基于支持向量机的微阵列基因表达数据分析方法

Microarray Gene Expression Data Anlysis Based on Support Vector Maching

DNA微阵列技术,使人们可以同时观测成千上万个基因的表达水平,对其数据的分析已成为生物信息学研究的焦点.针对微阵列基因表达数据维数高、样本小、非线性的特点,设计了一种基于支持向量机的基因表达数据分类识别方法,该方法采用信噪比进行基因特征提取,运用支持向量机的不同核函数进行性能测试,针对几个典型数据集的实验表明其识别效果良好.

Based on DNA microarray experiment, the expression level of thousands of genes can be observed simultaneously, and the method of the analysis is focused in bioinformatics. Because microarray gene expression data are high dimensions and few samples and nonlinear, a method of gene expression data analysis was put forward, in which the gene subset are extracted by the method of signal to noise ratio and the several kernels of support vector machine were applied to test the performances, this method has been successfully applied to several expression data sets.