
Ne = 2
pssm = linearize(code)
def apw_phat(site):
ep = score(code, site)
return 1 / (1 + exp(ep - mu))**(Ne - 1)
def linear_phat(site):
ep = score_seq(pssm, site)
return 1 / (1 + exp(ep - mu))**(Ne - 1)
def sample_apw_site():
return mh(apw_phat, proposal=mutate_site, x0=random_site(L))
apw_chain = mh(apw_phat, proposal=mutate_site, x0=random_site(L))
linear_chain = mh(linear_phat, proposal=mutate_site, x0=random_site(L))
apw_fits = map(apw_phat, apw_chain)
linear_fits = map(linear_phat, linear_chain)
return apw_fits, linear_fits
def sample_uniform_energy(matrix):
mu = sum(map(mean, matrix))
sigma = sqrt(sum(map(lambda x:variance(x,correct=False), matrix)))
ep_min = sum(map(min, matrix))
ep_max = sum(map(max, matrix))
M_min = 1/norm.pdf(ep_min, mu, sigma)
M_max = 1/norm.pdf(ep_max, mu, sigma)
M = max(M_min, M_max)
trials = 0
while True:
trials += 1
if trials % 10000 == 0:
print trials
site = random_site(L)
ep = score_seq(matrix, site)
ar = 1/(M*norm.pdf(ep, mu, sigma))
if random.random() < ar:
return site
def sample_uniform_energy(matrix):
mu = sum(map(mean, matrix))
sigma = sqrt(sum(map(lambda x: variance(x, correct=False), matrix)))
ep_min = sum(map(min, matrix))
ep_max = sum(map(max, matrix))
M_min = 1 / norm.pdf(ep_min, mu, sigma)
M_max = 1 / norm.pdf(ep_max, mu, sigma)
M = max(M_min, M_max)
trials = 0
while True:
trials += 1
if trials % 10000 == 0:
print trials
site = random_site(L)
ep = score_seq(matrix, site)
ar = 1 / (M * norm.pdf(ep, mu, sigma))
if random.random() < ar:
return site
def train_pairwise_model(motif, pc=1/16.0, decay_timescale=10000, take_stock=1000, eta=0.01, stop_crit=0.01):
L = len(motif[0])
N = len(motif)
fs = get_pairwise_freqs(motif, pc=pc)
ws = [{(b1, b2):0 for (b1,b2) in dinucs} for _ in range(int(choose(L,2)))]
x = random_site(L)
log_y = score(ws, x)
chain = []
# sses = [0.0] * (int(iterations/take_stock) + 1)
#chain = []
#for iteration in xrange(iterations):
iteration = 0
stock_counter = take_stock
while True:
xp = mutate_site(x)
log_yp = score(ws, xp)
if log(random.random()) < log_yp - log_y:
x = xp
log_y = log_yp
chain.append(x)
if iteration > 0 and iteration % stock_counter == 0:
current_fs = get_pairwise_freqs(sample(N,chain[iteration-stock_counter : iteration], replace=False))
sse = 0
for w, f, cur_f in zip(ws, fs, current_fs):
for b1, b2 in dinucs:
delta = f[b1, b2] - cur_f[b1,b2]
sse += delta**2
w[b1, b2] += eta*(delta) #* exp(-iteration/float(decay_timescale))
#sses[iteration/take_stock] = sse
sse_per_col_pair = sse/choose(L,2)
print iteration, stock_counter, sse_per_col_pair, exp(-iteration/float(decay_timescale)), ws[0]['A','A']
stock_counter += random.randrange(2)
#print "motif_ic:", motif_ic(chain[iteration-stock_counter : iteration])
if iteration > 0 and sse_per_col_pair < stop_crit:
print "breaking:", sse, sse_per_col_pair
break
log_y = score(ws, x) # recalculate this because weights change
#stock_counter += take_stock * (iteration > take_stock)
iteration += 1
return ws
def sample_site_bf(matrix, mu, Ne, ringer_site=None, verbose=False):
"""Sample site of length L from stationary fitness distribution under
E(s) at effective population Ne, chemical potential mu. (bf for
brute force)
"""
nu = Ne - 1
L = len(matrix)
if ringer_site is None:
ringer_site = ringer_motif(matrix,1)[0]
def phat(s):
ep = score_seq(matrix,s)
return (1 + exp(ep - mu))**(-nu)
phat_max = phat(ringer_site)
trials = 0
while True:
trials += 1
site = random_site(L)
ar = phat(site)/phat_max
if random.random() < ar:
if verbose:
print trials, ar
return site
def mr_system(alphas,init_system=None,G=100000.0,n=16,L=10,
sse_epsilon=0.00000001,use_annealing=True,scale=1000,
iterations=10000,motif_prob=0.5,verbose=False):
proposal = lambda matrix,motif:propose(matrix,motif,motif_prob=motif_prob)
if init_system is None:
matrix = [[0,0,0,0] for i in range(L)]
motif = [random_site(L) for i in range(n)]
else:
matrix,motif = init_system
if use_annealing:
scaled_sse = lambda(matrix,motif):((sse(matrix,motif,alphas,G,n))*scale)
return anneal(scaled_sse,
lambda(matrix,motif):proposal(matrix,motif),
(matrix,motif),
iterations=iterations,
stopping_crit = sse_epsilon*scale,verbose=verbose)
