Abstract

Molecular dynamics has shown success in obtaining biological insights by providing mechanistic interpretations of experimental data. However, the force fields used to describe how the atoms interact are biased towards keeping folded proteins folded and fail when applied to disordered proteins or protein aggregation. The idea of using the technique of automatic differentiation, most commonly used to train neural networks, to improve force fields is called differentiable molecular simulation (DMS). It overcomes the limitations of other methods by allowing multiple parameters to be tuned at once. Prior work has shown that a coarse-grained force field can be trained from scratch using this approach. Work to correct known deficiencies in all-atom implicit solvent force fields using DMS will be described, along with technical challenges when training such methods.