Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules.

IF 10.7 1区 综合性期刊 Q1 Multidisciplinary
Research Pub Date : 2025-08-25 eCollection Date: 2025-01-01 DOI:10.34133/research.0837
Manyi Yang, Duo Zhang, Xinyan Wang, BoWen Li, Linfeng Zhang, Weinan E, Tong Zhu, Han Wang
{"title":"Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules.","authors":"Manyi Yang, Duo Zhang, Xinyan Wang, BoWen Li, Linfeng Zhang, Weinan E, Tong Zhu, Han Wang","doi":"10.34133/research.0837","DOIUrl":null,"url":null,"abstract":"<p><p>The advent of machine learning (ML) in computational chemistry heralds a transformative approach to one of the quintessential challenges in computer-aided drug design (CADD): the accurate and cost-effective calculation of atomic interactions. By leveraging a neural network (NN) potential, we address this balance and push the boundaries of the NN potential's representational capacity. Our work details the development of a robust general-purpose NN potential, architected on the framework of DPA-2, a deep learning potential with attention, which demonstrates remarkable fidelity in replicating the interatomic potential energy surface for drug-like molecules comprising 8 critical chemical elements: H, C, N, O, F, S, Cl, and P. We employed state-of-the-art molecular dynamic (MD) techniques, including temperature acceleration and enhanced sampling, to construct a comprehensive dataset to ensure exhaustive coverage of relevant configurational spaces. Our rigorous testing protocols, including torsion scanning, structure relaxation, and high-temperature MD simulations across various organic molecules, have culminated in an NN model that achieves chemical precision commensurate with the highly regarded density functional theory model while substantially outstripping the accuracy of prevalent semi-empirical methods. This study presents a leap forward in the predictive modeling of molecular interactions, offering extensive applications in drug development and beyond.</p>","PeriodicalId":21120,"journal":{"name":"Research","volume":"8 ","pages":"0837"},"PeriodicalIF":10.7000,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12377527/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Research","FirstCategoryId":"103","ListUrlMain":"https://doi.org/10.34133/research.0837","RegionNum":1,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"Multidisciplinary","Score":null,"Total":0}
引用次数: 0

Abstract

The advent of machine learning (ML) in computational chemistry heralds a transformative approach to one of the quintessential challenges in computer-aided drug design (CADD): the accurate and cost-effective calculation of atomic interactions. By leveraging a neural network (NN) potential, we address this balance and push the boundaries of the NN potential's representational capacity. Our work details the development of a robust general-purpose NN potential, architected on the framework of DPA-2, a deep learning potential with attention, which demonstrates remarkable fidelity in replicating the interatomic potential energy surface for drug-like molecules comprising 8 critical chemical elements: H, C, N, O, F, S, Cl, and P. We employed state-of-the-art molecular dynamic (MD) techniques, including temperature acceleration and enhanced sampling, to construct a comprehensive dataset to ensure exhaustive coverage of relevant configurational spaces. Our rigorous testing protocols, including torsion scanning, structure relaxation, and high-temperature MD simulations across various organic molecules, have culminated in an NN model that achieves chemical precision commensurate with the highly regarded density functional theory model while substantially outstripping the accuracy of prevalent semi-empirical methods. This study presents a leap forward in the predictive modeling of molecular interactions, offering extensive applications in drug development and beyond.

类药物分子的从头算精度神经网络潜力。
计算化学中机器学习(ML)的出现预示着一种革命性的方法,可以解决计算机辅助药物设计(CADD)中最典型的挑战之一:准确而经济地计算原子相互作用。通过利用神经网络(NN)的潜力,我们解决了这种平衡,并推动了神经网络潜力的表征能力的界限。我们的工作详细介绍了基于DPA-2框架的鲁棒通用神经网络潜力的开发,这是一种具有注意力的深度学习潜力,它在复制由8个关键化学元素组成的药物类分子的原子间势能表面方面表现出了非凡的保真度:H, C, N, O, F, S, Cl和p。我们采用最先进的分子动力学(MD)技术,包括温度加速和增强采样,构建了一个全面的数据集,以确保详尽地覆盖相关的构型空间。我们严格的测试协议,包括扭转扫描、结构松弛和各种有机分子的高温MD模拟,最终形成了一个神经网络模型,该模型达到了与高度重视的密度泛函理论模型相称的化学精度,同时大大超过了流行的半经验方法的精度。这项研究在分子相互作用的预测建模方面取得了飞跃,在药物开发和其他领域提供了广泛的应用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Research
Research Multidisciplinary-Multidisciplinary
CiteScore
13.40
自引率
3.60%
发文量
0
审稿时长
14 weeks
期刊介绍: Research serves as a global platform for academic exchange, collaboration, and technological advancements. This journal welcomes high-quality research contributions from any domain, with open arms to authors from around the globe. Comprising fundamental research in the life and physical sciences, Research also highlights significant findings and issues in engineering and applied science. The journal proudly features original research articles, reviews, perspectives, and editorials, fostering a diverse and dynamic scholarly environment.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信