Sparse Bayesian Multiview Learning for Simultaneous Association Discovery and Diagnosis of Alzheimer's Disease

Authors

  • Shandian Zhe Purdue University
  • Zenglin Xu University of Electronic Science and Technology of China
  • Yuan Qi Purdue University
  • Peng Yu Eli lilly and Company

DOI:

https://doi.org/10.1609/aaai.v29i1.9473

Keywords:

Alzheimer's Disease, Association Study, Bayesian Sparse Modeling, Multiview Learning, Spike and Slab priors

Abstract

In the analysis and diagnosis of many diseases, such as the Alzheimer's disease (AD), two important and related tasks are usually required: i) selecting genetic and phenotypical markers for diagnosis, and ii) identifying associations between genetic and phenotypical features. While previous studies treat these two tasks separately, they are tightly coupled due to the same underlying biological basis. To harness their potential benefits for each other, we propose a new sparse Bayesian approach to jointly carry out the two important and related tasks. In our approach, we extract common latent features from different data sources by sparse projection matrices and then use the latent features to predict disease severity levels; in return, the disease status can guide the learning of sparse projection matrices, which not only reveal interactions between data sources but also select groups of related biomarkers. In order to boost the learning of sparse projection matrices, we further incorporate graph Laplacian priors encoding the valuable linkage disequilibrium (LD) information. To efficiently estimate the model, we develop a variational inference algorithm. Analysis on an imaging genetics dataset for AD study shows that our model discovers biologically meaningful associations between single nucleotide polymorphisms (SNPs) and magnetic resonance imaging (MRI) features, and achieves significantly higher accuracy for predicting ordinal AD stages than competitive methods.

Downloads

Published

2015-02-18

How to Cite

Zhe, S., Xu, Z., Qi, Y., & Yu, P. (2015). Sparse Bayesian Multiview Learning for Simultaneous Association Discovery and Diagnosis of Alzheimer’s Disease. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). https://doi.org/10.1609/aaai.v29i1.9473

Issue

Section

Main Track: Machine Learning Applications