返回一个序列中二核苷酸的分布情况

文件:	dinucleotides.rar
大小:	0KB
下载:	下载

输出一个序列然后返回其中的二核苷酸的分布情况：

 

 

# demonstrates
#
# - list comprehension
# - method fromkeys
# - sequence unpacking
# - method iteritems
# - gradually building complex string


def dinucleotide_distribution(s):
    """Return histogram of dinucleotide
    distribution in DNA string s"""

    nuc = "A", "C", "G", "T"

    keys = [ (a, b) for a in nuc for b in nuc]

    # create dictionary where all dinucleotide keys
    # have default value 0:
    d = dict.fromkeys( keys, 0 )

    for i in xrange(0, len(s)-1):
        d[(s[i], s[i+1])] += 1

    # build histogram string as a list first:
    histogram = []
    for (n1, n2), m in sorted(d.iteritems()):

        if m>0:
            histogram.append("%s%s : %3d"%(n1, n2, m))

    # turn list into string:
    return "\n".join(histogram)


s = raw_input("Input DNA string: ")
print dinucleotide_distribution(s.upper())