def main():
basedir = '/'.join(
os.path.dirname(os.path.realpath(__file__)).split('/')[:-2])
out_fname = sys.argv[1]
fivec_fname = "%s/Data/FiveC/HiFive/Nora_ESC_male_E14_prob.fcp" % basedir
fivec = hifive.FiveC(fivec_fname)
num_bins = 200
width = 16.92
plot_width = (width) / 2.0 - 2
c = canvas.canvas()
hist1, hist_min, hist_max, hist_ranges1 = get_histograms(
fivec, num_bins, 'raw')
temp = get_histograms(fivec, num_bins, 'fragment')
hist2 = temp[0]
hist_ranges2 = temp[3]
hist_min = min(hist_min, temp[1])
hist_max = max(hist_max, temp[2])
c.insert(
plot_distances(fivec, plot_width, hist1, hist_min, hist_max,
hist_ranges1))
c.insert(
plot_distances(fivec, plot_width, hist2, hist_min, hist_max,
hist_ranges2), [trafo.translate(plot_width + 0.8, 0)])
c.text(-0.6, plot_width * 0.5, "Log count", [
text.halign.center, text.valign.bottom,
text.size(-3),
trafo.rotate(90)
])
c.text(plot_width * 0.5, -0.4, "Log distance (Kb)",
[text.halign.center, text.valign.top,
text.size(-3)])
c.text(plot_width * 1.5 + 0.8, -0.4, "Log distance (Kb)",
[text.halign.center, text.valign.top,
text.size(-3)])
c.text(plot_width * 0.5, plot_width + 0.1, "Raw",
[text.halign.center, text.valign.bottom,
text.size(-2)])
c.text(plot_width * 1.5 + 0.8, plot_width + 0.1, "Corrected",
[text.halign.center, text.valign.bottom,
text.size(-2)])
c.insert(
hifive.plotting.plot_key(hist_min,
hist_max,
0.4,
plot_width * 2 + 0.8,
"%.0f",
orientation='top',
min_color="000000",
max_color="0000ff",
mid_color=None,
labelattrs=[text.size(-3)]),
[trafo.translate(0, plot_width + 0.4)])
c.text(plot_width * 1.0 + 0.4, plot_width + 1.3, "Interactions per bin",
[text.halign.center, text.valign.bottom,
text.size(-2)])
c.writePDFfile(out_fname)
def main():
out_fname = sys.argv[1]
basedir = '/'.join(os.path.dirname(os.path.realpath(__file__)).split('/')[:-2])
hic_phillips_fname1 = "%s/Data/HiC/HiCPipe/HM/mm9_ESC_NcoI_Phillips.hch" % basedir
hic_phillips_fname2 = "%s/Data/HiC/HiCPipe/HM/mm9_ESC_HindIII_Phillips.hch" % basedir
hic_nora_fname1 = "%s/Data/HiC/HiCPipe/HM/mm9_ESC_NcoI_Nora.hch" % basedir
hic_nora_fname2 = "%s/Data/HiC/HiCPipe/HM/mm9_ESC_HindIII_Nora.hch" % basedir
hic_phillips1 = h5py.File(hic_phillips_fname1, 'r')
hic_phillips2 = h5py.File(hic_phillips_fname2, 'r')
hic_nora1 = h5py.File(hic_nora_fname1, 'r')
hic_nora2 = h5py.File(hic_nora_fname2, 'r')
hm_phillips = {}
hm_nora = {}
for key in hic_phillips1.keys():
if key.count('unbinned_counts') == 0:
continue
region = int(key.split('.')[0])
hm_phillips[region] = dynamically_bin(hic_phillips1, hic_phillips2, region)
for key in hic_nora1.keys():
if key.count('unbinned_counts') == 0:
continue
region = int(key.split('.')[0])
hm_nora[region] = dynamically_bin(hic_nora1, hic_nora2, region)
fivec_fnames = {
"Prob_Phillips":"%s/Data/FiveC/HiFive/Phillips_ESC_probnodist.fcp" % basedir,
"Prob_Nora":"%s/Data/FiveC/HiFive/Nora_ESC_male_E14_probnodist.fcp" % basedir,
"Bin_Phillips":"%s/Data/FiveC/HiFive/Phillips_ESC_binnodist.fcp" % basedir,
"Bin_Nora":"%s/Data/FiveC/HiFive/Nora_ESC_male_E14_binnodist.fcp" % basedir,
"Exp_Phillips":"%s/Data/FiveC/HiFive/Phillips_ESC_expnodist.fcp" % basedir,
