Identifying Candidate Genetic Associations with MRI-Derived AD-Related ROI via Tree-Guided Sparse Learning

Abstract

Imaging genetics has attracted significant interests in recent studies. Traditional work has focused on mass-univariate statistical approaches that identify important single nucleotide polymorphisms (SNPs) associated with quantitative traits (QTs) of brain structure or function. More recently, to address the problem of multiple comparison and weak detection, multivariate analysis methods such as the least absolute shrinkage and selection operator (Lasso) are often used to select the most relevant SNPs associated with QTs. However, one problem of Lasso, as well as many other feature selection methods for imaging genetics, is that some useful prior information, e.g., the hierarchical structure among SNPs, are rarely used for designing a more powerful model. In this paper, we propose to identify the associations between candidate genetic features (i.e., SNPs) and magnetic resonance imaging (MRI)-derived measures using a tree-guided sparse learning (TGSL) method. The advantage of our method is that it explicitly models the complex hierarchical structure among the SNPs in the objective function for feature selection. Specifically, motivated by the biological knowledge, the hierarchical structures involving gene groups and linkage disequilibrium (LD) blocks as well as individual SNPs are imposed as a tree-guided regularization term in our TGSL model. Experimental studies on simulation data and the Alzheimer's Disease Neuroimaging Initiative (ADNI) data show that our method not only achieves better predictions than competing methods on the MRI-derived measures of AD-related region of interests (ROIs) (i.e., hippocampus, parahippocampal gyrus, and precuneus), but also identifies sparse SNP patterns at the block level to better guide the biological interpretation.

Fig. 1.

Illustration of the tree-structured hierarchical relationship among SNPs: group by gene and group by linkage disequilibrium (LD) blocks.

Fig. 2.

The flowchart of the proposed method.

Fig. 3.

The Top 20 AD risk genes used in this study and the numbers of their SNPs.

Fig. 4.

Illustration plot on LD of SNPs on APOE by Haploview.

Fig. 5.

Hierarchical structure grouping by LD blocks on APOE.

Fig. 6.

Comparison of RMSE with respect to different number of selected SNPs from 200 to 2000 by L1-regularized Lasso, Group Lasso, Elastic Net, the proposed TGSL in prediction on (a) Left Hippocampus, (b) Right Hippocampus, (c) Left Parahippocampal Gyrus, (d) Right Parahippocampal Gyrus, (e) Left Precuneus, and (f) Right Precuneus.

Fig. 7.

The patterns of SNP selections by L1-regularized Lasso, Group Lasso, Elastic Net, and the proposed TGSL on (a) Left Hippocampus and (b) Right Parahippocampal gyrus. The white entries are masked as selected SNPs.