Pathological changes within an organ can be reflected as proteomic patterns in blood. The mass spectrometry has been used as powerful tools to generate proteomic patterns from serum. The produced profiles can be viewed as high dimensional and correlation data for which More
Pathological changes within an organ can be reflected as proteomic patterns in blood. The mass spectrometry has been used as powerful tools to generate proteomic patterns from serum. The produced profiles can be viewed as high dimensional and correlation data for which the features of scientific interest are the peaks. Due to this complexity of data, an appropriate analysis method is needed such as wavelet transform. In this study, we proposed a pseudo-covariance wavelet-based feature extraction method for dimension reduction and de-correlation between mass spectra data. Our algorithm was applied to datasets of ovarian cancer obtained from the National Cancer Institute of USA. The proposed algorithm was used to extract the set of proteins as potential biomarkers in each dataset from reconstructed mass spectra. The selected biomarkers were able to diagnose ovarian cancer patients from non-cancer with high accurate results using standard diagnosis criteria. Using different classification algorithms, our approach yielded an accuracy of 98%, specificity of 97%, and sensitivity of 98%.
Manuscript profile
