Covariate-Adjusted Inference for Differential Analysis of High-Dimensional Networks
share
Differences between genetic networks corresponding to disease conditions may delineate the underlying disease mechanisms. Existing methods for differential network analysis do not account for dependence of networks on exogenous variables, or covariates. As a result, these approaches may detect spurious differential connections, which are induced by the effect of the exogenous variables on both the disease condition and the genetic network. To address this issue, we propose a covariate-adjusted test for differential network analysis. Our proposed method assesses differential network connectivity by testing the null hypothesis that the network is the same for individuals who have identical covariates and only differ in disease condition. We show empirically in a simulation study that the covariate-adjusted test exhibits improved type-1 error control in contrast to naive hypothesis testing procedures that do not account for exogenous variables. We additionally show that there are settings in which our proposed methodology provides improved power to detect differential connections. We illustrate our method by applying it to detect differences in breast cancer genetic networks by subtype.
READ FULL TEXT
