High Performance Biomedical Computing And Informatics

高性能生物医学计算和信息学

• 批准号: 6988044
• 负责人: calvin a johnson
• 金额: --
• 依托单位: CENTER FOR INFORMATION TECHNOLOGY
• 依托单位国家: 美国
• 资助国家: 美国
• 起止时间: 至
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/6988044
• 关键词: Internet; bioinformatics; computer program /software; computer system design /evaluation; data management; image processing; information retrieval; parallel processing; statistics /biometry

The goals of the High Performance Biomedical Computing and Informatics Program are to identify and solve those complex biomedical problems that can benefit from high performance computing and communications hardware, scientific database and Web technologies, data mining and visualization techniques, and modern software engineering principles and efficient algorithms. This effort includes the followings: (1) developing high performance computational methods and algorithms to analyze biomedical data and to simulate complex biological systems, (2) developing knowledge-based data management systems for the discovery of biomedical knowledge, including medical image repository and clinical information management systems, (3) providing high performance computing resources and software tools to NIH researchers, including special-purpose parallel computing machines, and (4) collaborating with NIH researchers and colleagues at other research centers in applying information technology to biomedical research problems. Using high performance parallel computing and knowledge-based data management systems, biomedical scientists can greatly reduce the time it takes to complete computationally intensive tasks, adopt new approaches for processing experimental data, and mine large complex datasets to find important data patterns. These may allow for the inclusion of more data in a calculation, the determination of a more accurate result, a reduction in the time needed to complete a long calculation, and the implementation of a new algorithm or more realistic model. High performance parallel computing allows biomedical scientists to analyze and study large datasets that cannot be processed within a practical amount of computer analysis time on conventional sequential or vector processing computing machines. With high bandwidth network connections and interactive user interfaces, parallel computing is readily accessible to a biomedical researcher in the laboratory or clinic at the investigator's computer workstation. Knowledge-based databases and data mining tools are powerful resources in modern biomedical research. They provide researchers ways to extract and use information from vast amounts of knowledge and data collected from wide-ranging sources such as public and commercial databases (e.g., genome sequences, chromosome, SNP, genetic diseases, EST cluster, gene mapping, gene expression, molecular biology, and literature databases). In addressing these complex data analysis and management challenges, the High Performance Computing and Informatics Office (HPCIO) of the Division of Computational Bioscience (DCB) in the Center for Information Technology (CIT) is developing high performance computing hardware and software infrastructure for a wide range of biomedical applications where computational speed, advanced data analysis, smart data mining and large-scale data management are important. These include gene expression data analysis, image processing of live-cell arrays, medical image and clinical information management, biostatistics, population genetics, and human genetic linkage analysis. The ultimate goal is to provide high performance parallel computing, scientific databases, and data analysis and visualization tools to facilitate the science that is done at the NIH. While developing the computationally demanding applications and scientific database systems, HPCIO is investigating the following challenging issues: (1) partitioning a problem into many parts that can be independently executed on different processors; (2) designing the parts so that the computing load can be distributed evenly over the available processors or dynamically balanced; (3) designing algorithms so that the number of processors is a parameter and the algorithms can be configured dynamically for the available machine; (4) developing tools and environments for producing portable parallel programs; (5) incorporating iinteractive data analysis and visualization tools into the user environment; (6) monitoring system performance; (7) proving that a parallel algorithm on a given machine meets its specifications; (8) evaluating modern parallel computer architectures for their performance characteristics on biomedical applications; and (9) developing and providing high performance database systems and data mining tools for archive and analysis of scientific data and medical images via Web-interfaces.

高性能生物医学计算和信息学项目的目标是识别和解决那些复杂的生物医学问题，这些问题可以受益于高性能计算和通信硬件、科学数据库和网络技术、数据挖掘和可视化技术以及现代软件工程原理和高效算法。这项工作包括以下内容：（1）开发高性能计算方法和算法来分析生物医学数据并模拟复杂的生物系统，（2）开发基于知识的数据管理系统以发现生物医学知识，包括医学图像存储库和临床信息管理系统，（3）为 NIH 研究人员提供高性能计算资源和软件工具，包括专用并行计算机，以及（4）与 NIH 研究人员和其他研究中心的同事合作，将信息技术应用于生物医学研究问题。使用高性能并行计算和基于知识的数据管理系统，生物医学科学家可以大大减少完成计算密集型任务所需的时间，采用新方法处理实验数据，并挖掘大型复杂数据集以找到重要的数据模式。这些可以允许在计算中包含更多数据，确定更准确的结果，减少完成长计算所需的时间，以及实施新算法或更现实的模型。高性能并行计算使生物医学科学家能够分析和研究传统顺序或矢量处理计算机上无法在实际计算机分析时间内处理的大型数据集。借助高带宽网络连接和交互式用户界面，生物医学研究人员可以在实验室或诊所的研究人员计算机工作站上轻松访问并行计算。基于知识的数据库和数据挖掘工具是现代生物医学研究的强大资源。它们为研究人员提供了从公共和商业数据库等广泛来源收集的大量知识和数据中提取和使用信息的方法（例如基因组序列、染色体、SNP、遗传疾病、EST 簇、基因图谱、基因表达、分子生物学和文献数据库）。为了应对这些复杂的数据分析和管理挑战，信息技术中心 (CIT) 计算生物科学部 (DCB) 的高性能计算和信息学办公室 (HPCIO) 正在为广泛的应用开发高性能计算硬件和软件基础设施。计算速度、高级数据分析、智能数据挖掘和大规模数据管理非常重要的一系列生物医学应用。其中包括基因表达数据分析、活细胞阵列图像处理、医学图像和临床信息管理、生物统计学、群体遗传学和人类遗传连锁分析。最终目标是提供高性能并行计算、科学数据库以及数据分析和可视化工具，以促进 NIH 的科学研究。在开发计算要求较高的应用程序和科学数据库系统时，HPCIO正在研究以下具有挑战性的问题：（1）将问题划分为可以在不同处理器上独立执行的许多部分； (2) 设计各个部分，以便计算负载可以均匀地分布在可用处理器上或动态平衡； (3)设计算法，使处理器的数量成为一个参数，并且可以针对可用机器动态配置算法； (4) 开发用于生成可移植并行程序的工具和环境； (5) 将交互式数据分析和可视化工具纳入用户环境； (6) 监控系统性能； (7) 证明给定机器上的并行算法满足其规范； (8) 评估现代并行计算机体系结构在生物医学应用中的性能特征； (9) 开发并提供高性能数据库系统和数据挖掘工具，用于通过网络界面归档和分析科学数据和医学图像。