Machine learning for collective variable discovery and enhanced sampling in biomolecular simulation
Machine learning for collective variable discovery and enhanced sampling in biomolecular simulation
复制标题
DOI：
10.1080/00268976.2020.1737742
复制
发表时间：
2020-03
影响因子：
1.7
通讯作者：
Hythem Sidky;Wei Chen;Andrew L. Ferguson
中科院分区：
文献类型：
--
作者：
Hythem Sidky;Wei Chen;Andrew L. Ferguson
经典分子动力学通过组成原子的位置和速度所跨越的相空间来模拟分子系统的时间演化。从生成的轨迹中提取的分子水平的热力学、动力学和结构数据为生物和分子材料的理解、工程和设计提供了有价值的信息。模拟多体原子系统的成本使得模拟大分子的成本过高，并且所得到的轨迹的高维性对分析提出了挑战。在算法、硬件和数据可用性进步的推动下，近年来人们对机器学习（尤其是深度学习）在分子模拟中的应用产生了浓厚的兴趣。这些技术在提取控制分子系统动力学的重要非线性集体变量的机制理解以及提供良好的低维系统表示（用于执行增强采样或开发长时间尺度动力学模型）方面显示了强大的功能和灵活性。本文的目的是介绍关键的机器学习方法，描述它们如何与统计力学理论结合成特定领域的工具，以及这些方法在理解和加速生物分子模拟中的详细应用。图形抽象
Classical molecular dynamics simulates the time evolution of molecular systems through the phase space spanned by the positions and velocities of the constituent atoms. Molecular-level thermodynamic, kinetic, and structural data extracted from the resulting trajectories provide valuable information for the understanding, engineering, and design of biological and molecular materials. The cost of simulating many-body atomic systems makes simulations of large molecules prohibitively expensive, and the high-dimensionality of the resulting trajectories presents a challenge for analysis. Driven by advances in algorithms, hardware, and data availability, there has been a flare of interest in recent years in the applications of machine learning – especially deep learning – to molecular simulation. These techniques have demonstrated great power and flexibility in both extracting mechanistic understanding of the important nonlinear collective variables governing the dynamics of a molecular system, and in furnishing good low-dimensional system representations with which to perform enhanced sampling or develop long-timescale dynamical models. It is the purpose of this article to introduce the key machine learning approaches, describe how they are married with statistical mechanical theory into domain-specific tools, and detail applications of these approaches in understanding and accelerating biomolecular simulation. GRAPHICAL ABSTRACT