Online Program Home
My Program

Abstract Details

Activity Number: 428
Type: Contributed
Date/Time: Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
Sponsor: Biometrics Section
Abstract #319116
Title: Module-Based Reconstruction of Gene Regulatory Network into Predictive Modeling for High-Dimensional Genomic Data
Author(s): Rui Zhong* and Xin Huang and Viswanath Devanarayan
Companies: AbbVie and AbbVie and AbbVie
Keywords: Biomarker ; Gene Regulatory Network ; Predictive Modeling ; Personalized medicine

Identification of biomarkers with prognostic or predictive power has been an interesting topic in both academia and industry. However, interpretation of biological significance of identified biomarkers has been a challenge. Genes and proteins work in network rather than individually and therefore hub genes within biological network might play a central role in multiple biological processes and functions and be potentially novel therapeutic targets. Reconstruction of gene regulatory networks can help us identify hub genes. Previously we have incorporated hub genes into predictive modeling in a supervised way and demonstrated that the proposed approach can yield more biologically meaningful signatures without compromising predictive performance. Here we proposed a novel unsupervised approach to adopt hub gene methodology into predictive modeling. Genes are clustered into sparse modules based on whole-genome sequencing data before hub genes are identified within each module. Afterwards, those hub genes are used as features for predictive modeling. We illustrate this using data from a Neuroblastoma study.

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

Back to the full JSM 2016 program

Copyright © American Statistical Association