def correctedScalingPlot(resolution, filename, experiment, genome, mouse=False, **kwargs):
"Paper figure to compare scaling before/after correction"
global pp
if (options.verbose):
print >> sys.stdout, "correctedScalingPlot: res: %d file1: %s exp1:%s gen:%s" % (resolution, filename, experiment, genome)
plt.figure()
Tanay = binnedDataAnalysis(resolution, genome)
Tanay.simpleLoad(filename, experiment)
Tanay.removePoorRegions()
Tanay.removeDiagonal()
Tanay.plotScaling(experiment, label="Raw data", color="#A7A241")
Tanay.iterativeCorrectWithSS()
Tanay.plotScaling(experiment, label="Corrected", color="#344370")
ax = plt.gca()
plotting.removeAxes()
fs = 6
plt.xlabel("Genomic distance (MB)", fontsize=6)
plt.ylabel("Contact probability", fontsize=6)
for xlabel_i in ax.get_xticklabels():
xlabel_i.set_fontsize(fs)
for xlabel_i in ax.get_yticklabels():
xlabel_i.set_fontsize(fs)
legend = plt.legend(loc=0, prop={"size": 6})
legend.draw_frame(False)
plt.xscale("log")
plt.yscale("log")
plt.show()
pp.savefig()
def plotCrossValidation():
"main figure subplot with corss-validation"
matplotlib.rcParams['font.sans-serif'] = 'Arial'
plt.figure(figsize=(1, 1))
FG = HiCdataset(workingFile1, myGenome)
FG.load(GMFrag)
Tanay = binnedData(1000000)
Tanay.simpleLoad("GM-all-10p", "GM-1")
#need to create these datasets using fragment-level analysis
Tanay.simpleLoad("GM-all-90p", "GM-9")
Tanay.removePoorRegions()
Tanay.iterativeCorrectWithSS()
Tanay.removeZeros()
b1, b2 = (Tanay.biasDict["GM-1"], Tanay.biasDict["GM-9"])
cPickle.dump((b1, b2), open("CrossValidatioN", 'wb'))
ax = plt.gca()
b1, b2 = cPickle.load(open("CrossValidatioN", 'rb'))
print cr(b1, b2)
plt.scatter(b1, b2, s=.7, color="k", linewidth=0)
plt.xlabel(r"10% reads", fontsize=8)
plt.ylabel(r"90% reads", fontsize=8)
plt.xlim((0, 1.5))
plt.ylim((0, 1.5))
plt.xticks([0, 0.5, 1, 1.5])
plt.yticks([0, 0.5, 1, 1.5])
removeAxes(shift=0)
fs = 6
for xlabel_i in ax.get_xticklabels():
xlabel_i.set_fontsize(fs)
for xlabel_i in ax.get_yticklabels():
xlabel_i.set_fontsize(fs)
plt.show()
def allDirectionalityRatios(ratioFunction):
"""
A simple plot which calculates all directionality ratios, plots them
and puts lines at 20 top highly expressed genes (Supp figure from our paper)
This is mostly matplotlib code.
"""
if not os.path.exists("savedHeatmaps"):
os.mkdir("savedHeatmaps")
wildRatio = np.log(ratioFunction("Wildtype_0min_BglII_rep1"))
for j, dataset in enumerate(datasets):
ax = plt.subplot(len(datasets), 1, j + 1)
curRatio = (ratioFunction(dataset))
plt.title("{1}, r = {0:.2f}, p={2:.2e}".format(pearsonr(curRatio, wildRatio)[0], names[dataset],
pearsonr(curRatio, wildRatio)[1]), fontsize=10)
plt.tick_params(axis='both', which='major', labelsize=10)
plt.tick_params(axis='both', which='minor', labelsize=8)
plt.plot(curRatio)
plt.ylim((0.25, 0.75))
plt.xlim((0, len(curRatio)))
#plt.ylim((0, 1))
plt.yticks((0.25, 0.5, 0.75))
geneCoor = [1162773, 3509071, 1180887, 543099, 1953250, 2522439, 3328524, 1503879, 900483, 242693, 3677144, 3931680, 3677704, 3762707, 3480870, 3829656, 1424678, 901855, 1439056, 3678537]
genePos = [i / 10000. for i in geneCoor]
#genePos = []
for lpos in genePos:
plt.vlines(lpos , -.8, .8, alpha=0.2, linewidth=1, color="black")
plt.xticks([0, 50, 100, 150, 200, 250, 300, 350, 400], ["" for i in xrange(9)], fontsize=98)
removeAxes(ax=ax)
plt.subplots_adjust(0.07, 0.05, 0.94, 0.95, 0.2, 0.5)
plt.show()
exit()
def allDirectionalityRatios(ratioFunction):
"""
A simple plot which calculates all directionality ratios, plots them
and puts lines at 20 top highly expressed genes (Supp figure from our paper)
This is mostly matplotlib code.
