def rejection_sample_site((matrix, mu, Ne)):
psfm = psfm_from_matrix(matrix)
log_psfm = [[log(p) for p in row] for row in psfm]
log_psfm_prob = lambda site:score_seq(log_psfm, site)
log_M = -sum(map(max,psfm))
sites = [sample_from_psfm(psfm) for _ in xrange(trials)]
log_fs = [log_fhat((matrix, mu, Ne), [site]) for site in sites]
log_qs = [log_psfm_prob(site) for site in sites]
ars = [exp(log_f - (log_q + log_M)) for log_f, log_q in zip(log_fs, log_qs)]
def rejection_sample_site((matrix, mu, Ne)):
psfm = psfm_from_matrix(matrix)
log_psfm = [[log(p) for p in row] for row in psfm]
log_psfm_prob = lambda site: score_seq(log_psfm, site)
log_M = -sum(map(max, psfm))
sites = [sample_from_psfm(psfm) for _ in xrange(trials)]
log_fs = [log_fhat((matrix, mu, Ne), [site]) for site in sites]
log_qs = [log_psfm_prob(site) for site in sites]
ars = [
exp(log_f - (log_q + log_M)) for log_f, log_q in zip(log_fs, log_qs)
]
def predict_ic_from_theta(theta, L):
sigma, mu, Ne = theta
nu = Ne - 1
ep_star = mu - log(Ne - 1)
matrix = sample_matrix(L, sigma)
ep_min = sum(map(min, matrix))
des_ep = max(ep_star, ep_min + 1)
def f(lamb):
psfm = psfm_from_matrix(matrix, lamb)
return sum([sum(ep*p for ep,p in zip(eps, ps)) for eps, ps in zip(matrix, psfm)]) - des_ep
log_psfm = [[log(p) for p in ps] for ps in psfm]
lamb = bisect_interval(f,-20,20)
sites = ([sample_from_psfm(psfm) for i in range(100)])
log_ps = [-nu*log(1+exp(score_seq(matrix, site) - mu)) for site in sites]
log_qs = [score_seq(log_psfm, site) for site in sites]
def predict_ic_from_theta(theta, L):
sigma, mu, Ne = theta
nu = Ne - 1
ep_star = mu - log(Ne - 1)
matrix = sample_matrix(L, sigma)
ep_min = sum(map(min, matrix))
des_ep = max(ep_star, ep_min + 1)
def f(lamb):
psfm = psfm_from_matrix(matrix, lamb)
return sum([
sum(ep * p for ep, p in zip(eps, ps))
for eps, ps in zip(matrix, psfm)
]) - des_ep
log_psfm = [[log(p) for p in ps] for ps in psfm]
lamb = bisect_interval(f, -20, 20)
sites = ([sample_from_psfm(psfm) for i in range(100)])
log_ps = [
-nu * log(1 + exp(score_seq(matrix, site) - mu)) for site in sites
]
log_qs = [score_seq(log_psfm, site) for site in sites]
def main_experiment(generate_data=False):
if generate_data:
iterations = 10000
prok_chains = [
posterior_chain2(motif, iterations=iterations)
for motif in tqdm(prok_motifs)
]
prok_bayes_spoofs = [[
motif_from_theta(theta, len(motif))
for theta in tqdm(chain[iterations / 2::500])
] for chain, motif in tqdm(zip(prok_chains, prok_motifs))]
prok_psfms = [
psfm_from_motif(motif, pc=1 / 4.0) for motif in prok_motifs
]
prok_psfm_spoofs = [[[
sample_from_psfm(psfm) for _ in range(len(motif))
] for _ in range(10)] for psfm, motif in zip(prok_psfms, prok_motifs)]
prok_maxent_spoofs = [
spoof_maxent_motifs(motif, 10) for motif in tqdm(prok_motifs)
]
prok_apws = map(lambda m: code_from_motif(m, pc=1 / 16.0),
tqdm(prok_motifs))
prok_apw_spoofs = [[[sample_site(apw) for _ in range(len(motif))]
for __ in range(10)]
for apw, motif in tqdm(zip(prok_apws, prok_motifs))]
euk_submotifs = map(subsample, euk_motifs)
euk_chains = [
posterior_chain2(motif, iterations=iterations)
for motif in tqdm(euk_submotifs)
]
euk_bayes_spoofs = [[
motif_from_theta(theta, len(motif))
for theta in tqdm(chain[iterations / 2::500])
] for chain, motif in tqdm(zip(euk_chains, euk_submotifs))]
euk_psfms = [
