Probabilistic Modeling of Information from Images and Text in Online Journals

在线期刊中图像和文本信息的概率建模

• 批准号: 7458122
• 负责人: Robert F Murphy
• 金额: $ 25.6万
• 依托单位: CARNEGIE-MELLON UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2006
• 资助国家: 美国
• 起止时间: 2006-07-01 至 2010-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/7458122
• 关键词: 3-Dimensional; Architecture; Area; Arts; Biomedical Research; Blast Cell; Classification; Collection; Computer software; Condition; Data; Data Set; Databases; Depth; Exhibits; Facility Construction Funding Category; Feeds; Fluorescence Microscopy; Future; Genes; Glycine decarboxylase; Goals; Harvest; Image; Individual; Journals; Literature; Location; Measures; Methods; Names; Numbers; Ontology; Operative Surgical Procedures; Paper; Pattern; Property; Protein Databases; Proteins; Proteomics; PubMed; Publications; Range; Reading; Research Personnel; Resources; Sampling; Scientist; Semantics; Standards of Weights and Measures; Statistical Models; Structure; Subcellular structure; System; Text; Time; Work; abstracting; base; cell type; data mining; fluorescence microscope; genome sequencing; high throughput screening; image processing; improved; intracellular protein transport; open source; programs; protein localization location; research study; text searching; tool; two-dimensional

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.

描述（由申请人提供）：该项目的目的是构建一个软件工具包，该工具包将使生物学家从在线文章集合中创建一个可以查询，浏览或用于支持数据挖掘活动的蛋白质亚细胞定位信息的数据库。我们已经开发了一个名为SLIF的系统，该系统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，并以随附的文本描述中显示的信息来注释它们。我们建议改进和扩展该系统，以生成一个强大的，全面的工具包，以从在线期刊中的文本和图像中提取有关亚细胞定位的信息，并分析，验证和查询所得信息的信息。

项目成果

Structured Correspondence Topic Models for Mining Captioned Figures in Biological Literature.

• DOI: 10.1145/1557019.1557031
• 发表时间: 2009
• 期刊: KDD : proceedings. International Conference on Knowledge Discovery & Data Mining
• 作者: Ahmed A;Xing EP;Cohen WW;Murphy RF
• 通讯作者: Murphy RF