"""
if not os.path.exists("savedHeatmaps"):
os.mkdir("savedHeatmaps")
wildRatio = np.log(ratioFunction("Wildtype_0min_BglII_rep1"))
for j, dataset in enumerate(datasets):
ax = plt.subplot(len(datasets), 1, j + 1)
curRatio = (ratioFunction(dataset))
plt.title("{1}, r = {0:.2f}, p={2:.2e}".format(
pearsonr(curRatio, wildRatio)[0], names[dataset],
pearsonr(curRatio, wildRatio)[1]),
fontsize=10)
plt.tick_params(axis='both', which='major', labelsize=10)
plt.tick_params(axis='both', which='minor', labelsize=8)
plt.plot(curRatio)
plt.ylim((0.25, 0.75))
plt.xlim((0, len(curRatio)))
#plt.ylim((0, 1))
plt.yticks((0.25, 0.5, 0.75))
geneCoor = [
1162773, 3509071, 1180887, 543099, 1953250, 2522439, 3328524,
1503879, 900483, 242693, 3677144, 3931680, 3677704, 3762707,
3480870, 3829656, 1424678, 901855, 1439056, 3678537
]
genePos = [i / 10000. for i in geneCoor]
#genePos = []
for lpos in genePos:
plt.vlines(lpos, -.8, .8, alpha=0.2, linewidth=1, color="black")
plt.xticks([0, 50, 100, 150, 200, 250, 300, 350, 400],
["" for i in xrange(9)],
fontsize=98)
removeAxes(ax=ax)
plt.subplots_adjust(0.07, 0.05, 0.94, 0.95, 0.2, 0.5)
plt.show()
exit()
def correctedScalingPlot(resolution,
filename,
experiment,
genome,
mouse=False,
**kwargs):
"Paper figure to compare scaling before/after correction"
global pp
if (options.verbose):
print >> sys.stdout, "correctedScalingPlot: res: %d file1: %s exp1:%s gen:%s" % (
resolution, filename, experiment, genome)
plt.figure()
Tanay = binnedDataAnalysis(resolution, genome)
Tanay.simpleLoad(filename, experiment)
Tanay.removePoorRegions()
Tanay.removeDiagonal()
Tanay.plotScaling(experiment, label="Raw data", color="#A7A241")
Tanay.iterativeCorrectWithSS()
Tanay.plotScaling(experiment, label="Corrected", color="#344370")
ax = plt.gca()
plotting.removeAxes()
fs = 6
plt.xlabel("Genomic distance (MB)", fontsize=6)
plt.ylabel("Contact probability", fontsize=6)
for xlabel_i in ax.get_xticklabels():
xlabel_i.set_fontsize(fs)
for xlabel_i in ax.get_yticklabels():
xlabel_i.set_fontsize(fs)
legend = plt.legend(loc=0, prop={"size": 6})
legend.draw_frame(False)
plt.xscale("log")
plt.yscale("log")
plt.show()
pp.savefig()
def plotDiagonalCorrelation(resolution,
filename1,
filename2,
experiment1,
experiment2,
genome,
mouse=False,
**kwargs):
"Correlation of diagonal bins - paper figure"
global pp
if (options.verbose):
print >> sys.stdout, "plotDiagonalCorrelation: res: %d file1: %s file2: %s exp1:%s exp2:%s gen:%s" % (
resolution, filename1, filename2, experiment1, experiment2, genome)
S = 50
x = numpy.arange(2, S)
Tanay = binnedData(resolution, genome)
Tanay.simpleLoad(filename1, experiment1)
Tanay.simpleLoad(filename2, experiment2)
Tanay.removeDiagonal(1)
Tanay.removePoorRegions()
Tanay.removeZeros()
pairs = [(experiment1, experiment2)]
cors = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors[j].append(
cr(numpy.diagonal(Tanay.dataDict[pair[0]], i),
numpy.diagonal(Tanay.dataDict[pair[1]], i))[0])
Tanay.iterativeCorrectWithoutSS(M=1)
cors2 = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors2[j].append(
cr(numpy.diagonal(Tanay.dataDict[pair[0]], i),
numpy.diagonal(Tanay.dataDict[pair[1]], i))[0])
