def doSaddle(filename, eig, gen):
c = cooler.Cooler(filename)
gen = Genome("/home/magus/HiC2011/data/" + gen, readChrms=["#", "X"])
gen.setResolution(getResolution(filename))
saddles = []
for chrom in range(gen.chrmCount):
saddle = np.zeros((5,5), dtype = float)
st = gen.chrmStartsBinCont[chrom]
end = gen.chrmEndsBinCont[chrom]
cur = c.matrix(balance=False).fetch(gen.idx2label[chrom])
cur = observedOverExpected(cur)
mask = np.sum(cur , axis=0) > 0
cur = cur [mask]
cur = cur [:, mask]
GC = eig[st:end]
GC = GC[mask]
if len(GC) > 5:
for i in range(5):
for j in range(5):
G1, G2 = np.percentile(GC, [20 * i, 20 * i + 20])
mask1 = (GC > G1) * (GC < G2)
G1, G2 = np.percentile(GC, [20 * j, 20 * j + 20])
mask2 = (GC > G1) * (GC < G2)
saddle[i, j] += cur[np.ix_(mask1, mask2)].mean()
saddles.append(saddle)
return saddles
def doSaddleError(filename, eig, gen, correct=False):
gen = Genome("/home/magus/HiC2011/data/" + gen, readChrms=["#", "X"])
cur = 0
data = h5dict(filename,'r')["heatmap"]
if correct:
data = completeIC(data)
gen.setResolution(getResolution(filename))
if eig == "GC":
eig = np.concatenate(gen.GCBin)
saddles = []
permutted = []
saddle = np.zeros((5,5), dtype = float)
for i in range(100):
permutted.append(np.zeros((5,5), dtype = float))
for chrom in range(gen.chrmCount):
st = gen.chrmStartsBinCont[chrom]
end = gen.chrmEndsBinCont[chrom]
cur = data[st:end, st:end]
cur = observedOverExpected(cur)
mask = np.sum(cur , axis=0) > 0
cur = cur [mask]
cur = cur [:, mask]
GC = eig[st:end]
GC = GC[mask]
if len(GC) > 5:
for i in range(5):
for j in range(5):
G1, G2 = np.percentile(GC, [20 * i, 20 * i + 20])
mask1 = (GC > G1) * (GC < G2)
G1, G2 = np.percentile(GC, [20 * j, 20 * j + 20])
mask2 = (GC > G1) * (GC < G2)
addition = cur[np.ix_(mask1, mask2)]
addition = np.reshape(addition, (-1))
for k in range(100):
resampled = np.random.choice(addition, len(addition), replace=True)
permutted[k][i,j] += resampled.mean()
saddle[i, j] += addition.mean()
return saddle, permutted
def doEigenvector(filename, genome):
if filename == "GC":
gen = Genome("/home/magus/HiC2011/data/" + genome, readChrms=["#","X"])
gen.setResolution(1000000)
GC = np.concatenate(gen.GCBin)
return GC
resolution = getResolution(filename)
BD = binnedData.binnedData(resolution, "/home/magus/HiC2011/data/" + genome, ["#","X"])
BD.simpleLoad(filename, "bla")
BD.removeDiagonal()
BD.removeBySequencedCount(0.5)
BD.removeCis()
BD.truncTrans(high=0.0005)
BD.removePoorRegions(cutoff=1)
BD.fakeCis()
BD.removeZeros()
BD.doEig(numPCs=2)
BD.restoreZeros(value=0)
return BD.EigDict["bla"][0]
def byChrEig(filename,
genome,
chromosomes="all",
resolution="auto",
byArm=True,
doSmooth=False):
from mirnylib.genome import Genome
if resolution == "auto":
resolution = getResolution(filename)
if type(genome) == str:
genome = Genome(genome)
assert isinstance(genome, Genome)
genome.setResolution(resolution)
mydict = mirnylib.h5dict.h5dict(filename)
if chromosomes == "all":
chromosomes = list(range(genome.chrmCount))
chromosomes = [i for i in chromosomes if "{0} {0}".format(i) in mydict]
if len(chromosomes) == 0:
raise ValueError("No chromosomes left. Check h5dict file.")
result = []
for chrom in chromosomes:
data = mydict["{0} {0}".format(chrom)]
if not byArm:
result.append(
completeEig(data, genome.GCBin[chrom], doSmooth=doSmooth))
else:
GC = genome.GCBin[chrom]
result.append(np.zeros(len(GC), dtype=float))
cent = genome.cntrMids[chrom] / resolution
result[-1][:cent] = completeEig(data[:cent, :cent],
genome.GCBin[chrom][:cent],
doSmooth=doSmooth)
result[-1][cent:] = completeEig(data[cent:, cent:],
genome.GCBin[chrom][cent:],
doSmooth=doSmooth)
return result