def compute_coefficients_ref(ks):
"""given ks, the roots of a polynomial P(x) = a_n x^n+...+a_1x^1+a_0,
compute sequence of coefficients a_n...a_0"""
coeffs = [1]
for k in ks:
coeffs = zipWith(lambda x,y:x+y,coeffs+[0],[0]+[-k*c for c in coeffs])
return coeffs
def sample_path_ref2(qf,koffs,t_final,chromosome=None,verbose=False):
"""Simulate a sample path until time t_final and return the marginal occupancies.
Integrates update, sample_path_ref framework.
"""
if chromosome is None: # then start from empty chromosome
chromosome = [0] * len(koffs)
t = 0
dt = 0
occs = [0 for c in chromosome]
while t < t_final:
rates = [koffs[i] if bs else qf for i,bs in enumerate(chromosome)]
sum_rate = sum(rates)
dt = random.expovariate(sum_rate)
t += dt
if t > t_final:
dt = t_final - t + dt
# update occupancies after deciding dt, before updating chromosome
occs = zipWith(lambda occ,ch:occ + ch*dt,occs,chromosome)
idx = inverse_cdf_sample(range(G),normalize(rates))
if chromosome[idx]: # if reaction is an unbinding reaction...
if verbose:
print "unbinding at: ",idx
chromosome[idx] = 0
qf += 1
else: # a binding reaction...
if verbose:
print "binding at: ",idx
chromosome[idx] = 1
qf -= 1
if verbose:
print "t:",t,"dt:",dt,"q:",qf,"qbound:",sum(chromosome),"mean occ:",sum([occ/t for occ in occs])
return [occ/t_final for occ in occs]
def sample_path_ref(qf,koffs,t_final,chromosome=None,verbose=False):
"""Simulate a sample path until time t_final and return the marginal occupancies"""
if chromosome is None: # then start from empty chromosome
chromosome = [0] * len(koffs)
chrom = chromosome[:]
new_chrom = chrom[:]
occupancies = [0 for c in chromosome]
t = 0
dt = 0
while t < t_final:
new_chrom,qf,dt = update(chrom,qf,koffs,verbose=verbose)
t += dt
# This ugly bit of code ensures that we only track the
# occupancies until exactly time t_final.
if t > t_final:
dt = t_final - t + dt
occupancies = zipWith(lambda occ,ch:occ + ch*dt,occupancies,chrom)
chrom = new_chrom[:]
if verbose:
print "t:",t,"dt:",dt,"q:",qf,"qbound:",sum(chrom),"mean occ:",sum([occ/t for occ in occupancies])
return [occ/t_final for occ in occupancies]
def mutation_matrix_ref(mu,w,mode="continuous",stochastic=False):
"mutation matrix for w columns at rate mu"
K = int(4**w)
M = np.zeros((K,K))
if mode == "continuous":
"""M is a transition rate matrix"""
res = 0
else:
"""M is a stochastic matrix"""
res = 1
for i,kmer_i in enumerate(make_kmers(w)):
sanity = 0
if not stochastic or (stochastic and random.random() < mu):
for j,kmer_j in enumerate(make_kmers(w)):
distance = w - sum(zipWith(lambda x,y:x==y,kmer_i,kmer_j))
if distance == 0:
M[i][j] = res - 3*w*mu
elif distance == 1:
M[i][j] = mu
sanity += 1
else:
M[i][i] = res
return np.transpose(M)
def update(self, final_time):
# Compute propensities
propensities = [propensity(self.state, self.time) for propensity in self.propensities]
self.logging(propensities)
p = sum(propensities) # rate of sum of random variables
# determine time of next reaction
if p == 0:
raise Exception("No possible reactions")
dt = rexp(p)
# optimize next line later
# determine which reaction
new_time = self.time + dt
if new_time < final_time:
v = inverse_cdf_sample(self.stoich_vectors, normalize(propensities))
# update state vector
self.state = zipWith(lambda x, y: x + y, self.state, v)
self.time = new_time
self.logging(str(self.time) + " " + str(self.state))
self.history.append((self.time, self.state))
# print self.state
self.reactions_performed += 1
else:
self.finished_run = True
def equilibrate(qtot, koffs, dt=0.01, iterations=1000):
q = qtot
ss = [0 for k in koffs]
def dqdt():
ans = -q * sum((1 - s) for s in ss) + sum(k * s for s, k in zip(ss, koffs))
# print "dqdt:",ans
return ans
def dsidt(i):
si = ss[i]
ki = koffs[i]
ans = q * (1 - si) - ki * si
# print "dsdt ",i,":",ans
return ans
for iteration in xrange(iterations):
dq = dqdt()
dssdt = [dsidt(i) for i, k in enumerate(koffs)]
q = q + dq * dt
ss = zipWith(lambda s, ds: s + ds * dt, ss, dssdt)
if iteration % 1000 == 0:
print q # ,ss,q + sum(ss)
return ss
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 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")
