网络药理学：14、SwissADME和PubChem和TCMSP互通（TCMSP爬虫批量得到化合物名称或Mol ID、批量转换为SDF文件/SMILES序列号/CID、SwissTarget批量下载）

TCMSP爬虫批量得到化合物名称或Mol ID

见我的另一篇博客：https://blog.youkuaiyun.com/zhiaidaidai/article/details/141960061（链接失效可以直接看本专栏p4）

通过化合物名称批量获得SMILES序列号/CID序列号

import pubchempy
import pandas as pd
import itertools
import time

def read_file(file_name) -> list:
    """
    读取化合物名称
    :param file_name: 含有化合物名称的txt或csv格式文件（含路径）
    :return: list
    """
    try:
        df = pd.read_csv(file_name, sep=',', encoding='utf-8-sig')
        if 'Molecule Name' in df.columns.values:
            return df['Molecule Name'].tolist()
    except pd.errors.ParserError:  # 如果文件不是CSV格式，说明是txt格式，继续尝试
        pass

    with open(file_name, 'r', encoding='utf-8-sig') as file:
        return [line.strip() for line in file.readlines()]


def get_compound_info(name: list):
    """
    获取化合物信息
    :param name: 化合物名称列表
    """
    try:
        compounds = pubchempy.get_compounds(name, 'name')
        for compound in compounds:
            result = {
                'name': name,
                'molecular_formula': compound.molecular_formula,
                'molecular_weight': compound.molecular_weight,
                'smiles': compound.isomeric_smiles,
                'synonyms': compound.synonyms,
                'cid': compound.cid
            }
            print(
                f"CID: {compound.cid}\tMass: {compound.exact_mass}\tName: {compound.iupac_name}\tMolfor: {compound.molecular_formula}\tSmi: {compound.isomeric_smiles}\tSyn: {compound.synonyms}")
            yield result
    except Exception as e:
        print("occurred error when processing compound", name)
        print(str(e))
        return


def chemName_to_Smiles_or_CID(input_file_name, output_file_name):
    """
    通过化合物名称批量获得SMILES序列号/CID序列号
    :param input_file_name:含有化合物名称的txt格式文件（含路径），一行一个化合物名称，换行符分隔
    :param output_file_name: 输出文件（含路径）
    """

    start_time = time.time()

    # 输入
    name_list = read_file(input_file_name)
    # 生成器优化循环遍历
    results = itertools.chain.from_iterable(get_compound_info(name) for name in name_list)
    # 输出
    dataframe = pd.DataFrame(results)
    dataframe.to_csv(output_file_name, index=False, sep=',')
    
    # 结束计时
    end_time = time.time()
    print(f"Total queries: {len(dataframe)}")
    print(f"Elapsed time: {end_time - start_time:.2f} seconds")


if __name__ == '__main__':
    print("start convert")

    input_file_name = "1-TCMSP.csv"
    output_file_name = "smiles_and_cid.csv"

    chemName_to_Smiles_or_CID(input_file_name, output_file_name)

SwissTargetPrediction批量下载csv文件

因为SwissTargetPrediction网站只能单个输入SMILES号并下载预测的靶点，于是写了个爬虫程序，能够批量输入SMILES号，下载csv文件并将文件命名为成分名称。

注意本人用的是edge的driver，需要自行下载。代码还有优化之处，现在是一个SMILES号开一个driver，比较浪费连接池资源，但是懒得改了hhh

# @Time    : 2024/11/10
# @Author  : shanshan
# @优快云    : https://blog.youkuaiyun.com/zhiaidaidai
# Copyright (c) 2024, shanshan Group All Rights Reserved.

import glob
import os
import time
from selenium import webdriver
from selenium.webdriver.edge.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

# ------------------------修改输入------------------------------
# 定义文件名和SMILES的pair列表
smiles_pairs = [
    ("compound1", "C1=CC(=C(C=C1C2=C(C(=O)C3=C(C=C(C=C3O2)O)O)O)O)O"),
    ("compound2", "C1CN2C(=NC3=CC=CC=C3C2=O)C4=C1C5=CC=CC=C5N4"),
]
# 默认的下载路径（win的）
download_path = os.path.expanduser("~/Downloads")
# ------------------------修改输入完毕--------------------------

def predict_and_download(driver, smiles_string):
    try:
        # 等待 SMILES 输入框可见
        smiles_input = WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.ID, "smilesBox"))
        )

        # 清空输入框并设置值，同时触发必要的事件
        driver.execute_script("""
            // 处理输入框
            var input = arguments[0];
            input.value = '';
            input.value = arguments[1];
            
            // 触发输入事件
            var inputEvent = new Event('input', { bubbles: true });
            input.dispatchEvent(inputEvent);
            
            // 触发change事件
            var changeEvent = new Event('change', { bubbles: true });
            input.dispatchEvent(changeEvent);
            
            // 获取并启用提交按钮
            var submitButton = document.getElementById('submitButton');
            submitButton.disabled = false;
            submitButton.removeAttribute('disabled');
            
            // 恢复按钮样式
            submitButton.style.backgroundColor = 'rgb(255, 0, 0)';

                              
            submitButton.style.color = 'rgb(255, 255, 255)';
        """, smiles_input, smiles_string)

        # 点击提交按钮
        submit_button = driver.find_element(By.ID, "submitButton")
        driver.execute_script("arguments[0].click();", submit_button)


        # 等待 CSV 下载按钮可见
        csv_button = WebDriverWait(driver, 10).until(
            EC.element_to_be_clickable((By.CSS_SELECTOR, ".buttons-csv"))
        )
        csv_button.click()

        # 等待下载完成
        time.sleep(3)  


         # 获取下载文件夹中最新的CSV文件 
        list_of_files = glob.glob(os.path.join(download_path, "*.csv"))
        latest_file = max(list_of_files, key=os.path.getctime)
        
        # 构建新的文件名
        new_filename = os.path.join(download_path, f"{filename}.csv")
        
        # 如果目标文件已存在，先删除
        if os.path.exists(new_filename):
            os.remove(new_filename)
            
        # 重命名文件
        os.rename(latest_file, new_filename)
        print(f"已将文件重命名为: {filename}.csv")

    except Exception as e:
        print(f"处理SMILES字符串 '{smiles_string}' 时出现错误：{e}")

if __name__ == '__main__':

    drivers = []  # 存储所有driver实例
    
    # 为每个SMILES pair创建一个新的浏览器窗口
    for filename, smiles in smiles_pairs:
        service = Service('./msedgedriver.exe')
        driver = webdriver.Edge(service=service)
        drivers.append(driver)
        
        # 打开目标URL
        driver.get("http://swisstargetprediction.ch/")
        # 确保页面加载完成
        WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.TAG_NAME, "body"))
        )
        predict_and_download(driver, smiles)
        driver.quit()