Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Manyi Yang, Duo Zhang, Xinyan Wang, BoWen Li, Linfeng Zhang, Weinan E, Tong Zhu, Han Wang
Format: Article
Language:English
Published: American Association for the Advancement of Science (AAAS) 2025-01-01
Series:Research
Online Access:https://spj.science.org/doi/10.34133/research.0837
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223262627692544
author Manyi Yang
Duo Zhang
Xinyan Wang
BoWen Li
Linfeng Zhang
Weinan E
Tong Zhu
Han Wang
author_facet Manyi Yang
Duo Zhang
Xinyan Wang
BoWen Li
Linfeng Zhang
Weinan E
Tong Zhu
Han Wang
author_sort Manyi Yang
collection DOAJ
description 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.
format Article
id doaj-art-c7c12a19ab3e434d86f70be30ec96691
institution Kabale University
issn 2639-5274
language English
publishDate 2025-01-01
publisher American Association for the Advancement of Science (AAAS)
record_format Article
series Research
spelling doaj-art-c7c12a19ab3e434d86f70be30ec966912025-08-25T19:50:27ZengAmerican Association for the Advancement of Science (AAAS)Research2639-52742025-01-01810.34133/research.0837Ab Initio Accuracy Neural Network Potential for Drug-Like MoleculesManyi Yang0Duo Zhang1Xinyan Wang2BoWen Li3Linfeng Zhang4Weinan E5Tong Zhu6Han Wang7The Institute of Green Chemistry and Engineering, Nanjing University, Suzhou, Jiangsu 215163, China.AI for Science Institute, Beijing 100080, China.DP Technology, Beijing 100080, China.Shanghai Engineering Research Center of Molecular Therapeutics & New Drug Development, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai 200062, China.AI for Science Institute, Beijing 100080, China.AI for Science Institute, Beijing 100080, China.Shanghai Engineering Research Center of Molecular Therapeutics & New Drug Development, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai 200062, China.National Key Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics, Beijing 100088, China.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.https://spj.science.org/doi/10.34133/research.0837
spellingShingle Manyi Yang
Duo Zhang
Xinyan Wang
BoWen Li
Linfeng Zhang
Weinan E
Tong Zhu
Han Wang
Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules
Research
title Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules
title_full Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules
title_fullStr Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules
title_full_unstemmed Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules
title_short Ab Initio Accuracy Neural Network Potential for Drug-Like Molecules
title_sort ab initio accuracy neural network potential for drug like molecules
url https://spj.science.org/doi/10.34133/research.0837
work_keys_str_mv AT manyiyang abinitioaccuracyneuralnetworkpotentialfordruglikemolecules
AT duozhang abinitioaccuracyneuralnetworkpotentialfordruglikemolecules
AT xinyanwang abinitioaccuracyneuralnetworkpotentialfordruglikemolecules
AT bowenli abinitioaccuracyneuralnetworkpotentialfordruglikemolecules
AT linfengzhang abinitioaccuracyneuralnetworkpotentialfordruglikemolecules
AT weinane abinitioaccuracyneuralnetworkpotentialfordruglikemolecules
AT tongzhu abinitioaccuracyneuralnetworkpotentialfordruglikemolecules
AT hanwang abinitioaccuracyneuralnetworkpotentialfordruglikemolecules