Logo image
Pattern Discovery in Brain Imaging Genetics via SCCA Modeling with a Generic Non-convex Penalty
Journal article   Open access   Peer reviewed

Pattern Discovery in Brain Imaging Genetics via SCCA Modeling with a Generic Non-convex Penalty

Lei Du, Kefei Liu, Xiaohui Yao, Jingwen Yan, Shannon L. Risacher, Junwei Han, Lei Guo, Andrew J. Saykin, Li Shen and Alzheimer’s Disease Neuroimaging Initiative
Scientific reports, Vol.7(1), 14052
10/25/2017
DOI: 10.1038/s41598-017-13930-y
PMCID: PMC5656688
PMID: 29070790
url
https://doi.org/10.1038/s41598-017-13930-yView
Published (Version of record) Open Access

Abstract

Brain imaging genetics intends to uncover associations between genetic markers and neuroimaging quantitative traits. Sparse canonical correlation analysis (SCCA) can discover bi-multivariate associations and select relevant features, and is becoming popular in imaging genetic studies. The L1-norm function is not only convex, but also singular at the origin, which is a necessary condition for sparsity. Thus most SCCA methods impose. l(1)-norm onto the individual feature or the structure level of features to pursuit corresponding sparsity. However, the. 1-norm penalty over-penalizes large coefficients and may incurs estimation bias. A number of non-convex penalties are proposed to reduce the estimation bias in regression tasks. But using them in SCCA remains largely unexplored. In this paper, we design a unified non-convex SCCA model, based on seven non-convex functions, for unbiased estimation and stable feature selection simultaneously. We also propose an efficient optimization algorithm. The proposed method obtains both higher correlation coefficients and better canonical loading patterns. Specifically, these SCCA methods with non-convex penalties discover a strong association between the APOE e4 rs429358 SNP and the hippocampus region of the brain. They both are Alzheimer's disease related biomarkers, indicating the potential and power of the non-convex methods in brain imaging genetics.
Multidisciplinary Sciences Science & Technology Science & Technology - Other Topics

Details

Metrics

Logo image