"Exp_Nora":"%s/Data/FiveC/HiFive/Nora_ESC_male_E14_expnodist.fcp" % basedir,
"Exp-KR_Phillips":"%s/Data/FiveC/HiFive/Phillips_ESC_expKRnodist.fcp" % basedir,
"Exp-KR_Nora":"%s/Data/FiveC/HiFive/Nora_ESC_male_E14_expKRnodist.fcp" % basedir,
}
data = {}
imgs = {}
ratio1 = 0
ratio2 = 0
for meth in ['Prob', 'Bin', 'Exp', 'Exp-KR']:
fc = hifive.FiveC(fivec_fnames["%s_Phillips" % meth])
fragments = fc.frags['fragments'][...]
regions = fc.frags['regions'][...]
counts = numpy.zeros(0, dtype=numpy.float64)
expected = numpy.zeros(0, dtype=numpy.float64)
hic_counts = numpy.zeros(0, dtype=numpy.float64)
hic_expected = numpy.zeros(0, dtype=numpy.float64)
skipped = []
for i in range(fc.frags['regions'].shape[0]):
temp = fc.cis_heatmap(i, datatype='fragment', arraytype='compact', binsize=0, skipfiltered=True)
if temp is None:
skipped.append(i)
continue
counts = numpy.hstack((counts, temp[:, :, 0].ravel()))
expected = numpy.hstack((expected, temp[:, :, 1].ravel()))
if i == 6:
ratio1 = temp.shape[1] / float(temp.shape[0])
imgs["%s_Phillips" % meth] = hifive.plotting.plot_full_array(temp, symmetricscaling=False)
if meth == 'Prob':
temp1 = numpy.zeros((temp.shape[0], temp.shape[1]), dtype=numpy.float32)
temp1[numpy.where(temp[:, :, 0] > 0.0)] = 1
if i == 6:
imgs["Raw_Phillips"] = hifive.plotting.plot_full_array(
numpy.dstack((temp[:, :, 0], temp1)), symmetricscaling=False)
binbounds = numpy.hstack((
fragments['start'][regions['start_frag'][i]:regions['stop_frag'][i]].reshape(-1, 1),
fragments['stop'][regions['start_frag'][i]:regions['stop_frag'][i]].reshape(-1, 1)))
valid = numpy.where(fc.filter[regions['start_frag'][i]:regions['stop_frag'][i]])[0]
binbounds = binbounds[valid, :]
temp = hm_phillips[i]
strands = fragments['strand'][regions['start_frag'][i]:regions['stop_frag'][i]][valid]
temp = temp[numpy.where(strands == 0)[0], :, :][:, numpy.where(strands == 1)[0], :]
hic_counts = numpy.hstack((hic_counts, temp[:, :, 0].ravel()))
hic_expected = numpy.hstack((hic_expected, temp[:, :, 1].ravel()))
if i == 6:
imgs["HiC_Phillips"] = hifive.plotting.plot_full_array(temp, symmetricscaling=False)
if meth == 'Prob':
data["Raw_Phillips"] = numpy.copy(counts)
where = numpy.where(hic_expected > 0.0)[0]
hic_counts[where] /= hic_expected[where]
data["HiC_Phillips"] = numpy.copy(hic_counts)
where = numpy.where(expected > 0.0)[0]
counts[where] /= expected[where]
data["%s_Phillips" % meth] = numpy.copy(counts)
fc = hifive.FiveC(fivec_fnames["%s_Nora" % meth])
temp = fc.cis_heatmap(0, datatype='fragment', arraytype='compact', binsize=0, skipfiltered=True)
ratio2 = temp.shape[1] / float(temp.shape[0])
imgs["%s_Nora" % meth] = hifive.plotting.plot_full_array(temp, symmetricscaling=False)
counts = temp[:, :, 0].ravel()
expected = temp[:, :, 1].ravel()
if meth == 'Prob':
temp1 = numpy.zeros((temp.shape[0], temp.shape[1]), dtype=numpy.float32)
temp1[numpy.where(temp[:, :, 0] > 0.0)] = 1
imgs["Raw_Nora"] = hifive.plotting.plot_full_array(
numpy.dstack((temp[:, :, 0], temp1)), symmetricscaling=False)
data["Raw_Nora"] = numpy.copy(counts)
fragments = fc.frags['fragments'][...]
