a = np.loadtxt(filename, dtype=str)
# check if there is only one bam file
if int(subprocess.check_output("wc -l %s | awk '{print $1}'"%filename, shell=True).strip()) == 1:
a = np.vstack((a, np.zeros(len(a))))
sampleNames = a[:,0]
all_reads = a[:,1].astype(float)/1E6
no_chrM = a[:, 2].astype(float)/1E6
chrM = a[:, 3].astype(float)/1E6
final = a[:, 4].astype(float)/1E6
final_q30 = a[:, 5].astype(float)/1E6
headers = np.array(['final over q30', 'final under q30', 'mitochondrial', 'duplicates', 'reads not aligned'])
vecs = np.array([final_q30,
final - final_q30,
chrM,
no_chrM - final,
all_reads - chrM - no_chrM])
# Now plot results
plt.figure(figsize=(6.5,5.5))
plot_barplot(vecs, labels=headers, samples=sampleNames)
plt.subplots_adjust(bottom=0.25, left=0.15, right=0.6)
ax = plt.gca()
ax.set_ylabel('number of reads (million)')
ax.set_ylim((0, np.max(np.sum(vecs, 0))*1.1))
ax.grid()
ax.set_xticklabels(sampleNames, rotation=90)
outFile = os.path.splitext(options.a)[0]+'.pdf'
plt.savefig(outFile)
np.save(outfile+'.npy', signals)
"""
for signal tracks, make plot
"""
span = 1E4
indx = np.arange(0, options.l+options.r, span, dtype=int)
xvalues = np.arange(-options.l, options.r, span)
fig = plt.figure(figsize=(5, 4))
ax = fig.add_subplot(111)
for signal in signals[0]:
ax.plot(xvalues, signal[indx], 'b', alpha=0.1)
ax.plot(xvalues, np.nanmean(signals[0, :, indx], 1), 'k')
plt.savefig('%s.%s.pdf'%(outfile, options.interval))
"""
Now, for conservation, etc, plot the conservation in distal sites. Dista,
"""
locBed = filefun.loadBedwScores(options.a)
locBed.distanceToTss = np.array(subprocess.check_output("bedtools closest -d -t first -a %s -b %s | awk '{print $NF}'"%(bedFileName, tssBedFileName), shell=True).split(), dtype=int)
locBed.distal = locBed.distanceToTss > 5E3
signals[0, np.all((locBed.distal, locBed.significant_up), axis=0)]
signals[0, locBed.distal]
signals[0, np.logical_not(locBed.distal)]
histogram.compare([signals[0, np.all((locBed.distal, locBed.significant_up), axis=0)],
signals[0, np.all((locBed.distal, locBed.no_change), axis=0)],
signals[0, np.logical_not(locBed.distal)]], labels=['up, distal', 'no change, distal', 'all promoter'])
plotfun.plot_barplot()
np.all((peakBed.distal, peakBed.enriched_region), axis=0),
]
# plot histogram and scatterplot
indxlabels = ["depleted", "enriched"]
for i, indx in enumerate(indices):
xvalues = xvalues_norm[indx]
yvalues = yvalues_norm[indx]
fig = plt.figure(figsize=(4, 4))
plotfun.plot_hexbin(xvalues, yvalues)
# plt.savefig('allDistalPeaks.%s.hexbinplot.pdf'%indxlabels[i])
plt.savefig("allDistalPeaks.%s.per_bp.hexbinplot.pdf" % indxlabels[i])
fig = plt.figure(figsize=(7, 4))
plotfun.plotHistogram(score[indices[0]], score[indices[1]], labels=indxlabels)
plt.savefig("allDistalPeaks.both.histogram.pdf")
"""
# plot barplot
filename = 'scoring/140815_peaks.coverageCorr.upwNfib.annstats'
labels, numpeaks = filefun.loadAnnstatFile(filename)
percentage_up = numpeaks/float(np.sum(numpeaks))
filename = 'scoring/140815_peaks.coverageCorr.all.annstats'
labels, numpeaks = filefun.loadAnnstatFile(filename)
percentage_all = numpeaks/float(np.sum(numpeaks))
indx = np.argsort(np.mean([percentage_up, percentage_all], 0))[::-1][:7]
vecs = np.transpose([np.append(percentage_all[indx], 1-np.sum(percentage_all[indx])),
np.append(percentage_up[indx], 1-np.sum(percentage_up[indx]))])
reorder = np.append(np.argsort(np.abs(percentage_up-percentage_all)[indx]), -1)
fig = plt.figure(figsize=(4,4))
plotfun.plot_barplot(vecs[reorder], labels=np.append(labels[indx], 'other')[reorder], cmap='binary', samples=['all peaks', 'up peaks'])