Common characteristics and noise filtering and its application in a proteomic pattern recognition system for cancer detection

High-throughput mass spectrometry technologies, such as surface enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-ToF-MS), generate large sets of complex data. The high dimensionality of these datasets poses analytical and computational challenges to the task of spectrum classification. In this paper, we describe a common characteristics and noise filter, which hones in on spectrum subsets with high discriminatory power. The filter is incorporated in a proteomic pattern recognition system. Our method is demonstrated on a set of 322 SELDI-ToF mass spectra of serum samples from prostate cancer patients and a control group. We show that our system can extract the discriminatory subsets from these spectra, and improve classification accuracy and computational speed compared to existing techniques.