A hybrid wavelet based feature extraction approach to analysis of high dimensional proteomic patterns

Pathologic states within an organ can be reflected by changes in serum proteomic patterns. Mass spectrometry is becoming an important tool that generates the proteomic patterns. Mass spectrometry yields complex functional data for which the features of scientific interest are the peaks. Due to this complexity of data, a higher order analysis such as wavelet transform is needed to uncover the differences in proteomic patterns. In this research, a wavelet based feature extraction method was applied to available data and used a modified Fisher's criterion to feature subset selection in order to identify the appropriate biomarkers from reconstructed mass spectra. Using different classification algorithms, proposed approach yielded an accuracy of 95%, specificity of 94%, and sensitivity of 97%.