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 doArmPlot(resolution, filename, experiment, genome, mouse=False, **kwargs):
"Plot an single interarm map - paper figure"
global pp
plt.figure()
if (options.verbose):
print >> sys.stdout, "doArmPlot: res: %d file: %s exp:%s gen:%s" % (resolution, filename, experiment, genome)
Tanay = binnedDataAnalysis(resolution, genome)
Tanay.simpleLoad(filename, experiment)
if mouse == True:
Tanay.fakeTranslocations([(0, 0, None, 12, 52000000, None),
(4, 45000000, None, 12, 0, 30000000),
(9, 0, 50000000, 12, 0, 35000000)])
Tanay.removeChromosome(19)
else:
Tanay.removeChromosome(22)
Tanay.removeDiagonal(1)
Tanay.removePoorRegions()
Tanay.truncTrans()
Tanay.fakeCis()
#mat_img(Tanay.dataDict["GM-all"])
#plt.figure(figsize = (3.6,3.6))
Tanay.averageTransMap(experiment, **kwargs)
#plotting.removeBorder()
cb = plt.colorbar(orientation="vertical")
#cb.set_ticks([-0.05,0.05,0.15])
for xlabel_i in cb.ax.get_xticklabels():
xlabel_i.set_fontsize(6)
def plotSixHeatmaps():
"Plots 6 heatmaps to a correlation supplementary figure"
plt.figure(figsize=(3, 3))
for size in [10]:
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=5)
BD.removeZeros()
beg1 = BD.chromosomeStarts[0]
beg2 = BD.chromosomeStarts[1]
end1 = BD.chromosomeEnds[0] - 1
end2 = BD.chromosomeEnds[1] - 1
data1 = BD.dataDict["HindIII"][beg1:end1, beg2:end2]
data2 = BD.dataDict["NcoI"][beg1:end1, beg2:end2]
data3 = BD.dataDict["control"][beg1:end1, beg2:end2]
def minmax(*args):
mi = min([i.min() for i in args])
ma = max([i.max() for i in args])
return mi, ma
vmin, vmax = minmax(data1, data2)
plt.subplot(321)
plt.imshow(data1, interpolation="nearest", vmin=vmin, vmax=vmax)
plt.title("HindIII, raw")
plt.colorbar()
plt.subplot(322)
plt.imshow(data2, interpolation="nearest", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.title("NcoI, raw")
BD.iterativeCorrectWithoutSS()
data1 = BD.dataDict["HindIII"][beg1:end1, beg2:end2]
data2 = BD.dataDict["NcoI"][beg1:end1, beg2:end2]
data3 = BD.dataDict["control"][beg1:end1, beg2:end2]
vmin, vmax = minmax(data1, data2, data3)
plt.subplot(323)
plt.imshow(data1, interpolation="nearest", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.title("HindIII, IC",)
plt.subplot(324)
plt.imshow(data2, interpolation="nearest", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.title("NcoI, IC")
plt.subplot(325)
plt.imshow(data1, interpolation="nearest", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.title("HindIII, 50%")
plt.subplot(326)
plt.imshow(data3, interpolation="nearest", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.title("HindIII, 50%")
plt.show()
def doArmPlot(resolution, filename, experiment, genome, mouse=False, **kwargs):
"Plot an single interarm map - paper figure"
global pp
plt.figure()
if (options.verbose):
print >> sys.stdout, "doArmPlot: res: %d file: %s exp:%s gen:%s" % (
resolution, filename, experiment, genome)
Tanay = binnedDataAnalysis(resolution, genome)
Tanay.simpleLoad(filename, experiment)
if mouse == True:
Tanay.fakeTranslocations([(0, 0, None, 12, 52000000, None),
(4, 45000000, None, 12, 0, 30000000),
(9, 0, 50000000, 12, 0, 35000000)])
Tanay.removeChromosome(19)
else:
Tanay.removeChromosome(22)
Tanay.removeDiagonal(1)
Tanay.removePoorRegions()
Tanay.truncTrans()
Tanay.fakeCis()
#mat_img(Tanay.dataDict["GM-all"])
#plt.figure(figsize = (3.6,3.6))
