蛋白质数据下载与处理部分

:::
包括PDB文件的下载以及pdb文件的预处理

:::

http://t.csdnimg.cn/Q4B7y

蛋白质PDB文件的下载

_**如果数据量较少，可以通过爬虫的方法**_

#下载PDB文件
pdb_name = ['12asA00']
def downloadPDB(pdb_name):
    complex_name = pdb_name.upper()#将蛋白质名称转化为大写
    #我们需要将pdbname选取前面四个字符12AS
    f = urllib.request.urlopen('http://files.rcsb.org/download/'+complex_name[:-3]+'.pdb')
    path_root = 'cath/pdbs/'#定义好下载位置
    os.makedirs(path_root, exist_ok=True)#判断是否存在文件位置，没有的话进行创建
    path = path_root+pdb_name[:-2]+'.pdb'#定义下载路径
    with open(path, 'wb') as g:
        F = f.readlines()
        for line in F:
            line = str(line,encoding='utf-8').strip()
            if line.startswith('ATOM'):#这里我们只写入原子的标识号为ATOM的部分
                # type = line[12:16].strip()
                chain = line[21:22]
                if chain == pdb_name[-3]:#也可以对PDB文件的链ID进行限制
                    line = line+'\n'
                    g.write(line.encode())

如果数据量较多，可以使用如下下载方式：

需要linux系统下载

import subprocess
path_root = 'cath/pdbs/'
os.makedirs(path_root, exist_ok=True)
b = []
for i in tqdm(cath40_data.values):
    pdb_name = i[0]
    complex_name = pdb_name.upper()
    pdb_url = 'http://files.rcsb.org/download/'+complex_name[:-3]+'.pdb'
    output_path = f"cath/pdbs/{pdb_name[:-3]}.pdb"
    
    try:
        subprocess.run(["wget", pdb_url, "-O", output_path], check=True)
        # print(f"文件 {pdb_name[:-3]}.pdb 下载成功！")
    except subprocess.CalledProcessError as e:
        b.append(pdb_name[:-3])
        # print(f"文件 {pdb_name[:-3]}.pdb 下载失败:", e)

在数据量较多的情况下，可能会下载失败，或者下载遗漏，可以通过一下程序判断文件是否存在指定文件路径中

import numpy as np
import os
#查询是否有PDB文件
def check_isfile(root, pdblist):
	def check_1pdb(root, pdbname):
		return (os.path.isfile(os.path.join(root, pdbname+ ".pdb")))

	return np.array(pdblist)[~np.array(list(map(lambda pdb: check_1pdb(root, str(pdb[0][:-3])), pdblist)))].tolist()

names = check_isfile('cath/pdbs/',cath40_data.values)

一种新的PDB文件下载方式，可以多进程快速下载

首先制作AlphaFoldDownloadLink文件，文件内容如下：

with open('SYSdata/AlphaFoldDownloadLink.txt', 'w', encoding='utf-8') as file:
    #names为要下载的PDB文件的名字
    for pdb_id in tqdm(names):
        al = []
        AlphaFold_PDB_Link = "https://alphafold.ebi.ac.uk/files/"+"AF-"+pdb_id[1]+"-F1-model_v4"+".pdb"
        al.append(pdb_id[0]+','+AlphaFold_PDB_Link)
        file.write('{:},{:}\n'.format(pdb_id[0],AlphaFold_PDB_Link))

import os
import requests
from concurrent.futures import ThreadPoolExecutor
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry
 
os.makedirs("SYSdata/SYSPDB/AlphaFold", exist_ok=True)#构建下载路径
count = 0
 
session = requests.Session()
session.trust_env = False  # 禁用环境代理
 
# 设置重试策略
retries = Retry(total=5, backoff_factor=1, status_forcelist=[500, 502, 503, 504])
adapter = HTTPAdapter(max_retries=retries)
session.mount('http://', adapter)
session.mount('https://', adapter)
 
def download(uniprot, link, count):
    # 在这里我是把1000个pdb文件写在一个文件里，可以根据自己需要修改
    try:
        response = session.get(link)
        response.raise_for_status()  # 如果响应状态码不是200，抛出HTTPError异常
        pdbcontent = response.text
        if os.path.isfile(os.path.join(f"SYSdata/SYSPDB/AlphaFold/{uniprot}.pdb")) == False:
            with open(f"SYSdata/SYSPDB/AlphaFold/{uniprot}.pdb", "a") as w:
                w.write(f"{pdbcontent}\n")
        return 1
    except (requests.exceptions.RequestException, ValueError) as e:
        print(f"Error downloading {line.strip()}: {e}")
        return 0
 
# 使用多线程下载
with open("SYSdata/AlphaFoldDownloadLink.txt") as f:
    with ThreadPoolExecutor(max_workers=10) as executor:
        futures = []
        for line in f:
            uniprot, link = line.strip("\n").split(",")
            futures.append(executor.submit(download, uniprot, link, count))
            count += 1
            if len(futures) >= 100:  # 控制每次提交的任务数量
                for future in futures:
                    future.result()  # 等待当前批次任务完成
                futures = []  # 清空当前批次任务
 
        # 处理剩余的任务
        for future in futures:
            future.result()
 
print(f"Total processed: {count}")

这种方式所下载的是完整的蛋白质文件，因此我们需要对下载文件进行进一步处理：

def extract_chain(input_pdb_file, output_pdb_file, chain_id):
    with open(input_pdb_file, 'r') as f_in:
        with open(output_pdb_file, 'w') as f_out:
            for line in f_in:
                if line.startswith('ATOM') and line[21] == chain_id:
                    f_out.write(line)

path_output = 'cath/newpdbs/'
path_input = 'cath/pdbs/'
os.makedirs(path_output, exist_ok=True)
for i in tqdm(cath40_data.values):
    pdb_name = i[0]
    chain_id = pdb_name[4]
    if os.path.isfile(os.path.join(path_output, pdb_name[:-3]+chain_id+'.pdb')) == False:#判断是否已经存在该文件
        extract_chain(os.path.join(path_input, pdb_name[:-3]+'.pdb'), os.path.join(path_output, pdb_name[:-3]+chain_id+'.pdb'),chain_id)path_output = 'cath/newpdbs/'

****