Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 484 - Methods for High-Dimensional Data in Genetics and Genomics
Type: Contributed
Date/Time: Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
Sponsor: Biometrics Section
Abstract #312881
Title: Variable Selection in Nonparametric Additive Quantile Regression for Genomic Data with Priori Information
Author(s): Peitao Wu* and Josee Dupuis and Ching-Ti Liu
Companies: Boston University and Boston University School of Public Health and Boston University
Keywords: data integration; group Lasso; network regularization; additive model

A priori information, such as biological pathways, is a useful supplement in identifying risk factors of a trait using genomic data. However, the commonly used methods to incorporate prior information provide a model for the mean function of the outcome and rely on unmet linear assumptions. To address these concerns, we propose a method for variable selection in nonparametric additive quantile regression with network regularization to incorporate the information encoded by known networks. We implement the group Lasso penalty to obtain a sparse model. We define the network-constrained penalty by the total L-2 norm of the difference between the effect functions of any two predictors that are linked in the known network. We further propose an efficient computation procedure to solve the optimization problem that arises in our model. Simulation studies show that our proposed method performs well in identifying more truly associated variables and less falsely associated variables than alternative approaches. We apply the proposed method to analyze the microarray gene-expression dataset in the Framingham Heart Study and identify several body mass index associated genes.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program