psfm_from_motif(motif, pc=1 / 4.0) for motif in euk_submotifs
]
euk_psfm_spoofs = [[[
sample_from_psfm(psfm) for _ in range(len(motif))
] for _ in range(10)] for psfm, motif in zip(euk_psfms, euk_submotifs)]
euk_maxent_spoofs = [
spoof_maxent_motifs(motif, 10) for motif in tqdm(euk_submotifs)
]
euk_apws = map(lambda m: code_from_motif(m, pc=1 / 16.0),
tqdm(euk_submotifs))
euk_apw_spoofs = [[[sample_site(apw) for _ in range(len(motif))]
for __ in range(10)]
for apw, motif in tqdm(zip(euk_apws, euk_submotifs))]
with open("prok_chains.pkl", 'w') as f:
cPickle.dump(prok_chains, f)
with open("prok_bayes_spoofs.pkl", 'w') as f:
cPickle.dump(prok_bayes_spoofs, f)
with open("prok_maxent_spoofs.pkl", 'w') as f:
cPickle.dump(prok_maxent_spoofs, f)
with open("prok_psfm_spoofs.pkl", 'w') as f:
cPickle.dump(prok_psfm_spoofs, f)
with open("prok_apw_spoofs.pkl", 'w') as f:
cPickle.dump(prok_apw_spoofs, f)
with open("euk_submotifs.pkl", 'w') as f:
cPickle.dump(euk_submotifs, f)
with open("euk_chains.pkl", 'w') as f:
cPickle.dump(euk_chains, f)
with open("euk_bayes_spoofs.pkl", 'w') as f:
cPickle.dump(euk_bayes_spoofs, f)
with open("euk_maxent_spoofs.pkl", 'w') as f:
cPickle.dump(euk_maxent_spoofs, f)
with open("euk_psfm_spoofs.pkl", 'w') as f:
cPickle.dump(euk_psfm_spoofs, f)
with open("euk_apw_spoofs.pkl", 'w') as f:
cPickle.dump(euk_apw_spoofs, f)
else:
with open("prok_chains.pkl") as f:
prok_chains = cPickle.load(f)
with open("prok_bayes_spoofs.pkl") as f:
prok_bayes_spoofs = cPickle.load(f)
with open("prok_maxent_spoofs.pkl") as f:
prok_maxent_spoofs = cPickle.load(f)
with open("prok_psfm_spoofs.pkl") as f:
prok_psfm_spoofs = cPickle.load(f)
with open("prok_apw_spoofs.pkl") as f:
prok_apw_spoofs = cPickle.load(f)
with open("euk_submotifs.pkl") as f:
euk_submotifs = cPickle.load(f)
with open("euk_chains.pkl") as f:
euk_chains = cPickle.load(f)
with open("euk_bayes_spoofs.pkl") as f:
euk_bayes_spoofs = cPickle.load(f)
with open("euk_maxent_spoofs.pkl") as f:
euk_maxent_spoofs = cPickle.load(f)
with open("euk_apw_spoofs.pkl") as f:
euk_apw_spoofs = cPickle.load(f)
with open("euk_psfm_spoofs.pkl") as f:
euk_psfm_spoofs = cPickle.load(f)
#--------
prok_ics = map(motif_ic, prok_motifs)
prok_mis = map(mi_per_col, prok_motifs)
prok_maxent_ics = [mean(map(motif_ic, xs)) for xs in prok_maxent_spoofs]
prok_maxent_mis = [mean(map(mi_per_col, xs)) for xs in prok_maxent_spoofs]
prok_psfm_ics = [mean(map(motif_ic, xs)) for xs in prok_psfm_spoofs]
prok_psfm_mis = [
mean(map(mi_per_col, xs)) for xs in tqdm(prok_psfm_spoofs)
]
prok_bayes_ics = [mean(map(motif_ic, xs)) for xs in prok_bayes_spoofs]
prok_bayes_mis = [
mean(map(mi_per_col, xs)) for xs in tqdm(prok_bayes_spoofs)
]
prok_apw_ics = [mean(map(motif_ic, xs)) for xs in prok_apw_spoofs]
prok_apw_mis = [mean(map(mi_per_col, xs)) for xs in prok_apw_spoofs]
prok_ics_pp = map(motif_ic_per_col, prok_motifs)
prok_maxent_ics_pp = [
mean(map(motif_ic_per_col, xs)) for xs in prok_maxent_spoofs
]
prok_psfm_ics_pp = [
mean(map(motif_ic_per_col, xs)) for xs in prok_psfm_spoofs
]
prok_bayes_ics_pp = [
mean(map(motif_ic_per_col, xs)) for xs in prok_bayes_spoofs
]
prok_apw_ics_pp = [
mean(map(motif_ic_per_col, xs)) for xs in prok_apw_spoofs
]
#--------
euk_ics = map(motif_ic, tqdm(euk_submotifs))
euk_mis = map(mi_per_col, tqdm(euk_submotifs))
