Chembench: the Integrated Web Portal to Accelerate Cheminformatics and Chemical G

描述（由申请人提供）：ChemBench：加速化学信息学和化学基因组学研究的综合门户网站。由于现代化学和生物学研究中高通量技术的日益普及，产生大量数据的实验科学家不再配备足够的工具和方法来管理，更不用说分析自己的数据了。现代化学和生物学研究需要复杂的公共领域工具来对大型实验数据集进行计算和统计分析，以创建可以帮助和优先考虑进一步实验的数据模型。化学信息学在过去的十年中已经成为一门新兴的研究学科，将计算，统计和信息方法与化学和生物学中的一些关键概念相结合。现代化学信息学被广泛定义为一门以化学为中心的科学学科，包括化学知识的创建、检索、管理、可视化、建模、发现和传播。化学信息学研究的进一步进展受到缺乏公共可用的计算工具和软件来分析化学基因组学数据的阻碍。该项目致力于通过一个名为Chembench的高级化学信息学门户网站来填补这一空白。目前的系统是在过去四年中在我们小组中建立的，最初得到了NIH路线图规划拨款的有限支持。该项目将通过为化学信息学家提供免费的模型构建工具和为生物学家和药物化学家提供免费的化合物活性预测工具，推动Chembench成为一个易于扩展和维护的系统，以满足计算和实验化学基因组学科学家的需求。计算工作流程，以纳入这些关键程序，并提供其透明的使用必须基于严格的软件设计方法和程序，构成本项目的具体目标1的重点。基于这一严格的计算基础设施，工作流程的功能关键要素包括以下模块：（i）化学数据准备，包括管理、描述符计算和化学空间可视化（目标2）;（ii）QSAR模型开发和统计验证（目标3）;（iii）预测外部化合物库中的计算命中（目标4）;及（iv）计算命中的分析及探索（目标5）。该门户网站是一个模块集合体，可作为自动化综合工作流程的一部分使用，也可根据用户的研究兴趣和具体专门知识单独使用。与生物信息学在改变现代生物医学研究中所起的作用类似，化学信息学有望彻底改变化学和化学生物学的所有研究领域。Chembench为实验和计算探针/药物发现研究人员提供知识发现工具和基础设施，使他们能够探索和利用化学基因组学数据库，建立严格的数据模型，并减少识别新的生物活性化合物所需的实验工作。Chembench门户网站将有助于将大规模的化学基因组学研究转化为新药的发现，以改善公众健康。 公共卫生相关性：该项目旨在开发一个公开可用的化学信息学ChemBench门户网站，为实验和计算探针/药物发现研究人员提供知识发现工具和基础设施，以探索和利用化学基因组学数据库，构建严格的数据模型，并减少所需的实验工作量。识别新型生物活性化合物（例如化学探针和候选药物）。

DESCRIPTION (provided by applicant): ChemBench: the Integrated Web Portal to Accelerate Cheminformatics and Chemical Genomics Research. Project Summary/Abstract As a result of growing proliferation of high-throughput technologies in modern chemical and biological research, the experimental scientists generating large volumes of data are no longer equipped with adequate tools and approaches to manage, let alone analyze, their own data. Modern chemical and biological research requires sophisticated public-domain tools for computational and statistical analysis of large experimental datasets to create data models that can aid and prioritize further experiments. Cheminformatics has emerged in the last decade as a burgeoning research discipline combining computational, statistical, and informational methodologies with some of the key concepts in chemistry and biology. Modern cheminformatics is defined broadly as a chemocentric scientific discipline encompassing the creation, retrieval, management, visualization, modeling, discovery, and dissemination of chemical knowledge. Further progress of cheminformatics research is hampered by the lack of publicly available computational tools and software to analyze chemical genomics data. This project endeavors to fill this gap through an advanced cheminformatics web portal called Chembench. The current system has been built in our group in the last four years with limited initial support from the NIH RoadMap planning grant. This project will advance Chembench to become an easily extensible and maintainable system addressing the needs of both computational and experimental chemical genomics scientists by providing a freely available model building tool for cheminformaticians and freely available compound activity predicting tools for biologists and medicinal chemists. The computational workflow to incorporate these key procedures and afford their transparent use must be based on rigorous software design approaches and procedures that constitute the focus of Specific Aim 1 of this project. Building upon this rigorous computational infrastructure, the functional key elements of the workflow include modules for (i) chemical data preparation including curation, descriptor calculation, and chemical space visualization (Aim 2); (ii) QSAR model development and statistical validation (Aim 3); (iii) prediction of computational hits in external compound libraries (Aim 4); and (iv) analysis and exploration of computational hits (Aim 5). The portal is designed as an aggregate of modules that can be used as part of an automated integrated workflow or individually, depending on the research interests and specific expertise of users. Similar to the role that bioinformatics has played in transforming modern biomedical research; cheminformatics is poised to revolutionize all areas of research in chemistry and chemical biology. Chembench provides the experimental and computational probe/drug discovery researchers with knowledge discovery tools and infrastructure that enables them to explore and exploit chemical genomics databases, build rigorous data models, and reduce the experimental effort required to identify novel biologically active compounds. The publicly available Chembench portal will help translate large scale chemical genomics research into the discovery of new medicines to improve public health. PUBLIC HEALTH RELEVANCE: This project intends to develop a publicly available cheminformatics ChemBench portal to provide the experimental and computational probe/drug discovery researchers with knowledge discovery tools and infrastructure to explore and exploit chemical genomics databases, build rigorous data models, and reduce the amount of experimental effort required to identify novel biologically active compounds such as chemical probes and drug candidates.