Diffusion enhancement model and its application in peak detection

It is a challenge for peak detection algorithms to detect some low-amplitude peaks and overlapped peaks contaminated by noise. Among of existing peak detection algorithms, the continuous wavelet transform (CWT)-based algorithm is the best. When the Mexican Hat wavelet is selected as the mother wavelet, the CWT of a signal is essentially equivalent to using the Gaussian function to smooth the 2nd derivative of the signal. Therefore, a natural idea is to combine the peak enhancement step and peak-preserving diffusion into peak detection process to improve the performance of peak detection. In the proposed algorithm, the Gaussian smoothing in the CWT-based algorithm is replaced with the peak-preserving diffusion filtering. As an assessment of the proposed algorithm, a simulated spectrum with low-amplitude peaks and overlapped peaks was generated and used to test the enhancement performance. Then 100 groups of simulated proteomics data sets in [1] were used to assess the proposed algorithm. In these data sets, the true peaks are known in each spectrum. Thus, the false discovery rate (FDR) is easy to find. Five typical peak detection programs were chosen to compare the proposed algorithm. The FDR and sensitivity is employed to compare the performance of these algorithms. Result shows that the proposed algorithm can improve the performance of peak detection.