Dear CP2K users and developers, I am using PLUMED to connect a machine learning force field (MLCG) trained on an ab initio dataset. I would like to clarify the following point: In a QM/MM calculation in CP2K, if I apply this MLCG force field (via PLUMED) to the MM region, what happens to the QM region and the QM/MM interaction term? Specifically, I have a coarse-grained (CG) force field for the MM region that is applied through PLUMED. Since this ML-based force field does not include explicit charge information, I am wondering: <ul> <li> Does it have any effect on the QM region itself? </li> <li> How is the QM/MM interaction energy affected? </li> <li> Are the Hellmann–Feynman forces still governing the QM region, or does the MLCG force field influence those calculations? </li> <li> How is the interaction term treated when the MM region is described by a CG machine-learning potential? </li> </ul> I would appreciate any clarification on how CP2K handles the interaction term in this setup. Best regards, Somayeh Ahmadkhani -- You received this message because you are subscribed to the Google Groups "cp2k" group. To unsubscribe from this group and stop receiving emails from it, send an email to <a href="mailto:cp2k+unsubscribe@googlegroups.com">cp2k+unsubscribe@googlegroups.com</a>. To view this discussion visit <a href="https://groups.google.com/d/msgid/cp2k/69a5e7db-5415-4540-9185-c0da59ac60d1n%40googlegroups.com?utm_medium=email&utm_source=footer">https://groups.google.com/d/msgid/cp2k/69a5e7db-5415-4540-9185-c0da59ac60d1n%40googlegroups.com</a>.