arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.18583q-bio.BMcs.LG
收藏

用于基于结构的药物设计的结合自适应扩散模型

Binding-Adaptive Diffusion Models for Structure-Based Drug Design

Tsinghua University(清华大学);Peng Cheng Laboratory(鹏城实验室);Peking University(北京大学);University of Science and Technology of China(中国科学技术大学);University of Chinese Academy of Sciences(中国科学院大学);ByteDance(字节跳动)

Zhilin Huang, Ling Yang, Zaixi Zhang, Xiangxin Zhou, Yu Bao, Xiawu Zheng, Yuwei Yang, Yu Wang, Wenming Yang

AI总结:

提出BindDM框架,通过自适应提取蛋白质-配体亚复合物并利用SE(3)等变网络与跨层级交互融合,增强靶点感知三维分子扩散生成,在CrossDocked2020上获得更真实结构和更高结合亲和力。

摘要:

基于结构的药物设计(SBDD)旨在生成与特定蛋白质靶点结合的三维配体分子。包括扩散模型在内的现有三维深度生成模型已在SBDD中展现出巨大潜力。然而,在三维空间中精确捕捉分子生成所必需的蛋白质-配体相互作用十分复杂。为解决这一问题,我们提出了一个新颖框架,即结合自适应扩散模型(BindDM)。在BindDM中,我们自适应地提取亚复合物,即结合位点中负责蛋白质-配体相互作用的关键部分。随后,使用SE(3)等变神经网络处理所选蛋白质-配体亚复合物,并将其传回复合物的每个原子,以利用结合相互作用信息增强具有靶点感知能力的三维分子扩散生成。我们通过跨层级相互作用节点迭代这一分层的复合物-亚复合物过程,以充分融合复合物及其对应亚复合物之间的全局结合上下文。在CrossDocked2020数据集上的实证研究表明,BindDM能够生成具有更真实三维结构、对蛋白质靶点具有更高结合亲和力的分子,其Avg. Vina Score最高可达-5.92,同时保持适当的分子性质。我们的代码可在https://github.com/YangLing0818/BindDM获取。

英文摘要:

Structure-based drug design (SBDD) aims to generate 3D ligand molecules that bind to specific protein targets. Existing 3D deep generative models including diffusion models have shown great promise for SBDD. However, it is complex to capture the essential protein-ligand interactions exactly in 3D space for molecular generation. To address this problem, we propose a novel framework, namely Binding-Adaptive Diffusion Models (BindDM). In BindDM, we adaptively extract subcomplex, the essential part of binding sites responsible for protein-ligand interactions. Then the selected protein-ligand subcomplex is processed with SE(3)-equivariant neural networks, and transmitted back to each atom of the complex for augmenting the target-aware 3D molecule diffusion generation with binding interaction information. We iterate this hierarchical complex-subcomplex process with cross-hierarchy interaction node for adequately fusing global binding context between the complex and its corresponding subcomplex. Empirical studies on the CrossDocked2020 dataset show BindDM can generate molecules with more realistic 3D structures and higher binding affinities towards the protein targets, with up to -5.92 Avg. Vina Score, while maintaining proper molecular properties. Our code is available at https://github.com/YangLing0818/BindDM

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