regions = fc.frags['regions'][...]
binbounds = numpy.hstack((
fragments['start'][regions['start_frag'][0]:regions['stop_frag'][0]].reshape(-1, 1),
fragments['stop'][regions['start_frag'][0]:regions['stop_frag'][0]].reshape(-1, 1)))
binbounds = binbounds[numpy.where(fc.filter[regions['start_frag'][0]:regions['stop_frag'][0]])[0], :]
temp = hm_nora[0]
strands = fragments['strand'][regions['start_frag'][0]:regions['stop_frag'][0]]
temp = temp[numpy.where(strands==0)[0], :, :][:, numpy.where(strands == 1)[0], :]
imgs["HiC_Nora"] = hifive.plotting.plot_full_array(temp, symmetricscaling=False)
hic_counts = temp[:, :, 0].ravel()
hic_expected = temp[:, :, 1].ravel()
where = numpy.where(hic_expected > 0.0)[0]
hic_counts[where] /= hic_expected[where]
data["HiC_Nora"] = numpy.copy(hic_counts)
where = numpy.where(expected > 0.0)[0]
counts[where] /= expected[where]
data["%s_Nora" % meth] = numpy.copy(counts)
correlations = {}
output = open(out_fname.replace('pdf', 'txt'), 'w')
print >> output, "Method\tPhillips\tNora"
for meth in methods:
temp = [meth]
for name in ["Phillips", "Nora"]:
valid = numpy.where((data["%s_%s" % (meth, name)] > 0.0) * (data["HiC_%s" % name] > 0.0))
correlations["%s_%s" % (meth, name)] = numpy.corrcoef(numpy.log(data["%s_%s" % (meth, name)][valid]),
numpy.log(data["HiC_%s" % name][valid]))[0, 1]
temp.append(str(correlations["%s_%s" % (meth, name)]))
print >> output, '\t'.join(temp)
output.close()
width = 16.8
spacer = 0.3
c = canvas.canvas()
plot_width = (width - spacer * 3.0 - 0.4) / 4.0
for i, meth in enumerate(["Raw", "Prob", "HiC"]):
meth_names = {"Raw":"Raw", "Prob":"HiFive", "HiC":"HiC"}
c.text(plot_width * (i + 1.5) + spacer * (i + 1), (ratio1 + ratio2) * plot_width + spacer + 0.1,
"%s" % meth_names[meth], [text.halign.center, text.valign.bottom, text.size(-2)])
c.insert(bitmap.bitmap(0, 0, imgs["%s_Phillips" % meth], width=plot_width),
[trafo.translate((i + 1) * (plot_width + spacer), plot_width * ratio2 + spacer)])
c.insert(bitmap.bitmap(0, 0, imgs["%s_Nora" % meth], width=plot_width),
[trafo.translate((i + 1) * (plot_width + spacer), 0)])
g = graph.graphxy(width=plot_width - 0.8, height=plot_width * ratio1,
x=graph.axis.nestedbar(painter=graph.axis.painter.bar(nameattrs=None)),
y=graph.axis.lin(painter=painter),
x2=graph.axis.lin(parter=None, min=0, max=1),
y2=graph.axis.lin(parter=None, min=0, max=1))
for i, meth in enumerate(methods):
