Gene Discovery Using Pareto Depth Sampling Distributions

Most methods for finding interesting gene expression profiles from gene microarray data are based on a single discriminant, e.g. the classical paired t-test. Here a different approach is introduced based on gene ranking according to Pareto depth in multiple discriminants. The novelty of our approach, which is an extension of our previous work on Pareto front analysis (PFA), is that a gene’s relative rank is determined according to the ordinal theory of multiple objective optimization. Furthermore, the distribution of each gene’s rank, called Pareto depth, is determined by resampling over the microarray replicates. This distribution is called the Pareto depth sampling distribution (PDSD) and it is used to assess the stability of each ranking. We illustrate and compare the PDSD approach with both simulated and real gene microarray experiments.