def motif_degradation_experiment():
"""what is the effect of repeatedly inferring a motif from selected sites?"""
from motifs import Escherichia_coli
motif = Escherichia_coli.LexA
n = len(motif)
matrix = matrix_from_motif(motif)
assumed_copies = 10 * n
mu = approximate_mu(matrix, assumed_copies, G)
for i in range(10):
print i, "motif ic:", motif_ic(motif)
motif = select_sites_by_occupancy(matrix, mu, n)
matrix = matrix_from_motif(motif)
def restriction_of_range_half_site_experiment(motif):
"""is energy of first half-site negatively correlated with energy of second half-site?"""
L = len(motif[0])
l = L/2
mat = matrix_from_motif(motif)
eps1 = [score_seq(mat[:l], site[:l]) for site in motif]
eps2 = [score_seq(mat[l:], site[l:]) for site in motif]
return pearsonr(eps1,eps2)
def restriction_of_range_motif_spoof_experiment(motifs):
all_eps = []
all_spoof_eps = []
for motif in tqdm(motifs):
mat = matrix_from_motif(motif)
eps = [score_seq(mat, site) for site in motif]
spoofs = spoof_psfm(motif, pc=0)
spoof_eps = [score_seq(mat, site) for site in spoofs]
all_eps.append(eps)
all_spoof_eps.append(spoof_eps)
return all_eps, all_spoof_eps
def spoof_motif(motif, Ne=None, iterations=10000):
matrix = matrix_from_motif(motif)
L = len(motif[0])
n = len(motif)
sigma = sigma_from_matrix(matrix)
spoof_matrix = sample_matrix(L, sigma)
bio_ic = motif_ic(motif)
# this method of reading site_mu, site_sigma off of motif is slightly suspect...
site_mu = site_mu_from_matrix(matrix_from_motif(motif))
site_sigma = site_sigma_from_matrix(matrix_from_motif(motif))
# now need to find mu, nu
n = len(motif)
assumed_copies = 10 * n
mu = approximate_mu(matrix, assumed_copies, G)
spoof_mu = approximate_mu(spoof_matrix, assumed_copies, G)
if Ne is None:
Ne = estimate_Ne(spoof_matrix, spoof_mu, n, bio_ic)
print "chose Ne:", Ne
spoof_matrix, chain = sella_hirsch_mh(Ne=Ne,
matrix=spoof_matrix,
mu=mu,
n=n)
return spoof_matrix, chain, Ne
def restriction_of_range_loo_experiment(motif):
"""can energy of a given position be predicted from energy of remaining bases?"""
L = len(motif[0])
mat = matrix_from_motif(motif)
eps = [score_seq(mat,site) for site in motif]
mean_ep = mean(eps)
results = []
for j in range(L):
print j
loo_mat = mat[:j] + mat[j+1:]
for site in motif:
loo_ep = score_seq(loo_mat,site[:j] + site[j+1:])
pred_ep = mean_ep - loo_ep
obs_ep = score_seq([mat[j]],[site[j]])
results.append((pred_ep, obs_ep))
return results
def spoof_motifs_occ(motif, num_motifs=10, trials=1, sigma=None,Ne_tol=10**-4,double_sigma=True):
N = len(motif)
L = len(motif[0])
copies = 10*N
if sigma is None:
sigma = sigma_from_matrix(pssm_from_motif(motif,pc=1))
epsilon = (1+double_sigma)*sigma # 15 Jan 2016
print "sigma:", sigma
#bio_ic = motif_ic(motif)
mat = matrix_from_motif(motif)
eps = [score_seq(mat, site) for site in motif]
mu = gle_approx_mu(mat, copies)
bio_occ = mean([1/(1+exp(ep-mu)) for ep in eps])
def f(Ne):
return expected_occupancy(epsilon, Ne, L, copies) - bio_occ
Ne = log_regress_spec2(f,[1,10],tol=10**-3)
