Graph Neural Networks Accelerated Molecular Dynamics

Abstract

Molecular Dynamics (MD) simulation is a powerful tool for understanding the dynamics and structure of matter. Since the resolution of MD is atomic-scale, achieving long time-scale simulations with femtosecond integration is very expensive. In each MD step, numerous iterative computations are performed to calculate energy based on different types of interaction and their corresponding spatial gradients. These repetitive computations can be learned and surrogated by a deep learning model like a Graph Neural Network (GNN). In this work, we developed a GNN Accelerated Molecular Dynamics (GAMD) model that directly predicts forces given the state of the system (atom positions, atom types), bypassing the evaluation of potential energy. By training the GNN on a variety of data sources (simulation data derived from classical MD and density functional theory), we show that GAMD can predict the dynamics of two typical molecular systems, Lennard-Jones system and Water system, in the NVT ensemble with velocities regulated by a thermostat. We further show that GAMD's learning and inference are agnostic to the scale, where it can scale to much larger systems at test time. We also perform a comprehensive benchmark test comparing our implementation of GAMD to production-level MD softwares, showing GAMD's competitive performance on the large-scale simulation.

arXiv commentpreprint

References in corpus (46)

• Adam: A Method for Stochastic Optimization
• Neural Message Passing for Quantum Chemistry
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine learning for molecular simulation
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Machine Learning Unifies the Modelling of Materials and Molecules
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Interaction Networks for Learning about Objects, Relations and Physics
• How van der Waals interactions determine the unique properties of water
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Learning to Simulate Complex Physics with Graph Networks
• Ab initio thermodynamics of liquid and solid water
• Directional Message Passing for Molecular Graphs
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• FCHL revisited: faster and more accurate quantum machine learning
• Hierarchical modeling of molecular energies using a deep neural network
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Robust and efficient configurational molecular sampling via Langevin Dynamics
• TorchMD: A deep learning framework for molecular simulations
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• Graph Neural Networks in Particle Physics
• Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules
• Orbital Graph Convolutional Neural Network for Material Property Prediction
• Ab initio quality neural-network potential for sodium
• Fingerprints for spin-selection rules in the interaction dynamics of O2 at Al(111)
• Quantum-mechanical exploration of the phase diagram of water
• Message Passing Neural PDE Solvers
• High-Dimensional Potential Energy Surfaces for Molecular Simulations
• Learning Mesh-Based Simulation with Graph Networks
• Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex Multi-Element Extended Systems
• Differentiable Molecular Simulations for Control and Learning
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations

Cited by in corpus (9)

• Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations
• Graph Neural Networks for Molecules
• Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogates
• A panoramic aerodynamic performance prediction method for turbomachinery cascades using transformer-enhanced neural operator
• Evaluating the Transferability of Machine-Learned Force Fields for Material Property Modeling
• Neural Network Predicts Ion Concentration Profiles under Nanoconfinement