In recent years, machine learning (ML) methods have become increasingly popular in computational chemistry. After being trained on appropriate ab initio reference data, these methods allow to accurately predict the properties of chemical systems, circumventing the need for explicitly solving the electronic Schrödinger equation. Because of their computational efficiency and scalability to large datasets, deep neural networks (DNNs) are a particularly promising ML algorithm for chemical applications. This work introduces PhysNet, a DNN architecture designed for predicting energies, forces and dipole moments of chemical systems. PhysNet achieves state-of-the-art performance on the QM9, MD17 and ISO17 benchmarks. Further, two new datasets are generated in order to probe the performance of ML models for describing chemical reactions, long-range interactions, and condensed phase systems. It is shown that explicitly including electrostatics in energy predictions is crucial for a qualitatively correct description of the asymptotic regions of a potential energy surface (PES). PhysNet models trained on a systematically constructed set of small peptide fragments (at most eight heavy atoms) are able to generalize to considerably larger proteins like deca-alanine (Ala$_{10}$): The optimized geometry of helical Ala$_{10}$ predicted by PhysNet is virtually identical to ab initio results (RMSD = 0.21 Å). By running unbiased molecular dynamics (MD) simulations of Ala$_{10}$ on the PhysNet-PES in gas phase, it is found that instead of a helical structure, Ala$_{10}$ folds into a wreath-shaped configuration, which is more stable than the helical form by 0.46 kcal mol$^{-1}$ according to the reference ab initio calculations.
xDH double hybrid functionals can be qualitatively incorrect for non-equilibrium geometries: Dipole moment inversion and barriers to radical-radical association using XYG3 and XYGJ-OS
An atom-based machine-learned dipole-moment model and application to conjugated systems
Quemix Inc.（Quemix公司）；The University of Tokyo（东京大学）；JSR Corporation（JSR公司）；National Institutes for Quantum Science and Technology (QST)（国立量子科学技术研究院）；RIKEN Center for Computational Science (R-CCS)（理化学研究所计算科学中心）
ECENet: An Edge Cluster Expansion Line-Graph Neural Network
Kenneth S. Pitzer Theory Center and Department of Chemistry（肯尼斯·S·皮策理论中心与化学系）；Chemical Sciences Division, Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室化学科学部）；Departments of Bioengineering and Chemical and Biomolecular Engineering University of California, Berkeley（加州大学伯克利分校生物工程和化学与分子生物工程系）