Tanay.iterativeCorrectWithoutSS(M=20)
cors3 = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors3[j].append(
cr(numpy.diagonal(Tanay.dataDict[pair[0]], i),
numpy.diagonal(Tanay.dataDict[pair[1]], i))[0])
matplotlib.rcParams['font.sans-serif'] = 'Arial'
print "Eigenvectors"
print cors
print cors2
print cors3
plt.figure(figsize=(8, 4))
ax = plt.gca()
for j, pair in enumerate(pairs):
plt.subplot(1, len(pairs), j)
fs = 8
for xlabel_i in ax.get_xticklabels():
xlabel_i.set_fontsize(fs)
for xlabel_i in ax.get_yticklabels():
xlabel_i.set_fontsize(fs)
plt.title("%s vs %s" % pair)
plt.plot(x / 5., cors3[j], color="#E5A826", label="Iterative")
plt.plot(x / 5., cors2[j], color="#28459A", label="Single")
plt.plot(x / 5., cors[j], color="#E55726", label="Raw")
plt.xlabel("Genomic Separation, MB", fontsize=8)
plt.ylabel("Spearman correlation", fontsize=8)
plt.legend()
legend = plt.legend(prop={"size": 6}, loc=9, handlelength=2)
legend.draw_frame(False)
plt.ylim((0, 1))
removeAxes(shift=0)
plt.show()
pp.savefig()
def plotFigure2c():
TR = HiCdataset()
TR.load("GM-all.refined")
hm = TR.buildHeatmap(1, 1, 1000000, False, False)
TR.calculateWeights()
TR.weights = np.ones(len(TR.weights), float) # if you want to correct just by fragment density, not by length dependence
hm2 = TR.buildHeatmap(1, 1, 1000000, False, weights=True)
hm2[np.isnan(hm2)] = 0
mask = np.sum(hm, axis=0) > 0
"""p1-6 are 6 lines to be plotted, below is plotting only"""
p1 = np.sum(hm, axis=0)[mask]
p3 = np.sum(correct(hm), axis=0)[mask]
p5 = np.sum(ultracorrect(hm, 40), axis=0)[mask]
p4 = np.sum(correct(hm2), axis=0)[mask]
p2 = np.sum(hm2, axis=0)[mask]
p6 = np.sum(ultracorrect(hm2, 40), axis=0)[mask]
matplotlib.rcParams['font.sans-serif'] = 'Arial'
dashstyle = (3, 3)
plt.figure(figsize=(4, 4))
ax = plt.subplot(2, 1, 1)
plt.xlim((0, 80))
plt.ylim((0, 2))
plt.ylabel("Total coverage", fontsize=8)
line21 = plt.plot(p1 / p1.mean(), "-", linewidth=1, color="#e5a826")[0]
line22 = plt.plot(
p3 / p3.mean(), "--", linewidth=1, color="#e5a826")[0]
line22.set_dashes(dashstyle)
line23 = plt.plot(p5 / p5.mean(), linewidth=1, color="grey")[0]
for xlabel_i in ax.get_xticklabels():
xlabel_i.set_fontsize(8)
for xlabel_i in ax.get_yticklabels():
xlabel_i.set_fontsize(8)
legend = plt.legend([line21, line22, line23],
["Raw data", "Single correction", "Iterative correction"], prop={"size": 6}, loc=1, handlelength=2)
legend.draw_frame(False)
removeAxes(shift=0, ax=ax)
for i in ax.spines.values():
i.set_color('none')
ax.axhline(linewidth=1, color='black')
ax.axvline(linewidth=1, color='black')
ax2 = plt.subplot(2, 1, 2, sharex=ax)
plt.xlim((0, 80))
plt.ylim((0, 2))
plt.xlabel("Position on chom 1 (MB)", fontsize=8)
plt.ylabel("Total coverage", fontsize=8)
line1 = plt.plot(p4 / p4.mean(), "--", color="#9b3811", linewidth=1)[0]
line1.set_dashes(dashstyle)
line2 = plt.plot(p2 / p2.mean(), "-", color="#9b3811", linewidth=1)[0]
line3 = plt.plot(p6 / p6.mean(), linewidth=1, color="grey")[0]
for xlabel_i in ax2.get_xticklabels():
xlabel_i.set_fontsize(8)
for xlabel_i in ax2.get_yticklabels():
xlabel_i.set_fontsize(8)
legend = plt.legend([line2, line1, line3],
