在自由能计算中使用机器学习相互作用势的考量
Considerations in the use of ML interaction potentials for free energy calculations
AI总结:
本文研究 EQNN 机器学习力场预测丁烷与 ADP 自由能面时训练数据的影响,发现覆盖 FES 特征区域比 CV 分布更关键,且从头算标签可改善高自由能构型的外推。
摘要:
机器学习力场(MLFF)有望以更高的计算效率,在从头算理论水平上准确描述分子的势能面。在各类 MLFF 中,等变图神经网络(EQNN)在准确性和性能方面展现出巨大潜力,也是本工作的重点。EQNN 恢复自由能面(FES)的能力仍有待深入研究。在本工作中,我们研究了训练数据中集合变量(CV)分布对 EQNN 预测丁烷和丙氨酸二肽(ADP)自由能面准确性的影响。文中提出了一个可推广的工作流程:通过经典分子动力学模拟生成训练构型,并利用从头算计算获得能量和力。我们评估了训练数据中的键约束和角约束如何影响 EQNN 力场在经典理论水平和从头算理论水平上重现分子 FES 的准确性。结果表明,只要训练数据包含来自系统 FES 特征区域的构型,模型的准确性就不会受到训练期间所采样 CV 分布的影响。然而,当训练数据来自经典模拟时,EQNN 难以对具有高自由能的构型进行自由能外推。相比之下,使用相同构型、但基于从头算数据训练的模型表现出更高的外推准确性。这些发现强调了为 EQNN 建立全面训练数据集以预测 FES 的困难,并凸显了预先掌握系统 FES 知识的重要性。
英文摘要:
Machine learning force fields (MLFFs) promise to accurately describe the potential energy surface of molecules at the ab initio level of theory with improved computational efficiency. Within MLFFs, equivariant graph neural networks (EQNNs) have shown great promise in accuracy and performance and are the focus of this work. The capability of EQNNs to recover free energy surfaces (FES) remains to be thoroughly investigated. In this work, we investigate the impact of collective variables (CVs) distribution within the training data on the accuracy of EQNNs predicting the FES of butane and alanine dipeptide (ADP). A generalizable workflow is presented in which training configurations are generated with classical molecular dynamics simulations, and energies and forces are obtained with ab initio calculations. We evaluate how bond and angle constraints in the training data influence the accuracy of EQNN force fields in reproducing the FES of the molecules at both classical and ab initio levels of theory. Results indicate that the model's accuracy is unaffected by the distribution of sampled CVs during training, given that the training data includes configurations from characteristic regions of the system's FES. However, when the training data is obtained from classical simulations, the EQNN struggles to extrapolate the free energy for configurations with high free energy. In contrast, models trained with the same configurations on ab initio data show improved extrapolation accuracy. The findings underscore the difficulties in creating a comprehensive training dataset for EQNNs to predict FESs and highlight the importance of prior knowledge of the system's FES.
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。