首页 | 本学科首页   官方微博 | 高级检索  
     

GenExtractor:基于Web的基因信息挖掘
引用本文:刘海军,忻健,万虎,王翼飞. GenExtractor:基于Web的基因信息挖掘[J]. 高技术通讯, 2006, 16(4): 395-398
作者姓名:刘海军  忻健  万虎  王翼飞
作者单位:上海大学数学系,上海,200444
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%.

关 键 词:Web  数据挖掘  生物数据库  向量空间模型
收稿时间:2005-06-02
修稿时间:2005-06-02

GenExtractor: a web-based gene information mining system
Liu Haijun,Xin Jian,Wan Hu,Wang Yifei. GenExtractor: a web-based gene information mining system[J]. High Technology Letters, 2006, 16(4): 395-398
Authors:Liu Haijun  Xin Jian  Wan Hu  Wang Yifei
Affiliation:Department of Mathematics, Shanghai University, Shanghai 200444
Abstract: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%.
Keywords:with relatively wide scope.It is tested that the precision factor of the system reaches 60% and the recall factor reaches 82.1%.Key words: Web  data mining  biological database  vector space model(VSM)
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号