Tanay.averageTransMap(experiment, **kwargs)
#plotting.removeBorder()
cb = plt.colorbar(orientation="vertical")
#cb.set_ticks([-0.05,0.05,0.15])
for xlabel_i in cb.ax.get_xticklabels():
xlabel_i.set_fontsize(6)
def getInterValues(filenames, genome):
allValues = []
for i in filenames:
BD = binnedDataAnalysis(1000000, "/home/magus/HiC2011/data/{0}".format(genome), readChrms=["#", "X"])
BD.simpleLoad("{1}/{0}-1000k.hm".format(i, genome), "test")
BD.truncTrans(high=0.0001)
allValues.append(BD.interchromosomalValues("test"))
return allValues
def compareCorrelationOfEigenvectors():
"""Plot correlation figure with eigenvector correlation between datasets
paper figure """
Tanay = binnedDataAnalysis(1000000, "../../../data/hg18")
Tanay.simpleLoad("../../../ErezPaperData/hg18/GM-HindIII-hg18-1M.hm",
"Erez")
Tanay.simpleLoad("../../../ErezPaperData/hg18/GM-NcoI-hg18-1M.hm", "NcoI")
Tanay.simpleLoad("../../../tcc/hg18/tcc-HindIII-hg18-1M.hm", "TCC")
Tanay.removeDiagonal()
Tanay.removePoorRegions()
Tanay.removeZeros()
Tanay.truncTrans()
Tanay.fakeCis()
M = 10
Tanay.doEig(numPCs=M)
E1 = Tanay.EigDict["Erez"]
E2 = Tanay.EigDict["NcoI"]
E3 = Tanay.EigDict["TCC"]
data = numpy.zeros((M, M))
data2 = numpy.zeros((M, M))
data3 = numpy.zeros((M, M))
for i in xrange(M):
for j in xrange(M):
data[i][j] = abs(numpy.corrcoef(E2[i], E1[j])[0, 1])
data2[i][j] = abs(numpy.corrcoef(E3[i], E1[j])[0, 1])
data3[i][j] = abs(numpy.corrcoef(E3[i], E2[j])[0, 1])
plt.figure(figsize=(7.5, 2.5))
plt.gcf().subplots_adjust(0.2, 0.2, 0.85, 0.85)
plt.subplot(131)
plt.xlabel("HiC 2009, HindIII")
plt.ylabel("HiC 2009, NcoI")
#plt.title("Abs. correlation between eigenvectors")
plt.imshow(data, interpolation="nearest", vmin=0, vmax=1)
plt.colorbar()
plt.subplot(132)
plt.xlabel("HiC 2009, HindIII")
plt.ylabel("TCC 2011, HindIII")
#plt.title("Abs. correlation between eigenvectors")
plt.imshow(data2, interpolation="nearest", vmin=0, vmax=1)
plt.colorbar()
plt.subplot(133)
plt.xlabel("HiC 2009, NcoI")
plt.ylabel("TCC 2011, HindIII")
#plt.title("Abs. correlation between eigenvectors")
plt.imshow(data3, interpolation="nearest", vmin=0, vmax=1)
plt.colorbar()
plt.show()
raise
def compareCorrelationOfEigenvectors(
resolution, filename1, filename2, experiment1, experiment2, genome, mouse=False, **kwargs
):
"""Plot correlation figure with eigenvector correlation between datasets
paper figure """
global pp
if options.verbose:
print >> sys.stdout, "compareCorrelationOfEigenvectors: res: %d file1: %s file2: %s exp1:%s exp2:%s gen:%s" % (
resolution,
filename1,
filename2,
experiment1,
experiment2,
genome,
)
plt.figure()
Tanay = binnedDataAnalysis(resolution, genome)
Tanay.simpleLoad(filename1, experiment1)
Tanay.simpleLoad(filename2, experiment2)
Tanay.removeDiagonal()
Tanay.removePoorRegions()
Tanay.removeZeros()
Tanay.truncTrans()
Tanay.fakeCis()
M = 10
Tanay.doEig(numPCs=M)
E1 = Tanay.EigDict[experiment1]
E2 = Tanay.EigDict[experiment2]
data = numpy.zeros((M, M))
for i in xrange(M):
for j in xrange(M):
data[i][j] = abs(numpy.corrcoef(E2[i], E1[j])[0, 1])
plt.figure(figsize=(8, 8))
plt.gcf().subplots_adjust(0.2, 0.2, 0.85, 0.85)
plt.subplot(111)
plt.xlabel(experiment1)
plt.ylabel(experiment2)
# plt.title("Abs. correlation between eigenvectors")
plt.imshow(data, interpolation="nearest", vmin=0, vmax=1)
plt.colorbar()
plt.show()
pp.savefig()
def compareCorrelationOfEigenvectors(resolution,
filename1,
