def plotCisToTransHotFragments(dataset="../../../mouse/data/combined/"\
"mouse1_merged.frag",
workingFile="../../../tcc/working/workingMouse.frag",
cacheFile="../../../tcc/working/workingMouseFiltered.frag",
genomeFolder="../../../data/mm9", label=None):
mirnylib.systemutils.setExceptionHook()
if not os.path.exists(cacheFile):
print "caching parsed data"
FH = HiCdataset(workingFile, genomeFolder)
FH.load(dataset)
FH.filterRsiteStart(offset=5)
FH.filterDuplicates()
#TR.save(filename[1]+".dat")
FH.filterLarge()
FH.maskFilter(FH.DS)
FH.save(cacheFile)
FH = HiCdataset(workingFile, genomeFolder)
FH.load(cacheFile)
fs = FH.fragmentSum()
FH.saveFragments()
FH.maskFilter(FH.chrms1 == FH.chrms2)
FH.originalFragments()
fsCis = FH.fragmentSum()
args = numpy.argsort(fs)
fsSort = 1. * fs[args]
fsCisSort = 1. * fsCis[args]
cisToTrans = fsCisSort / fsSort
p1, p2, p3 = numpy.percentile(fsSort, [99, 99.5, 99.9])
bins = mirnylib.numutils.logbins(1, fsSort.max(), 1.08)
counts = numpy.histogram(fsSort, bins)
values = numpy.histogram(fsSort, bins, weights=cisToTrans)
plt.plot(0.5 * (values[1][:-1] + values[1][1:]), values[0] /
counts[0], '.', label=label)
for linep in p1, p2, p3:
plt.vlines(linep, 0, 1)
plt.xlabel("Counts per fragment")
plt.ylabel("Cis-to-trans ratio")
plt.title("Vertical lines are at 99%,99.5% and 99.9% reads per fragment")
niceShow()
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 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()
plt.yscale("log")
for filename in filelist:
scalings = give_slices(
base="{0}/blockDATA2.dat".format(filename),
tosave=None,
nproc=4,
slices=[250],
sliceParams=(200),
multipliers=numpy.arange(0.850001, 1.0001, 0.001),
# multipliers=[1],
mode="chain",
loadFunction=polymerutils.load)
setExceptionHook()
values = [i[0] for i in scalings]
values = numpy.array(values)
values[:, 0, :] /= 2500
labels = [
"{0}; time = ".format(filename) + str(i[1]["slice"]) for i in scalings
]
for scaling, label in map(None, values, labels):
plt.plot(*scaling[0], label=label)
a = logbins(10, 10000, 1.2)
a = numpy.array(a)
plt.plot(a / 2500., 1e-5 * a**(-0.5), label="Proposed -0.5 scaling")
plt.xlabel("distance (MB)")
niceShow()
exit()
plt.plot(*value[0],
color=color,
linestyle=linestyle,
label="L={0}; num={1}".format(len, num))
#values1[:, 0, :] /= (1000000. / 600)
#cPickle.dump((scalings, values), open("consScaff", 'wb'))
#exit()
setExceptionHook()
a = logbins(10, 10000, 1.2)
a = numpy.array(a)
plt.xlabel("distance (MB)")
niceShow("log")
exit()
for scaling, label in zip(values, labels):
plt.plot(*scaling[1], label=label)
a = logbins(10, 10000, 1.2)
a = numpy.array(a)
plt.plot(a, 2 * a**(1 / 6.))
niceShow("log")
for scaling, label in zip(values, labels):
plt.plot(*scaling[2], label=label)
niceShow("log")
pc = scalings[0][0][0][1]
rg = scalings[0][0][1][1]
def plotCorrelationAtDifferentBinning():
"""Plots figure with correlation at different binning.
Note the caching and creating of binned heatmaps flags below.
