GRAPPA - Our Machine learned Molecular Mechanics Force Field - Now Published!

With GRAPPA, we present our machine-learned Molecular Dynamics Force Field, which is capable of predicting force-field parameters for a wide range of molecules. By combining graph-based neural networks with a transformer architecture, we achieve impressive accuracy and performance—seamlessly integrated into established MD engines such as GROMACS and OpenMM.

GRAPPA was developed by our PhD students Leif Seute and Eric Hartmann and was published in Chemical Science on January 15. If you’d like to learn more or try out GRAPPA, you can find the software on our GitHub.