Benchmarking a dual-scale hybrid simulation framework for small globular proteins combining the CHARMM36 and Martini2 models

Abstract

Multi-scale models in which varying resolutions are considered in a single molecular dynamics simulation setup are gaining importance in integrative modeling. However, combining atomistic and coarse-grain resolutions, especially for coarse-grain force fields derived from top-down approaches, have not been well explored. In this study, we have implemented and tested a dual-resolution simulation approach to model globular proteins in atomistic detail (represented by the CHARMM36 model) with the surrounding solvent in Martini2 coarse-grain detail. The hybrid scheme considered is an extension of a model implemented earlier for mainly lipid and water molecules. We have considered a set of small globular proteins and have extensively compared to atomistic benchmark simulations as well as a host of experimental observables. We show that the protein structural dynamics sampled in the hybrid scheme is robust, and the intra-protein contact maps are reproduced, despite increased fluctuations of the loop regions. A good match is observed with experimental small angle X-ray scattering (SAXS) and NMR observables, such as chemical shifts and ${}^3{J}_{(H_N-H_{\alpha })}$-coupling, with the best match obtained for the chemical shifts. However, deviations are observed in the water dynamics and protein–water interactions which we attribute to the limitation of solvent screening in the coarse-grain force field. The computational speed-up achieved is about 2–3 times compared to an all-atom system. Overall, the hybrid model is able to retain the main features of the underlying atomistic conformational landscape with a two-fold speed-up in computational cost.