Rosalind第18题——ros_bio18_ORF

如果第一次阅读，请查看写在前面

#翻译过程的if，else写的极其拙劣，以后有时间有了更好的方法再来重写
#B站未琢三个碱基为一体遍历是一种比较好的思路，可以借鉴
import re

with open("../examples/ros_bio18_ORF.txt") as f:
    file = f.readlines()

table = {} # 密码子表
#RNA密码子表
codon = """UUU F      CUU L      AUU I      GUU V
UUC F      CUC L      AUC I      GUC V
UUA L      CUA L      AUA I      GUA V
UUG L      CUG L      AUG M      GUG V
UCU S      CCU P      ACU T      GCU A
UCC S      CCC P      ACC T      GCC A
UCA S      CCA P      ACA T      GCA A
UCG S      CCG P      ACG T      GCG A
UAU Y      CAU H      AAU N      GAU D
UAC Y      CAC H      AAC N      GAC D
UAA Stop   CAA Q      AAA K      GAA E
UAG Stop   CAG Q      AAG K      GAG E
UGU C      CGU R      AGU S      GGU G
UGC C      CGC R      AGC S      GGC G
UGA Stop   CGA R      AGA R      GGA G
UGG W      CGG R      AGG R      GGG G """
codon = codon.split("\n")
#将密码子表字符串转为字典
for line in codon:
    i = 0
    pattern = re.compile(r'(.{3} \S+)\s*(.{3} \S+)\s*(.{3} \S+)\s*(.{3} \S+)')
    m = pattern.match(line)
    while i <= 4:
        single = m.group(i).split(" ")
        table.update({single[0]: single[1]})
        i += 1

#将序列读入sequence
base = {'A': 'U', 'G': 'C', 'C': 'G', 'T': 'A'}
dna = ''
for line in file:
    line = re.sub("\n", "", line)
    m = re.match(r'^>.*', line)
    if m:
        continue
    else:
        dna += line
#获取dna的补码mrna和反向补码
mrna = dna.replace('T', 'U')
r_mrna = ''.join([base[i] for i in dna[::-1]])
rna = [mrna, r_mrna]

#遍历两个rna，对每个rna进行三次循环，给起始密码子和终止密码子各设置一个开关，以便获取是否开始翻译的信息
all_pro = []
for index in rna:
    n = 0
    while n < 3:
        i = n
        protein = ''
        start = end = 0
        location = []
        while i < len(index):
            amino = index[i:i+3]
            if len(amino) != 3:
                break
            if table[amino] == 'M':
                if protein == '':
                    location = i + 3 # 获取起始密码子的索引，在翻译结束后从location继续遍历寻找新的起始密码子
                protein += table[amino]
                start = 1
            elif table[amino] == 'Stop' and start == 1:
                end = 1
            elif protein != '':
                protein += table[amino]
            if start == 1 and end == 1:
                all_pro.append(protein)
                protein = ''
                start = end = 0
                i = location
                continue
            i += 3
        n += 1

all_pro = list(set(all_pro)) # 删除列表重复元素
for e in all_pro:
    print(e)