empirical bayes analysis of a microarray experiment（经验贝叶斯分析微阵列实验）.pdf

Empirical Bayes Analysis of a Microarray Experiment Bradley Efron, Robert Tibshirani , John D. Storey, and Virginia Tusher Microarrays are a novel technology that facilitates the simultaneous measurement of thousands of gene expression levels. A typi- cal microarray experiment can produce millions of data points, raising serious problems of data reduction, and simultaneous infer- ence. We consider one such experiment in which oligonucleotide arrays were employed to assess the genetic effects of ionizing radiation on seven thousand human genes. A simple nonparametric empirical Bayes model is introduced, which is used to guide the ef cient reduction of the data to a single summary statistic per gene, and also to make simultaneous inferences concern- ing which genes were affected by the radiation. Although our focus is on one speci c experiment, the proposed methods can be applied quite generally. The empirical Bayes inferences are closely related to the frequentist false discovery rate (FDR) criterion. 1. INTRODUCTION and Chu (2001) approached the simultaneity problem through the method of false discovery rates (FDRs), as discussed later. Through the use of DNA microarrays, a novel technology, Our inferences here will be based on a simple nonpara- it is now possible to obtain quantitative measurements for the metric empirical Bayes model. The model produces useful a expression of thousands of genes present in a biological sam-