Identifying Biomarkers from Mass Spectrometry Data with Ordinal Outcome

摘要: In recent years, there has been an increased interest in using protein mass spectroscopy to identify molecular markers that discriminate diseased from healthy individuals. Existing methods are tailored towards classifying observations into nominal categories. Sometimes, however, the outcome of may be measured on ordered scale. Ignoring this natural ordering results some loss information. paper, we propose a Bayesian model for analysis spectrometry data with outcome. The method provides unified approach identifying relevant and predicting class membership. This is accomplished by building stochastic search variable selection within ordinal model. We apply methodology ovarian cancer cases also utilize wavelet-based techniques remove noise spectra prior analysis. associated being healthy, having low grade cancer, or high case. For comparison, repeated conventional classification procedures found improved predictive accuracy our method.