def get_expression(cell, ch, start, end, resolution, min_expre=0):
re = replication_data(cell,
"ExpGenes",
chromosome=ch,
start=start,
end=end,
resolution=resolution,
raw=True)
X = []
Y = []
D = []
xm = []
ym = []
Ym = []
Xm = []
#std = np.nanstd(re["signalValue"])
for istart, iend, v, strand in zip(re["chromStart"], re["chromEnd"],
re["signalValue"], re["strand"]):
# print(istart*5,strand)
if strand == "+":
X.extend([istart, iend, iend + 1])
Y.extend([v, v, np.nan])
else:
Xm.extend([istart, iend, iend + 1])
Ym.extend([v, v, np.nan])
xm.append(istart / 2 + iend / 2)
ym.append(v)
D.append(strand)
mean = np.nanmean(Y)
stdv = np.nanstd(Y)
print(mean, stdv)
Y = np.array(Y)
X = np.array(X)
Ym = np.array(Ym)
Xm = np.array(Xm)
D = np.array(D)
xm = np.array(xm)
ym = np.array(ym)
directionp = np.arange(start, end, resolution) * 0
for istart, iend, v in zip(X[::3], X[1::3], Y[::3]):
if v > min_expre:
# print(start,istart,iend,int(round((istart-start)/resolution)),int(round((iend-start)/resolution)))
directionp[int(round(istart - start / resolution)
):int(round(iend - start / resolution))] = 1
directionm = np.arange(start, end, resolution) * 0
for istart, iend, v in zip(Xm[::3], Xm[1::3], Ym[::3]):
if v > min_expre:
directionm[int(round(istart - start / resolution)
):int(round(iend - start / resolution))] = 1
return X * resolution, Y, Xm * resolution, Ym, directionp - directionm
args = parser.parse_args()
chromlength = [248956422, 242193529, 198295559, 190214555, 181538259,
170805979, 159345973, 145138636, 138394717,
133797422, 135086622, 133275309, 114364328, 107043718,
101991189, 90338345, 83257441,
80373285, 58617616, 64444167, 46709983, 50818468]
#os.makedirs(args.root, exist_ok=True)
data = []
for ch, l in enumerate(chromlength, 1):
Y = []
for file in args.files:
x, y = replication_data("hela", file, filename=file,
chromosome=ch, start=0, end=None, resolution=5)
if args.remove is not None:
print(file,"removing %i points" %np.sum(y>args.remove))
y[y>args.remove] = np.nan
Y.append(y)
#if len(args.files) == 1:
# data.append(Y)
#else:
#
data.append(np.nanmean(Y,axis=0))
X = [["chr%i" % i] * len(d) for i, d in enumerate(data, 1)]
start,
end,
resolution,
min_expre=1)
d3p = direction
x = Xg
d3p = Yg
#ymg[ymg<1] = np.nan
sup_sig = [xmg, -ymg, "neg"]
#d3p[np.abs(d3p)<1]=np.nan
elif "[" not in signal and "--" not in signal:
print("H")
x, d3p = replication_data(cell,
signal,
chromosome=ch,
start=start,
end=end,
resolution=mini(resolution, signal),
raw=False,
filename=None)
elif "--" in signal or ":" in signal:
weights_list = []
if "--" in signal:
signal, sigv = signal.split("--")
if ":" in sigv:
sigv, *weights_list = sigv.split(":")
x, d3p = replication_data(cell,
signal,
chromosome=ch,
start=start,
end=end,
MRTstd = score["MRTstd"][0]
RFDp = float(score["RFDp"][0].split(",")[0][1:])
RFDstd = score["RFDstd"][0]
RepTime = score["RepTime"][0]
#scorev = 2-c1-c2
return MRTp, MRTstd, RFDp, RFDstd, RepTime
for mark in marks:
