def dbEntropy(inFileName,wordsize): """ deprecated """ vec_len=[] stat=Stat() file_db=open(inFileName) seq=Bioseq() numseq=0 while 1: seq.read(file_db) if seq.sequence==None: break i=seq.entropy(wordsize) stat.add(i) numseq=numseq+1 print 'sequence #',numseq,'=',seq.getLength(),'[',seq.header[0:40],'...] entropy',i vec_len.append((-i,numseq,seq.header)) file_db.close() vec_len.sort() for s in vec_len: print 'I=',-s[0],'=> #',s[1], s[2] print stat.string() return vec_len
def dbRelEntropy(inFileName,wordsize):
"""
deprecated
"""
file_db=open(inFileName)
seq=Bioseq()
refocc={}
sumlen=0
while 1:
seq.read(file_db)
if seq.sequence==None:
break
sumlen=sumlen+seq.getLength()-wordsize
occ=seq.occ_word(wordsize)
if(len(refocc)==0):
refocc=occ
else:
for w in occ.keys():
if refocc.has_key(w):
refocc[w]=refocc[w]+occ[w]
else:
refocc[w]=occ[w]
file_db.close()
reffreq={}
for w in refocc.keys():
reffreq[w]=float(refocc[w]+1)/sumlen
vec_len=[]
stat=Stat()
file_db=open(inFileName)
numseq=0
while 1:
seq.read(file_db)
if seq.sequence==None:
break
i=seq.rel_entropy(reffreq)
stat.add(i)
numseq=numseq+1
print 'sequence #',numseq,'=',seq.getLength(),'[',seq.header[0:40],'...] entropy',i
vec_len.append((i,numseq,seq.header))
file_db.close()
vec_len.sort()
for s in vec_len:
print 'H=',s[0],'=> #',s[1], s[2]
print stat.string()
return vec_len