euk_maxent_ics = [
mean(map(motif_ic, xs)) for xs in tqdm(euk_maxent_spoofs)
]
euk_maxent_mis = [
mean(map(mi_per_col, xs)) for xs in tqdm(euk_maxent_spoofs)
]
euk_psfm_ics = [mean(map(motif_ic, xs)) for xs in tqdm(euk_psfm_spoofs)]
euk_psfm_mis = [mean(map(mi_per_col, xs)) for xs in tqdm(euk_psfm_spoofs)]
euk_bayes_ics = [mean(map(motif_ic, xs)) for xs in tqdm(euk_bayes_spoofs)]
euk_bayes_mis = [
mean(map(mi_per_col, xs)) for xs in tqdm(euk_bayes_spoofs)
]
euk_apw_ics = [mean(map(motif_ic, xs)) for xs in tqdm(euk_apw_spoofs)]
euk_apw_mis = [mean(map(mi_per_col, xs)) for xs in tqdm(euk_apw_spoofs)]
euk_ics_pp = map(motif_ic_per_col, euk_motifs)
euk_maxent_ics_pp = [
mean(map(motif_ic_per_col, xs)) for xs in euk_maxent_spoofs
]
euk_psfm_ics_pp = [
mean(map(motif_ic_per_col, xs)) for xs in euk_psfm_spoofs
]
euk_bayes_ics_pp = [
mean(map(motif_ic_per_col, xs)) for xs in euk_bayes_spoofs
]
euk_apw_ics_pp = [mean(map(motif_ic_per_col, xs)) for xs in euk_apw_spoofs]
#ic_min, ic_max, mi_min, mi_max = 4.5, 25, -0.1, 0.7
ic_min, ic_max, mi_min, mi_max = -.1, 2.6, -0.05, 1
#ic_xtext, ic_ytext, mi_xtext, mi_ytext = 5, 20, -0.05, 0.5
ic_xtext, ic_ytext, mi_xtext, mi_ytext = -0.05, 2.2, -0.05, 0.85
mi_xticks = [0, 0.25, 0.5, 0.75, 1]
ic_yticks = [0, 0.5, 1, 1.5, 2]
revscatter = lambda xs, ys: scatter(ys, xs)
sns.set_style('dark')
plt.subplot(4, 4, 1)
plt.xticks([])
#plt.yticks([])
plt.yticks(ic_yticks, ic_yticks)
r, p = revscatter(prok_ics_pp, prok_maxent_ics_pp)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, prok_ics_pp,
prok_maxent_ics_pp)))
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
plt.text(ic_xtext, ic_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.ylabel("MaxEnt", fontsize='large')
plt.subplot(4, 4, 3)
plt.xticks([])
plt.yticks(mi_xticks, mi_xticks)
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(prok_mis, prok_maxent_mis)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, prok_mis, prok_maxent_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4, 4, 5)
plt.xticks([])
#plt.yticks([])
plt.yticks(ic_yticks, ic_yticks)
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(prok_ics_pp, prok_psfm_ics_pp)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, prok_ics_pp, prok_psfm_ics_pp)))
plt.text(ic_xtext, ic_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.ylabel("PSFM", fontsize='large')
plt.subplot(4, 4, 7)
plt.xticks([])
plt.yticks(mi_xticks, mi_xticks)
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(prok_mis, prok_psfm_mis)
rmsd = sqrt(mean(zipWith(lambda x, y: (x - y)**2, prok_mis,
prok_psfm_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4, 4, 9)
plt.xticks([])
#plt.yticks([])
plt.yticks(ic_yticks, ic_yticks)
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(prok_ics_pp, prok_apw_ics_pp)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, prok_ics_pp, prok_apw_ics_pp)))
plt.text(ic_xtext, ic_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.ylabel("APW", fontsize='large')
#plt.xlabel("IC (bits)",fontsize='large')
plt.subplot(4, 4, 11)
plt.xticks([])
plt.yticks(mi_xticks, mi_xticks)
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(prok_mis, prok_apw_mis)
rmsd = sqrt(mean(zipWith(lambda x, y: (x - y)**2, prok_mis, prok_apw_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4, 4, 13)
#plt.xticks([])