["HindIII corrected", "Single correction", "Iterative correction"], prop={"size": 6}, loc=1, handlelength=2)
legend.draw_frame(False)
removeAxes(shift=0, ax=ax2)
plotting.niceShow()
def showAllDatasets():
setExceptionHook()
#plt.figure(figsize=(25, 15))
fig = plt.figure()
#size of the figure
fw = fig.get_figwidth() * fig.get_dpi()
fh = fig.get_figheight() * fig.get_dpi()
#get subplot configuration
sx, sy = subplots(len(datasets))
for j, dataset in enumerate(datasets):
curPlot = plt.subplot(sx, sy, j + 1)
heatmap = 1. * h5dict(hm(dataset), 'r')["heatmap"]
#fill in gaps - obsolete, as heatmaps are with overlaps
for _ in range(1):
zeros = np.sum(heatmap, axis=0) == 0
zeros = np.nonzero(zeros)[0]
heatmap[zeros] = heatmap[zeros - 1]
heatmap[:, zeros] = heatmap[:, zeros - 1]
#regular IC protocol
mirnylib.numutils.fillDiagonal(heatmap, 0, 0)
mirnylib.numutils.fillDiagonal(heatmap, 0, 1)
mirnylib.numutils.fillDiagonal(heatmap, 0, -1)
heatmap = trunc(heatmap, low=0, high=0.0001)
heatmap = ultracorrect(heatmap)
diag2value = np.mean(np.diagonal(heatmap, 2))
mirnylib.numutils.fillDiagonal(heatmap, 1.5 * diag2value, 0)
mirnylib.numutils.fillDiagonal(heatmap, 1.2 * diag2value, 1)
mirnylib.numutils.fillDiagonal(heatmap, 1.2 * diag2value, -1)
newHeatmap = heatmap
#Top highly expressed genes
#genePos = [18, 56, 77, 117, 143, 215, 234, 256, 266, 286, 300, 326, 336, 367, 379]
geneCoor = [1162773, 3509071, 1180887, 543099, 1953250, 2522439, 3328524, 1503879, 900483, 242693, 3677144, 3931680, 3677704, 3762707, 3480870, 3829656, 1424678, 901855, 1439056, 3678537]
# here we commited to 10kb resolution - change below if you're not
genePos = [i / 10000. for i in geneCoor]
genePos = []
#putting lines at highly expressed genes
for lpos in genePos:
plt.hlines(lpos , 0, 500, linewidth=0.7, color="black", alpha=0.2, zorder=1)
plt.vlines(lpos , 0, 500, linewidth=0.7, color="black", alpha=0.2, zorder=1)
pass
#performing adaptive smoothing
smoothedHeatmap = adaptiveSmoothing(newHeatmap, 20)
smoothedHeatmap /= np.mean(np.sum(heatmap, axis=0))
#print dataset, sum([np.diagonal(smoothedHeatmap, i).sum() for i in range(60, 140)])
#maps = [[smoothedHeatmap, smoothedHeatmap[:30]],
# [smoothedHeatmap[:, :30], smoothedHeatmap[:30, :30]]]
#smoothedHeatmap = np.hstack([np.vstack(i) for i in maps])
allx = []
ally = []
plt.title(dataset, fontsize=10)
plt.imshow((smoothedHeatmap), interpolation="none", vmax=0.035, cmap="acidblues", zorder=0)
#plt.imshow((smoothedHeatmap), interpolation="nearest", vmin=0, vmax=np.exp(-4.5), cmap="fall", zorder=0)
plt.xticks([])
plt.yticks([])
plt.subplots_adjust(left=0.05, # the left side of the subplots of the figure
right=0.95, # the right side of the subplots of the figure
bottom=0.05, # the bottom of the subplots of the figure
top=0.95 , # the top of the subplots of the figure
wspace=0.1, # the amount of width reserved for blank space between subplots
hspace=0.2)
#cPickle.dump(scaling, open(dataset.split("/")[-1] + "scaling", 'w'))
#plt.ylim((400, 200))
#plt.xlim((0, 200))
#code below just puts the P(s) over the heatmap
N = len(smoothedHeatmap)
pts = np.array([[1, 0], [N, N], [N, 0]])