Y = numpy.zeros(2, dtype=numpy.float32)
col = method_colors[meth]
for j, name in enumerate(["Phillips", "Nora"]):
Y[j] = correlations["%s_%s" % (meth, name)]
g.plot(graph.data.points(zip(zip(range(Y.shape[0]), [i] * Y.shape[0]), Y), xname=1, y=2),
[graph.style.changebar([col])])
g.text(-0.8, plot_width * ratio1 * 0.5, "Correlation",
[text.halign.center, text.valign.top, text.size(-3), trafo.rotate(90)])
g.text((plot_width - 0.8) * 0.25, -0.1, "Phillips",
[text.halign.center, text.valign.top, text.size(-3)])
g.text((plot_width - 0.8) * 0.75, -0.1, "Nora",
[text.halign.center, text.valign.top, text.size(-3)])
c.insert(g, [trafo.translate(0.8, plot_width * ratio2 + spacer)])
c.text(width, (ratio1 + ratio2 * 0.5) * plot_width + spacer, "Phillips",
[text.halign.center, text.valign.top, trafo.rotate(-90), text.size(-2)])
c.text(width, ratio1 * 0.5 * plot_width, "Nora",
[text.halign.center, text.valign.top, trafo.rotate(-90), text.size(-2)])
meth_names = {"Raw":"Raw", "Prob":"HiFive-Probability", "Exp":"HiFive-Express", "Bin":"HiFive-Binning",
"Exp-KR":"HiFive-ExpressKR", "Exp-KR-dist":"HiFive-ExpressKR-dist"}
for i, meth in enumerate(methods):
c.fill(path.rect(1.0, plot_width * ratio1 - 1.0 - i * 0.5, 0.2, 0.2), [method_colors[meth]])
c.text(1.3, plot_width * ratio1 - 0.9 - i * 0.5, "%s" % meth_names[meth],
[text.halign.left, text.valign.middle, text.size(-3)])
c.writePDFfile(out_fname)
def main():
out_fname = sys.argv[1]
basedir = '/'.join(
os.path.dirname(os.path.realpath(__file__)).split('/')[:-2])
hic_fname1 = "%s/Data/HiC/HiFive/mm9_ESC_NcoI_prob.hcp" % basedir
hic_fname2 = "%s/Data/HiC/HiFive/mm9_ESC_HindIII_prob.hcp" % basedir
fivec_fnames = {
"Prob_Phillips":
"%s/Data/FiveC/HiFive/Phillips_ESC_prob.fcp" % basedir,
"Prob_Nora":
"%s/Data/FiveC/HiFive/Nora_ESC_male_E14_prob.fcp" % basedir,
"Bin_Phillips":
"%s/Data/FiveC/HiFive/Phillips_ESC_bin.fcp" % basedir,
"Bin_Nora":
"%s/Data/FiveC/HiFive/Nora_ESC_male_E14_bin.fcp" % basedir,
"Exp_Phillips":
"%s/Data/FiveC/HiFive/Phillips_ESC_exp.fcp" % basedir,
"Exp_Nora":
"%s/Data/FiveC/HiFive/Nora_ESC_male_E14_exp.fcp" % basedir,
"Exp-KR_Phillips":
"%s/Data/FiveC/HiFive/Phillips_ESC_expKR.fcp" % basedir,
"Exp-KR_Nora":
"%s/Data/FiveC/HiFive/Nora_ESC_male_E14_expKR.fcp" % basedir,
}
hic1 = hifive.HiC(hic_fname1)
hic2 = hifive.HiC(hic_fname2)
hic_hm = {'Phillips': {}}
fc = hifive.FiveC(fivec_fnames["Prob_Phillips"])
fragments = fc.frags['fragments'][...]
