Rosalind第22题——ros_bio22_SPLC

如果第一次阅读，请查看写在前面

import re

#引入fasta文件得到dna序列
with open("../examples/ros_bio22_SPLC.txt")as f:
    file = f.readlines()
fasta = {}
for line in file:
    line = re.sub(r'\n', "", line)
    m = re.match(r'^>.*', line)
    if m:
        name = m.group()
        fasta[name] = ''
    else:
        fasta[name] += line

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

#获取母串序列，并分别剪切两个子串，得到没有内含子的dna，再替换T成U转录得rna
seq = []
for value in fasta.values():
    seq.append(value)
dna = seq.pop(0)
real_dna = dna[:dna.find(seq[0])] + dna[dna.find(seq[0]) + len(seq[0]):]
real_dna = real_dna[:real_dna.find(seq[1])] + real_dna[real_dna.find(seq[1]) + len(seq[1]):]
rna = real_dna.replace('T', 'U')

#翻译
i = 0
protein = ''
while i < len(rna):
    if table[rna[i: i+3]] == 'Stop':
        break
    protein += table[rna[i: i+3]]
    i += 3
print(protein)