Suppplementary paper figure
"""
sizes = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
setExceptionHook()
cache = False
create = False
if create == True:
if cache == True:
#-------------------standard version code-----------------
FR = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
override=False, inMemory=True)
FR.load("../../../ErezPaperData/hg18/GM-HindIII-hg18_refined.frag")
FR3 = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
override=False, inMemory=True)
FR3.load("../../../ErezPaperData/hg18/GM-HindIII-hg18"\
"_refined.frag")
FR2 = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
override=False, inMemory=True)
FR2.load("../../../ErezPaperData/hg18/GM-NcoI-hg18_refined.frag")
#----------------------cross-check code----------------
# FR = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
# override=False, inMemory=True)
# FR.load("../../../ErezPaperData/hg18/GM-NcoI-hg18_refined.frag")
#
# FR3 = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
# override=False, inMemory=True)
# FR3.load("../../../ErezPaperData/hg18/GM-NcoI-hg18_refined.frag")
#
# FR2 = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
# override=False, inMemory=True)
# FR2.load("../../../ErezPaperData/hg18/G"\
# "M-HindIII-hg18_refined.frag")
#-------end corss-check code ---------------------------------
#--------Filter only trans DS reads-----------------
FR.maskFilter(FR.DS * (FR.chrms1 != FR.chrms2))
FR2.maskFilter(FR2.DS * (FR2.chrms1 != FR2.chrms2))
FR3.maskFilter(FR3.DS * (FR3.chrms1 != FR3.chrms2))
#Now create two halfs of one dataset and down-sample second dataset
#----------------------standard version code--------
fraction = 0.5 * len(FR.DS) / float(len(FR2.DS))
rarray = numpy.random.random(len(FR.DS))
mask1 = rarray < 0.5
mask3 = rarray >= 0.5
mask2 = numpy.random.random(len(FR2.DS)) < fraction
#-------------------- cross-check code---------
#fraction = 0.5 * len(FR2.DS) / float(len(FR.DS))
#rarray = numpy.random.random(len(FR.DS))
#mask1 = rarray < fraction
#mask3 = (rarray > fraction) * (rarray < fraction * 2)
#mask2 = numpy.random.random(len(FR2.DS)) > 0.5
#-----------------------------------------
FR.maskFilter(mask1)
FR2.maskFilter(mask2)
FR3.maskFilter(mask3)
FR.save("../../../tcc/working/cache1")
FR2.save("../../../tcc/working/cache2")
FR3.save("../../../tcc/working/cache3")
else:
FR = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
override=False, inMemory=True)
FR.load("../../../tcc/working/cache1")
FR3 = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
override=False, inMemory=True)
FR3.load("../../../tcc/working/cache3")
FR2 = fragmentHiC.HiCdataset("bla", "../../../data/hg18",
override=False, inMemory=True)
FR2.load("../../../tcc/working/cache2")
for size in sizes:
FR.saveHeatmap("../../../tcc/working/HindIII_%d.hm" %
size, size * 1000000)
FR2.saveHeatmap("../../../tcc/working/NcoI_%d.hm" %
size, size * 1000000)
FR3.saveHeatmap("../../../tcc/working/control_%d.hm" %
size, size * 1000000)
p1 = []
p2 = []
p3 = []
p4 = []
evs = []
for size in sizes:
BD = binnedDataAnalysis(size * 1000000, "../../../data/hg18")
BD.simpleLoad("../../../tcc/working/HindIII_%d.hm" % size, "HindIII")
BD.simpleLoad("../../../tcc/working/NcoI_%d.hm" % size, "NcoI")
BD.simpleLoad("../../../tcc/working/control_%d.hm" % size, "control")
BD.removeDiagonal()
BD.removePoorRegions(cutoff=2)
BD.removeCis()
data1 = BD.dataDict["HindIII"]
data2 = BD.dataDict["NcoI"]
data3 = BD.dataDict["control"]