else:
scaled_sse = lambda(matrix,motif):exp((sse(matrix,motif,alphas,G,n))*-scale)
return mh(scaled_sse,
lambda(matrix,motif):proposal(matrix,motif),
(matrix,motif),
iterations=iterations,
every=100,verbose=True)
def sample_species2():
bd = [random.choice(aas) for i in range(L)]
site = random_site(L)
sites = [site for i in range(n)]
return (bd, sites)
def sample_apw_site():
return mh(apw_phat, proposal=mutate_site, x0=random_site(L))
def sample_apw_site():
return mh(apw_phat, proposal=mutate_site, x0=random_site(L))
def log_Z_analytic((matrix, mu, Ne), N):
"""compute log_Z analytically"""
acc = 0
nu = Ne - 1
L = len(matrix)
for kmer in kmers(L):
ep = score_seq(matrix, "".join(kmer))
acc += (1/(1+exp(ep-mu)))**(Ne-1)
return N * log(acc)
def log_ZS_naive((matrix, mu, Ne), trials=1000):
acc = 0
nu = Ne - 1
L = len(matrix)
for i in xrange(trials):
ep = score_seq(matrix, random_site(L))
acc += (1/(1+exp(ep-mu)))**(Ne-1)
mean_Zs = acc / trials
return L * log(4) + log(mean_Zs)
def log_ZM_naive((matrix, mu, Ne), N, trials=1000):
return N * log_ZS_naive((matrix, mu, Ne), trials=1000)
def log_ZS_hack((matrix, mu, Ne), N):
L = len(matrix)
mat_mu = sum(map(mean,matrix))
mat_sigma = sqrt(sum(map(lambda xs:variance(xs,correct=False), matrix)))
log_perc_below_threshold = norm.logcdf(mu - log((Ne-1)), mat_mu, mat_sigma)
log_Zs = L * log(4) + log_perc_below_threshold
return log_Zs
from sample import direct_sampling,rsa
from project_utils import score_seq,sample_average,inverse_cdf_sampler,falling_fac
from utils import random_site,pairs,mh,maybesave,transpose,product
from matplotlib import pyplot as plt
from math import log,exp
import random
random.seed(1)
genome = "ACGTTGCA" * 5 + random_site(80) + "ACGTTGCA" * 5 + random_site(10)
G = len(genome)
beta = 1
energy_matrix = [[-2,0,0,0],
[-0,-2,0,0],
[-0,0,-2,0],
[-0,0,0,-2],
[-0,0,0,-2],
[-0,0,-2,0],
[-0,-2,0,0],
[-2,0,0,0]]
w = len(energy_matrix)
config_len = G-w
interaction_energy = -8 # TFs in contact get -2 added to configuration energy
exclusion_energy = 1000000
eps =[score_seq(energy_matrix,genome[i:i+w]) for i in range(G-w+1)]
ks = [exp(-ep) for ep in eps]
def positions(config):
return [i for i,x in enumerate(config) if x > 0]
def from_positions(poses):
def sample_Zb_terms(L,sigma,trials=10000):
matrix = sample_matrix(L,sigma)
return [score_seq(matrix,random_site(L)) for i in xrange(trials)]
"""compute log_Z analytically"""
acc = 0
nu = Ne - 1
L = len(matrix)
for kmer in kmers(L):
ep = score_seq(matrix, "".join(kmer))
acc += (1 / (1 + exp(ep - mu)))**(Ne - 1)
return N * log(acc)
def log_ZS_naive((matrix, mu, Ne), trials=1000):
acc = 0
nu = Ne - 1
L = len(matrix)
for i in xrange(trials):
ep = score_seq(matrix, random_site(L))
acc += (1 / (1 + exp(ep - mu)))**(Ne - 1)
mean_Zs = acc / trials
return L * log(4) + log(mean_Zs)
def log_ZM_naive((matrix, mu, Ne), N, trials=1000):
return N * log_ZS_naive((matrix, mu, Ne), trials=1000)
def log_ZS_hack((matrix, mu, Ne), N):
L = len(matrix)
mat_mu = sum(map(mean, matrix))
mat_sigma = sqrt(sum(map(lambda xs: variance(xs, correct=False), matrix)))
log_perc_below_threshold = norm.logcdf(mu - log((Ne - 1)), mat_mu,
mat_sigma)
def mh_motif(n,w,desired_ic,epsilon,scale=10,iterations=10000):
"""Find a motif satisfying desired_ic +/- epsilon by mh sampling"""
motif = [random_site(w) for i in range(n) ]
f = lambda m:exp(-abs(desired_ic-motif_ic(m))*scale)
proposal = mutate_motif
return mh(f,proposal,motif,iterations=iterations)
def sample_sites(n=n,L=L):
return [random_site(L) for i in range(n)]
def Zb_from_matrix_ref(matrix,G):
L = len(matrix)
eps = np.array([score_seq(matrix,random_site(L)) for i in trange(G)])
return np.sum(np.exp(-eps))
"""
This file contains data for the genome (GENOME) and DNA binding domain (TRUE_ENERGY_MATRIX)
"""
from utils import random_site
W = 10 # width of DNA binding domain
TRUE_ENERGY_MATRIX = ([[-2,0,0,0] for i in range(W)])
with open('genome.fa') as f:
lines = f.readlines()
#GENOME = lines[1]
GENOME = random_site(5000000)
L = len(GENOME)
MEAN_FRAG_LENGTH = 250
# Mon May 12 19:20:38 EDT 2014
# toy genome of 10k bases, MEAN_FRAG_LENGTH = 50 works perfectly
