MACE-OFF23: Transferable Machine Learning Force Fields for Organic Molecules

Classical empirical force fields have dominated biomolecular simulation for over 50 years. Although widely used in drug discovery, crystal structure prediction, and biomolecular dynamics, they generally lack the accuracy and transferability required for predictive modelling. In this paper, we introduce MACE-OFF23, a transferable force field for organic molecules created using state-of-the-art machine learning technology and first-principles reference data computed with a high level of quantum mechanical theory. MACE-OFF23 demonstrates the remarkable capabilities of local, short-range models by accurately predicting a wide variety of gas and condensed phase properties of molecular systems. It produces accurate, easy-to-converge dihedral torsion scans of unseen molecules, as well as reliable descriptions of molecular crystals and liquids, including quantum nuclear effects. We further demonstrate the capabilities of MACE-OFF23 by determining free energy surfaces in explicit solvent, as well as the folding dynamics of peptides. Finally, we simulate a fully solvated small protein, observing accurate secondary structure and vibrational spectrum. These developments enable first-principles simulations of molecular systems for the broader chemistry community at high accuracy and low computational cost.