Gene expression pattern extraction based on wavelet analysis

By viewing a gene expression profile as a pseudtime signal, we apply wavelet transformation (WT) to analyze gene expression data in a time-frequency manner. As a result, two pattern extraction approaches, continuous wavelet transformation (CWT)-based one and discrete wavelet transformation (DWT)-based one, are proposed to extract hidden expression patterns for cancer classification and are compared. Gene expression data are highly redundant and highly noisy, and hidden gene correlation patterns play more important roles to cancer classification than any single gene or simple combinations of genes. The CWT can more efficiently detect the consistent correlation signature than the DWT due to the availability of more detail information. Testing results on two publicly available gene expression datasets show the effectiveness and efficiency of the CWT-based approach.