def analyze_mi_tests(prok_tests, euk_tests):
pass
prok_q = fdr(concat(prok_tests))
euk_q = fdr(concat(euk_tests))
prok_correlated_percentage = count(lambda x:x <= prok_q,(concat(prok_tests)))/float(len(concat(prok_tests)))
euk_correlated_percentage = count(lambda x:x <= euk_q,(concat(euk_tests)))/float(len(concat(euk_tests)))
prok_ds = [[j - i for (i, coli), (j,colj) in choose2(list(enumerate(transpose(motif))))]
for motif in prok_motifs]
euk_ds = [[j - i for (i, coli), (j,colj) in choose2(list(enumerate(transpose(motif))))]
for motif in euk_motifs]
def binom_ci(xs):
"""return width of error bar"""
bs_means = sorted([mean(bs(xs)) for x in range(1000)])
mu = mean(xs)
return (mu - bs_means[25], bs_means[975] - mu)
prok_cis = [binom_ci([t <= prok_q for t,d in zip(concat(prok_tests), concat(prok_ds)) if d == i])
for i in trange(1,20)]
euk_cis = [binom_ci([t <= euk_q for t,d in zip(concat(euk_tests), concat(euk_ds)) if d == i])
for i in trange(1,20)]
plt.errorbar(range(1,20),
[mean([t <= prok_q for t,d in zip(concat(prok_tests), concat(prok_ds)) if d == i])
for i in range(1,20)],yerr=transpose(prok_cis),label="Prokaryotic Motifs",capthick=1)
plt.errorbar(range(1,20),
[mean([t <= euk_q for t,d in zip(concat(euk_tests), concat(euk_ds)) if d == i])
for i in range(1,20)],yerr=transpose(euk_cis),label="Eukaryotic Motifs",capthick=1)
plt.xlabel("Distance (bp)",fontsize="large")
plt.ylabel("Proportion of Significant Correlations",fontsize="large")
plt.legend(fontsize='large')
def on_off_experiment2(num_motifs=100,filename="gini-vs-mi-correlation-in-on-off-spoofs.pdf"):
"""compare MI vs Gini on biological_motifs"""
bio_motifs = [getattr(tfdf,tf) for tf in tfdf.tfs]
Ns = map(len, bio_motifs)
spoofses = [spoof_on_off_motif(motif,num_motifs=num_motifs,trials=1) for motif in bio_motifs]
spoof_ginises = mmap(motif_gini,tqdm(spoofses))
spoof_mises = mmap(total_motif_mi,tqdm(spoofses))
cors, ps = [],[]
for ginis, mis in zip(ginises, mises):
cor, p = pearsonr(ginis,mis)
cors.append(cor)
ps.append(p)
q = fdr(ps)
plt.scatter(cors,ps,filename="gini-vs-mi-correlation-in-on-off-spoofs.pdf")
plt.plot([-1,1],[q,q],linestyle='--',label="FDR-Adjusted Significance Level")
plt.semilogy()
plt.legend()
plt.xlabel("Pearson Correlation Coefficient")
plt.ylabel("P value")
plt.xlim([-1,1])
plt.ylim([10**-4,1+1])
cor_ps = zip(cors,ps)
sig_negs = [(c,p) for (c,p) in cor_ps if c < 0 and p < q]
sig_poses = [(c,p) for (c,p) in cor_ps if c > 0 and p < q]
insigs = [(c,p) for (c,p) in cor_ps if p > q]
def weighted_correlation(cor_p_Ns):
cors,ps,Ns = transpose(cor_p_Ns)
return sum([cor*N for (cor,N) in zip (cors,Ns)])/sum(Ns)
plt.title("Gini-MI Correlation Coefficient vs. P-value for On-Off Simulations from Prokaryotic Motifs")
maybesave(filename)
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 analyze_motif(motif, trials=1000):
cols = transpose(motif)
L = len(cols)
