Developing a Machine-Learning Interatomic Potential for Non-Covalent Interactions in Proteins

TL;DR

This paper introduces PANIP, a machine learning interatomic potential trained on protein non-covalent interactions, achieving quantum accuracy and outperforming existing models in predicting diverse molecular interactions.

Contribution

The paper presents PANIP, a novel ensemble MLIP trained with active learning on protein fragment interactions, offering high accuracy and transferability for modeling non-covalent interactions in proteins.

Findings

PANIP achieves <0.2 kcal/mol MAE on out-of-distribution systems.

PANIP outperforms ANI-2x, especially for charged dimers.

Enables QM-level protein-ligand binding energy estimation at near force-field costs.

Abstract

Machine learning interatomic potentials (MLIPs) enable efficient modeling of molecular interactions with quantum mechanical (QM) accuracy. However, constructing robust and representative training datasets that capture subtle, system-specific interaction motifs remains challenging. We introduce PANIP (PAirwise Non-covalent Interaction Potential), an ensemble MLIP model built upon the NequIP framework and trained on non-covalent interactions (NCIs) between protein-derived fragments. PANIP is trained using an automated multi-fidelity active learning (MFAL) workflow, in which a representative training subset, termed PDB-FRAGID (PDB Fragment Interaction Dataset), was distilled from an otherwise prohibitively large pool of fragment dimers extracted from the Protein Data Bank (PDB). PANIP retains $\omega$B97X-D3BJ/def2-TZVPP-level accuracy and achieves mean absolute errors below 0.2 kcal/mol on out-of-distribution systems, demonstrating excellent transferability across diverse NCI motifs. Compared to the widely used ANI-2x potential, PANIP delivers substantially lower errors, particularly for charged and strongly interacting dimers. Coupled with a fragmentation-based energy decomposition scheme, PANIP estimates protein-ligand binding energies at near force-field computational cost yet QM-level accuracy, enabling its use as a fragment-based scoring function that rivals specialized docking scoring functions.