regions = fc.frags['regions'][...]
for i in range(fc.frags['regions'].shape[0]):
binbounds = numpy.hstack(
(fragments['start']
[regions['start_frag'][i]:regions['stop_frag'][i]].reshape(-1, 1),
fragments['stop']
[regions['start_frag'][i]:regions['stop_frag'][i]].reshape(-1,
1)))
binbounds = binbounds[numpy.where(
fc.filter[regions['start_frag'][i]:regions['stop_frag'][i]])[0], :]
hic_hm['Phillips'][i] = dynamically_bin(hic1, hic2,
regions['chromosome'][i],
binbounds)
fc = hifive.FiveC(fivec_fnames["Prob_Nora"])
fragments = fc.frags['fragments'][...]
regions = fc.frags['regions'][...]
binbounds = numpy.hstack(
(fragments['start']
[regions['start_frag'][0]:regions['stop_frag'][0]].reshape(-1, 1),
fragments['stop']
[regions['start_frag'][0]:regions['stop_frag'][0]].reshape(-1, 1)))
binbounds = binbounds[numpy.where(
fc.filter[regions['start_frag'][0]:regions['stop_frag'][0]])[0], :]
hic_hm['Nora'] = dynamically_bin(hic1, hic2, regions['chromosome'][0],
binbounds)
dist_corr = find_correlations(hic_hm, fivec_fnames, out_fname, True)
nodist_corr = find_correlations(hic_hm, fivec_fnames, out_fname, False)
c = canvas.canvas()
width = 16.8
spacer = 0.4
plot_width = (width - spacer * 2) / 2.5
plot_height = plot_width
key_width = width - (plot_width + spacer) * 2
phillips_img = plot_correlation_diffs(dist_corr, nodist_corr, 'Phillips',
plot_width, plot_height)
nora_img = plot_correlation_diffs(dist_corr, nodist_corr, 'Nora',
plot_width, plot_height)
key_img = plot_key(key_width, plot_height)
c.insert(phillips_img)
c.insert(nora_img, [trafo.translate(plot_width + spacer, 0)])
c.insert(key_img, [trafo.translate((plot_width + spacer) * 2, 0)])
c.text(0, plot_height, "a",
[text.halign.left, text.valign.top,
text.size(-1)])
c.text(plot_width + spacer, plot_height, "b",
[text.halign.left, text.valign.top,
text.size(-1)])
c.writePDFfile(out_fname)
def find_correlations(hic_hm, fivec_fnames, out_fname, dist):
data = {}
for meth in ['Prob', 'Bin', 'Exp', 'Exp-KR']:
if dist:
fname = fivec_fnames['%s_Phillips' % meth]
else:
fname = fivec_fnames['%s_Phillips' % meth].replace(
'.fcp', 'nodist.fcp')
fc = hifive.FiveC(fname)
fragments = fc.frags['fragments'][...]
regions = fc.frags['regions'][...]
