KnowEng, a Scalable Knowledge Engine for Large-Scale Genomic Data-OVERALL

描述（由申请人提供）：拟议的卓越中心的主要目标是建立一个强大的和可扩展的基因组学知识引擎，KnowEnG。KnowEnG将通过整合来自最先进的数据挖掘和机器学习研究的多种分析方法来改变生物医学研究人员分析其全基因组数据的方式，以使用有关基因之间关系的现有知识作为背景，并提供直观和专业设计的用户界面。为了实现这些目标，该项目包括以下组成部分：（1）收集和整合现有的知识库，记录基因及其功能之间的联系，成为一个单一的知识网络;（2）开发计算方法，在这种预先存在的知识的背景下分析全基因组用户数据集;（3）将这些方法实现为可以部署在公共或私有云中的可扩展软件组件;（4）以HUBZero工具包为基础，设计和实现一个基于网络的用户界面，以图形驱动和直观的方式对用户提供的数据集进行交互式分析;（5）在临床科学（乳腺癌药物基因组学）、行为科学（识别行为模式下的基因调控模块）和药物发现（基于基因组预测微生物合成新型生物活性化合物的能力）的三个大规模项目中彻底测试KnowEnG环境的功能和有用性。KnowEng环境将部署在云基础设施中，并完全可供社区使用，该中心开发的软件也将如此。拟议的中心是伊利诺伊大学（UIUC），一个公认的世界领先的计算科学和工程，和马约诊所，在世界领先的临床护理和研究机构之一，之间的合作，并将设在UIUC基因组生物学研究所，其中有国家的最先进的设施和国家认可的多学科团队为基础的基因组研究计划。

DESCRIPTION (provided by applicant): The primary goal of the proposed Center of Excellence is to build a powerful and scalable Knowledge Engine for Genomics, KnowEnG. KnowEnG will transform the way biomedical researchers analyze their genome-wide data by integrating multiple analytical methods derived from the most advanced data mining and machine learning research to use the full breadth of existing knowledge about the relationships between genes as background, and providing an intuitive and professionally designed user interface. In order to achieve these goals, the project includes the following components: (1) gathering and integrating existing knowledgebases documenting connections between genes and their functions into a single Knowledge Network; (2) developing computational methods for analyzing genome-wide user datasets in the context of this pre-existing knowledge; (3) implementing these methods into scalable software components that can be deployed in a public or private cloud; (4) designing and implementing a Web-based user interface, based on the HUBZero toolkit, that enables the interactive analysis of user-supplied datasets in a graphics-driven and intuitive fashion; (5) thoroughly testing the functionality and usefulness of the KnowEnG environment in three large scale projects in the clinical sciences (pharmacogenomics of breast cancer), behavioral sciences (identification of gene regulatory modules underlying behavioral patterns) and drug discovery (genome-based prediction of the capacity of microorganisms to synthesize novel biologically active compounds). The KnowEng environment will be deployed in a cloud infrastructure and fully available to the community, as will be the software developed by the Center. The proposed Center is a collaboration between the University of Illinois (UIUC), a recognized world leader in computational science and engineering, and the Mayo Clinic, one of the leading clinical care and research organizations in the worid, and will be based at the UIUC Institute for Genomic Biology, which has state-of-the-art facilities and a nationally recognized program of multidisciplinary team-based genomic research.