This work presents a systematic methodology for describing the transient dynamics of coarse-grained molecular systems inferred from all-atom simulated data. We suggest Langevin-type dynamics where the coarse-grained interaction potential depends explicitly on time to efficiently approximate the transient coarse-grained dynamics. We apply the path-space force matching approach at the transient dynamics regime to learn the proposed model parameters. In particular, we parameterize the coarse-grained potential both with respect to the pair distance of the CG particles and the time, and we obtain an evolution model that is explicitly time-dependent. Moreover, we follow a data-driven approach to estimate the friction kernel, given by appropriate correlation functions directly from the underlying all-atom molecular dynamics simulations. To explore and validate the proposed methodology we study a benchmark system of a moving particle in a box. We examine the suggested model's effectiveness in terms of the system's correlation time and find that the model can approximate well the transient time regime of the system, depending on the correlation time of the system. As a result, in the less correlated case, it can represent the dynamics for a longer time interval. We present an extensive study of our approach to a realistic high-dimensional water molecular system. Posing the water system initially out of thermal equilibrium we collect trajectories of all-atom data for the, empirically estimated, transient time regime. Then, we infer the suggested model and strengthen the model's validity by comparing it with simplified Markovian models.

翻译：本文提出了一种系统方法，用于描述从全原子模拟数据推断出的粗粒化分子系统的瞬态动力学。我们建议采用朗之万型动力学，其中粗粒化相互作用势显式依赖于时间，以高效近似粗粒化瞬态动力学。我们将路径空间力匹配方法应用于瞬态动力学区间，以学习所提模型参数。特别地，我们同时根据粗粒化粒子的对间距和时间来参数化粗粒化势，从而得到一个显式依赖于时间的演化模型。此外，我们采用数据驱动方法，通过直接从底层全原子分子动力学模拟中获取的相关函数来估计摩擦核。为探索和验证所提方法，我们研究了一个箱子中运动粒子的基准系统。我们以系统的关联时间为指标检验所提模型的有效性，发现模型能够根据系统的关联时间很好地近似瞬态时间区间。因此，在弱关联情况下，模型可在更长的时间间隔内表征动力学行为。我们针对真实的高维水分子系统开展了广泛研究。将水系统初始置于热力学非平衡态后，我们收集了经验估计瞬态时间区间内的全原子轨迹数据。随后，我们推断出所提模型，并通过与简化马尔可夫模型进行比较，增强了模型的有效性。