def gccontentforonechr(fastarep,chrsizepath,species,GCoutrep,resolution):
resolution=int(resolution)
sizedict=utils.loadchrsizedict(chrsizepath,resolution)
matcolsize=sizedict["HicUsedTotalSize"] #HicUsedTotalSize HicChrBeginchr2
mat=np.zeros(matcolsize)
k=0
for i in utils.dictchr[species]:
print(i)
o=open(fastarep+i+".fa","r")
l=o.readline()
s=""
#init
l=l.split(" ")
l=o.readline()
while l:
l=l.replace("\n","")
s+=l
l=o.readline()
o.close()
i=0
j=resolution
if resolution>len(s):
mat[k]=gcpercent(s)
k+=1
while j<len(s):
mat[k]=gcpercent(s[i:j])
i+=resolution
j+=resolution
k+=1
toto={}#just to be un matlab savemat format
toto['mat']=mat
scpio.savemat(GCoutrep+str(resolution)+"pbGCvec.mat",toto)
utils.savematrixasfilelist3(mat,GCoutrep+str(resolution)+"pbGCvec.csv")
def transformHiClistofpatterninDensity(setlist,TEtype,nameout): L=len(setlist) returnlist=[0]*L i=0 while i<L: returnlist[i]=setlist[i].count(TEtype) i+=1 utils.savematrixasfilelist3(returnlist,nameout)
basemat=convert.loadmatrixselected(matrixfilename,beginfend,endfend)
#matrix filtering
print("FILTERING")
pos_out=HiCutils.get_outliers(basemat)
basematfilter=basemat[np.ix_(~pos_out, ~pos_out)]
basematfilter=np.copy(basematfilter)
#basematfilter=basematfilter[0:1000,0:1000]
print(len(basemat),len(basematfilter))
fh5 = h5py.File(repositoryout+"inputmat.hdf5", "w")
fh5['data'] = basemat
fh5.close()
fh5 = h5py.File(repositoryout+"inputmat_filtered.hdf5", "w")
fh5['data']=basematfilter
fh5.close()
utils.savematrixasfilelist3(pos_out,repositoryout+"filteredbin.txt")
if Operation=="Boost":
print("Boost Hic")
boosted=BoostHiC(basematfilter)
#save
fh5 = h5py.File(repositoryout+"boostedmat.hdf5", "w")
fh5['data']=boosted
fh5.close()
elif Operation=="Sample":
print("SAMPLING")
Sample(basematfilter,repositoryout)