| 急性白血病相关基因的文本挖掘分析 |
| |
| 引用本文： | 闫雷,崔雷.急性白血病相关基因的文本挖掘分析[J].情报学报,2008,27(2):169-174. |
| |
| 作者姓名： | 闫雷 崔雷 |
| |
| 作者单位： | 中国医科大学信息管理与信息系统(医学)系,沈阳,110001 |
| |
| 摘 要： | 从PubMed检索1966年到2005年9月6日间白血病与基因关系的相关文献3 529篇.经编程处理生成主题词词篇矩阵并进行聚类.通过聚类树图可将所提取的主题词/副主题词分成13类,经对比原始文献进行验证,全部29种基因中只与ALL相关的有3种, 占10.34%;只与AML相关的有8种,占27.59%.特异的可用于鉴别ALL和AML的基因有11种,占37.93%.通过主题词的共现关系进行聚类可以基本实现发现基因与疾病之间的联系,但该方法所获得的相关基因较少,不利于对疾病与基因关系的全面了解.
|
| 关 键 词： | 白血病 基因 文本挖掘 聚类分析 |
| 修稿时间： | 2007年1月16日 |
Finding Relationship Between Acute Leukemia and Related Genes by Texual Data Mining |
| |
| Yan Lei,Cui Lei.Finding Relationship Between Acute Leukemia and Related Genes by Texual Data Mining[J].Journal of the China Society for Scientific andTechnical Information,2008,27(2):169-174. |
| |
| Authors: | Yan Lei Cui Lei |
| |
| Institution: | Yan Lei Cui Lei (Faculty of Information Management , Information System(Medicine),China Medical University,Shenyang 110001) |
| |
| Abstract: | We collected articles about leukemia related genes through PubMed from 1966 to September 6th 2005 as mining samples,3529 articles were found.From the sample,we extracted 75 MeSH and subheadings about acute leukemia and genes whose frequencies are greater than 2.Then we calculated the MeSH-paper co-occurrence matrix.The matrix was clustered by hierarchical cluster analysis using Binary measure hamaun alternative and centroid clustering method.The Mesh-paper matrix contained 29 related genes.According to the ... |
| |
| Keywords: | leukemia genes textual mining cluster analysis |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