filename2,
experiment1,
experiment2,
genome,
mouse=False,
**kwargs):
"""Plot correlation figure with eigenvector correlation between datasets
paper figure """
global pp
if (options.verbose):
print >> sys.stdout, "compareCorrelationOfEigenvectors: res: %d file1: %s file2: %s exp1:%s exp2:%s gen:%s" % (
resolution, filename1, filename2, experiment1, experiment2, genome)
plt.figure()
Tanay = binnedDataAnalysis(resolution, genome)
Tanay.simpleLoad(filename1, experiment1)
Tanay.simpleLoad(filename2, experiment2)
Tanay.removeDiagonal()
Tanay.removePoorRegions()
Tanay.removeZeros()
Tanay.truncTrans()
Tanay.fakeCis()
M = 10
Tanay.doEig(numPCs=M)
E1 = Tanay.EigDict[experiment1]
E2 = Tanay.EigDict[experiment2]
data = numpy.zeros((M, M))
for i in xrange(M):
for j in xrange(M):
data[i][j] = abs(numpy.corrcoef(E2[i], E1[j])[0, 1])
plt.figure(figsize=(8, 8))
plt.gcf().subplots_adjust(0.2, 0.2, 0.85, 0.85)
plt.subplot(111)
plt.xlabel(experiment1)
plt.ylabel(experiment2)
#plt.title("Abs. correlation between eigenvectors")
plt.imshow(data, interpolation="nearest", vmin=0, vmax=1)
plt.colorbar()
plt.show()
pp.savefig()
def doReconstructedArmPlot(filename=GM1M, genome=myGenome,
usePCs=[0, 1], mouse=False,
**kwargs):
"Plot an PC2-PC3 interarm map - supp paper figure"
Tanay = binnedDataAnalysis(1000000, genome)
Tanay.simpleLoad(filename, "GM-all")
if mouse == True:
Tanay.fakeTranslocations([(0, 0, None, 12, 52000000, None),
(4, 45000000, None, 12, 0, 30000000),
(9, 0, 50000000, 12, 0, 35000000)])
Tanay.removeChromosome(19)
else:
Tanay.removeChromosome(22)
Tanay.removeDiagonal()
Tanay.removePoorRegions()
Tanay.removeZeros()
Tanay.truncTrans()
Tanay.fakeCis()
Tanay.doEig(numPCs=max(usePCs) + 1)
print Tanay.eigEigenvalueDict
Tanay.restoreZeros(value=0)
PCs = Tanay.EigDict["GM-all"][usePCs]
eigenvalues = Tanay.eigEigenvalueDict["GM-all"][usePCs]
proj = reduce(lambda x, y: x + y,
[PCs[i][:, None] * PCs[i][None, :] * \
eigenvalues[i] for i in xrange(len(PCs))])
mask = PCs[0] != 0
mask = mask[:, None] * mask[None, :]
data = Tanay.dataDict["GM-all"]
datamean = numpy.mean(data[mask])
proj[mask] += datamean
Tanay.dataDict["BLA"] = proj
Tanay.averageTransMap("BLA", **kwargs)
cb = plt.colorbar(orientation="vertical")
for xlabel_i in cb.ax.get_xticklabels():
xlabel_i.set_fontsize(6)
def correctedScalingPlot():
"Paper figure to compare scaling before/after correction"
plt.figure(figsize=(4, 4))
Tanay = binnedDataAnalysis(200000, genome=myGenome)
Tanay.simpleLoad(GM200kBreaks, "GM-all")
Tanay.removePoorRegions()
Tanay.removeDiagonal()
Tanay.plotScaling("GM-all", label="Raw data", color="#A7A241")
Tanay.iterativeCorrectWithSS()
Tanay.plotScaling("GM-all", label="Corrected", color="#344370")
ax = plt.gca()
mirnylib.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()
def doArmPlot(filename=GM1M, genome=myGenome, mouse=False, **kwargs):
"Plot an single interarm map - paper figure"
Tanay = binnedDataAnalysis(1000000, genome)
Tanay.simpleLoad(filename, "GM-all")
if mouse == True:
Tanay.fakeTranslocations([(0, 0, None, 12, 52000000, None),
(4, 45000000, None, 12, 0, 30000000),
(9, 0, 50000000, 12, 0, 35000000)])
Tanay.removeChromosome(19)
else:
Tanay.removeChromosome(22)
Tanay.removeDiagonal(1)
Tanay.removePoorRegions()
Tanay.truncTrans()
Tanay.fakeCis()
#mat_img(Tanay.dataDict["GM-all"])
#plt.figure(figsize = (3.6,3.6))
Tanay.averageTransMap("GM-all", **kwargs)
