Repeatability of Relative Free Energy Calculations in Solution with ANI-2x and MACE-OFF23

TL;DR

The study examines how well neural network potentials can predict tautomeric states in water, finding that one model is reliable while another shows inconsistent results due to poor sampling.

Contribution

A novel energy mixing approach for alchemical free energy calculations using NNPs, revealing performance differences between ANI-2x and MACE-OFF23.

Findings

MACE-OFF23 produced converged free energy results, while ANI-2x showed significant variability.

ANI-2x's issues stem from slow water dynamics and overstabilization of metastable states.

The energy mixing method is generalizable to other alchemical transformations.

Abstract

We investigate the
feasibility and challenges of using neural network
potentials (NNPs) for alchemical free energy calculations, employing
a single-coordinate dual-topology approach. As a model application,
we compute free energy differences between tautomer pairs to predict
the preferred tautomeric state in aqueous solution. A central aspect
of our approach is based on energy mixing via the selective masking
of interactions involving dummy atoms, enabling a smooth interpolation
between tautomeric states. This methodology is independent of the
specific NNP architecture and holds potential for broader application
to larger alchemical transformations. We tested this framework using
two well-known NNPs: ANI-2x and MACE-OFF23­(small). While MACE-OFF23­(small)
produced converged free energy results, simulations with ANI-2x showed
significant variability across repeated runs. Our analysis traced
this inconsistency to slow water dynamics and the overstabilization
of artificial metastable states of the solute under ANI-2x, causing
difficulties in converging sampling. Although transferable NNPs offer
the advantage of general applicability without system-specific parametrization,
our findings emphasize the importance of evaluating their performance
in the condensed phase before employing them for free energy simulations.

Figures