ps = []
for col1, col2 in (choose2(cols)):
actual_mi = dna_mi(col1,col2)
perm_mis = [dna_mi(col1,permute(col2)) for i in xrange(trials)]
p = percentile(actual_mi, perm_mis)
#print p
ps.append(p)
q = fdr(ps)
correlated_pairs = [(i,j) for (i,j),p in zip(choose2(range(L)),ps) if p < q]
num_correlated = len(correlated_pairs)
print "correlated column pairs:", num_correlated, "%1.2f" % ((num_correlated)/choose(L,2))
return correlated_pairs
def analyze_motif(motif, trials=1000):
cols = transpose(motif)
L = len(cols)
ps = []
for col1, col2 in (choose2(cols)):
actual_mi = dna_mi(col1, col2)
perm_mis = [dna_mi(col1, permute(col2)) for i in xrange(trials)]
p = percentile(actual_mi, perm_mis)
#print p
ps.append(p)
q = fdr(ps)
correlated_pairs = [(i, j) for (i, j), p in zip(choose2(range(L)), ps)
if p < q]
num_correlated = len(correlated_pairs)
print "correlated column pairs:", num_correlated, "%1.2f" % (
(num_correlated) / choose(L, 2))
return correlated_pairs
def analyze_mi_tests2(tests, motifs, q=None, label=None):
q = fdr(concat(tests))
correlated_percentage = count(lambda x:x <= q,(concat(tests)))/float(len(concat(tests)))
ds = [[j - i for (i, coli), (j,colj) in choose2(list(enumerate(transpose(motif))))]
for motif in motifs]
def binom_ci(xs):
"""return width of error bar"""
bs_means = sorted([mean(bs(xs)) for x in range(1000)])
mu = mean(xs)
return (mu - bs_means[25], bs_means[975] - mu)
tests_by_dist = [[t <= q for t,d in zip(concat(tests), concat(ds)) if d == i] for i in range(1, 20)]
mean_vals = map(lambda xs:mean(xs) if xs else 0, tests_by_dist)
cis = map(lambda xs:binom_ci(xs) if xs else (0,0), tests_by_dist)
plt.errorbar(range(1,20),
mean_vals,yerr=transpose(cis),label=label,capthick=1)
plt.xlabel("Distance (bp)",fontsize="large")
plt.ylabel("Proportion of Significant Correlations",fontsize="large")
plt.legend()
def analyze_correlation_positions(all_tests, alpha="fdr"):
if alpha == "fdr":
alpha = fdr(concat(all_tests))
print "alpha:",alpha
ds = []
d_controls = []
for tests in all_tests:
K = len(tests)
L = find(lambda l:round(choose(l,2))==K, range(50))
if L is None:
print K
raise Exception()
for k, (i,j) in enumerate(choose2(range(L))):
if j == i + 1 and tests[k] <= alpha:
d = i/float(L)
ds.append(d)
d_controls.append(random.randrange(L-1)/float(L))
plt.scatter(d, tests[k])
return ds, d_controls
def on_off_experiment2(num_motifs=100,
filename="gini-vs-mi-correlation-in-on-off-spoofs.pdf"):
"""compare MI vs Gini on biological_motifs"""
bio_motifs = [getattr(tfdf, tf) for tf in tfdf.tfs]
Ns = map(len, bio_motifs)
spoofses = [
spoof_on_off_motif(motif, num_motifs=num_motifs, trials=1)
for motif in bio_motifs
]
spoof_ginises = mmap(motif_gini, tqdm(spoofses))
spoof_mises = mmap(total_motif_mi, tqdm(spoofses))
cors, ps = [], []
for ginis, mis in zip(ginises, mises):
cor, p = pearsonr(ginis, mis)
cors.append(cor)
ps.append(p)
q = fdr(ps)
