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

TL;DR

FENNIX is a hybrid machine learning and force-field approach that predicts local and long-range molecular properties, enabling accurate energy calculations and molecular dynamics simulations for small molecules and liquids.

Contribution

It introduces a novel hybrid model combining equivariant neural networks with physically-motivated energy terms for improved molecular property prediction.

Findings

Accurate gas-phase energy predictions for small molecules.

Transferability to condensed phase and stable MD simulations of water.

Successful computation of free energy landscapes and reactive dissociation processes.

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.