Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801 United States.
Walker Department of Mechanical Engineering, Oden Institute for Computational Engineering & Sciences, The University of Texas at Austin, Austin, Texas 78712 United States.
J Phys Chem A. 2022 Mar 10;126(9):1562-1570. doi: 10.1021/acs.jpca.1c10865. Epub 2022 Feb 24.
Molecular dynamics (MD) simulations are widely used to obtain the microscopic properties of atomistic systems when the interatomic potential or the coarse-grained potential is known. In many practical situations, however, it is necessary to predict the interatomic or coarse-grained potential, which is a tremendous challenge. Many approaches have been developed to predict the potential parameters based on various techniques, including the relative entropy method, integral equation theory, etc., but these methods lack transferability and are limited to a specific range of thermodynamic states. Recently, data-driven and machine learning approaches have been developed to overcome such limitations. In this study, we expand the range of thermodynamic states used to train deep inverse liquid-state theory (DeepILST), a deep learning framework for solving the inverse problem of liquid-state theory. We also assess the performance of DeepILST in coarse-graining various multiatom molecules and identify the molecular characteristics that affect the coarse-graining performance of DeepILST.
分子动力学（MD）模拟被广泛用于获得原子系统的微观性质，前提是知道原子间势或粗粒化势。然而，在许多实际情况下，需要预测原子间或粗粒化势，这是一个巨大的挑战。已经开发了许多方法来基于各种技术预测潜在参数，包括相对熵方法、积分方程理论等，但这些方法缺乏可转移性，并且仅限于特定的热力学状态范围。最近，数据驱动和机器学习方法已经被开发出来以克服这些限制。在这项研究中，我们扩展了用于训练深度逆液相理论（DeepILST）的热力学状态范围，DeepILST 是一种用于解决液相理论逆问题的深度学习框架。我们还评估了 DeepILST 在粗粒化各种多原子分子中的性能，并确定了影响 DeepILST 粗粒化性能的分子特征。
