Detecting signals in pharmacogenomic genome-wide association studies

In a common pharmacogenomic scenario, outcome measures are compared for treated and untreated Subjects across genotype-defined subgroups. The key question is whether treatment benefit (or harm) is particularly strong in certain subgroups, and therefore the statistical analysis focuses on the interaction between treatment and genotype. However, genome-wide analysis in such scenarios requires careful statistical thought as, in addition to the usual problems of multiple testing, the marker-defined sample sizes, and therefore power, vary across the individual genotypes being evaluated. The variability in power means that the usual practice of using a common P-value threshold across tests has difficulties. The reason is that the use of a fixed threshold, with variable power, implies that the costs of type I and type II errors vary across tests in a manner that is implicit rather than dictated by the analyst. In this paper we discuss this problem and describe an easily implementable solution based on Bayes factors. We pay particular attention to the specification of priors, which is not a straightforward task. The methods are illustrated using data from a randomized controlled clinical trial in which homocysteine levels are compared in individuals receiving low and high doses of folate supplements and across marker subgroups.