plt.scatter(cors,
ps,
filename="gini-vs-mi-correlation-in-on-off-spoofs.pdf")
plt.plot([-1, 1], [q, q],
linestyle='--',
label="FDR-Adjusted Significance Level")
plt.semilogy()
plt.legend()
plt.xlabel("Pearson Correlation Coefficient")
plt.ylabel("P value")
plt.xlim([-1, 1])
plt.ylim([10**-4, 1 + 1])
cor_ps = zip(cors, ps)
sig_negs = [(c, p) for (c, p) in cor_ps if c < 0 and p < q]
sig_poses = [(c, p) for (c, p) in cor_ps if c > 0 and p < q]
insigs = [(c, p) for (c, p) in cor_ps if p > q]
def weighted_correlation(cor_p_Ns):
cors, ps, Ns = transpose(cor_p_Ns)
return sum([cor * N for (cor, N) in zip(cors, Ns)]) / sum(Ns)
plt.title(
"Gini-MI Correlation Coefficient vs. P-value for On-Off Simulations from Prokaryotic Motifs"
)
maybesave(filename)
def analyze_correlated_digrams_canonical(prok_tests, euk_tests, filename=None):
digrams = [(b1,b2) for b1 in "ACGT" for b2 in "ACGT"]
canonical_digrams = sorted(list(set([min(dg,tuple(wc(dg))) for dg in digrams])))
prok_q = fdr(concat(prok_tests))
euk_q = fdr(concat(euk_tests))
prok_digrams = defaultdict(int)
prok_corr_digrams = defaultdict(int)
prok_adj_digrams = defaultdict(int)
for tests, motif in tqdm(zip(prok_tests, prok_motifs)):
for test, ((i,coli),(j,colj)) in zip(tests, choose2(list(enumerate(transpose((motif)))))):
for bi,bj in transpose((coli,colj)):
rev_comp = tuple(wc((bi,bj)))
if (bi, bj) > rev_comp:
bi, bj = rev_comp
prok_digrams[(bi,bj)] += 1
if j == i + 1:
prok_adj_digrams[(bi,bj)] += 1
if test <= prok_q:
prok_corr_digrams[(bi,bj)] += 1
prok_corr_N = float(sum(prok_corr_digrams.values()))
prok_adj_N = float(sum(prok_adj_digrams.values()))
prok_N = float(sum(prok_digrams.values()))
#prok_ps = normalize(prok_digrams.values())
#prok_adj_ps = normalize(prok_adj_digrams.values())
#prok_corr_ps = normalize(prok_corr_digrams.values())
prok_ps = normalize([prok_digrams[dg] for dg in canonical_digrams])
prok_adj_ps = normalize([prok_adj_digrams[dg] for dg in canonical_digrams])
prok_corr_ps = normalize([prok_corr_digrams[dg] for dg in canonical_digrams])
prok_yerr = [1.96*sqrt(1.0/prok_N*p*(1-p)) for p in prok_ps]
prok_adj_yerr = [1.96*sqrt(1.0/prok_adj_N*p*(1-p)) for p in prok_adj_ps]
prok_corr_yerr = [1.96*sqrt(1.0/prok_corr_N*p*(1-p)) for p in prok_corr_ps]
euk_digrams = defaultdict(int)
euk_corr_digrams = defaultdict(int)
euk_adj_digrams = defaultdict(int)
for tests, motif in tqdm(zip(euk_tests, euk_motifs)):
for test, ((i,coli),(j,colj)) in zip(tests, choose2(list(enumerate(transpose((motif)))))):
for bi,bj in transpose((coli,colj)):
rev_comp = tuple(wc((bi,bj)))
if (bi, bj) > rev_comp:
bi, bj = rev_comp
euk_digrams[(bi,bj)] += 1
if j == i + 1:
euk_adj_digrams[(bi,bj)] += 1
if test <= euk_q:
euk_corr_digrams[(bi,bj)] += 1
euk_corr_N = float(sum(euk_corr_digrams.values()))
euk_adj_N = float(sum(euk_adj_digrams.values()))
euk_N = float(sum(euk_digrams.values()))