p = Polygon(pts, closed=True, facecolor=(0.8, 0.8, 0.8), linewidth=0, alpha=0.7, zorder=2)
ax = plt.gca()
ax.add_patch(p)
Bbox = matplotlib.transforms.Bbox.from_bounds(.55, .55, .35, .42)
tBbox = matplotlib.transforms.TransformedBbox(Bbox, ax.transAxes).get_points()
l, b, w, h = tBbox[0, 0] / fw, tBbox[0, 1] / fh, (tBbox[1, 0] - tBbox[0, 0]) / fw, (tBbox[1, 1] - tBbox[0, 1]) / fh
axins = fig.add_axes([l, b, w, h], axisbg=(0, 0, 0, 0), xscale="log", yscale="log")
removeAxes(ax=axins)
for xlabel_i in axins.get_xticklabels(): xlabel_i.set_fontsize(6)
for xlabel_i in axins.get_yticklabels(): xlabel_i.set_fontsize(6)
N = len(smoothedHeatmap)
st = int(0.05 * N)
end = int(0.45 * N)
st2 = int(0.55 * N)
end2 = int(0.95 * N)
axins.plot(*scaling(0.5 * (smoothedHeatmap[st:end, st:end] + smoothedHeatmap[st2:end2, st2:end2])), color="blue", label="intra-arm")
if (dataset in ['Wildtype_0min_BglII_rep1', "ML2000_0hr"]):
myscaling = scaling(0.5 * (smoothedHeatmap[st:end, st:end] + smoothedHeatmap[st2:end2, st2:end2]))
#axins.plot(*scaling(smoothedHeatmap[st:end, end2:st2:-1]), color="green", label="inter-arm")
axins.set_xlabel("kb", fontsize=6)
axins.set_ylabel("Pc", fontsize=6)
axins.grid()
if "myscaling" in locals():
axins.plot(*myscaling, color="grey")
#axins.set_xticks([])
#axins.set_yticks([])
#axins.tick_params(color="red")
#axins.set_xlabel("Mb")
#axins.set_ylabel("Pc")
for i, line in enumerate(axins.get_xticklines() + axins.get_yticklines()):
if i % 2 == 1: # odd indices
line.set_visible(False)
#if dataset != "Wildtype_0min_BglII_rep1":
# data = cPickle.load(open("scalings/{0}".format(dataset)))
# axins.plot(*data, color="blue")
#axins.xscale("log")
#axins.yscale("log")
#end strange code
plt.show()
def plotFigure2c():
TR = HiCdataset()
TR.load("GM-all.refined")
hm = TR.buildHeatmap(1, 1, 1000000, False, False)
TR.calculateWeights()
TR.weights = np.ones(
len(TR.weights), float
) # if you want to correct just by fragment density, not by length dependence
hm2 = TR.buildHeatmap(1, 1, 1000000, False, weights=True)
hm2[np.isnan(hm2)] = 0
mask = np.sum(hm, axis=0) > 0
"""p1-6 are 6 lines to be plotted, below is plotting only"""
p1 = np.sum(hm, axis=0)[mask]
p3 = np.sum(correct(hm), axis=0)[mask]
p5 = np.sum(ultracorrect(hm, 40), axis=0)[mask]
p4 = np.sum(correct(hm2), axis=0)[mask]
p2 = np.sum(hm2, axis=0)[mask]
p6 = np.sum(ultracorrect(hm2, 40), axis=0)[mask]
matplotlib.rcParams['font.sans-serif'] = 'Arial'
dashstyle = (3, 3)
plt.figure(figsize=(4, 4))
ax = plt.subplot(2, 1, 1)
plt.xlim((0, 80))
plt.ylim((0, 2))
plt.ylabel("Total coverage", fontsize=8)
line21 = plt.plot(p1 / p1.mean(), "-", linewidth=1, color="#e5a826")[0]
line22 = plt.plot(p3 / p3.mean(), "--", linewidth=1, color="#e5a826")[0]
line22.set_dashes(dashstyle)
line23 = plt.plot(p5 / p5.mean(), linewidth=1, color="grey")[0]
for xlabel_i in ax.get_xticklabels():
xlabel_i.set_fontsize(8)
for xlabel_i in ax.get_yticklabels():
xlabel_i.set_fontsize(8)
legend = plt.legend(
[line21, line22, line23],
["Raw data", "Single correction", "Iterative correction"],
prop={"size": 6},
loc=1,
handlelength=2)
legend.draw_frame(False)
