The RPI Exploratory Center for Cheminformatics(RMI)

化学信息学研究探索性中心(ECCR)P20的目的 规划赠款旨在开发一种机制，以便在化学信息学相关领域不断发展的专家核心之间建立和激励合作试点项目，范围从编码和捕获分子信息的方法到机器学习和数据挖掘技术，再到预测模型的开发、验证、解释和利用。除了这些研究工作外，该中心还将汇集一批领域专家和应用科学家，他们将成为赠款过程中开发的分子性质模型和建模方法所提供的知识的数据生成者和最终用户。该小组还将测试新的化学信息学软件，该软件将构成这项工作的有形可交付产品。十大应用项目模块 作为本提案的一部分，介绍了中心内不同群体和专业领域之间可能进行的互动。拟议中心背后的统一愿景是，在这里所代表的每个子学科中所做的许多工作都可以在化学信息学的背景下表达：许多不同的项目领域可以被分成一个或多个重叠的类别：“数据生成器”(那些使用理论或实验方法来创建或提取知识的人)，“机器学习和数据挖掘”组(他们执行模型验证、特征选择、模式识别、平均作用力的生成和基于知识的势能工作)，以及“性质-预测”组(他们执行化学感知的模型建立、分子性质描述符生成、 定量结构-财产关系建模、验证和解释)和“应用”小组，他们利用作为中心一部分开发的新工具和方法提供的信息。我们坚信，这些领域的专业知识可以在这项规划拨款提案中结合起来，产生比各部分之和更大的东西。探索中心将为新的跨学科项目提供种子，并培训这些领域的研究生。 相关性：化学信息的产生、挖掘和分析方面的进展对开发新的药物疗法以及生物信息学和分子医学的现代方法至关重要。

The purpose of this Exploratory Center for Cheminformatics Research (ECCR) P20 planning grant is to develop a mechanism for bringing together and stimulating collaborative pilot projects among a constantly-evolving nucleus of experts in Cheminformatics-related fields ranging from methods of encoding and capturing molecular information, to machine learning and data mining techniques, to predictive model development, validation, interpretation and utilization. In addition to these research efforts, the Center will bring together a set of domain specialists and application scientists who will serve as both data generators and end users of the knowledge provided by the molecular property models and modeling methods developed during the course of the grant. This group will also test the new Cheminformatics software that will constitute a tangible, deliverable product from this work. Ten application project modules that exemplify possible interactions between various groups and areas of expertise within the Center are presented as part of this proposal. The unifying vision behind the proposed Center is that much of what is done in each of the subdisciplines represented here can be expressed in a Cheminformatics context: The many diverse project areas can be grouped into one or more overlapping categories: "Data Generators" (those who use either theoretical or experimental methods for creating or extracting knowledge), "Machine Learning and Datamining" groups (who perform model validation, feature selection, pattern recognition, generation of potentials of mean force and knowledge-based potential work), as well as "Property-Prediction" groups (who perform chemically-aware model building, molecular property descriptor generation, Quantitative Structure-Property Relationship modeling, validation, and interpretation), and "Application" groups who utilize the information made available using the new tools and methods that are developed as part of the Center. It is our strong belief that these areas of expertise can be brought together within this Planning Grant proposal to generate something larger than the sum of the parts. The Exploratory Center will seed new interdisciplinary projects and train graduate students in these areas. Relevance: Advances in the generation, mining and analysis of chemical information is crucial to the development of new drug therapies, and to modern methods of bioinformatics and molecular medicine.