2025 - AIDD - python的autodock vina 批量分子对接改进版本2.0-全自动对接,完全全自动对接

2025 - AIDD - python的autodock vina 批量分子对接改进版本2.0-全自动对接,完全全自动对接

python 复制代码
import warnings
from pathlib import Path
import subprocess
from itertools import product
import numpy as np
import pandas as pd
from MDAnalysis import Universe
from openbabel import pybel
import os
import requests  # 用于下载文件

# 清楚 warning 信息

# Filter warnings
warnings.filterwarnings("ignore")

# 设置工作目录
HERE = Path(os.getcwd())
DATA = HERE / 'data'
DATA.mkdir(parents=True, exist_ok=True)

# CSV 文件路径
RESULT_CSV = DATA / 'result_dock.csv'

# 初始化 CSV 文件
if not RESULT_CSV.exists():
    pd.DataFrame(columns=['pdb', 'ligand_resnames', 'smiles', 'dock_info']).to_csv(RESULT_CSV, index=False)


class Structure(Universe):
    """Core object to load structures with."""

    @classmethod
    def from_string(cls, pdb_path):
        """Load a structure from a local PDB file."""
        return cls(pdb_path)


def download_pdb(pdb_id, save_path):
    """从 RCSB PDB 数据库下载 PDB 文件."""
    url = f"https://files.rcsb.org/download/{pdb_id}.pdb"
    response = requests.get(url)
    if response.status_code == 200:
        with open(save_path, "wb") as file:
            file.write(response.content)
        print(f"{pdb_id} 下载成功.")
    else:
        raise ValueError(f"无法下载 {pdb_id}: {response.status_code}")


# 提取蛋白质并保存为 PDB 格式
def extract_protein_to_pdb(structure, protein_path):
    """Extract protein from structure and save it as PDB."""
    protein = structure.select_atoms("protein")
    protein.write(str(protein_path))


# 自动检测所有配体残基
def find_all_ligand_resnames(structure):
    """返回所有非蛋白质和非水分子的残基名称列表"""
    ligand_atoms = structure.select_atoms("not protein and not resname HOH")
    return list(set(ligand_atoms.resnames))


def pdb_to_pdbqt(pdb_path, pdbqt_path, pH=7.4):
    """Convert a PDB file to a PDBQT file."""
    molecule = list(pybel.readfile("pdb", str(pdb_path)))[0]
    molecule.OBMol.CorrectForPH(pH)
    molecule.addh()
    for atom in molecule.atoms:
        atom.OBAtom.GetPartialCharge()
    molecule.write("pdbqt", str(pdbqt_path), overwrite=True)


def smiles_to_pdbqt(smiles, pdbqt_path, pH=7.4):
    """Convert a SMILES string to a PDBQT file."""
    molecule = pybel.readstring("smi", smiles)
    molecule.OBMol.CorrectForPH(pH)
    molecule.addh()
    molecule.make3D(forcefield="mmff94s", steps=10000)
    for atom in molecule.atoms:
        atom.OBAtom.GetPartialCharge()
    molecule.write("pdbqt", str(pdbqt_path), overwrite=True)


def run_smina(ligand_path, protein_path, out_path, pocket_center, pocket_size):
    """Perform docking with Smina."""
    output_text = subprocess.check_output([
        "smina",
        "--receptor", str(protein_path),
        "--ligand", str(ligand_path),
        "--out", str(out_path),
        "--center_x", str(pocket_center[0]),
        "--center_y", str(pocket_center[1]),
        "--center_z", str(pocket_center[2]),
        "--size_x", str(pocket_size[0]),
        "--size_y", str(pocket_size[1]),
        "--size_z", str(pocket_size[2])
    ])
    return output_text.decode("utf-8")


def parse_dock_info(dock_output):
    """解析 Smina 输出中的对接信息"""
    dock_lines = dock_output.splitlines()
    dock_data = []
    capture = False
    for line in dock_lines:
        if "mode" in line and "affinity" in line:  # 开始捕获表格数据
            capture = True
            continue
        if capture:
            if line.strip() == "" or "Refine time" in line or "Loop time" in line:
                break
            dock_data.append(line.strip())
    return "\n".join(dock_data)


def split_sdf_file(sdf_path):
    """Split an SDF file into separate files for each molecule."""
    sdf_path = Path(sdf_path)
    stem = sdf_path.stem
    parent = sdf_path.parent
    molecules = pybel.readfile("sdf", str(sdf_path))
    for i, molecule in enumerate(molecules, 1):
        molecule.write("sdf", str(parent / f"{stem}_{i}.sdf"), overwrite=True)



pdb_list = pd.read_csv('data/pdb.csv')['pdb_id']
# 读取 data 里面的 pic50_greater_equal_9.0.csv 文件,获取其中的 SMILES,前面的 20 个
smiles_list = pd.read_csv('data/pic50_greater_equal_9.0.csv')['smiles'][:20]

# 遍历所有 PDB 和 SMILES 的笛卡尔积
for pdb_id, smiles in product(pdb_list, smiles_list):
    # 创建每个 PDB 的独立目录
    pdb_dir = DATA / f"data_{pdb_id}"
    pdb_dir.mkdir(parents=True, exist_ok=True)

