Robust Network-Based Regularization and Variable Selection for High-Dimensional Genomic Data in Cancer Prognosis

• Activity Number: 237 - Feature Selection and Statistical Learning in Genomics
• Type: Contributed
• Date/Time: Monday, July 31, 2017 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Genomics and Genetics
• Author(s): Jie Ren* and Yinhao Du and Dewey Molenda and Yu Jiang and Wu Cen
• Companies: Department of Statistics, Kansas State University and Department of Statistics, Kansas State University and Department of Statistics, Kansas State University and School of Public Health, University of Memphis and Department of Statistics, Kansas State University
• Keywords: Network-based regularization ; Robustness ; Cancer prognosis ; Variable selection

Abstract

In cancer genomic studies, an important objective is to identify prognostic markers associated with patients' survival. Network-based regularization has achieved success in variable selections for high-dimensional cancer genomic data, due to its ability to incorporate the correlations among genomic features. However, as survival time data usually follow skewed distributions, and are contaminated by outliers, network-constrained regularization that does not take the robustness into account leads to false identifications of network structure and biased estimation of patients' survival. In this study, we develop a novel robust network based variable selection method under the accelerated failure time (AFT) model. Extensive simulation studies show the advantage of the proposed method over the alternatives in terms of identification and predictive performance. A case study of The Cancer Genome Atlas (TCGA) lung cancer data with high dimensional gene expression measurements demonstrates that the proposed approach has identified markers with important implications.