OntoMate：一种辅助大鼠基因组数据库编目的文本挖掘工具。
OntoMate: a text-mining tool aiding curation at the Rat Genome Database.
作者信息
Liu Weisong, Laulederkind Stanley J F, Hayman G Thomas, Wang Shur-Jen, Nigam Rajni, Smith Jennifer R, De Pons Jeff, Dwinell Melinda R, Shimoyama Mary
机构信息
Human and Molecular Genetics Center, Medical College of Wisconsin, Department of Quantitative Health Sciences, University of Massachusetts Medical School, Department of Physiology, Medical College of Wisconsin and Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Rd, Milwaukee, WI 53226-3548, USA Human and Molecular Genetics Center, Medical College of Wisconsin, Department of Quantitative Health Sciences, University of Massachusetts Medical School, Department of Physiology, Medical College of Wisconsin and Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Rd, Milwaukee, WI 53226-3548, USA.
Human and Molecular Genetics Center, Medical College of Wisconsin, Department of Quantitative Health Sciences, University of Massachusetts Medical School, Department of Physiology, Medical College of Wisconsin and Department of Surgery, Medical College of Wisconsin, 8701 Watertown Plank Rd, Milwaukee, WI 53226-3548, USA
出版信息
Database (Oxford). 2015 Jan 25;2015. doi: 10.1093/database/bau129. Print 2015.
The Rat Genome Database (RGD) is the premier repository of rat genomic, genetic and physiologic data. Converting data from free text in the scientific literature to a structured format is one of the main tasks of all model organism databases. RGD spends considerable effort manually curating gene, Quantitative Trait Locus (QTL) and strain information. The rapidly growing volume of biomedical literature and the active research in the biological natural language processing (bioNLP) community have given RGD the impetus to adopt text-mining tools to improve curation efficiency. Recently, RGD has initiated a project to use OntoMate, an ontology-driven, concept-based literature search engine developed at RGD, as a replacement for the PubMed (http://www.ncbi.nlm.nih.gov/pubmed) search engine in the gene curation workflow. OntoMate tags abstracts with gene names, gene mutations, organism name and most of the 16 ontologies/vocabularies used at RGD. All terms/ entities tagged to an abstract are listed with the abstract in the search results. All listed terms are linked both to data entry boxes and a term browser in the curation tool. OntoMate also provides user-activated filters for species, date and other parameters relevant to the literature search. Using the system for literature search and import has streamlined the process compared to using PubMed. The system was built with a scalable and open architecture, including features specifically designed to accelerate the RGD gene curation process. With the use of bioNLP tools, RGD has added more automation to its curation workflow. Database URL: http://rgd.mcw.edu.
大鼠基因组数据库（RGD）是大鼠基因组、遗传和生理数据的首要储存库。将科学文献中的自由文本数据转换为结构化格式是所有模式生物数据库的主要任务之一。RGD花费了大量精力人工整理基因、数量性状位点（QTL）和品系信息。生物医学文献数量的迅速增长以及生物自然语言处理（bioNLP）领域的积极研究，促使RGD采用文本挖掘工具来提高整理效率。最近，RGD启动了一个项目，使用OntoMate（RGD开发的一种本体驱动、基于概念的文献搜索引擎）来替代基因整理工作流程中的PubMed（http://www.ncbi.nlm.nih.gov/pubmed）搜索引擎。OntoMate用基因名称、基因突变、生物体名称以及RGD使用的16种本体/词汇表中的大部分对摘要进行标注。所有标注到摘要的术语/实体都会在搜索结果中与摘要一同列出。所有列出的术语都与整理工具中的数据输入框和术语浏览器相链接。OntoMate还为物种、日期和其他与文献搜索相关的参数提供用户激活的过滤器。与使用PubMed相比，使用该系统进行文献搜索和导入简化了流程。该系统采用了可扩展的开放架构构建，包括专门为加速RGD基因整理过程而设计的功能。通过使用bioNLP工具，RGD在其整理工作流程中增加了更多自动化。数据库网址：http://rgd.mcw.edu。
Zotero 插件