Navigating protein landscapes with a machine-learned transferable coarse-grained model

TL;DR

This paper introduces a deep learning-based coarse-grained protein model that is transferable, computationally efficient, and capable of accurately predicting various protein structures and dynamics, outperforming traditional all-atom simulations in speed.

Contribution

The authors develop a universal, chemically transferable coarse-grained force field using deep learning, enabling extrapolative molecular dynamics for diverse protein sequences.

Findings

Successfully predicts folded and intermediate structures

Captures fluctuations of intrinsically disordered proteins

Operates several orders of magnitude faster than all-atom models

Abstract

The most popular and universally predictive protein simulation models employ all-atom molecular dynamics (MD), but they come at extreme computational cost. The development of a universal, computationally efficient coarse-grained (CG) model with similar prediction performance has been a long-standing challenge. By combining recent deep learning methods with a large and diverse training set of all-atom protein simulations, we here develop a bottom-up CG force field with chemical transferability, which can be used for extrapolative molecular dynamics on new sequences not used during model parametrization. We demonstrate that the model successfully predicts folded structures, intermediates, metastable folded and unfolded basins, and the fluctuations of intrinsically disordered proteins while it is several orders of magnitude faster than an all-atom model. This showcases the feasibility of a universal and computationally efficient machine-learned CG model for proteins.