根据Uniprot ID/PDB ID批处理获取蛋白质.pdb文件

1.根据Uniprot ID批处理获取蛋白质.pdb文件

由于Uniprot的ID号可能对应多个NCBI的ID，但是根据Alphafold可以获取其唯一的PDB文件，所以用代码批处理获得.pdb文件如下：

import pandas as pd
import numpy as np
from Bio import SeqIO
from Bio import PDB
import requests

# 但是可能会出现 InsecureRequestWarning 警告，
# 虽然不影响代码采集但是看着不舒服，可以加上下面两行：
import urllib3
urllib3.disable_warnings()

headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:95.0) Gecko/20100101 Firefox/95.0'}

def read_file(file_name):
    pro_swissProt = []
    with open(file_name, 'r') as fp:

        for line in fp:
            if line.startswith('>'):#作用：判断字符串是否以指定字符或子字符串开头
                pro_swissProt.append(line[1:-1])
    return pro_swissProt

file1 = '/AD/all1.csv'

ID=read_file(file1)

j = 0
not_exist_list = []

for i in ID:
    j = j + 1
    print(j)
    print(i)
    url = 'https://alphafold.ebi.ac.uk/files/AF-'+i+'-F1-model_v1'+'.pdb'
    print(url)

    r = requests.get(url, headers=headers, verify=False)
    with open('/AD/Information/PDB