Class Prediction for Biomarkers of Susceptibility for Treatment Decision

Abstract

A main goal of pharmacogenomics is to develop genomic signatures to predict patients' responses to drug or biologic therapy for treatment decision. We present an approach to developing a biomarker classifier for identifying a fraction of susceptible patients who should be spared unnecessary treatment.? The approach involves two steps. The first step is to identify a set of biomarkers of susceptibility from a mixture of biomarkers of susceptibility and biomarkers of response; the second step is to develop a classifier using an ensemble classification algorithm, as the number of susceptible patients is generally much smaller than the number of non-susceptible patients.? Important issues and applications will be discussed about the development of biomarker classifiers to identify a small number of susceptible patients.