Feature selection for classification of SELDI-TOF-MS proteomic profiles

作     者：Hauskrecht, Milos Pelikan, Richard Malehorn, David E. Bigbee, William L. Lotze, Michael T. Zeh III, Herbert J. Whitcomb, David C. Lyons-Weiler, James 

作者机构：Department of Computer Science University of Pittsburgh Pittsburgh PA United States University of Pittsburgh Cancer Institute University of Pittsburgh Pittsburgh PA United States Clinical Proteomics Facility University of Pittsburgh Pittsburgh PA United States Department of Pathology University of Pittsburgh Pittsburgh PA United States Department of Surgery University of Pittsburgh Pittsburgh PA United States Department of Medicine Cell Biology and Physiology Department of Human Genetics University of Pittsburgh Pittsburgh PA United States Cancer Biomarkers Laboratory University of Pittsburgh Pittsburgh PA United States Centers for Pathology and Oncology Informatics University of Pittsburgh Pittsburgh PA United States Center for Biomedical Informatics University of Pittsburgh Pittsburgh PA United States Department of Computer Science 5329 Sennott Building University of Pittsburgh Pittsburgh PA 15260 United States 

出 版 物：《Applied Bioinformatics》 (Appl. Bioinform.)

年 卷 期：2005年第4卷第4期

页      面：227-246页

摘      要：Background: Proteomic peptide profiling is an emerging technology harbouring great expectations to enable early detection, enhance diagnosis and more clearly define prognosis of many diseases. Although previous research work has illustrated the ability of proteomic data to discriminate between cases and controls, significantly less attention has been paid to the analysis of feature selection strategies that enable learning of such predictive models. Feature selection, in addition to classification, plays an important role in successful identification of proteomic biomarker panels. Methods: We present a new, efficient, multivariate feature selection strategy that extracts useful feature panels directly from the high-throughput spectra. The strategy takes advantage of the characteristics of surface-enhanced laser desorption/ionisation time-of-flight mass spectrometry (SELDI-TOF-MS) profiles and enhances widely used univariate feature selection strategies with a heuristic based on multivariate de-correlation filtering. We analyse and compare two versions of the method: one in which all feature pairs must adhere to a maximum allowed correlation (MAC) threshold, and another in which the feature panel is built greedily by deciding among best univariate features at different MAC levels. Results: The analysis and comparison of feature selection strategies was carried out experimentally on the pancreatic cancer dataset with 57 cancers and 59 controls from the University of Pittsburgh Cancer Institute, Pittsburgh, Pennsylvania, USA. The analysis was conducted in both the whole-profile and peak-only modes. The results clearly show the benefit of the new strategy over univariate feature selection methods in terms of improved classification performance. Conclusion: Understanding the characteristics of the spectra allows us to better assess the relative importance of potential features in the diagnosis of cancer. Incorporation of these characteristics into feature selection strat