Rosalind第31题——ros_bio31_TRAN

如果第一次阅读，请查看写在前面

import re

#读取fasta文件
table = {}
with open('../examples/ros_bio31_TRAN.txt') as f:
    file = f.readlines()
for line in file:
    line = re.sub(r'\n', '', line)
    m = re.match(r'^>.*', line)
    if m:
        name = m.group()
        table[name] = ''
    else:
        table[name] += line

#取出两个序列，消去两序列同一位置相同碱基得到新的两个序列
seq = [x for x in table.values()]
front = seq.pop(0)
rear = seq.pop(0)
fseq = ''
rseq = ''
for i in range(len(front)):
    if front[i] == rear[i]:
        continue
    else:
        fseq += front[i]
        rseq += rear[i]

#创建transition的字典，不匹配此字典即为transversion的字符，遍历两字符串得出sit和sve的个数
transit = {'A': 'G', 'G': 'A', 'C': 'T', 'T': 'C'}
sit = 0
sve = 0
for i in range(len(fseq)):
    if transit[fseq[i]] == rseq[i]:
        sit += 1
    else:
        sve += 1
ratio = sit/sve
print("{:.11f}".format(ratio))