|
|||||
|
|
| 复杂疾病驱使的融合SDA-SVM集成基因挖掘方法 | |
| 引用本文： | 杨德印,李霞,郝大鹏,张杰,张瑞杰,饶绍奇.复杂疾病驱使的融合SDA-SVM集成基因挖掘方法[J].生物信息学,2007,5(1):15-18. |
| 作者姓名： | 杨德印 李霞 郝大鹏 张杰 张瑞杰 饶绍奇 |
| 作者单位： | 1. 哈尔滨医科大学生物信息学系,哈尔滨,150086 2. 哈尔滨医科大学生物信息学系,哈尔滨,150086;哈尔滨工业大学计算机学院,哈尔滨,150001;首都医科大学生物医学工程学院,北京,100054;同济大学生命科学与技术学院,上海,200092 3. 哈尔滨医科大学生物信息学系,哈尔滨,150086;Departments of CardiovasCular Medicine and Molecular Cardiology,Cleveland Clinic Foundation leveland,ohio 44195,USA |
| 基金项目： | 国家自然科学基金;国家高技术研究发展计划(863计划);黑龙江省科技攻关项目;黑龙江省自然科学基金;211工程建设项目;哈尔滨医科大学校科研和教改项目 |
| 摘 要： | 提出了一种新颖的复杂疾病驱使的融合SDA-SVM(Stepwise Discriminant Analysis-Support Vector Machine,SDA-SVM)技术的集成基因挖掘方法。该集成方法融合逐步判别分析和支持向量机的优点,能够有效地进行复杂疾病相关基因的深度挖掘,使得挖掘出的基因能够较好地识别疾病类型和亚型。通过将该方法应用于一套弥散性大B细胞淋巴瘤DNA表达谱数据,并与其它基因挖掘方法对比,结果表明该方法挖掘出的基因具有较高的疾病相关性和较强的疾病类型识别能力。 |
| 关 键 词： | 微阵列 集成决策 基因挖掘 逐步判别分析 支持向量机 |
| 文章编号： | 1672-5565（2007）-01-15-04 |
| 修稿时间： | 2006-03-162006-10-22 |
An ensemble analysis approach by fusion of stepwise discriminant analysis and support vector machine for gene mining |
|
| YANG De-yin,LI Xia,HAO Da-peng,ZHANG jie,ZHANG Rui-jie,RAO Shao-qi.An ensemble analysis approach by fusion of stepwise discriminant analysis and support vector machine for gene mining[J].China Journal of Bioinformation,2007,5(1):15-18. | |
| Authors: | YANG De-yin LI Xia HAO Da-peng ZHANG jie ZHANG Rui-jie RAO Shao-qi |
| Institution: | 1.Department of Bioinformatics; Harbin Medical University Harbin 150086; China; 2.Deparment of Computer Science; Harbin Institute of Technology Harbin 150080; 3.Biomedical Engineering Institute of CUMS Beijing 10004; 4.College of Biological Science and Technology; Tongji University Shanghai 200092; 5.Departments of Cardiovascular Medicine and Molecular Cardiology; Cleveland Clinic Foundation Cleveland; 0hio 44195; USA |
| Abstract: | This paper proposes a novel ensemble approach which combines the merits of stepwise discriminant analysis and support vector machine for extracting disease relevant genes and for classifying biological types.By comparing the proposed method with other gene mining methods using a public dataset of the diffuse large b-cell lymphoma,the result demonstrates that the genes extracted by the proposed method have higher disease relevancy and also yield better classification performance. |
| Keywords: | Microarray Ensemble theory Gene mining Stepwise discriminant analysis Support vector machine |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |