BIGDATA: IA: Collaborative Research: In Situ Data Analytics for Next Generation Molecular Dynamics Workflows

BIGDATA：IA：协作研究：下一代分子动力学工作流程的原位数据分析

• 批准号: 1841758
• 负责人: Michela Taufer
• 金额: $ 98万
• 依托单位: University of Tennessee Knoxville
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-06-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1841758&HistoricalAwards=false
• 关键词: BIGDATA; IA; Collaborative; Research; Situ; BIGDATA; IA; Collaborative; Research; Situ

Molecular dynamics simulations studying the classical time evolution of a molecular system at atomic resolution are widely recognized in the fields of chemistry, material sciences, molecular biology and drug design; these simulations are one of the most common simulations on supercomputers. Next-generation supercomputers will have dramatically higher performance than do current systems, generating more data that needs to be analyzed (i.e., in terms of number and length of molecular dynamics trajectories). The coordination of data generation and analysis cannot rely on manual, centralized approaches as it does now. This interdisciplinary project integrates research from various areas across programs such as computer science, structural molecular biosciences, and high performance computing to transform the centralized nature of the molecular dynamics analysis into a distributed approach that is predominantly performed in situ. Specifically, this effort combines machine learning and data analytics approaches, workflow management methods, and high performance computing techniques to analyze molecular dynamics data as it is generated, save to disk only what is really needed for future analysis, and annotate molecular dynamics trajectories to drive the next steps in increasingly complex simulations' workflows. The investigators tackle the data challenge of data analysis of molecular dynamics simulations on the next-generation supercomputers by (1) creating new in situ methods to trace molecular events such as conformational changes, phase transitions, or binding events in molecular dynamics simulations at runtime by locally reducing knowledge on high-dimensional molecular organization into a set of relevant structural molecular properties; (2) designing new data representations and extend unsupervised machine learning techniques to accurately and efficiently build an explicit global organization of structural and temporal molecular properties; (3) integrating simulation and analytics into complex workflows for runtime detection of changes in structural and temporal molecular properties; and (4) developing new curriculum material, online courses, and online training material targeting data analytics. The project's harnessed knowledge of molecular structures' transformations at runtime can be used to steer simulations to more promising areas of the simulation space, identify the data that should be written to congested parallel file systems, and index generated data for retrieval and post-simulation analysis. Supported by this knowledge, molecular dynamics workflows such as replica exchange simulations, Markov state models, and the string method with swarms of trajectories can be executed ?from the outside? (i.e., without reengineering the molecular dynamics code).

在化学，材料科学，分子生物学和药物设计的领域中，在原子分辨率下研究分子系统经典时间演变的分子动力学模拟。这些模拟是超级计算机上最常见的模拟之一。 下一代超级计算机的性能将比当前系统高，生成需要分析的更多数据（即，就分子动力学轨迹的数量和长度而言）。数据生成和分析的协调不能像现在这样依赖手动的集中式方法。 这个跨学科项目将来自计算机科学，结构分子生物科学和高性能计算等方案的各个领域的研究融为一体，以将分子动力学分析的集中性转变为一种分布式方法，该方法主要在原位进行。具体而言，这项工作结合了机器学习和数据分析方法，工作流程管理方法和高性能计算技术，以分析分子动力学数据，除非仅磁盘仅磁盘以后进行分析所需的内容，并注释分子动力学轨迹，以使越来越复杂的复杂模拟工作的下一步驱动下一步。研究人员通过（1）通过（1）创建新的原位方法来解决分子动力学模拟数据分析的数据挑战，以追踪分子事件，例如构象变化，相变，相位过渡或分子动力学模拟在运行时的分子动力学模拟中的分子动力学模拟，通过在局部降低相关分子的知识中的知识中，将相关的结构性属性降低到相关的结构属性中， （2）设计新的数据表示并扩展了无监督的机器学习技术，以准确有效地建立一个明确的结构和时间分子特性的全球组织； （3）将模拟和分析集成到复杂的工作流程中，以检测结构和时间分子特性变化的运行时； （4）开发新的课程材料，在线课程和在线培训材料针对数据分析。该项目对分子结构在运行时的转换的知识可用于引导模拟到模拟空间的更有前途的领域，确定应写入拥挤的并行文件系统的数据，以及索引生成的数据以检索和仿真分析。在这些知识的支持下，可以从外部执行分子动力学工作流，例如复制交换模拟，马尔可夫州模型和带有轨迹群的弦方法？ （即，不重新设计分子动力法典）。