plt.yticks(ic_yticks, ic_yticks)
plt.xticks(ic_yticks, ic_yticks)
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(prok_ics_pp, prok_bayes_ics_pp)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, prok_ics_pp, prok_bayes_ics_pp)))
plt.text(ic_xtext, ic_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.xlabel("Prok IC", fontsize='large')
plt.ylabel("Bayes", fontsize='large')
plt.subplot(4, 4, 15)
#plt.xticks([])
plt.xticks(mi_xticks, mi_xticks)
plt.yticks(mi_xticks, mi_xticks)
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(prok_mis, prok_bayes_mis)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, prok_mis, prok_bayes_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.xlabel("Prok MI", fontsize='large')
#--- euk plots ---#
plt.subplot(4, 4, 2)
plt.xticks([])
plt.yticks([])
r, p = revscatter(euk_ics_pp, euk_maxent_ics_pp)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, euk_ics_pp, euk_maxent_ics_pp)))
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
plt.text(ic_xtext, ic_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
#plt.ylabel("MaxEnt",fontsize='large')
plt.subplot(4, 4, 4)
plt.xticks([])
plt.yticks([])
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(euk_mis, euk_maxent_mis)
rmsd = sqrt(mean(zipWith(lambda x, y: (x - y)**2, euk_mis,
euk_maxent_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4, 4, 6)
plt.xticks([])
plt.yticks([])
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(euk_ics_pp, euk_psfm_ics_pp)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, euk_ics_pp, euk_psfm_ics_pp)))
plt.text(ic_xtext, ic_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
#plt.ylabel("PSFM",fontsize='large')
plt.subplot(4, 4, 8)
plt.xticks([])
plt.yticks([])
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(euk_mis, euk_psfm_mis)
rmsd = sqrt(mean(zipWith(lambda x, y: (x - y)**2, euk_mis, euk_psfm_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4, 4, 10)
plt.xticks([])
plt.yticks([])
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(euk_ics_pp, euk_apw_ics_pp)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, euk_ics_pp, euk_apw_ics_pp)))
plt.text(ic_xtext, ic_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
#plt.ylabel("APW",fontsize='large')
#plt.xlabel("IC (bits)",fontsize='large')
plt.subplot(4, 4, 12)
plt.xticks([])
plt.yticks([])
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(euk_mis, euk_apw_mis)
rmsd = sqrt(mean(zipWith(lambda x, y: (x - y)**2, euk_mis, euk_apw_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4, 4, 14)
#plt.xticks([])
#
plt.yticks([])
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(euk_ics_pp, euk_bayes_ics_pp)
rmsd = sqrt(
mean(zipWith(lambda x, y: (x - y)**2, euk_ics_pp, euk_bayes_ics_pp)))
plt.text(ic_xtext, ic_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
#plt.ylabel("Bayes",fontsize='large')
plt.xlabel("Euk IC", fontsize='large')
plt.subplot(4, 4, 16)
#plt.xticks([])
plt.xticks(mi_xticks, mi_xticks)
plt.yticks([])
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(euk_mis, euk_bayes_mis)
rmsd = sqrt(mean(zipWith(lambda x, y: (x - y)**2, euk_mis, euk_bayes_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext * 0.8, s='$RMSD$ = %1.3f' % rmsd)
#plt.axis('off')
#plt.xlabel("MI (bits/column pair)",fontsize='large')
