Probabilistic Modeling of Information from Images/Text

描述(由申请人提供)：这个项目的目标是建立一个软件工具包，使生物学家能够从在线文章集合中创建一个蛋白质亚细胞定位信息数据库，该数据库可以被查询、浏览或用于支持数据挖掘活动。我们开发了一个名为SLIF的系统，它可以从在线论文中收集荧光显微镜图像，使用图像处理方法对其进行分析，并使用附带的文本描述中出现的信息对其进行注释。我们建议改进和扩展这一系统，以产生一个健壮的、全面的工具包，用于从在线期刊中找到的文本和图像中提取有关亚细胞定位的信息，以及分析、验证和查询产生的信息体。

DESCRIPTION (provided by applicant): The goal of this project is to build a software toolkit that will enable a biologist to create, from a collection of on-line articles, a database of protein subcellular localization information that can be queried, browsed, or used to support data-mining activities. We have developed a system, called SLIF, which can harvest fluorescence microscope images from online papers, analyze them using image-processing methods, and annotate them with information appearing in the accompanying textual description. We propose to improve and extend this system so as to produce a robust, comprehensive toolkit for extracting information about subcellular localization from the text and images found in online journals, as well as analyzing, verifying and querying the resulting body of information.