mask = (numpy.sum(
data1, axis=0) > 0) * (numpy.sum(data2, axis=0) > 0)
validMask = mask[:, None] * mask[None, :]
transmask = BD.chromosomeIndex[:, None] != BD.chromosomeIndex[None, :]
cormask = transmask * validMask
c1 = scipy.stats.spearmanr(data1[cormask], data2[cormask])[0]
c4 = scipy.stats.spearmanr(data1[cormask], data3[cormask])[0]
if size == 1:
evs.append(BD.interchromosomalValues("HindIII"))
evs.append(BD.interchromosomalValues("NcoI"))
evs.append(BD.interchromosomalValues("control"))
p4.append(c4)
p1.append(c1)
print "size\t%d\traw:" % size, c1,
BD.removeZeros()
BD.fakeCis() # does iterative correction as well
BD.restoreZeros(value=0)
data1 = BD.dataDict["HindIII"]
data2 = BD.dataDict["NcoI"]
data3 = BD.dataDict["control"]
c2 = scipy.stats.spearmanr(data1[cormask], data2[cormask])[0]
c3 = scipy.stats.spearmanr(data1[cormask], data3[cormask])[0]
if size == 1:
evs.append(BD.interchromosomalValues("HindIII"))
evs.append(BD.interchromosomalValues("NcoI"))
evs.append(BD.interchromosomalValues("control"))
print evs
p3.append(c3)
p2.append(c2)
print "\tcorrected:", c2, "\tcontrol", c3
plt.plot(sizes, p1, label="Raw data, between enzymes")
plt.plot(sizes, p2, label="Iteratively corrected, between")
plt.plot(sizes, p3, label="IC, within")
plt.xlabel("Bin size, MB")
plt.xticks(range(1, 11))
plt.ylabel("Spearman correlation coefficient")
plt.legend()
niceShow()
setExceptionHook()
0 / 0
def plotTanayGenomicFeature():
"""Shows how genomic feature is spawned by Eig1, not Tanay domains
paper supplementary figure"""
Tanay = experimentalBinnedData(1000000, myGenome)
Tanay.simpleLoad(GM1M, "GM-all")
Tanay.loadTanayDomains()
Tanay.loadWigFile("../../../histoneMarks/hg18/wgEncodeUwDnaseSeqRawSignal"\
"Rep1Gm06990.bigWig", label="feature")
#Tanay.loadWigFile("../../../histoneMarks/hg18/wgEncodeBroadChipSeqSignal"\
#"Gm12878H3k9ac.wig", label = "feature",
#control = "../../../histoneMarks/hg18/wgEncodeBroadChipSeqSignal"\
#"Gm12878Control.wig")
#Tanay.loadWigFile("../../../histoneMarks/hg18/wgEncodeBroadChipSeqSignal"\
#"Gm12878H3k4me3.wig", label = "feature",
#control = "../../../histoneMarks/hg18/wgEncodeBroadChipSeqSignal"\
#"Gm12878Control.wig")
Tanay.removeDiagonal()
Tanay.removePoorRegions()
Tanay.removeZeros()
Tanay.fakeCis()
Tanay.doEig()
E1 = Tanay.EigDict["GM-all"][0]
E2 = Tanay.EigDict["GM-all"][1]
GC = Tanay.trackDict["GC"]
if scipy.stats.spearmanr(E1, GC)[0] < 0:
E1 = -E1
if scipy.stats.spearmanr(E2, GC)[0] < 0:
E2 = -E2
TD = Tanay.trackDict["TanayDomains"]
print scipy.stats.spearmanr(Tanay.trackDict["feature"], E1)
plt.scatter(Tanay.trackDict["feature"], E1, c=TD, s=4, linewidth=0)
cm = plt.cm.get_cmap("jet")
print "Our 2r is", (
numpy.corrcoef(Tanay.trackDict["feature"], E1)[0, 1]) ** 2
tset = set(TD)
tfeature = numpy.zeros_like(TD, dtype=float)
feature = Tanay.trackDict["feature"]
for i in tset:
#print i
#print numpy.mean(feature[TD==i])
tfeature[TD == i] = numpy.mean(feature[TD == i])
#print tfeature
print "Tanay r2 is", (numpy.corrcoef(tfeature, E1)[0, 1]) ** 2
plt.legend([matplotlib.lines.Line2D([0], [0], color=cm(i), marker="o",
markersize=8, linewidth=0) \
for i in [0.333, 0.666, 0.999]],
["Active", "Centromere proximal", "Centromere distal"], loc=2)
plt.ylabel("Eig1GW")
#plt.xlabel("UWashington DNAse")
#plt.xlabel("H3K9ac ChIP-seq")
plt.xlabel("H3K4me3 ChIP-seq")
plt.title("Color represents domain from (Yaffe 2011)")
niceShow(subplotAdjust=(0.13, 0.11, 0.97, 0.92))