ros_bio8_PROT

如果第一次阅读，请查看写在前面

import re
table = {} # 密码子表
num = 0 # mrna索引
protein = '' #蛋白序列
#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
#读取文件
with open("../examples/ros_bio8_PROT.txt") as f:
    mrna = f.read()
#翻译蛋白
while num < len(mrna):
    if table[mrna[num:num+3]] == 'Stop':
        break
    protein = protein + table[mrna[num:num+3]]
    num += 3
print(protein)