Variable Selection for High-Dimensional Nonparametric Ordinary Differential Equation Models with Applications to Dynamic Gene Regulatory Networks

• Activity Number: 240
• Type: Contributed
• Date/Time: Monday, August 4, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Hongqi Xue*+
• Companies: University of Rochester Medical Center
• Keywords: variable selection ; adaptive group Lasso ; differential equations ; time course microarray data ; high dimensional data ; sparse additive model

Abstract

The gene regulation network (GRN) is a high-dimensional complex system, which can be represented by various mathematical or statistical models. The ordinary differential equation (ODE) model is one of the popular dynamic GRN models. High-dimensional linear ODE models have been proposed to identify GRNs, but with a limitation of the linear regulation effect assumption. We propose a nonparametric additive ODE model, coupled with two-stage smoothing-based ODE estimation methods and adaptive group LASSO techniques, to model dynamic GRNs that could flexibly deal with nonlinear regulation effects. The asymptotic properties of the proposed method are established under the "large p, small n" setting. Simulation studies are performed to validate the proposed approach. An application example for identifying the nonlinear dynamic GRN of T-cell activation is used to illustrate the usefulness of the proposed method. This is a joint work with Tao Lu, Hua Liang and Hulin Wu.