plt.xlabel("Euk MI", fontsize='large')
plt.tight_layout()
maybesave("spoof-statistics-rmsd.pdf")
def prop(_):
return sample_from_psfm(tilted_psfm)
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
ans_ref = ((N * L * log(4)) + log_perc_below_threshold)
ans = N * log_Zs
return ans
def log_ZS_importance((matrix, mu, Ne), trials=1000):
L = len(matrix)
psfm = psfm_from_matrix(matrix)
log_psfm = [[log(p) for p in row] for row in psfm]
log_psfm_prob = lambda site: score_seq(log_psfm, site)
sites = [sample_from_psfm(psfm) for _ in xrange(trials)]
mean_ZS = mean(
exp(
log_fhat((matrix, mu, Ne), [site]) + log(1.0 / 4**L) -
log_psfm_prob(site)) for site in sites)
ZS = 4**L * mean_ZS
return log(ZS)
def log_ZS_importance_ref((matrix, mu, Ne), trials=1000):
L = len(matrix)
psfm = [[0.25] * 4 for _ in range(L)]
log_psfm = [[log(p) for p in row] for row in psfm]
log_psfm_prob = lambda site: score_seq(log_psfm, site)
sites = [sample_from_psfm(psfm) for _ in xrange(trials)]
mean_ZS = mean(
def prop(_):
return sample_from_psfm(tilted_psfm)
def main_experiment(generate_data=False):
if generate_data:
iterations = 10000
prok_chains = [posterior_chain2(motif,iterations=iterations) for motif in tqdm(prok_motifs)]
prok_bayes_spoofs = [[motif_from_theta(theta, len(motif)) for theta in tqdm(chain[iterations/2::500])]
for chain, motif in tqdm(zip(prok_chains, prok_motifs))]
prok_psfms = [psfm_from_motif(motif, pc=1/4.0) for motif in prok_motifs]
prok_psfm_spoofs = [[[sample_from_psfm(psfm) for _ in range(len(motif))] for _ in range(10)]
for psfm, motif in zip(prok_psfms, prok_motifs)]
prok_maxent_spoofs = [spoof_maxent_motifs(motif, 10) for motif in tqdm(prok_motifs)]
prok_apws = map(lambda m:code_from_motif(m, pc=1/16.0),tqdm(prok_motifs))
prok_apw_spoofs = [[[sample_site(apw) for _ in range(len(motif))] for __ in range(10)]
for apw, motif in tqdm(zip(prok_apws,prok_motifs))]
euk_submotifs = map(subsample, euk_motifs)
euk_chains = [posterior_chain2(motif,iterations=iterations) for motif in tqdm(euk_submotifs)]
euk_bayes_spoofs = [[motif_from_theta(theta, len(motif)) for theta in tqdm(chain[iterations/2::500])]
for chain, motif in tqdm(zip(euk_chains, euk_submotifs))]
euk_psfms = [psfm_from_motif(motif, pc=1/4.0) for motif in euk_submotifs]
euk_psfm_spoofs = [[[sample_from_psfm(psfm) for _ in range(len(motif))] for _ in range(10)]
for psfm, motif in zip(euk_psfms, euk_submotifs)]
euk_maxent_spoofs = [spoof_maxent_motifs(motif, 10) for motif in tqdm(euk_submotifs)]
euk_apws = map(lambda m:code_from_motif(m, pc=1/16.0),tqdm(euk_submotifs))
euk_apw_spoofs = [[[sample_site(apw) for _ in range(len(motif))] for __ in range(10)]
for apw, motif in tqdm(zip(euk_apws,euk_submotifs))]
with open("prok_chains.pkl",'w') as f:
cPickle.dump(prok_chains,f)
with open("prok_bayes_spoofs.pkl",'w') as f:
cPickle.dump(prok_bayes_spoofs,f)
with open("prok_maxent_spoofs.pkl",'w') as f:
cPickle.dump(prok_maxent_spoofs,f)
with open("prok_psfm_spoofs.pkl",'w') as f:
cPickle.dump(prok_psfm_spoofs,f)
with open("prok_apw_spoofs.pkl",'w') as f:
cPickle.dump(prok_apw_spoofs,f)
with open("euk_submotifs.pkl",'w') as f:
cPickle.dump(euk_submotifs,f)
with open("euk_chains.pkl",'w') as f:
cPickle.dump(euk_chains,f)
with open("euk_bayes_spoofs.pkl",'w') as f:
cPickle.dump(euk_bayes_spoofs,f)
with open("euk_maxent_spoofs.pkl",'w') as f:
