An international team led by Einstein Professor Cecilia Clementi in the Department of Physics at Freie Universität Berlin introduces a breakthrough in protein simulation. The study, published in the July 18, 2025, issue of Nature Chemistry, presents CGSchNet, a machine-learned coarse-grained (CG) model that can accurately and efficiently simulate proteins like never before. Operating significantly faster than traditional all-atom molecular dynamics, CGSchNet enables larger proteins and complex systems to be explored – offering potential applications in drug discovery and protein engineering that could advance cancer treatment methods for example.