plt.figure(figsize=(4,4))
plotfun.plot_manylines(yvalues, x=xvalues, labels=['all sites', 'up peaks', 'no change'])
ax = plt.gca()
plt.legend(loc='lower right')
ax.set_xlabel('motif score')
ax.set_ylabel('cumulative frequency')
plt.tight_layout()
plt.savefig('%s.sitescore.peakvalue.pdf'%outfile)
# plot dendrogram
plt.figure()
signal_clusters = dendrogram(linkage(footprintVecs_norm, metric='euclidean'), labels=labels)
plt.title('all profiles')
plt.savefig('%s.all.dendrogram.pdf'%(outfile))
reorder = np.array(signal_clusters['leaves'])
plotfun.plotAggregateSignal(footprintVecs_norm[reorder], labels=labels[reorder])
plt.savefig('%s.all.normalizedbyinsertions.background_sub.pdf'%outfile)
else:
print "skipped plotting background-subtracted profile because no background was provided"
# reduce by replicates
footprintMats = np.load(options.m)
footprintMats_red = np.zeros((2, footprintMats.shape[1], footprintMats.shape[2]))
footprintMats_red[0] = np.sum(footprintMats[parameters.indices_high_noreplicates], 0)
footprintMats_red[1] = np.sum(footprintMats[parameters.indices_low_noreplicates], 0)
footprintMats = np.copy(footprintMats_red)
labels = ['hyperaccessible', 'tumorigenic']
numSamples = 2
# find correlations
## from bw files, extract signal about 5kb away from bed data
# print "finding baseline..."
## Do 5000 random points
# numBackgroundSites = 5000
# indx = np.unique(np.linspace(0, numSites-1, numBackgroundSites).astype(int))
# baselineBed = np.copy(bedFile)[indx]
# baselineBed[:,1] = (baselineBed[:,1].astype(int)-5000).astype(str)
# baselineBed[:,2] = (baselineBed[:,2].astype(int)-5000).astype(str)
# for i, bw in enumerate(bws):
# print "Extracting background signal for %s:\t%s"%(labels[i], os.path.basename(bw))
# pool = Pool(processes=options.p)
# baselineArray = pool.map(functools.partial(findInsertions, bw, baselineBed), range(0, numBackgroundSites))
# pool.close()
# baseline = processSignal(baselineArray)
# signals[i].baseline = baseline.final
# plot and save
finalSignal = np.array([signals[i].final for i in range(len(signals))])
if options.tn5 is None:
for i in range(len(signals)):
finalSignal[i][:, :-1] = finalSignal[i][:, 1:]
np.save(outfile, finalSignal)
numSamples = len(bws)
footprintVecs = np.array(
[np.mean(finalSignal[i], 0) * np.mean(finalSignal) / np.mean(finalSignal[i]) for i in range(numSamples)]
)
plotfun.plotAggregateSignal(footprintVecs)
plt.savefig(outfile + ".normalize.aggregate.pdf")