removeAxes(shift=0, ax=ax)
for i in ax.spines.values():
i.set_color('none')
ax.axhline(linewidth=1, color='black')
ax.axvline(linewidth=1, color='black')
ax2 = plt.subplot(2, 1, 2, sharex=ax)
plt.xlim((0, 80))
plt.ylim((0, 2))
plt.xlabel("Position on chom 1 (MB)", fontsize=8)
plt.ylabel("Total coverage", fontsize=8)
line1 = plt.plot(p4 / p4.mean(), "--", color="#9b3811", linewidth=1)[0]
line1.set_dashes(dashstyle)
line2 = plt.plot(p2 / p2.mean(), "-", color="#9b3811", linewidth=1)[0]
line3 = plt.plot(p6 / p6.mean(), linewidth=1, color="grey")[0]
for xlabel_i in ax2.get_xticklabels():
xlabel_i.set_fontsize(8)
for xlabel_i in ax2.get_yticklabels():
xlabel_i.set_fontsize(8)
legend = plt.legend(
[line2, line1, line3],
["HindIII corrected", "Single correction", "Iterative correction"],
prop={"size": 6},
loc=1,
handlelength=2)
legend.draw_frame(False)
removeAxes(shift=0, ax=ax2)
plotting.niceShow()
def showAllDatasets():
setExceptionHook()
#plt.figure(figsize=(25, 15))
fig = plt.figure()
#size of the figure
fw = fig.get_figwidth() * fig.get_dpi()
fh = fig.get_figheight() * fig.get_dpi()
#get subplot configuration
sx, sy = subplots(len(datasets))
for j, dataset in enumerate(datasets):
curPlot = plt.subplot(sx, sy, j + 1)
heatmap = 1. * h5dict(hm(dataset), 'r')["heatmap"]
#fill in gaps - obsolete, as heatmaps are with overlaps
for _ in range(1):
zeros = np.sum(heatmap, axis=0) == 0
zeros = np.nonzero(zeros)[0]
heatmap[zeros] = heatmap[zeros - 1]
heatmap[:, zeros] = heatmap[:, zeros - 1]
#regular IC protocol
mirnylib.numutils.fillDiagonal(heatmap, 0, 0)
mirnylib.numutils.fillDiagonal(heatmap, 0, 1)
mirnylib.numutils.fillDiagonal(heatmap, 0, -1)
heatmap = trunc(heatmap, low=0, high=0.0001)
heatmap = ultracorrect(heatmap)
diag2value = np.mean(np.diagonal(heatmap, 2))
mirnylib.numutils.fillDiagonal(heatmap, 1.5 * diag2value, 0)
mirnylib.numutils.fillDiagonal(heatmap, 1.2 * diag2value, 1)
mirnylib.numutils.fillDiagonal(heatmap, 1.2 * diag2value, -1)
newHeatmap = heatmap
#Top highly expressed genes
#genePos = [18, 56, 77, 117, 143, 215, 234, 256, 266, 286, 300, 326, 336, 367, 379]
geneCoor = [
1162773, 3509071, 1180887, 543099, 1953250, 2522439, 3328524,
1503879, 900483, 242693, 3677144, 3931680, 3677704, 3762707,
3480870, 3829656, 1424678, 901855, 1439056, 3678537
]
# here we commited to 10kb resolution - change below if you're not
genePos = [i / 10000. for i in geneCoor]
genePos = []
#putting lines at highly expressed genes
for lpos in genePos:
plt.hlines(lpos,
0,
500,
linewidth=0.7,
color="black",
alpha=0.2,
zorder=1)
plt.vlines(lpos,
0,
500,
linewidth=0.7,
color="black",
alpha=0.2,
zorder=1)
pass
#performing adaptive smoothing
smoothedHeatmap = adaptiveSmoothing(newHeatmap, 20)
smoothedHeatmap /= np.mean(np.sum(heatmap, axis=0))
#print dataset, sum([np.diagonal(smoothedHeatmap, i).sum() for i in range(60, 140)])
#maps = [[smoothedHeatmap, smoothedHeatmap[:30]],
# [smoothedHeatmap[:, :30], smoothedHeatmap[:30, :30]]]
#smoothedHeatmap = np.hstack([np.vstack(i) for i in maps])
allx = []
ally = []
plt.title(dataset, fontsize=10)
plt.imshow((smoothedHeatmap),
interpolation="none",
vmax=0.035,
cmap="acidblues",
