Molecular dynamics with multiple time scales: How to avoid pitfalls

Multiple time scale methodologies have gained widespread use in molecular dynamics simulations and are implemented in a variety of ways across numerous packages. However, performance of the algorithms depends upon the details of the implementation. This is particularly important in the way in which the nonbonded interactions are partitioned. In this work, we show why some previous implementations give rise to energy drifts, and how this can be corrected. We also provide a recipe for using multiple time step methods to generate stable trajectories in large scale biomolecular simulations, where long trajectories are needed. © 2010 American Chemical Society.