Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects

Abstract

We introduce FENNIX (Force-Field-Enhanced Neural Network InteraXions), a hybrid approach between machine-learning and force-fields. We leverage state-of-the-art equivariant neural networks to predict local energy contributions and multiple atom-in-molecule properties that are then used as geometry-dependent parameters for physically-motivated energy terms which account for long-range electrostatics and dispersion. Using high-accuracy ab initio data (small organic molecules/dimers), we trained a first version of the model. Exhibiting accurate gas-phase energy predictions, FENNIX is transferable to the condensed phase. It is able to produce stable Molecular Dynamics simulations, including nuclear quantum effects, for water predicting accurate liquid properties. The extrapolating power of the hybrid physically-driven machine learning FENNIX approach is exemplified by computing: i) the solvated alanine dipeptide free energy landscape; ii) the reactive dissociation of small molecules.

References in corpus (36)

• Decoupled Weight Decay Regularization
• Neural Message Passing for Quantum Chemistry
• Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• 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
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Competing quantum effects in the dynamics of a flexible water model
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• 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
• Minimal Basis Iterative Stockholder: Atoms in Molecules for Force-Field Development
• A deep potential model with long-range electrostatic interactions
• Incorporating long-range physics in atomic-scale machine learning
• Rational Construction of Stochastic Numerical Methods for Molecular Sampling
• Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• GemNet: Universal Directional Graph Neural Networks for Molecules
• q-AQUA: a many-body CCSD(T) water potential, including 4-body interactions, demonstrates the quantum nature of water from clusters to the liquid phase
• e3nn: Euclidean Neural Networks
• TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations
• The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Tinker-HP : Accelerating Molecular Dynamics Simulations of Large Complex Systems with Advanced Point Dipole Polarizable Force Fields using GPUs and Multi-GPUs systems
• Accurate biomolecular simulations account for electronic polarization
• Scalable Hybrid Deep Neural Networks/Polarizable Potentials Biomolecular Simulations including long-range effects
• Development of the Quantum Inspired SIBFA Many-Body Polarizable Force Field: Enabling Condensed Phase Molecular Dynamics Simulations
• Assessment of SAPT and Supermolecular EDAs Approaches for the Development of Separable and Polarizable force fields
• Nuclear Quantum Effects in liquid water at near classical computational cost using the adaptive Quantum Thermal Bath
• Routine Molecular Dynamics Simulations Including Nuclear Quantum Effects: from Force Fields to Machine Learning Potentials
• Crystal Structure Representations for Machine Learning Models of Formation Energies
• Improving Condensed Phase Water Dynamics with Explicit Nuclear Quantum Effects: the Polarizable Q-AMOEBA Force Field
• Wigner kernels: body-ordered equivariant machine learning without a basis

Cited by in corpus (10)

• Scalable Hybrid Deep Neural Networks/Polarizable Potentials Biomolecular Simulations including long-range effects
• On the design space between molecular mechanics and machine learning force fields
• $\Delta$-Machine Learning to Elevate DFT-based Potentials and a Force Field to the CCSD(T) Level Illustrated for Ethanol
• FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
• Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials
• Lambda-ABF-OPES: Faster Convergence with High Accuracy in Alchemical Free Energy Calculations
• The Q-AMOEBA (CF) Polarizable Potential
• Considerations in the use of ML interaction potentials for free energy calculations
• Machine-Learned Potentials for Solvation Modeling
• Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces