def changevalue(ifile,
ref,
ofile,
gfile,
step=10,
suppress=False,
buffer=None):
from random import randint
if ifile != ref: print('\nnormalizing', ifile, '...')
else: print('\nsaving reference ...')
tm = time()
fi, fr = open(ifile), open(ref)
wg = Wig(step=step, gfile=gfile)
for line in fi:
col = line.split()
rcol = fr.readline().split()
if len(rcol) == 0: rcol = [0.0]
cr, pos, vl = col[2], int(col[3]) / step, float(rcol[0])
wg.data[cr][pos] = vl
n = 0
for line in fr:
n += 1
if n > 0:
print(
'Warning: the input genome size is smaller than the reference genome size by',
n, 'wiggle steps!')
wg.save(ofile, suppress=suppress)
print('time cost:', time() - tm)
def load(self, path, suppress=False):
'''
Description:
Load multiple Wig class instances from wiggle format files located in one directory
Parameter:
path: a path to the directory that contain the wiggle format files
Value:
None
'''
paths = path
for path in paths.split(','):
#wigs={}
if os.path.isdir(path):
for infile in glob.glob(os.path.join(path, '*.wig')):
fname = os.path.split(infile)[-1]
if fname[-4:] == '.wig': fname = fname[:-4]
self.set(
fname, Wig(infile, step=self.step, suppress=suppress)
) ########## ---add--- by kaifu on Aug 15,2012 ##########
#wigs[infile]=Wig(infile,step=self.step) ########## ---delete--- by kaifu on Aug 15,2012 ##########
elif os.path.isfile(path):
fname = os.path.split(path)[-1]
if fname[-4:] == '.wig': fname = fname[:-4]
self.set(
fname, Wig(path, step=self.step, suppress=suppress)
) ########## ---add--- by kaifu on Aug 15,2012 ##########
def rawsort(ifile,sort_ofile,gfile,format,step=10,suppress=False,buffer=None):
tm=time()
if format=='wig':
print '\nconverting',ifile,'...'
raw_ofile=sort_ofile[:-3]+'raw.wiq'
wg=Wig(file=ifile,gfile=gfile,step=step,suppress=suppress)
wg.ajust_size(gfile=gfile)
wg.save(file=raw_ofile,format="wiq",step=step,suppress=suppress)
print 'time cost:',time()-tm
tm=time()
else:raw_ofile=ifile
print '\nsorting',raw_ofile,'...'
temp=ifile[:-3]+'temp'
while os.path.isdir(temp):temp=temp+'.temp'
os.mkdir(temp)
if buffer!=None:cmd='sort -r -n -s -k1 -k2 -o '+sort_ofile+' --buffer-size '+str(buffer)+' --temporary-directory '+str(temp)+' '+raw_ofile
else:cmd='sort -r -n -s -k1 -k2 -o '+sort_ofile+' --temporary-directory '+str(temp)+' '+raw_ofile
os.system(cmd)
if format=='wig':
print 'Removing ',raw_ofile,'...'
os.system('rm '+raw_ofile)
print 'removing',temp
os.system('rm '+str(temp)+' -r')
print 'time cost:',time()-tm
def toWig(self,fs=None,extend=0,mifrsz=10,mafrsz=300):
'''
Description:
Calculate nucleosome occupancy from the reads data
Parameter:
fs: average size of fragments that are subject to sequencing and generate the reads, only for signgle-end reads. When this value is not given, a fs value will be infered by the program. For paired-end reads loaded buy the function loadBedPaired(), set fs to 0.
extend: a interger value, each read will be extend to this length.
mifrsz: the minimal estimated average fragment size, only for single-end reads
mafrsz: the maximal estimated average fragment size, only for single-end reads
Value: a Wig class instance
'''
step=self.step
if fs==None:fs=self.fragSizeDis(minsize=mifrsz,maxsize=mafrsz)
if extend<=0:extend=fs
print 'extend to',extend
old_extend=extend
fragsize,extend=fs/(2*step),extend/(2*step)
wg=Wig(step=step)
print 'generating wig ...'
for chr in self.data:
tmax=max(1000,fragsize*4,extend*4)
if self.data[chr]['+'].size<tmax:self.data[chr]['+'].resize(tmax,refcheck=0)
if self.data[chr]['-'].size<tmax:self.data[chr]['-'].resize(tmax,refcheck=0)
wg.addChr(chr)
lth=self.data[chr]['+'].size
wg.resizeChr(chr,lth*step)
self.data[chr]['+'][fragsize:lth]=self.data[chr]['+'][0:(lth-fragsize)]
for i in range(fragsize):self.data[chr]['+'][i]=0
self.data[chr]['+'][0:(lth-fragsize)]+=self.data[chr]['-'][fragsize:lth]
for p in range(-extend,extend+1):wg.data[chr][extend:(lth-extend)]+=self.data[chr]['+'][(extend+p):(lth-extend+p)]
wg.foldChange(old_extend*1.0/wg.step) ##### added by Kaifu on May29, 2014
return wg
def changevalue(ifile,ref,ofile,gfile,step=10,suppress=False,buffer=None):
from random import randint
if ifile!=ref:print '\nnormalizing',ifile,'...'
else:print '\nsaving reference ...'
tm=time()
fi,fr=open(ifile),open(ref)
wg=Wig(step=step,gfile=gfile)
for line in fi:
col=line.split()
rcol=fr.readline().split()
if len(rcol)==0:rcol=[0.0]
cr,pos,vl=col[2],int(col[3])/step,float(rcol[0])
wg.data[cr][pos]=vl
n=0
for line in fr:n+=1
if n>0:print 'Warning: the input genome size is smaller than the reference genome size by',n,'wiggle steps!'
wg.save(ofile,suppress=suppress)
print 'time cost:',time()-tm
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 rawsort(ifile,sort_ofile,gfile,format,step=10,suppress=False,buffer=None):
tm=time()
if format=='wig':
print('\nconverting',ifile,'...')
raw_ofile=sort_ofile[:-3]+'raw.wiq'
wg=Wig(file=ifile,gfile=gfile,step=step,suppress=suppress)
wg.ajust_size(gfile=gfile)
wg.save(file=raw_ofile,format="wiq",step=step,suppress=suppress)
print('time cost:',time()-tm)
tm=time()
else:raw_ofile=ifile
print('\nsorting',raw_ofile,'...')
temp=ifile[:-3]+'temp'
while os.path.isdir(temp):temp=temp+'.temp'
os.mkdir(temp)
if buffer!=None:cmd='sort -r -n -s -k1 -k2 -o '+sort_ofile+' --buffer-size '+str(buffer)+' --temporary-directory '+str(temp)+' '+raw_ofile
else:cmd='sort -r -n -s -k1 -k2 -o '+sort_ofile+' --temporary-directory '+str(temp)+' '+raw_ofile
os.system(cmd)
if format=='wig':
print('Removing ',raw_ofile,'...')
os.system('rm '+raw_ofile)
print('removing',temp)
os.system('rm '+str(temp)+' -r')
print('time cost:',time()-tm)
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