中文摘要：

目的针对基因表达数据,探索新的有效特征提取和分类方法。方法采用小波多分辨率分析（MRA）方法提取基因表达的特征和前馈式神经网络（BP神经网络）方法进行特征分类。结果基因表达具有明显的多尺度特征,最大平均分类率为94.72%。结论采用多尺度理论对基因表达数据进行分析是一种新的有效的生物信息学方法,值得进一步探索与研究。

英文摘要：

Objective To search a new and effective method for feature extraction and classification based on gene expression data.Methods The features of gene expression were extracted by the wavelet multi-resolution analysis,and the features were classified by the BP neural network methods.Results There was multi-scale feature for gene expression;the maximum average classification rate was 94.72%.Conclusion Multi-scale theory analysis of gene expression is a new and effective bioinformatics method,which is worth further exploration and research.