Cancer classification from serial analysis of gene expression with event models

详细信息    查看全文

• 作者：Xin Jin ; Anbang Xu and Rongfang Bie
• 关键词：Serial analysis of gene expression (SAGE) ; Event models ; Cancer classification ; Gene selection
• 刊名：Applied Intelligence
• 出版年：2008
• 出版时间：August, 2008
• 年：2008
• 卷：29
• 期：1
• 页码：35-46
• 全文大小：1.1 MB

文摘

Cancer class prediction and discovery is beneficial to imperfect non-automated cancer diagnoses which affect patient cancer treatments. Serial Analysis of Gene Expression (SAGE) is a relatively new method for monitoring gene expression levels and is expected to contribute significantly to the progress in cancer treatment by enabling an automatic, precise and early diagnosis. A promising application of SAGE gene expression data is classification of cancers. In this paper, we build three event models (the multivariate Bernoulli model, the multinomial model and the normalized multinomial model) for SAGE gene expression profiles. The event models based methods are compared with the standard Na?ve Bayes method. Both binary classification and multicategory classification are investigated. Experiments results on several SAGE datasets show that event models are better than standard Na?ve Bayes in general. Normalized Information Gain (NIG), an extension of Information Gain (IG), is proposed for gene selection. The impact of gene correlation on the classification performance is investigated.