zorder=0)
#plt.imshow((smoothedHeatmap), interpolation="nearest", vmin=0, vmax=np.exp(-4.5), cmap="fall", zorder=0)
plt.xticks([])
plt.yticks([])
plt.subplots_adjust(
left=0.05, # the left side of the subplots of the figure
right=0.95, # the right side of the subplots of the figure
bottom=0.05, # the bottom of the subplots of the figure
top=0.95, # the top of the subplots of the figure
wspace=
0.1, # the amount of width reserved for blank space between subplots
hspace=0.2)
#cPickle.dump(scaling, open(dataset.split("/")[-1] + "scaling", 'w'))
#plt.ylim((400, 200))
#plt.xlim((0, 200))
#code below just puts the P(s) over the heatmap
N = len(smoothedHeatmap)
pts = np.array([[1, 0], [N, N], [N, 0]])
p = Polygon(pts,
closed=True,
facecolor=(0.8, 0.8, 0.8),
linewidth=0,
alpha=0.7,
zorder=2)
ax = plt.gca()
ax.add_patch(p)
Bbox = matplotlib.transforms.Bbox.from_bounds(.55, .55, .35, .42)
tBbox = matplotlib.transforms.TransformedBbox(
Bbox, ax.transAxes).get_points()
l, b, w, h = tBbox[0, 0] / fw, tBbox[0, 1] / fh, (
tBbox[1, 0] - tBbox[0, 0]) / fw, (tBbox[1, 1] - tBbox[0, 1]) / fh
axins = fig.add_axes([l, b, w, h],
axisbg=(0, 0, 0, 0),
xscale="log",
yscale="log")
removeAxes(ax=axins)
for xlabel_i in axins.get_xticklabels():
xlabel_i.set_fontsize(6)
for xlabel_i in axins.get_yticklabels():
xlabel_i.set_fontsize(6)
N = len(smoothedHeatmap)
st = int(0.05 * N)
end = int(0.45 * N)
st2 = int(0.55 * N)
end2 = int(0.95 * N)
axins.plot(*scaling(0.5 * (smoothedHeatmap[st:end, st:end] +
smoothedHeatmap[st2:end2, st2:end2])),
color="blue",
label="intra-arm")
if (dataset in ['Wildtype_0min_BglII_rep1', "ML2000_0hr"]):
myscaling = scaling(0.5 * (smoothedHeatmap[st:end, st:end] +
smoothedHeatmap[st2:end2, st2:end2]))
#axins.plot(*scaling(smoothedHeatmap[st:end, end2:st2:-1]), color="green", label="inter-arm")
axins.set_xlabel("kb", fontsize=6)
axins.set_ylabel("Pc", fontsize=6)
axins.grid()
if "myscaling" in locals():
axins.plot(*myscaling, color="grey")
#axins.set_xticks([])
#axins.set_yticks([])
#axins.tick_params(color="red")
#axins.set_xlabel("Mb")
#axins.set_ylabel("Pc")
for i, line in enumerate(axins.get_xticklines() +
axins.get_yticklines()):
if i % 2 == 1: # odd indices
line.set_visible(False)
#if dataset != "Wildtype_0min_BglII_rep1":
# data = cPickle.load(open("scalings/{0}".format(dataset)))
# axins.plot(*data, color="blue")
#axins.xscale("log")
#axins.yscale("log")
#end strange code
plt.show()
def plotDiagonalCorrelation():
"Correlation of diagonal bins - paper figure"
S = 50
x = numpy.arange(2, S)
Tanay = binnedData(200000, myGenome)
Tanay.simpleLoad(GM200k, "GM-HindIII")
Tanay.simpleLoad(GM200kNcoI, "GM-NcoI")
Tanay.simpleLoad(tcc200k, "TCC")
Tanay.removeDiagonal(1)
Tanay.removePoorRegions()
Tanay.removeZeros()
pairs = [("GM-HindIII", "GM-NcoI"), ("GM-HindIII", "TCC"), (
"GM-NcoI", "TCC")]
cors = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors[j].append(cr(
numpy.diagonal(Tanay.dataDict[pair[0]], i),
numpy.diagonal(Tanay.dataDict[pair[1]], i)
)[0])
Tanay.iterativeCorrectWithoutSS(M=1)
cors2 = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors2[j].append(cr(
