<br>基于机器学习的隐式溶剂模型，用于水溶液丙氨酸二肽分子动力学模拟,RSC Advances

当前位置： X-MOL 学术 › RSC Adv. › 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.)

基于机器学习的隐式溶剂模型，用于水溶液丙氨酸二肽分子动力学模拟
RSC Advances ( IF 3.9 ) Pub Date : 2023-02-03 , DOI: 10.1039/d2ra08180f
Songyuan Yao ₁ , Richard Van ₁ , Xiaoliang Pan ₁ , Ji Hwan Park ₂ , Yuezhi Mao ₃ , Jingzhi Pu ₄ , Ye Mei _{5,

6,

7} , Yihan Shao ₁

Affiliation

受到 Noé 和同事最近开发基于机器学习的隐式溶剂模型以模拟溶剂化肽的工作的启发 [Chen等人，2017]。， J.化学。物理。 , 2021, 155 , 084101]，在这里我们报告了另一项关于使用机器学习 (ML) 技术直接从显式溶剂分子动力学 (MD) 模拟“推导”隐式溶剂模型的可能性的研究。对于丙氨酸二肽，基于分子的 DeepPot-SE 表示的机器学习潜力 (MLP) 经过训练，以捕获其与其平均溶剂环境配置 (ASEC) 的相互作用。预测的溶质力与参考值的 RMSD 偏差仅为 0.4 kcal mol ^-1 Å ^-1 ，基于 MLP 的自由能表面与显式溶剂 MD 模拟获得的结果的 RMSD 差异小于 0.9 kcal摩尔^-1 。我们的 MLP 训练协议还可以在 ASEC 环境中准确再现量子力学 (QM) 溶质上的组合量子力学分子力学 (QM/MM) 力，从而能够开发基于 ML 的精确隐式溶剂模型，用于从头开始-QM MD 模拟。这种用于 QM 计算的基于 ML 的隐式溶剂模型在训练阶段（使用 ASEC 减少了要标记的数据点数量）和推理阶段（可以在相对较小的情况下评估 MLP）都具有成本效益。除了溶质的 QM 计算之外的额外成本。

"点击查看英文标题和摘要"

Machine learning based implicit solvent model for aqueous-solution alanine dipeptide molecular dynamics simulations

Inspired by the recent work from Noé and coworkers on the development of machine learning based implicit solvent model for the simulation of solvated peptides [Chen et al., J. Chem. Phys., 2021, 155, 084101], here we report another investigation of the possibility of using machine learning (ML) techniques to “derive” an implicit solvent model directly from explicit solvent molecular dynamics (MD) simulations. For alanine dipeptide, a machine learning potential (MLP) based on the DeepPot-SE representation of the molecule was trained to capture its interactions with its average solvent environment configuration (ASEC). The predicted forces on the solute deviated only by an RMSD of 0.4 kcal mol⁻¹ Å⁻¹ from the reference values, and the MLP-based free energy surface differed from that obtained from explicit solvent MD simulations by an RMSD of less than 0.9 kcal mol⁻¹. Our MLP training protocol could also accurately reproduce combined quantum mechanical molecular mechanical (QM/MM) forces on the quantum mechanical (QM) solute in ASEC environment, thus enabling the development of accurate ML-based implicit solvent models for ab initio-QM MD simulations. Such ML-based implicit solvent models for QM calculations are cost-effective in both the training stage, where the use of ASEC reduces the number of data points to be labelled, and the inference stage, where the MLP can be evaluated at a relatively small additional cost on top of the QM calculation of the solute.

更新日期：2023-02-03

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南