当前位置: X-MOL 学术arXiv.cs.CE › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
An Extendible, Graph-Neural-Network-Based Approach for Accurate Force Field Development of Large Flexible Organic Molecules
arXiv - CS - Computational Engineering, Finance, and Science Pub Date : 2021-06-02 , DOI: arxiv-2106.00927
Xufei Wang, Yuanda Xu, Han Zheng, Kuang Yu

An accurate force field is the key to the success of all molecular mechanics simulations on organic polymers and biomolecules. Accuracy beyond density functional theory is often needed to describe the intermolecular interactions, while most correlated wavefunction (CW) methods are prohibitively expensive for large molecules. Therefore, it posts a great challenge to develop an extendible ab initio force field for large flexible organic molecules at CW level of accuracy. In this work, we face this challenge by combining the physics-driven nonbonding potential with a data-driven subgraph neural network bonding model (named sGNN). Tests on polyethylene glycol polymer chains show that our strategy is highly accurate and robust for molecules of different sizes. Therefore, we can develop the force field from small molecular fragments (with sizes easily accessible to CW methods) and safely transfer it to large polymers, thus opening a new path to the next-generation organic force fields.

中文翻译:

一种可扩展的、基于图神经网络的大柔性有机分子精确力场开发方法

准确的力场是有机聚合物和生物分子的所有分子力学模拟成功的关键。通常需要超出密度泛函理论的精度来描述分子间相互作用,而大多数相关波函数 (CW) 方法对于大分子来说成本过高。因此,在 CW 精度水平上为大型柔性有机分子开发可扩展的从头算力场是一个巨大的挑战。在这项工作中,我们通过将物理驱动的非键合潜力与数据驱动的子图神经网络键合模型(称为 sGNN)相结合来应对这一挑战。对聚乙二醇聚合物链的测试表明,我们的策略对于不同大小的分子具有高度的准确性和鲁棒性。所以,
更新日期:2021-06-03
down
wechat
bug