    # 定义 PDB 文件路径
    pdb_path = pdb_dir / f"{pdb_id}.pdb"

    # 如果 PDB 文件不存在,则从 RCSB 下载
    if not pdb_path.exists():
        print(f"{pdb_id} 文件不存在,正在下载...")
        download_pdb(pdb_id, pdb_path)

    # 加载结构
    structure = Structure.from_string(pdb_path)

    # 提取并保存蛋白质部分
    protein_path = pdb_dir / "protein.pdb"
    extract_protein_to_pdb(structure, protein_path)

    # 转换蛋白质为 PDBQT 格式
    protein_pdbqt_path = pdb_dir / "protein.pdbqt"
    pdb_to_pdbqt(protein_path, protein_pdbqt_path)

    # 检测所有 ligand
    all_ligands = find_all_ligand_resnames(structure)

    # all_ligands[0]变为shape为(1,)的数组,方便后续循环
    # all_ligands = ["VX6"]
    print(f"{pdb_id} - Detected Ligands: {all_ligands}")

    # 对所有 ligand 进行处理
    for ligand_resname in all_ligands:
        # 创建 ligand-specific 子目录
        ligand_dir = pdb_dir / f"ligand_{ligand_resname}"
        ligand_dir.mkdir(parents=True, exist_ok=True)

        # 自动检测口袋中心和大小
        ligand = structure.select_atoms(f"resname {ligand_resname}")
        print(f"Processing {pdb_id} {smiles} {ligand_resname}")
        pocket_center = (ligand.positions.max(axis=0) + ligand.positions.min(axis=0)) / 2
        pocket_size = ligand.positions.max(axis=0) - ligand.positions.min(axis=0) + 5

        # 创建针对 SMILES 的子目录
        smiles_hash = smiles.replace("(", "").replace(")", "").replace("=", "").replace("-", "").replace("/","").replace("\\", "").replace(".", "").replace(",", "").replace(":", "")
        smiles_dir = ligand_dir / f"smiles_{smiles_hash}"
        smiles_dir.mkdir(parents=True, exist_ok=True)

        # 定义文件路径
        ligand_path = smiles_dir / "ligand.pdbqt"
        docking_out_path = smiles_dir / "ligand_docking.sdf"
        log_path = smiles_dir / "docking_log.txt"

        # 转换配体为 PDBQT 格式
        smiles_to_pdbqt(smiles, ligand_path)

        # 运行对接并保存日志
        docking_output = run_smina(ligand_path, protein_pdbqt_path, docking_out_path, pocket_center, pocket_size)
        with open(log_path, "w") as log_file:
            log_file.write(f"PDB: {pdb_id}\nSMILES: {smiles}\nLigand Resname: {ligand_resname}\n")
            log_file.write(f"Pocket Center: {pocket_center}\nPocket Size: {pocket_size}\n\nDocking Output:\n")
            log_file.write(docking_output)

        # 拆分 SDF 文件
        split_sdf_file(docking_out_path)

        # 提取对接结果并更新到 CSV
        dock_info = parse_dock_info(docking_output)
        new_row = {'pdb': pdb_id, 'ligand_resnames': ligand_resname, 'smiles': smiles, 'dock_info': dock_info}
        result_df = pd.read_csv(RESULT_CSV)
        result_df = pd.concat([result_df, pd.DataFrame([new_row])], ignore_index=True)
        # 保存更新的结果到 CSV 文件
        result_df.to_csv(RESULT_CSV, index=False)

print("Docking workflow completed successfully!")
相关推荐
包饭厅咸鱼1 分钟前
QT----使用onnxRuntime运行图像分类模型
开发语言·qt·分类
MavenTalk15 分钟前
如何根据不同的场景选择YOLO相应的基座模型
python·yolo·yolo11n·yolo11m·yolo11s·yolo11x
神奇的代码在哪里17 分钟前
使用python开发任天堂gameboy模拟器|pyboy开发实践
python·宝可梦·pyboy·gameboy模拟器·任天堂掌机模拟器
Matlab程序猿小助手28 分钟前
【MATLAB源码-第303期】基于matlab的蒲公英优化算法(DO)机器人栅格路径规划,输出做短路径图和适应度曲线.
开发语言·算法·matlab·机器人·kmeans
不爱编程的小九九28 分钟前
小九源码-springboot097-java付费自习室管理系统
java·开发语言·spring boot
坚持就完事了37 分钟前
正则表达式与Python的re模块
python·正则表达式
Alex艾力的IT数字空间37 分钟前
基于PyTorch和CuPy的GPU并行化遗传算法实现
数据结构·人工智能·pytorch·python·深度学习·算法·机器学习
云知谷41 分钟前
【经典书籍】C++ Primer 第16章模板与泛型编程精华讲解
c语言·开发语言·c++·软件工程·团队开发
keerduoba1 小时前
EWCCTF2025 Tacticool Bin wp
python
workflower1 小时前
基本作业-管理⾃⼰的源代码
开发语言·单元测试·软件工程·需求分析·个人开发