TY - JOUR A1 - Majewski, Maciej A1 - Pérez, Adrià A1 - Thölke, Philipp A1 - Doerr, Stefan A1 - Charron, Nicholas A1 - Giorgino, Toni A1 - Husic, Brooke A1 - Clementi, Cecilia A1 - Noé, Frank A1 - De Fabritiis, Gianni T1 - Machine learning coarse-grained potentials of protein thermodynamics T2 - Nature Communications N2 - A generalized understanding of protein dynamics is an unsolved scientific problem, the solution of which is critical to the interpretation of the structure-function relationships that govern essential biological processes. Here, we approach this problem by constructing coarse-grained molecular potentials based on artificial neural networks and grounded in statistical mechanics. For training, we build a unique dataset of unbiased all-atom molecular dynamics simulations of approximately 9 ms for twelve different proteins with multiple secondary structure arrangements. The coarse-grained models are capable of accelerating the dynamics by more than three orders of magnitude while preserving the thermodynamics of the systems. Coarse-grained simulations identify relevant structural states in the ensemble with comparable energetics to the all-atom systems. Furthermore, we show that a single coarse-grained potential can integrate all twelve proteins and can capture experimental structural features of mutated proteins. These results indicate that machine learning coarse-grained potentials could provide a feasible approach to simulate and understand protein dynamics. Y1 - 2023 UR - https://opus4.kobv.de/opus4-zib/frontdoor/index/index/docId/9348 VL - 14 ER -