Molecular relaxation by reverse diffusion with time step prediction

Abstract

Molecular relaxation, finding the equilibrium state of a non-equilibrium structure, is an essential component of computational chemistry to understand reactivity. Classical force field (FF) methods often rely on insufficient local energy minimization, while neural network FF models require large labeled datasets encompassing both equilibrium and non-equilibrium structures. As a remedy, we propose MoreRed, molecular relaxation by reverse diffusion, a conceptually novel and purely statistical approach where non-equilibrium structures are treated as noisy instances of their corresponding equilibrium states. To enable the denoising of arbitrarily noisy inputs via a generative diffusion model, we further introduce a novel diffusion time step predictor. Notably, MoreRed learns a simpler pseudo potential energy surface (PES) instead of the complex physical PES. It is trained on a significantly smaller, and thus computationally cheaper, dataset consisting of solely unlabeled equilibrium structures, avoiding the computation of non-equilibrium structures altogether. We compare MoreRed to classical FFs, equivariant neural network FFs trained on a large dataset of equilibrium and non-equilibrium data, as well as a semi-empirical tight-binding model. To assess this quantitatively, we evaluate the root-mean-square deviation between the found equilibrium structures and the reference equilibrium structures as well as their energies.

References in corpus (32)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Recent developments in the PySCF program package
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine learning for molecular simulation
• Comparing molecules and solids across structural and alchemical space
• Resolution-of-identity approach to Hartree-Fock, hybrid density functionals, RPA, MP2, and \textit{GW} with numeric atom-centered orbital basis functions
• Long-range correlation energy calculated from coupled atomic response functions
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Alchemical and structural distribution based representation for improved QML
• Equivariant message passing for the prediction of tensorial properties and molecular spectra
• Exploration of Reaction Pathways and Chemical Transformation Networks
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Automated Discovery of Elementary Chemical Reaction Steps Using Freezing String and Berny Optimization Methods
• The Exploration of Chemical Reaction Networks
• Inverse design of 3d molecular structures with conditional generative neural networks
• QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
• Molecular geometry prediction using a deep generative graph neural network
• Machine learning based energy-free structure predictions of molecules (closed and open-shell), transition states, and solids
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis
• Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
• Reliable estimation of prediction uncertainty for physico-chemical property models
• Mechanism Deduction from Noisy Chemical Reaction Networks
• Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
• Molecular relaxation by reverse diffusion with time step prediction

Cited by in corpus (2)

• On the design space between molecular mechanics and machine learning force fields
• Molecular relaxation by reverse diffusion with time step prediction