def samplingTotal(self,
region_file=None,
region_out_file=None,
exclude_low_percent=1,
exclude_high_percent=1,
bnum=100000,
nonzero=False):
'''
Description:
caculate the sum of each wig's values after excluding the low and high percentile
Parameter:
None
Value:
None
'''
#if exclude_low_percent==0 and exclude_high_percent==0:return None
#else:
#print 'calculating normalization factors by sampling ...'
names = self.data.keys()
if exclude_low_percent == 0 and exclude_high_percent == 0 and region_file == None:
return None
sampling_total = {}
if region_file == None:
print 'calculate total signal in each sample after excluding the top', exclude_high_percent, 'and bottom', exclude_low_percent, 'percents of genomic regions with extremely high and low signal values'
wsums = {}
for name in names:
wsums[name] = self.data[name].sum()
wavg = sum(wsums.values()) / len(wsums.values())
rfwig = deepcopy(self.data[names[0]])
rfwig.foldChange(wavg * 1.0 / wsums[names[0]])
for name in names[1:]:
self.data[name].foldChange(wavg * 1.0 / wsums[name])
rfwig.add(self.data[name])
self.data[name].foldChange(wsums[name] * 1.0 / wavg)
rfwig.foldChange(1.0 / len(names))
lowcut, highcut = rfwig.percentile(
p=[exclude_low_percent, 100 - exclude_high_percent],
bnum=bnum,
nonzero_end=nonzero)
rg = rfwig.regionWithinValueRange(lowcut, highcut)
if region_out_file != None: rg.save(region_out_file)
else:
print 'calculate total signal in each sample in genomic regions defined by', region_file
rg = Wig(region_file)
for name in names:
sampling_total[name] = self.data[name].multiply(rg).sum()
print rg.sum(), '(' + str(
rg.sum() * 100.0 /
rg.gsize()) + '%) of', rg.gsize(), 'base pairs calculated:'
for name in names:
print name, sampling_total[name], '(' + str(
sampling_total[name] * 100.0 /
self.data[name].sum()) + '% of total)'
return sampling_total
def samplingTotal(self,region_file=None,region_out_file=None,exclude_low_percent=1,exclude_high_percent=1,bnum=100000,nonzero=False):
'''
Description:
caculate the sum of each wig's values after excluding the low and high percentile
Parameter:
None
Value:
None
'''
#if exclude_low_percent==0 and exclude_high_percent==0:return None
#else:
#print 'calculating normalization factors by sampling ...'
names=list(self.data.keys())
if exclude_low_percent==0 and exclude_high_percent==0 and region_file==None: return None
sampling_total={}
if region_file==None:
sys.stdout.write('calculate total signal in each sample after excluding the top ' +
str(exclude_high_percent) + ' and bottom ' + str(exclude_low_percent) +
'percents of genomic regions with extremely high and low signal values\n')
wsums={}
for name in names:wsums[name]=self.data[name].sum()
wavg=functions.div(sum(wsums.values()),len(list(wsums.values())))
rfwig=deepcopy(self.data[names[0]])
rfwig.foldChange(functions.div(wavg*1.0,wsums[names[0]]))
for name in names[1:]:
self.data[name].foldChange(functions.div(wavg*1.0,wsums[name]))
rfwig.add(self.data[name])
self.data[name].foldChange(functions.div(wsums[name]*1.0,wavg))
rfwig.foldChange(functions.div(1.0,len(names)))
lowcut,highcut=rfwig.percentile(p=[exclude_low_percent,100-exclude_high_percent],bnum=bnum,nonzero_end=nonzero)
rg=rfwig.regionWithinValueRange(lowcut,highcut)
if region_out_file!=None:rg.save(region_out_file)
else:
sys.stdout.write('calculate total signal in each sample in genomic regions defined by' + region_file + "\n")
rg=Wig(region_file)
for name in names:sampling_total[name]=self.data[name].multiply(rg).sum()
sys.stdout.write(str(rg.sum()) + ' (' + str(functions.div(rg.sum()*100.0,rg.gsize())) +
' %) of ' + str(rg.gsize()) + ' base pairs calculated:\n')
for name in names:
sys.stdout.write(name + str(sampling_total[name]) + ' (' +
str(functions.div(sampling_total[name]*100.0,self.data[name].sum())) + '% of total)\n')
return sampling_total
def samplingTotal(self,region_file=None,region_out_file=None,exclude_low_percent=1,exclude_high_percent=1,bnum=100000,nonzero=False):
'''
Description:
caculate the sum of each wig's values after excluding the low and high percentile
Parameter:
None
Value:
None
'''
#if exclude_low_percent==0 and exclude_high_percent==0:return None
#else:
#print 'calculating normalization factors by sampling ...'
names=self.data.keys()
if exclude_low_percent==0 and exclude_high_percent==0 and region_file==None: return None
sampling_total={}
if region_file==None:
print 'calculate total signal in each sample after excluding the top',exclude_high_percent,'and bottom',exclude_low_percent,'percents of genomic regions with extremely high and low signal values'
wsums={}
for name in names:wsums[name]=self.data[name].sum()
wavg=sum(wsums.values())/len(wsums.values())
rfwig=deepcopy(self.data[names[0]])
rfwig.foldChange(wavg*1.0/wsums[names[0]])
for name in names[1:]:
self.data[name].foldChange(wavg*1.0/wsums[name])
rfwig.add(self.data[name])
self.data[name].foldChange(wsums[name]*1.0/wavg)
rfwig.foldChange(1.0/len(names))
lowcut,highcut=rfwig.percentile(p=[exclude_low_percent,100-exclude_high_percent],bnum=bnum,nonzero_end=nonzero)
rg=rfwig.regionWithinValueRange(lowcut,highcut)
if region_out_file!=None:rg.save(region_out_file)
else:
print 'calculate total signal in each sample in genomic regions defined by',region_file
rg=Wig(region_file)
for name in names:sampling_total[name]=self.data[name].multiply(rg).sum()
print rg.sum(),'('+str(rg.sum()*100.0/rg.gsize())+'%) of',rg.gsize(),'base pairs calculated:'
for name in names:print name,sampling_total[name],'('+str(sampling_total[name]*100.0/self.data[name].sum())+'% of total)'
return sampling_total