Training atomic neural networks using fragment-based data generated in virtual reality

Abstract

The ability to understand and engineer molecular structures relies on having accurate descriptions of the energy as a function of atomic coordinates. Here we outline a new paradigm for deriving energy functions of hyperdimensional molecular systems, which involves generating data for low-dimensional systems in virtual reality (VR) to then efficiently train atomic neural networks (ANNs). This generates high quality data for specific areas of interest within the hyperdimensional space that characterizes a molecule's potential energy surface (PES). We demonstrate the utility of this approach by gathering data within VR to train ANNs on chemical reactions involving fewer than 8 heavy atoms. This strategy enables us to predict the energies of much higher-dimensional systems, e.g. containing nearly 100 atoms. Training on datasets containing only 15K geometries, this approach generates mean absolute errors around 2 kcal/mol. This represents one of the first times that an ANN-PES for a large reactive radical has been generated using such a small dataset. Our results suggest VR enables the intelligent curation of high-quality data, which accelerates the learning process.

References in corpus (15)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• FCHL revisited: faster and more accurate quantum machine learning
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Sampling molecular conformations and dynamics in a multi-user virtual reality framework
• Training neural nets to learn reactive potential energy surfaces using interactive quantum chemistry in virtual reality
• Interactive molecular dynamics in virtual reality from quantum chemistry to drug binding: An open-source multi-person framework
• Interactive Chemical Reactivity Exploration
• A parallel multistate framework for atomistic non-equilibrium reaction dynamics of solutes in strongly interacting organic solvents
• Real-time Quantum Chemistry
• Self-Parametrizing System-Focused Atomistic Models
• Real-time feedback from iterative electronic structure calculations

Cited by in corpus (6)

• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Automated construction of quantum-classical hybrid models
• PhysNet Meets CHARMM: A Framework for Routine Machine Learning / Molecular Mechanics Simulations
• Free energy along drug-protein binding pathways interactively sampled in virtual reality
• Measuring the limit of perception of bond stiffness of interactive molecules in VR via a gamified psychophysics experiment
• Virtual Reality for Understanding Artificial-Intelligence-driven Scientific Discovery with an Application in Quantum Optics