#plotting.removeBorder()
cb = plt.colorbar(orientation="vertical")
#cb.set_ticks([-0.05,0.05,0.15])
for xlabel_i in cb.ax.get_xticklabels():
xlabel_i.set_fontsize(6)
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()
from hiclib.binnedData import binnedDataAnalysis
import os
import sys
workingGenome = "hg18"
genomeFolder = "../../../data/hg19"
if not os.path.exists(genomeFolder):
try:
genomeFolder = sys.argv[1]
except:
raise StandardError(
"Please provide hg19 Genome folder in the code or as a first argument"
)
a = binnedDataAnalysis(1000000, genomeFolder)
a.simpleLoad("../fragmentHiC/test-1M.hm", "test")
a.removeDiagonal()
a.removePoorRegions()
a.removeCis()
a.fakeCis()
a.removeZeros()
a.iterativeCorrectWithoutSS()
a.doEig()
a.export("test", "testHeatmap")
print "everything worked, but no verification of result was made, because we haven't written it yet..."
def compareInterarmMaps(resolution,
filename1,
filename2,
experiment1,
experiment2,
genome,
mouse=False,
**kwargs):
"plots witn 8 inetrarm maps - paper supplement figure"
global pp
if (options.verbose):
print >> sys.stdout, "compareInterarmMaps: res: %d file1: %s file2: %s exp1:%s exp2:%s gen:%s" % (
resolution, filename1, filename2, experiment1, experiment2, genome)
Tanay = binnedDataAnalysis(resolution, genome)
Tanay.simpleLoad(filename1, experiment1)
Tanay.simpleLoad(filename2, experiment2)
Tanay.removeDiagonal()
Tanay.removePoorRegions(cutoff=2)
#Tanay.removeStandalone(3)
fs = 10
vmin = None
vmax = None
plt.figure(figsize=(12, 16))
plt.subplot(421)
plt.title(experiment1 + ", raw", fontsize=fs)
Tanay.averageTransMap(experiment1, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(422)
plt.title(experiment2 + ", raw", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.iterativeCorrectWithSS()
vmin = None
vmax = None
plt.subplot(425)
plt.title(experiment1 + ", with SS reads", fontsize=fs)
Tanay.averageTransMap(experiment1, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(426)
plt.title(experiment2 + ", with SS reads", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.iterativeCorrectWithoutSS()
vmin = None
vmax = None
plt.subplot(423)
plt.title(experiment1 + ", no SS reads", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(424)
plt.title(experiment2 + ", no ss reads", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.fakeCis()
vmin = None
vmax = None
plt.subplot(427)
plt.title(experiment1 + ", trans only", fontsize=fs)
Tanay.averageTransMap(experiment1, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(428)
plt.title(experiment2 + ", trans only", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.show()
pp.savefig()
def compareInterarmMaps():
"plots witn 8 inetrarm maps - paper supplement figure"
Tanay = binnedDataAnalysis(1000000, myGenome)
Tanay.simpleLoad(GM1M, "GM-all")
Tanay.simpleLoad(GM1MNcoI, "GM-NcoI")
Tanay.removeDiagonal()
Tanay.removePoorRegions(cutoff=2)
#Tanay.removeStandalone(3)
fs = 10
vmin = None
vmax = None
plt.subplot(421)
plt.title("GM, HindIII, raw", fontsize=fs)
Tanay.averageTransMap("GM-all", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(422)
plt.title("GM, NcoI, raw", fontsize=fs)
Tanay.averageTransMap("GM-NcoI", vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.iterativeCorrectWithSS()
vmin = None
vmax = None
plt.subplot(425)
plt.title("GM, HindIII, with SS reads", fontsize=fs)