cPickle.dump(euk_maxent_spoofs,f)
with open("euk_psfm_spoofs.pkl",'w') as f:
cPickle.dump(euk_psfm_spoofs,f)
with open("euk_apw_spoofs.pkl",'w') as f:
cPickle.dump(euk_apw_spoofs,f)
else:
with open("prok_chains.pkl") as f:
prok_chains = cPickle.load(f)
with open("prok_bayes_spoofs.pkl") as f:
prok_bayes_spoofs = cPickle.load(f)
with open("prok_maxent_spoofs.pkl") as f:
prok_maxent_spoofs = cPickle.load(f)
with open("prok_psfm_spoofs.pkl") as f:
prok_psfm_spoofs = cPickle.load(f)
with open("prok_apw_spoofs.pkl") as f:
prok_apw_spoofs = cPickle.load(f)
with open("euk_submotifs.pkl") as f:
euk_submotifs = cPickle.load(f)
with open("euk_chains.pkl") as f:
euk_chains = cPickle.load(f)
with open("euk_bayes_spoofs.pkl") as f:
euk_bayes_spoofs = cPickle.load(f)
with open("euk_maxent_spoofs.pkl") as f:
euk_maxent_spoofs = cPickle.load(f)
with open("euk_apw_spoofs.pkl") as f:
euk_apw_spoofs = cPickle.load(f)
with open("euk_psfm_spoofs.pkl") as f:
euk_psfm_spoofs = cPickle.load(f)
#--------
prok_ics = map(motif_ic, prok_motifs)
prok_mis = map(mi_per_col, prok_motifs)
prok_maxent_ics = [mean(map(motif_ic,xs)) for xs in prok_maxent_spoofs]
prok_maxent_mis = [mean(map(mi_per_col,xs)) for xs in prok_maxent_spoofs]
prok_psfm_ics = [mean(map(motif_ic,xs)) for xs in prok_psfm_spoofs]
prok_psfm_mis = [mean(map(mi_per_col,xs)) for xs in tqdm(prok_psfm_spoofs)]
prok_bayes_ics = [mean(map(motif_ic,xs)) for xs in prok_bayes_spoofs]
prok_bayes_mis = [mean(map(mi_per_col,xs)) for xs in tqdm(prok_bayes_spoofs)]
prok_apw_ics = [mean(map(motif_ic,xs)) for xs in prok_apw_spoofs]
prok_apw_mis = [mean(map(mi_per_col,xs)) for xs in prok_apw_spoofs]
prok_ics_pp = map(motif_ic_per_col, prok_motifs)
prok_maxent_ics_pp = [mean(map(motif_ic_per_col,xs)) for xs in prok_maxent_spoofs]
prok_psfm_ics_pp = [mean(map(motif_ic_per_col,xs)) for xs in prok_psfm_spoofs]
prok_bayes_ics_pp = [mean(map(motif_ic_per_col,xs)) for xs in prok_bayes_spoofs]
prok_apw_ics_pp = [mean(map(motif_ic_per_col,xs)) for xs in prok_apw_spoofs]
#--------
euk_ics = map(motif_ic, tqdm(euk_submotifs))
euk_mis = map(mi_per_col, tqdm(euk_submotifs))
euk_maxent_ics = [mean(map(motif_ic,xs)) for xs in tqdm(euk_maxent_spoofs)]
euk_maxent_mis = [mean(map(mi_per_col,xs)) for xs in tqdm(euk_maxent_spoofs)]
euk_psfm_ics = [mean(map(motif_ic,xs)) for xs in tqdm(euk_psfm_spoofs)]
euk_psfm_mis = [mean(map(mi_per_col,xs)) for xs in tqdm(euk_psfm_spoofs)]
euk_bayes_ics = [mean(map(motif_ic,xs)) for xs in tqdm(euk_bayes_spoofs)]
euk_bayes_mis = [mean(map(mi_per_col,xs)) for xs in tqdm(euk_bayes_spoofs)]
euk_apw_ics = [mean(map(motif_ic,xs)) for xs in tqdm(euk_apw_spoofs)]
euk_apw_mis = [mean(map(mi_per_col,xs)) for xs in tqdm(euk_apw_spoofs)]
euk_ics_pp = map(motif_ic_per_col, euk_motifs)
euk_maxent_ics_pp = [mean(map(motif_ic_per_col,xs)) for xs in euk_maxent_spoofs]
euk_psfm_ics_pp = [mean(map(motif_ic_per_col,xs)) for xs in euk_psfm_spoofs]
euk_bayes_ics_pp = [mean(map(motif_ic_per_col,xs)) for xs in euk_bayes_spoofs]
euk_apw_ics_pp = [mean(map(motif_ic_per_col,xs)) for xs in euk_apw_spoofs]
#ic_min, ic_max, mi_min, mi_max = 4.5, 25, -0.1, 0.7
ic_min, ic_max, mi_min, mi_max = -.1, 2.6, -0.05, 1
#ic_xtext, ic_ytext, mi_xtext, mi_ytext = 5, 20, -0.05, 0.5
ic_xtext, ic_ytext, mi_xtext, mi_ytext = -0.05, 2.2, -0.05, 0.85