x, d = replication_data(cell,
mark,
chromosome=ch,
start=start,
end=end,
resolution=5,
raw=False,
oData=False,
bp=True,
bpc=False)
print(mark, d)
if d == []:
print("Skipping %s" % mark)
continue
for kon in [5e-7]:
for ndiff in [30, 45, 60, 75, 90, 105, 120]:
#ndiff = 60
for random_activation in [0, 0.05, 0.1, 0.2]:
for dori in [5, 15, 30]:
if "/" in mark:
mark0 = "Epi_Bigger"
def detect_peaks(start,
end,
ch,
resolution_polarity=5,
exp_factor=4,
percentile=85,
cell="K562",
cellMRT=None,
cellRFD=None,
nanpolate=False,
fsmooth=None,
gsmooth=5,
recomp=False,
dec=None,
fich_name=None,
sim=True,
expRFD="OKSeq",
rfd_only=False):
rpol = resolution_polarity
if fich_name is None:
if cellMRT is None:
cellMRT = cell
if cellRFD is None:
cellRFD = cell
print(start, end, cellRFD, ch, rpol)
x_pol, pol_exp = replication_data(cellRFD,
expRFD,
chromosome=ch,
start=start,
end=end,
resolution=rpol,
raw=False,
pad=True)
if "Yeast" in cellMRT:
resolution = 1
else:
resolution = 10
if not rfd_only:
x_mrt, mrt_exp = replication_data(cellMRT,
"MRT",
chromosome=ch,
start=start,
end=end,
resolution=resolution,
raw=False)
else:
pol_expc = pol_exp.copy()
pol_expc[np.isnan(pol_expc)] = 0
#mrt_exp = np.array(pd.Series(np.cumsum(pol_expc)).rolling(10000, min_periods=1, center=True).apply(lambda x: np.mean(x<x[len(x)//2])))[::2]
if nanpolate:
pol_exp = nan_polate(pol_exp)
if fsmooth != None:
pol_exp = smooth(pol_exp, fsmooth)
ratio_res = resolution // rpol
pol_exp /= rpol
Smpol = np.copy(pol_exp)
#print(mrt_exp.shape[0]*2, pol_exp.shape, ratio_res,)
if not rfd_only:
nmrt = mapboth(mrt_exp, pol_exp, ratio_res, pad=True)
else:
strain = pd.read_csv(fich_name, sep=",")
resolution = 5
x_pol = strain.chromStart
if sim:
pol_exp = strain.RFDs
mrt_exp = strain.MRTs
else:
pol_exp = strain.RFDe
mrt_exp = strain.MRTe
nmrt = mrt_exp
Smpol = np.copy(pol_exp)
ratio_res = 1
if not rfd_only:
for delta in [0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8][::-1]:
c1 = nmrt > delta
Smpol[c1] = np.array(sm(Smpol, gsmooth))[c1]
Smpol = sm(Smpol, 3)
else:
Smpol = sm(Smpol, 10)
delta = Smpol[1:] - Smpol[:-1]
delta -= np.nanmin(delta)
percentile = np.percentile(delta[~np.isnan(delta)], percentile)
print("Threshold value", percentile)
delta[delta < percentile] = 0.0
if recomp:
pol_exp = smooth(pol_exp, 2)
deltap = pol_exp[1:] - pol_exp[:-1]
deltap -= np.nanmin(delta)
deltap[delta <= 0] = 0
#deltap[deltap < percentile] = 0
delta = deltap
delta[delta < 0] = 0
if dec != None:
if dec != 2:
raise
else:
for i, (ok0, ok1,
ok2) in enumerate(zip(pol_exp, pol_exp[1:], pol_exp[2:])):
if ok0 + 0.05 > ok2:
delta[i] = 0 # shifted from one on purpose
delta[i + 1] = 0
if not rfd_only:
delta *= mapboth(np.exp(-exp_factor * mrt_exp),
delta,
ratio_res,
pad=True)
delta[np.isnan(delta)] = 0
return x_pol, np.concatenate(([0], delta))
def compare(simu,
signal,
cell,
res,
ch,
start,
end,
trim=0.05,
return_exp=False,
rescale=1,
nanpolate=False,
smoothf=None,
trunc=False,
pad=False,
return_mask=False,
