def cumsum_test():
arca_reads = get_arca_reads(1000000)
true_rdm = density_from_reads(arca_reads, G)
pssm = make_pssm(Escherichia_coli.ArcA)
comb_rdm = true_rdm[0] + true_rdm[1]
print "fwd_scores"
fwd_scores = score_genome_np(pssm, genome)
print "rev_scores"
rev_scores = score_genome_np(pssm, wc(genome))
scores = np.log(np.exp(fwd_scores) + np.exp(rev_scores))
probs = np.exp(scores)/np.sum(np.exp(scores))
print "sorting scores"
score_js = sorted_indices(scores)[::-1] # order scores from greatest to least
print "sorting probs"
prob_js = sorted_indices(probs)[::-1] # ditto
plt.plot(cumsum(rslice(comb_rdm, score_js)), label="scores")
plt.plot(cumsum(rslice(comb_rdm, prob_js)), label="boltzmann probs")
comb_rdm_copy = list(comb_rdm)
controls = 5
for i in range(controls):
print i
random.shuffle(comb_rdm_copy)
plt.plot(cumsum(comb_rdm_copy), color='r')
plt.legend(loc=0)
plt.xlim(0, 1)
plt.ylim(0, 1)
plt.show()
def make_correlation_structure_by_length():
q = fdr(concat(euk_tests))
plt.close() # get rid of output from cluster_motif
lens = map(len, euk_motifs)
jss = [indices_where(lens, lambda x:10**i <= x < 10**(i+1)) for i in range(1, 4+1)]
for i,js in tqdm(enumerate(jss)):
analyze_mi_tests2(rslice(euk_tests, js), rslice(euk_motifs, js), label=str("10**%s" % (i+1)), q=q)
def make_correlation_structure_by_cluster_figure():
from motif_clustering import cluster_motif
q = fdr(concat(euk_tests))
euk_clusterses = [map(cluster_motif, tqdm(euk_motifs)) for i in range(3)]
plt.close() # get rid of output from cluster_motif
mean_lens = map(lambda xs:round(mean(xs)), transpose([map(len,cs) for cs in euk_clusterses]))
jss = [indices_where(mean_lens, lambda x:x==i) for i in range(1, 5+1)]
for i,js in tqdm(enumerate(jss)):
analyze_mi_tests2(rslice(euk_tests, js), rslice(euk_motifs, js), label=str(i+1), q=q)
def main():
prok_motifs, euk_motifs = get_motifs()
prok_motifs = [
sample(200, motif, replace=False) if len(motif) > 200 else motif
for motif in tqdm(prok_motifs)
]
mis = map(motif_mi, prok_motifs)
js = sorted_indices(mis)
maxent_mis = [
mean(map(motif_mi, spoof_maxent_motifs(motif, 1000)))
for motif in tqdm(prok_motifs)
]
uniform_mis = [
mean(map(motif_mi, spoof_uniform_motifs(motif, 1000)))
for motif in tqdm(prok_motifs)
]
perm_mis = [
mean(map(motif_mi, [perm_motif(motif) for _ in xrange(1000)]))
for motif in tqdm(prok_motifs)
]
plt.plot(rslice(mis, js))
plt.plot(rslice(maxent_mis, js))
plt.plot(rslice(perm_mis, js))
def sample_site_cftp(matrix, mu, Ne):
L = len(matrix)
f = seq_scorer(matrix)
def log_phat(s):
ep = f(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])
#middle_sites = [[random_site(L)] for i in range(10)]
#trajs = [[best_site]] + middle_sites + [[worst_site]]
trajs = [[best_site],[worst_site]]
ords = [rslice("ACGT",sorted_indices(row)) for row in matrix]
def mutate_site(site,(ri,direction)):
b = (site[ri])
idx = ords[ri].index(b)
idxp = min(max(idx + direction,0),3)
bp = ords[ri][idxp]
return subst(site,bp,ri)
def esp_ref(ks,j):
"""compute jth elementary symmetric polynomial on ks"""
n = len(ks)
return sum(product(rslice(ks,comb)) for comb in itertools.combinations(range(n),j))
def linear_interpolate(xs, ys):
js = sorted_indices(xs)
xs = sorted(xs)
ys = rslice(ys, js)