numpy.diagonal(Tanay.dataDict[pair[0]], i),
numpy.diagonal(Tanay.dataDict[pair[1]], i)
)[0])
Tanay.iterativeCorrectWithoutSS(M=20)
cors3 = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors3[j].append(cr(
numpy.diagonal(Tanay.dataDict[pair[0]], i),
numpy.diagonal(Tanay.dataDict[pair[1]], i)
)[0])
matplotlib.rcParams['font.sans-serif'] = 'Arial'
#plt.figure(figsize = (2.3,1.8))
print cors
print cors2
print cors3
plt.figure(figsize=(10, 3))
ax = plt.gca()
for j, pair in enumerate(pairs):
plt.subplot(1, len(pairs), j)
fs = 8
for xlabel_i in ax.get_xticklabels():
xlabel_i.set_fontsize(fs)
for xlabel_i in ax.get_yticklabels():
xlabel_i.set_fontsize(fs)
plt.title("%s vs %s" % pair)
plt.plot(x / 5., cors3[j], color="#E5A826", label="Iterative")
plt.plot(x / 5., cors2[j], color="#28459A", label="Single")
plt.plot(x / 5., cors[j], color="#E55726", label="Raw")
plt.xlabel("Genomic Separation, MB", fontsize=8)
plt.ylabel("Spearman correlation", fontsize=8)
plt.legend()
legend = plt.legend(prop={"size": 6}, loc=9, handlelength=2)
legend.draw_frame(False)
plt.ylim((0, 1))
removeAxes(shift=0)
plt.show()
def plotDiagonalCorrelation(resolution, filename1, filename2, experiment1, experiment2, genome, mouse=False, **kwargs):
"Correlation of diagonal bins - paper figure"
global pp
if options.verbose:
print >> sys.stdout, "plotDiagonalCorrelation: res: %d file1: %s file2: %s exp1:%s exp2:%s gen:%s" % (
resolution,
filename1,
filename2,
experiment1,
experiment2,
genome,
)
S = 50
x = numpy.arange(2, S)
Tanay = binnedData(resolution, genome)
Tanay.simpleLoad(filename1, experiment1)
Tanay.simpleLoad(filename2, experiment2)
Tanay.removeDiagonal(1)
Tanay.removePoorRegions()
Tanay.removeZeros()
pairs = [(experiment1, experiment2)]
cors = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors[j].append(
cr(numpy.diagonal(Tanay.dataDict[pair[0]], i), numpy.diagonal(Tanay.dataDict[pair[1]], i))[0]
)
Tanay.iterativeCorrectWithoutSS(M=1)
cors2 = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors2[j].append(
cr(numpy.diagonal(Tanay.dataDict[pair[0]], i), numpy.diagonal(Tanay.dataDict[pair[1]], i))[0]
)
Tanay.iterativeCorrectWithoutSS(M=20)
cors3 = [[] for _ in pairs]
for i in x:
for j, pair in enumerate(pairs):
cors3[j].append(
cr(numpy.diagonal(Tanay.dataDict[pair[0]], i), numpy.diagonal(Tanay.dataDict[pair[1]], i))[0]
)
matplotlib.rcParams["font.sans-serif"] = "Arial"
print "Eigenvectors"
print cors
print cors2
print cors3
plt.figure(figsize=(8, 4))
ax = plt.gca()
for j, pair in enumerate(pairs):
plt.subplot(1, len(pairs), j)
fs = 8
for xlabel_i in ax.get_xticklabels():
xlabel_i.set_fontsize(fs)
for xlabel_i in ax.get_yticklabels():
xlabel_i.set_fontsize(fs)
plt.title("%s vs %s" % pair)
plt.plot(x / 5.0, cors3[j], color="#E5A826", label="Iterative")
plt.plot(x / 5.0, cors2[j], color="#28459A", label="Single")
plt.plot(x / 5.0, cors[j], color="#E55726", label="Raw")
plt.xlabel("Genomic Separation, MB", fontsize=8)
plt.ylabel("Spearman correlation", fontsize=8)
plt.legend()
legend = plt.legend(prop={"size": 6}, loc=9, handlelength=2)
legend.draw_frame(False)
plt.ylim((0, 1))
removeAxes(shift=0)
plt.show()
pp.savefig()