一种新型多类别生物芯片cdna基因表达数据标准化-电子与信息学报.pdfVIP

第 31 卷第 6 期 电 子 与 信 息 学 报 Vol.31No.6 2009 年 6 月 Journal of Electronics Information Technology Jun. 2009 一种新型多类别生物芯片 cDNA 基因表达数据标准化方法 ① ② 吕建平 Wang Yue ①(苏州大学电子信息学院 苏州 215021) ② (Virginia Polytechnic Institute and State University, Arlington VA22203, USA) 摘 要：cDNA 生物芯片表达数据广泛用于生物医学研究，利用计算机对其进行处理还有很多挑战性课题。该文提 出了一种新的基于不变基因的多类生物芯片监督型集合 cDNA 表达数据标准化方法。在达到标准化的同时，该方 法也可直接用于基因表达数据的特征选择，实验证明效果较好。 关键词：DNA 基因；跨类；标准化；多类多样本；特征选择 中图分类号：TP391.4 文献标识码：A 文章编号：1009-5896(2009)06-1350-04 A Cross-phenotype Normalization Method for cDNA Gene Expression Data ① ② Lü Jian-ping Wang Yue ① (School of EE Information, Soochow University, Suzhou 215021, China) ② (Virginia Polytechnic Institute and State University, Arlington VA22203, USA) Abstract: cDNA microarray expression data is widely used to help biomedical research. There are so many challenges when the computer and pattern recognition methods are used to process and analysis the data. In this paper, a novel hybrid cross-phenotype normalization method is proposed which deals with supervised multi-class multi-sample cDNA expression data set based on invariantly expressed genes. The algorithm can be directly used as a feature selection method for gene classifier. The result is satisfactory. Key words: DNA gene; Cross-phenotype; Normalization; Multi-class and multi samples; Feature selection 1 引言