Machine learning force fields for molecular dynamics require prior potentials

Summary

Machine learning force fields for MD simulations require prior potentials to reduce the conformational space accessible during simulation and prevent poor exploration (1).

See also

• MD potentials from ML are more effective when protein-specific

1.

Majewski M, Pérez A, Thölke P, Doerr S, Charron NE, Giorgino T, et al. Machine learning coarse-grained potentials of protein thermodynamics. Nature Communications. 2023;14(1). Available from: https://doi.org/10.1038/s41467-023-41343-1