mi_xticks = [0, 0.25, 0.5, 0.75, 1]
ic_yticks = [0, 0.5, 1, 1.5, 2]
revscatter = lambda xs, ys:scatter(ys, xs)
sns.set_style('dark')
plt.subplot(4,4,1)
plt.xticks([])
#plt.yticks([])
plt.yticks(ic_yticks, ic_yticks)
r, p = revscatter(prok_ics_pp, prok_maxent_ics_pp)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, prok_ics_pp, prok_maxent_ics_pp)))
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
plt.text(ic_xtext, ic_ytext,s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.ylabel("MaxEnt",fontsize='large')
plt.subplot(4,4,3)
plt.xticks([])
plt.yticks(mi_xticks, mi_xticks)
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(prok_mis, prok_maxent_mis)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, prok_mis, prok_maxent_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4,4,5)
plt.xticks([])
#plt.yticks([])
plt.yticks(ic_yticks, ic_yticks)
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(prok_ics_pp, prok_psfm_ics_pp)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, prok_ics_pp, prok_psfm_ics_pp)))
plt.text(ic_xtext, ic_ytext,s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.ylabel("PSFM",fontsize='large')
plt.subplot(4,4,7)
plt.xticks([])
plt.yticks(mi_xticks, mi_xticks)
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(prok_mis, prok_psfm_mis)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, prok_mis, prok_psfm_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4,4,9)
plt.xticks([])
#plt.yticks([])
plt.yticks(ic_yticks, ic_yticks)
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(prok_ics_pp, prok_apw_ics_pp)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, prok_ics_pp, prok_apw_ics_pp)))
plt.text(ic_xtext, ic_ytext,s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.ylabel("APW",fontsize='large')
#plt.xlabel("IC (bits)",fontsize='large')
plt.subplot(4,4,11)
plt.xticks([])
plt.yticks(mi_xticks, mi_xticks)
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(prok_mis, prok_apw_mis)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, prok_mis, prok_apw_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4,4,13)
#plt.xticks([])
plt.yticks(ic_yticks, ic_yticks)
plt.xticks(ic_yticks, ic_yticks)
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(prok_ics_pp, prok_bayes_ics_pp)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, prok_ics_pp, prok_bayes_ics_pp)))
plt.text(ic_xtext, ic_ytext,s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.xlabel("Prok IC",fontsize='large')
plt.ylabel("Bayes",fontsize='large')
plt.subplot(4,4,15)
#plt.xticks([])
plt.xticks(mi_xticks, mi_xticks)
plt.yticks(mi_xticks, mi_xticks)
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(prok_mis, prok_bayes_mis)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, prok_mis, prok_bayes_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.xlabel("Prok MI",fontsize='large')
#--- euk plots ---#
plt.subplot(4,4,2)
plt.xticks([])
plt.yticks([])
r, p = revscatter(euk_ics_pp, euk_maxent_ics_pp)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, euk_ics_pp, euk_maxent_ics_pp)))
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
plt.text(ic_xtext, ic_ytext,s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
#plt.ylabel("MaxEnt",fontsize='large')
plt.subplot(4,4,4)
plt.xticks([])
plt.yticks([])
