Search for: All records

Abstract In the last several years, there has been a surge in the development of machine learning potential (MLP) models for describing molecular systems. We are interested in a particular area of this field — the training of system‐specific MLPs for reactive systems — with the goal of using these MLPs to accelerate free energy simulations of chemical and enzyme reactions. To help new members in our labs become familiar with the basic techniques, we have put together a self‐guided Colab tutorial (https://cc-ats.github.io/mlp_tutorial/), which we expect to be also useful to other young researchers in the community. Our tutorial begins with the introduction of simple feedforward neural network (FNN) and kernel‐based (using Gaussian process regression, GPR) models by fitting the two‐dimensional Müller‐Brown potential. Subsequently, two simple descriptors are presented for extracting features of molecular systems: symmetry functions (including the ANI variant) and embedding neural networks (such as DeepPot‐SE). Lastly, these features will be fed into FNN and GPR models to reproduce the energies and forces for the molecular configurations in a Claisen rearrangement reaction. 

Following the formulation of cavity quantum-electrodynamical time-dependent density functional theory (cQED-TDDFT) models [Flick et al., ACS Photonics 6, 2757–2778 (2019) and Yang et al., J. Chem. Phys. 155, 064107 (2021)], here, we report the derivation and implementation of the analytic energy gradient for polaritonic states of a single photochrome within the cQED-TDDFT models. Such gradient evaluation is also applicable to a complex of explicitly specified photochromes or, with proper scaling, a set of parallel-oriented, identical-geometry, and non-interacting molecules in the microcavity.