当前位置: X-MOL 学术Ann. Phys. (Berlin) › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Learning Unravels a Dynamic Hierarchy While Empowering Molecular Dynamics Simulations
Annalen Der Physik ( IF 2.2 ) Pub Date : 2020-02-13 , DOI: 10.1002/andp.201900526
Ariel Fernández 1, 2, 3
Affiliation  

Molecular dynamics (MD) provide predictive understanding of the behavior of condensed matter. However, its true potential remains largely untested because relevant timescales are often inaccessible, limited portions of conformation space get sampled, and infrequent events are usually irreproducible. A culprit is the huge informational burden required to iterate integration steps. To address the problem, deep learning is applied to encode the dynamics into a shorthand embodiment retaining only essential topological features of the vector field that steers MD integration. The flow is simplified via an equivalence relation that identifies conformations within basins of attraction in potential energy and encodes the dynamics onto a modulo‐basin “quotient space” where fast motions are averaged out. The quotient space projection enables coverage of realistic timescales while unraveling the underlying dynamic hierarchy. Deep learning is exploited to propagate the simplified trajectory beyond MD‐accessible timescales and to reconstruct it at atomistic level. As shown, the quotient‐encoding‐propagating‐decoding scheme generates within a few hours protein folding pathways with experimentally verified outcomes. By contrast, MD computations covering comparable timespans would take over a hundred days on special‐purpose supercomputers. Thus, quotient space constitutes a model for hierarchical understanding of MD simulation while enabling access to realistic timescales.

中文翻译:

深度学习在赋予分子动力学模拟能力的同时揭示了动态层次结构

分子动力学(MD)提供了对冷凝物行为的预测性理解。然而,由于相关时间尺度通常是不可访问的,只有有限的构象空间部分被采样,并且偶发事件通常是不可再现的,因此它的真正潜力在很大程度上尚未得到检验。罪魁祸首是迭代集成步骤所需的巨大信息负担。为了解决该问题,应用深度学习将动力学编码为简化的实施例,该实施例仅保留引导MD集成的矢量场的基本拓扑特征。通过等价关系简化了流动,该等价关系标识了势能吸引盆地内的构象,并将动力学编码到模态盆地“商空间”中,在该商空间中快速运动被平均化。商空间投影可以覆盖实际的时标,同时可以揭示基本的动态层次结构。深度学习被用来在MD可访问的时间范围之外传播简化的轨迹,并在原子级上对其进行重构。如图所示,商编码-传播-解码方案可在数小时内生成蛋白质折叠途径,并经过实验验证。相比之下,在特殊用途的超级计算机上,涵盖可比较时间跨度的MD计算将花费一百多天。因此,商空间构成了用于对MD仿真进行分层理解的模型,同时能够访问实际的时标。深度学习被用来在MD可访问的时间范围之外传播简化的轨迹,并在原子级上对其进行重构。如图所示,商编码-传播-解码方案可在数小时内生成蛋白质折叠途径,并经过实验验证。相比之下,在特殊用途的超级计算机上,涵盖可比较时间跨度的MD计算将花费一百多天。因此,商空间构成了用于对MD仿真进行分层理解的模型,同时能够访问实际的时标。深度学习被用来在MD可访问的时间范围之外传播简化的轨迹,并在原子级上对其进行重构。如图所示,商编码-传播-解码方案可在数小时内生成蛋白质折叠途径,并经过实验验证。相比之下,在特殊用途的超级计算机上,涵盖可比较时间跨度的MD计算将花费一百多天。因此,商空间构成了一个模型,用于对MD仿真进行分层理解,同时能够访问实际的时标。
更新日期:2020-02-13
down
wechat
bug