Machine Learning Interatomic Potentials: library for efficient training, model development and simulation of molecular systems

TL;DR

This paper introduces a user-friendly MLIP library that enables efficient training and simulation of molecular systems, bridging the gap between machine learning models and industrial molecular dynamics applications.

Contribution

The paper presents a versatile MLIP library with multiple models and MD wrappers, designed for both industry and ML developers, enhancing accessibility and efficiency.

Findings

Includes three model architectures: MACE, NequIP, ViSNet

Supports integration with molecular dynamics tools ASE and JAX-MD

Provides pre-trained models for organic molecules

Abstract

Machine Learning Interatomic Potentials (MLIP) are a novel in silico approach for molecular property prediction, creating an alternative to disrupt the accuracy/speed trade-off of empirical force fields and density functional theory (DFT). In this white paper, we present our MLIP library which was created with two core aims: (1) provide to industry experts without machine learning background a user-friendly and computationally efficient set of tools to experiment with MLIP models, (2) provide machine learning developers a framework to develop novel approaches fully integrated with molecular dynamics tools. The library includes in this release three model architectures (MACE, NequIP, and ViSNet), and two molecular dynamics (MD) wrappers (ASE, and JAX-MD), along with a set of pre-trained organics models. The seamless integration with JAX-MD, in particular, facilitates highly efficient MD simulations, bringing MLIP models significantly closer to industrial application. The library is available on GitHub and on PyPI under the Apache license 2.0.