return [sample_motif(sigma, Ne, L, copies, N) for _ in range(num_motifs)]
def analyze_bio_motifs(Nes,trials=20):
results = {}
for tf_idx,tf in enumerate(Escherichia_coli.tfs):
Ne = Nes[tf]
bio_motif = getattr(Escherichia_coli,tf)
n,L = len(bio_motif),len(bio_motif[0])
bio_matrix = matrix_from_motif(bio_motif)
sigma = sigma_from_matrix(bio_matrix)
matrix_chains = [sella_hirsch_mh(n=n,L=L,sigma=sigma,Ne=Ne,init='ringer') for i in range(trials)]
ics = [mean(map(motif_ic,chain[-1000:])) for (matrix,chain) in matrix_chains]
ginis = [mean(map(motif_gini,chain[-1000:])) for (matrix,chain) in matrix_chains]
mis = [mean(map(total_motif_mi,chain[-1000:])) for (matrix,chain) in matrix_chains]
print "results for:",tf,tf_idx
print motif_ic(bio_motif),mean(ics),sd(ics)
print motif_gini(bio_motif),mean(ginis),sd(ginis)
print total_motif_mi(bio_motif),mean(mis),sd(mis)
results[tf] = (mean(ics),sd(ics),mean(ginis),sd(ginis),mean(mis),sd(mis))
return results
def main_experiment(samples=30, iterations=10000, delta_ic=0.1):
results_dict = {}
for tf_idx, tf in enumerate(tfdf.tfs):
print "starting on:", tf
motif = getattr(tfdf, tf)
if motif_ic(motif) < 5:
print "excluding", tf, "for low IC"
continue
bio_ic = motif_ic(motif)
n = len(motif)
L = len(motif[0])
matrix = matrix_from_motif(motif)
sigma = sigma_from_matrix(matrix)
mu = approximate_mu(matrix, n, G)
Ne = estimate_Ne(matrix, mu, n, bio_ic)
spoofs = []
ar = 0
spoof_trials = 0.0
while len(spoofs) < samples:
spoof_trials += 1
matrix, chain = sella_hirsch_mh(Ne=Ne,
mu=mu,
n=1,
matrix=sample_matrix(L, sigma),
init='ringer',
iterations=iterations)
spoof_motif = concat(
[random.choice(chain[iterations / 2:]) for i in range(n)])
if abs(motif_ic(spoof_motif) - bio_ic) < delta_ic:
spoofs.append(spoof_motif)
ar += 1
print "spoof acceptance rate:", ar / spoof_trials, len(
spoofs), samples, spoof_trials
#spoofs = [chain[-1] for (spoof_matrix,chain,Ne) in [spoof_motif(motif,Ne) for i in range(samples)]]
results_dict[tf] = {
fname: map(eval(fname), spoofs)
for fname in "motif_ic motif_gini total_motif_mi".split()
}
print "finished:", tf, "(%s/%s)" % (tf_idx, len(tfdf.tfs))
print bio_ic, mean_ci(results_dict[tf]['motif_ic'])
return results_dict
def spoof_motifs_occ(motif,
num_motifs=10,
trials=1,
sigma=None,
Ne_tol=10**-4,
double_sigma=True):
N = len(motif)
L = len(motif[0])
copies = 10 * N
if sigma is None:
sigma = sigma_from_matrix(pssm_from_motif(motif, pc=1))
epsilon = (1 + double_sigma) * sigma # 15 Jan 2016
print "sigma:", sigma
#bio_ic = motif_ic(motif)
mat = matrix_from_motif(motif)
eps = [score_seq(mat, site) for site in motif]
mu = gle_approx_mu(mat, copies)
bio_occ = mean([1 / (1 + exp(ep - mu)) for ep in eps])
def f(Ne):
return expected_occupancy(epsilon, Ne, L, copies) - bio_occ
Ne = log_regress_spec2(f, [1, 10], tol=10**-3)
return [sample_motif(sigma, Ne, L, copies, N) for _ in range(num_motifs)]
def score_sd(motif):
matrix = matrix_from_motif(motif)
eps = [score_seq(matrix, site) for site in motif]
return sd(eps)