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(euk_mis, euk_maxent_mis)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, euk_mis, euk_maxent_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4,4,6)
plt.xticks([])
plt.yticks([])
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(euk_ics_pp, euk_psfm_ics_pp)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, euk_ics_pp, euk_psfm_ics_pp)))
plt.text(ic_xtext, ic_ytext,s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
#plt.ylabel("PSFM",fontsize='large')
plt.subplot(4,4,8)
plt.xticks([])
plt.yticks([])
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(euk_mis, euk_psfm_mis)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, euk_mis, euk_psfm_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4,4,10)
plt.xticks([])
plt.yticks([])
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(euk_ics_pp, euk_apw_ics_pp)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, euk_ics_pp, euk_apw_ics_pp)))
plt.text(ic_xtext, ic_ytext,s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
#plt.ylabel("APW",fontsize='large')
#plt.xlabel("IC (bits)",fontsize='large')
plt.subplot(4,4,12)
plt.xticks([])
plt.yticks([])
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(euk_mis, euk_apw_mis)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, euk_mis, euk_apw_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
plt.subplot(4,4,14)
#plt.xticks([])
#
plt.yticks([])
plt.xlim(ic_min, ic_max)
plt.ylim(ic_min, ic_max)
r, p = revscatter(euk_ics_pp, euk_bayes_ics_pp)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, euk_ics_pp, euk_bayes_ics_pp)))
plt.text(ic_xtext, ic_ytext,s='$r^2$ = %1.3f' % (r**2))
plt.text(ic_xtext, ic_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
#plt.ylabel("Bayes",fontsize='large')
plt.xlabel("Euk IC",fontsize='large')
plt.subplot(4,4,16)
#plt.xticks([])
plt.xticks(mi_xticks, mi_xticks)
plt.yticks([])
plt.xlim(mi_min, mi_max)
plt.ylim(mi_min, mi_max)
r, p = revscatter(euk_mis, euk_bayes_mis)
rmsd = sqrt(mean(zipWith(lambda x,y:(x-y)**2, euk_mis, euk_bayes_mis)))
plt.text(mi_xtext, mi_ytext, s='$r^2$ = %1.3f' % (r**2))
plt.text(mi_xtext, mi_ytext*0.8,s='$RMSD$ = %1.3f' % rmsd)
#plt.axis('off')
#plt.xlabel("MI (bits/column pair)",fontsize='large')
plt.xlabel("Euk MI",fontsize='large')
plt.tight_layout()
maybesave("spoof-statistics-rmsd.pdf")
def log_Z_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
ans_ref = ((N*L * log(4)) + log_perc_below_threshold)
ans = N * log_Zs
return ans
def log_ZS_importance((matrix, mu, Ne), trials=1000):
L = len(matrix)
psfm = psfm_from_matrix(matrix)
log_psfm = [[log(p) for p in row] for row in psfm]
log_psfm_prob = lambda site:score_seq(log_psfm, site)
sites = [sample_from_psfm(psfm) for _ in xrange(trials)]
mean_ZS = mean(exp(log_fhat((matrix, mu, Ne), [site]) + log(1.0/4**L) - log_psfm_prob(site))
for site in sites)
ZS = 4**L * mean_ZS
return log(ZS)
def log_ZS_importance_ref((matrix, mu, Ne), trials=1000):
L = len(matrix)
psfm = [[0.25]*4 for _ in range(L)]
log_psfm = [[log(p) for p in row] for row in psfm]
log_psfm_prob = lambda site:score_seq(log_psfm, site)
sites = [sample_from_psfm(psfm) for _ in xrange(trials)]
mean_ZS = mean(exp(log_fhat((matrix, mu, Ne), [site]) + log(1.0/4**L) - log_psfm_prob(site))
for site in sites)
ZS = 4**L * mean_ZS
return log(ZS)