Tanay.averageTransMap("GM-all", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(426)
plt.title("GM, NcoI, with SS reads", fontsize=fs)
Tanay.averageTransMap("GM-NcoI", vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.iterativeCorrectWithoutSS()
vmin = None
vmax = None
plt.subplot(423)
plt.title("GM, HindIII, no SS reads", fontsize=fs)
Tanay.averageTransMap("GM-all", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(424)
plt.title("GM, NcoI, no ss reads", fontsize=fs)
Tanay.averageTransMap("GM-NcoI", vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.fakeCis()
vmin = None
vmax = None
plt.subplot(427)
plt.title("GM, HindIII, trans only", fontsize=fs)
Tanay.averageTransMap("GM-all", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(428)
plt.title("GM, NcoI, trans only", fontsize=fs)
Tanay.averageTransMap("GM-NcoI", vmin=vmin, vmax=vmax)
plt.colorbar()
plt.show()
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 compareInterarmMaps(resolution, filename1, filename2, experiment1, experiment2, genome, mouse=False, **kwargs):
"plots witn 8 inetrarm maps - paper supplement figure"
global pp
if options.verbose:
print >> sys.stdout, "compareInterarmMaps: res: %d file1: %s file2: %s exp1:%s exp2:%s gen:%s" % (
resolution,
filename1,
filename2,
experiment1,
experiment2,
genome,
)
Tanay = binnedDataAnalysis(resolution, genome)
Tanay.simpleLoad(filename1, experiment1)
Tanay.simpleLoad(filename2, experiment2)
Tanay.removeDiagonal()
Tanay.removePoorRegions(cutoff=2)
# Tanay.removeStandalone(3)
fs = 10
vmin = None
vmax = None
plt.figure(figsize=(12, 16))
plt.subplot(421)
plt.title(experiment1 + ", raw", fontsize=fs)
Tanay.averageTransMap(experiment1, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(422)
plt.title(experiment2 + ", raw", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.iterativeCorrectWithSS()
vmin = None
vmax = None
plt.subplot(425)
plt.title(experiment1 + ", with SS reads", fontsize=fs)
Tanay.averageTransMap(experiment1, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(426)
plt.title(experiment2 + ", with SS reads", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.iterativeCorrectWithoutSS()
vmin = None
vmax = None
plt.subplot(423)
plt.title(experiment1 + ", no SS reads", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(424)
plt.title(experiment2 + ", no ss reads", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
Tanay.fakeCis()
vmin = None
vmax = None
plt.subplot(427)
plt.title(experiment1 + ", trans only", fontsize=fs)
Tanay.averageTransMap(experiment1, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.subplot(428)
plt.title(experiment2 + ", trans only", fontsize=fs)
Tanay.averageTransMap(experiment2, vmin=vmin, vmax=vmax)
plt.colorbar()
plt.show()
pp.savefig()
from hiclib.binnedData import binnedDataAnalysis
import os
import sys
workingGenome = "hg18"
genomeFolder = "../../../data/hg19"
if not os.path.exists(genomeFolder):
try:
genomeFolder = sys.argv[1]
except:
raise StandardError("Please provide hg19 Genome folder in the code or as a first argument")
a = binnedDataAnalysis(1000000, genomeFolder)
a.simpleLoad("../fragmentHiC/test-1M.hm", "test")
a.removeDiagonal()
a.removePoorRegions()
a.removeCis()
a.fakeCis()
a.removeZeros()
a.iterativeCorrectWithoutSS()
a.doEig()
a.export("test", "testHeatmap")
print "everything worked, but no verification of result was made, because we haven't written it yet..."
