arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.08810physics.comp-phcs.CEcs.LG
收藏

通过学习有效动力学加速分子系统的模拟

Accelerated Simulations of Molecular Systems through Learning of their Effective Dynamics

ETH Zurich(苏黎世联邦理工学院);Technical University of Munich(慕尼黑工业大学);National Institute of Chemistry(国家化学研究所);University of Ljubljana(卢布尔雅那大学);Harvard University(哈佛大学)

Pantelis R. Vlachas, Julija Zavadlav, Matej Praprotnik, Petros Koumoutsakos

摘要:

模拟对于理解和预测复杂分子系统的演化至关重要。然而,尽管算法和专用硬件取得了进展,但获取捕获生物分子结构进化所需的时间尺度仍然是一项艰巨的任务。在这项工作中,我们提出了一种新的框架,通过学习分子系统的有效动力学(LED),将模拟时间尺度提高了三个数量级。LED通过使用混合密度网络(MDN)自编码器在粗尺度和细尺度之间采用概率映射来增强无方程方法,并使用长短期记忆MDN来演化非马尔可夫潜在动态。我们证明了LED在Müeller-Brown电位、Trp笼蛋白和丙氨酸二肽中的有效性。LED识别可解释的降阶表示,并可以在任何时刻生成相应的全原子分子轨迹。我们相信,所提出的框架提供了一个显着增加模拟能力,并打开了新的视野,为复杂的分子系统的有效建模。

英文摘要:

Simulations are vital for understanding and predicting the evolution of complex molecular systems. However, despite advances in algorithms and special purpose hardware, accessing the timescales necessary to capture the structural evolution of bio-molecules remains a daunting task. In this work we present a novel framework to advance simulation timescales by up to three orders of magnitude, by learning the effective dynamics (LED) of molecular systems. LED augments the equation-free methodology by employing a probabilistic mapping between coarse and fine scales using mixture density network (MDN) autoencoders and evolves the non-Markovian latent dynamics using long short-term memory MDNs. We demonstrate the effectiveness of LED in the Müeller-Brown potential, the Trp Cage protein, and the alanine dipeptide. LED identifies explainable reduced-order representations and can generate, at any instant, the respective all-atom molecular trajectories. We believe that the proposed framework provides a dramatic increase to simulation capabilities and opens new horizons for the effective modeling of complex molecular systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