an extensive comparison of recent classification tools applied to microarry data 2005.pdf

下载文档

2
0
约 17页
2017-04-11 发布于江苏
举报
版权申诉
保障服务

an extensive comparison of recent classification tools applied to microarry data 2005.pdf

1、本文档共17页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。

an extensive comparison of recent classification tools applied to microarry data 2005

Computational Statistics Data Analysis 48 (2005) 869–885 /locate/csda An extensive comparison of recent classi%cation tools applied to microarray data Jae Won Leea ;? , Jung Bok Leea , Mira Parkb , Seuck Heun Songa aDepartment of Statistics, Korea University, 5-1 Anam-dong, Sungbuk-gu, Seoul 136-701, South Korea bDepartment of Pre-Medicine, Eulji Medical College, Taejeon 301-832, South Korea Received 20 December 2003; received in revised form 4 March 2004 Abstract Since most classi%cation articles have applied a single technique to a single gene expression dataset, it is crucial to assess the performance of each method through a comprehensive com- parative study. We evaluate by extensive comparison study extending Dudoit et al. (J. Amer. Statist. Assoc. 97 (2002) 77) the performance of recently developed classi%cation methods in microarray experiment, and provide the guidelines for %nding the most appropriate classi%cation tools in various situations. We extend their comparison in three directions: more classi%cation methods (21 methods), more datasets (7 datasets) and more gene selection techniques (3 meth- ods). Our comparison study shows several interesting facts and provides the biologists and the biostatisticians some insights into the classi%cation tools in microarray data analysis. This study also shows that the more sophisticated classi%ers give better performances than classical meth- ods such as kNN, DLDA, DQDA and the choice of gene selection method has much eect on the performance of the classi%cation methods, and thus the classi%cation methods should be considered together with the gene selection criteria. c? 2004 Elsevier B.V. All rights reserved. Keywords: Microarray; Classi%cation; Feature selection 1. Introduction The recent development of microarray technologies to monitor gene expression in model organisms, cell lines, and human tissues has become an important part of biolog- ical research over the last several years. Microarrays allow the monito