刷题记:RNA翻译成蛋白质

参考Rosalind http://rosalind.info/problems/prot/ 下面是考虑了开放阅读框ORF的写法：

import os
os.getcwd()
codon_table = {
    'GCU':'A', 'GCC':'A', 'GCA':'A', 'GCG':'A', 'CGU':'R', 'CGC':'R',   
    'CGA':'R', 'CGG':'R', 'AGA':'R', 'AGG':'R', 'UCU':'S', 'UCC':'S',
    'UCA':'S', 'UCG':'S', 'AGU':'S', 'AGC':'S', 'AUU':'I', 'AUC':'I',
    'AUA':'I', 'UUA':'L', 'UUG':'L', 'CUU':'L', 'CUC':'L', 'CUA':'L',
    'CUG':'L', 'GGU':'G', 'GGC':'G', 'GGA':'G', 'GGG':'G', 'GUU':'V',
    'GUC':'V', 'GUA':'V', 'GUG':'V', 'ACU':'T', 'ACC':'T', 'ACA':'T',
    'ACG':'T', 'CCU':'P', 'CCC':'P', 'CCA':'P', 'CCG':'P', 'AAU':'N',
    'AAC':'N', 'GAU':'D', 'GAC':'D', 'UGU':'C', 'UGC':'C', 'CAA':'Q',
    'CAG':'Q', 'GAA':'E', 'GAG':'E', 'CAU':'H', 'CAC':'H', 'AAA':'K',
    'AAG':'K', 'UUU':'F', 'UUC':'F', 'UAU':'Y', 'UAC':'Y', 'AUG':'M',
    'UGG':'W', 'UAG':'STOP', 'UGA':'STOP', 'UAA':'STOP'
    }

rna = ""
for line in open("./03_python_learnning/PythonTest/rosalind_prot.txt","r"):
    if not line.startswith(">"):
        rna = rna + line.strip()
with open("./03_python_learnning/PythonTest/prot.txt","w") as f:
    for openframe in range(3):
        pro = ""
        f.write("Openfram"+ str(openframe +1) + "\n")
        for i in range(openframe,len(rna),3):
            codon = rna[i:i+3]
            if codon in codon_table:
                if codon_table[codon] == "STOP":
                    pro = pro + "*"
                else:
                    pro = pro + codon_table[codon]
            else:
                pro = pro + "-"
        f.write(str(pro) + "\n")   
f.close()

涉及到的python知识点：文件读写；字典；判断与循环语句