masking=True,
propagateNan=True):
x, exp_signal = replication_data(cell,
signal,
chromosome=ch,
start=start,
end=end,
resolution=res,
raw=False,
pad=pad)
print(len(exp_signal), len(simu))
exp_signal *= rescale
l = None
if trunc and len(simu) != len(exp_signal):
print("Truncating", len(simu), len(exp_signal))
l = min(len(simu), len(exp_signal))
simu = simu[:l]
exp_signal = exp_signal[:l]
mask_exp = np.array([not np.isnan(e) for e in exp_signal])
if masking:
maskl = masking # kb
if propagateNan:
mask_exp = propagate_n_false(mask_exp, int(maskl / res))
exclude = int(maskl / res)
mask_exp[:exclude] = False
mask_exp[-exclude:] = False
#Due to masking
mask_exp[np.isnan(simu)] = False
if smoothf is not None:
exp_signal = nan_polate(exp_signal)
exp_signal = smooth(exp_signal, smoothf)
if simu is not None:
ret = [
stats.pearsonr(simu[mask_exp], exp_signal[mask_exp]),
np.mean((simu[mask_exp] - exp_signal[mask_exp])**2)**0.5
]
else:
ret = [None, None]
if return_exp:
ret.append(exp_signal)
if return_mask:
ret.append([mask_exp, l])
return ret
170805979, 159345973, 145138636, 138394717,
133797422, 135086622, 133275309, 114364328, 107043718,
101991189, 90338345, 83257441,
80373285, 58617616, 64444167, 46709983, 50818468]
data = []
X = []
for ch in range(1,len(chroms)+1):
if type(chroms) == list:
end = chroms[ch-1]
end=int(end / 1000)
else:
end = None
print(ch,end)
x, y = replication_data("hela", args.file, filename=args.file,
chromosome=ch, start=0, end=end, resolution=resolution)
if to1:
y = nan_polate(y)
data.append(y)
X = [["chr%i" % i] * len(d) for i, d in enumerate(data, 1)]
Pos = [range(0, len(d) * resolution * 1000, resolution * 1000) for i, d in enumerate(data, 1)]
X = np.concatenate(X).tolist()
Pos = np.concatenate(Pos).tolist()
data = np.concatenate(data, axis=0)
pd.DataFrame({"chrom":X, "chromStart":np.array(Pos),"chromEnd":np.array(Pos) ,"signalValue":data}).to_csv(args.output,sep="\t",index=False)
gsmooth=args.gsmooth)
f = resolution // resolution_polarity
#ext = mapboth(d3p0, d3p, f)
#d3p[ext == 0] = 0
for i in range(len(d3p0)):
d3p0[i] = sum(d3p[i * f:min(i * f + 1, len(d3p))])
d3p = d3p0
if args.correct:
x, DNaseI = replication_data(cell,
"DNaseI",
chromosome=ch,
start=start,
end=end,
resolution=resolution,
raw=False)
x, CNV = replication_data(cell,
"CNV",
chromosome=ch,
start=start,
end=end,
resolution=resolution,
raw=False)
CNV[CNV == 0] = 2
DNaseI[np.isnan(DNaseI)] = 0
DNaseI /= CNV
DNaseIsm = smooth(DNaseI, 100)
if args.signal == "peak":
x, d3p = detect_peaks(start,
end,
ch,
resolution_polarity=resolution_polarity,
exp_factor=exp_factor,
percentile=percentile,
cell=cell,
nanpolate=True)
if args.correct:
x, DNaseI = replication_data(cell,
"DNaseI",
chromosome=ch,
start=start,
end=end,
resolution=resolution,
raw=False)
x, CNV = replication_data(cell,
"CNV",
chromosome=ch,
start=start,
end=end,
resolution=resolution,
raw=False)
CNV[CNV == 0] = 2
DNaseI[np.isnan(DNaseI)] = 0
DNaseI /= CNV
DNaseIsm = smooth(DNaseI, 100)