# euk_ps = normalize(euk_digrams.values())
# euk_adj_ps = normalize(euk_adj_digrams.values())
# euk_corr_ps = normalize(euk_corr_digrams.values())
euk_ps = normalize([euk_digrams[dg] for dg in canonical_digrams])
euk_adj_ps = normalize([euk_adj_digrams[dg] for dg in canonical_digrams])
euk_corr_ps = normalize([euk_corr_digrams[dg] for dg in canonical_digrams])
euk_yerr = [1.96*sqrt(1.0/euk_N*p*(1-p)) for p in euk_ps]
euk_adj_yerr = [1.96*sqrt(1.0/euk_adj_N*p*(1-p)) for p in euk_adj_ps]
euk_corr_yerr = [1.96*sqrt(1.0/euk_corr_N*p*(1-p)) for p in euk_corr_ps]
palette = sns.cubehelix_palette(4)
ax = plt.subplot(211)
# plt.bar(range(16),normalize(prok_digrams.values()))
# plt.bar(range(16),normalize(prok_corr_digrams.values()),color='g')
# plt.bar([x-0.2 for x in range(16)], prok_relative_ratios.values(), color='g', label="Correlated Column-pairs",width=0.2)
# plt.bar([x for x in range(16)],prok_adj_relative_ratios.values(),color='r',alpha=1,yerr=prok_adj_yerr,label="Adjacent Column-pairs",width=0.2)
# plt.bar([x+0.2 for x in range(16)],[1]*16,color='b',alpha=1,yerr=(prok_yerr),capsize=10,capstyle='butt',label="All Column-pairs",width=0.2)
plt.bar([x-0.2 for x in range(len(canonical_digrams))], prok_ps, label="All Column-Pairs",width=0.2,yerr=prok_yerr,color=palette[0])
plt.bar([x for x in range(len(canonical_digrams))],prok_adj_ps,label="Adj. Column-Pairs",
width=0.2,yerr=prok_adj_yerr,color=palette[1])
plt.bar([x+0.2 for x in range(len(canonical_digrams))],prok_corr_ps,alpha=1,
capstyle='butt',label="Corr. Adj. Column-Pairs",width=0.2,yerr=prok_corr_yerr,color=palette[3])
#plt.plot([0,16],[1.0/16, 1.0/16],linestyle='--',color=palette[3],label="Equiprobability",linewidth=1)
ax.set_xticks([x for x in range(len(canonical_digrams))])
ax.set_xticklabels( ["".join(dg) for dg in canonical_digrams],fontsize='large')
plt.xlim(-0.5,10.5)
plt.ylim(0,0.3)
#plt.xlabel("Dimer",fontsize='large')
plt.ylabel("Prokaryotic Frequency",fontsize='large')
#plt.ylim(0,2)
plt.legend(loc='upper right')
ax2 = plt.subplot(212)
#plt.plot([0,16],[1.0/16, 1.0/16],linestyle='--',color=palette[3],label="Equiprobability",linewidth=1)
plt.bar([x-0.2 for x in range(len(canonical_digrams))], euk_ps, label="All Column-Pairs",width=0.2,yerr=euk_yerr,color=palette[0])
plt.bar([x for x in range(len(canonical_digrams))],euk_adj_ps,label="Adj. Column-Pairs",
width=0.2,yerr=euk_adj_yerr,color=palette[1])
plt.bar([x+0.2 for x in range(len(canonical_digrams))],euk_corr_ps,alpha=1,
capstyle='butt',label="Corr. Adj. Column-Pairs",width=0.2,yerr=euk_corr_yerr,color=palette[3])
ax2.set_xticks([x for x in range(len(canonical_digrams))])
ax2.set_xticklabels( ["".join(dg) for dg in canonical_digrams],fontsize='large')
#plt.xlabel("Dimer",fontsize='large')
plt.xlim(-0.5,10.5)
plt.ylim(0,0.2)
plt.ylabel("Eukaryotic Frequency",fontsize='large')
#plt.ylim(0,2)
plt.legend(loc='upper right')
maybesave(filename)
