fasta.py 文件源码

def cal_entropy(self,l=3):
        '''calculate entropy for each sequence'''
        for (id,seq) in self.seqs.items():
            entropy = 0
            dna_chars_uniq = FrameKmer.all_possible_kmer(l)
            dna_len = len(seq)

            for c in dna_chars_uniq:
                if 'N' in c:
                    continue
                prop = seq.count(c)/(1.0*dna_len)
                if prop ==0:
                    continue
                information = numpy.log2(1.0/prop)
                entropy += prop * information
            yield(id, entropy)