counts = numpy.zeros(0, dtype=numpy.float64)
expected = numpy.zeros(0, dtype=numpy.float64)
hic_counts = numpy.zeros(0, dtype=numpy.float64)
hic_expected = numpy.zeros(0, dtype=numpy.float64)
skipped = []
for i in range(fc.frags['regions'].shape[0]):
temp = fc.cis_heatmap(i,
datatype='fragment',
arraytype='compact',
binsize=0,
skipfiltered=True)
if temp is None:
skipped.append(i)
continue
counts = numpy.hstack((counts, temp[:, :, 0].ravel()))
expected = numpy.hstack((expected, temp[:, :, 1].ravel()))
if meth == 'Prob':
temp1 = numpy.zeros((temp.shape[0], temp.shape[1]),
dtype=numpy.float32)
temp1[numpy.where(temp[:, :, 0] > 0.0)] = 1
binbounds = numpy.hstack((
fragments['start']
[regions['start_frag'][i]:regions['stop_frag'][i]].reshape(
-1, 1), fragments['stop']
[regions['start_frag'][i]:regions['stop_frag'][i]].reshape(
-1, 1)))
valid = numpy.where(
fc.filter[regions['start_frag'][i]:regions['stop_frag'][i]]
)[0]
binbounds = binbounds[valid, :]
strands = fragments['strand'][
regions['start_frag'][i]:regions['stop_frag'][i]][valid]
temp = hic_hm['Phillips'][i][numpy.where(
strands == 0)[0], :, :][:,
numpy.where(strands == 1)[0], :]
hic_counts = numpy.hstack((hic_counts, temp[:, :, 0].ravel()))
hic_expected = numpy.hstack((hic_expected, temp[:, :,
1].ravel()))
if meth == 'Prob':
where = numpy.where(hic_expected > 0.0)[0]
hic_counts[where] /= hic_expected[where]
data["HiC_Phillips"] = numpy.copy(hic_counts)
where = numpy.where(expected > 0.0)[0]
counts[where] /= expected[where]
data["%s_Phillips" % meth] = numpy.copy(counts)
if dist:
fname = fivec_fnames['%s_Nora' % meth]
else:
fname = fivec_fnames['%s_Nora' % meth].replace(
'.fcp', 'nodist.fcp')
fc = hifive.FiveC(fname)
temp = fc.cis_heatmap(0,
datatype='fragment',
arraytype='compact',
binsize=0,
skipfiltered=True)
counts = temp[:, :, 0].ravel()
expected = temp[:, :, 1].ravel()
if meth == 'Prob':
temp1 = numpy.zeros((temp.shape[0], temp.shape[1]),
dtype=numpy.float32)
temp1[numpy.where(temp[:, :, 0] > 0.0)] = 1
fragments = fc.frags['fragments'][...]
regions = fc.frags['regions'][...]
binbounds = numpy.hstack(
(fragments['start']
[regions['start_frag'][0]:regions['stop_frag'][0]].reshape(
-1, 1), fragments['stop']
[regions['start_frag'][0]:regions['stop_frag'][0]].reshape(
-1, 1)))
binbounds = binbounds[numpy.where(
fc.filter[regions['start_frag'][0]:regions['stop_frag'][0]]
)[0], :]
strands = fragments['strand'][
regions['start_frag'][0]:regions['stop_frag'][0]]
temp = hic_hm['Nora'][numpy.where(
strands == 0)[0], :, :][:, numpy.where(strands == 1)[0], :]
hic_counts = temp[:, :, 0].ravel()
hic_expected = temp[:, :, 1].ravel()
where = numpy.where(hic_expected > 0.0)[0]
hic_counts[where] /= hic_expected[where]
data["HiC_Nora"] = numpy.copy(hic_counts)
where = numpy.where(expected > 0.0)[0]
counts[where] /= expected[where]
data["%s_Nora" % meth] = numpy.copy(counts)
correlations = {}
for meth in methods:
for name in ["Phillips", "Nora"]:
valid = numpy.where((data["%s_%s" % (meth, name)] > 0.0) *
(data["HiC_%s" % name] > 0.0))
correlations["%s_%s" % (meth, name)] = numpy.corrcoef(
numpy.log(data["%s_%s" % (meth, name)][valid]),
numpy.log(data["HiC_%s" % name][valid]))[0, 1]
if not dist:
output = open(out_fname.replace('pdf', 'txt'), 'w')
print >> output, "Method\tPhillips\tNora"
for meth in methods:
temp = [meth]
for name in ["Phillips", "Nora"]:
temp.append(str(correlations["%s_%s" % (meth, name)]))
print >> output, '\t'.join(temp)
output.close()
return correlations