GenExtractor：基于Web的基因信息挖掘  

GenExtractor： a web-based gene information mining system

作　　者：刘海军[1] 忻健[1] 万虎[1] 王翼飞[1] 

机构地区：[1]上海大学数学系,上海200444

出　　处：《高技术通讯》2006年第4期395-398,共4页Chinese High Technology Letters

基　　金：863计划（2002AA234021）资助项目.

摘　　要：开发了基于Web的基因信息挖掘系统——GenExtractor,它通过自动连接生物数据库,按照指定的染色体区域寻找候选基因,搜集并集成相关信息,为科研人员检索生物数据库和查找候选基因提供了一个有效的工具.该系统能够在更加精细的染色体区域内对指定功能基因进行查找,并对关键词的要求比较宽泛。经测试，其平均查准率达到60%，平均查全率达到82.1%。A web-based text mining system named GenExtractor has been developed, which can connect some biology databases automatically to search candidate genes and collect related information according to assigned chromosome region. It is a useful tool for researchers to search biological databases and seek candidate genes. This system is able to retrieve the genes for given function in the more precise region. And it can accept some key words with relatively wide scope. It is tested that the precision factor of the system reaches 60% and the recall factor reaches 82.1%.

关 键 词：WEB 数据挖掘 生物数据库 向量空间模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]