Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science

Abstract

The MACE architecture represents the state of the art in the field of machine learning force fields for a variety of in-domain, extrapolation and low-data regime tasks. In this paper, we further evaluate MACE by fitting models for published benchmark datasets. We show that MACE generally outperforms alternatives for a wide range of systems from amorphous carbon, universal materials modelling, and general small molecule organic chemistry to large molecules and liquid water. We demonstrate the capabilities of the model on tasks ranging from constrained geometry optimisation to molecular dynamics simulations and find excellent performance across all tested domains. We show that MACE is very data efficient, and can reproduce experimental molecular vibrational spectra when trained on as few as 50 randomly selected reference configurations. We further demonstrate that the strictly local atom-centered model is sufficient for such tasks even in the case of large molecules and weakly interacting molecular assemblies.

References in corpus (33)

• CP2K: An Electronic Structure and Molecular Dynamics Software Package -- Quickstep: Efficient and Accurate Electronic Structure Calculations
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Machine-learning based interatomic potential for amorphous carbon
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• FCHL revisited: faster and more accurate quantum machine learning
• MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
• An Accurate and Transferable Machine Learning Potential for Carbon
• The first-principles phase diagram of monolayer nanoconfined water
• Equivariant message passing for the prediction of tensorial properties and molecular spectra
• Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations
• Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules
• Fantastic Generalization Measures and Where to Find Them
• TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations
• E(n) Equivariant Graph Neural Networks
• The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
• Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
• Transfer learning for chemically accurate interatomic neural network potentials
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Tensor-reduced atomic density representations
• Incorporating Nuclear Quantum Effects in Molecular Dynamics with a Constrained Minimized Energy Surface
• Pre-training via Denoising for Molecular Property Prediction
• TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials
• Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size
• Geometric and Physical Quantities Improve E(3) Equivariant Message Passing
• Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics Simulation
• Equivariant Graph Attention Networks for Molecular Property Prediction

Cited by in corpus (16)

• Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces
• On the design space between molecular mechanics and machine learning force fields
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Machine-Learned Atomic Cluster Expansion Potentials for Fast and Quantum-Accurate Thermal Simulations of Wurtzite AlN
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Modelling complex proton transport phenomena -- Exploring the limits of fine-tuning and transferability of foundational machine-learned force fields
• Extending the atomic decomposition and many-body representation, a chemistry-motivated monomer-centered approach for machine learning potentials
• Efficient dataset generation for machine learning perovskite alloys
• EOSnet: Embedded Overlap Structures for Graph Neural Networks in Predicting Material Properties
• Geographic-style maps with a local novelty distance help navigate the materials space
• Machine-Learned Potentials for Solvation Modeling
• Resolving the Body-Order Paradox of Machine Learning Interatomic Potentials
• Thermal conductivities of monolayer graphene oxide from machine learning molecular dynamics simulations
• Machine learning model for efficient nonthermal tuning of the charge density wave in monolayer NbSe${}_2$
• Role of Wadsley Defects and Cation Disorder to Enhance MoNb12O33 Diffusion
• High-Pressure Inelastic Neutron Spectroscopy: A true test of Machine-Learned Interatomic Potential energy landscapes