氨基酸三字母序列转单字母序列

氨基酸三字母序列转单字母序列

1.氨基酸对照数据

对照数据集：提取码：amin
实例数据：提取码：data

2. 对照code

#%% 氨基酸的3 to 1  
#导入package
import pandas as pd
from pandas import DataFrame as df
import numpy as np
import re
 
Amino_acid_path="D:\Topic\\alphafold\\Amino_acid.csv"#氨基酸对照表路径
amino_acid=pd.read_csv(Amino_acid_path)
amino_acid=np.array(amino_acid)
amino_acid=amino_acid.tolist()
#%%将氨基酸对照变转化为dict类型
amino_map={}
for i in range(len(amino_acid)):
    amino_map[amino_acid[i][0]]=amino_acid[i][1]

#%%读入三字母氨基酸序列
amino_path="D:\Topic\demodata.txt"
#读入每个氨基酸序列文件
with open(amino_path, 'r', encoding='utf-8') as f:
	aminofile = f.read()  # 读取全部内容后，按行存储为list
    #根据第一个大写字母分割三字母氨基酸并存为列表
aminofileList=re.sub(r"([A-Z])",r" \1",aminofile).split()
#%%
#转化为单字母
amino_one=str()
for j in aminofileList:
    amino_one=amino_one+amino_map[j]
    #保存文件
amino_one_path="D:\Topic\dataresult.fasta"
with open(amino_one_path,'w') as f:
	f.write(amino_one)