Imaging genetics research based on Sparse Canonical Correlation Analysis (SCCA) helps to discover the correlation between pathological features reflected by neuroimaging and genotypic variation. Multi-Task SCCA (MTSCCA) method is to identify bi-multivariate associations between SNPs and multi-modal imaging QTs. However, the MTSCCA method is unsupervised and cannot identify diagnosis-guided genotype-phenotype associations. In order to improve the performance and interpretability of MTSCCA, we propose an improved MTSCCA algorithm, which is a supervised sparse bivariate learning model fused with a linear regression model, in which the regression part plays a guiding role in imaging QT selection. To jointly understand the relationship between genotypes and phenotypes of multiple tasks, in this study, gene expression data and single nucleotide polymorphisms (SNPs) as genetic data are considered in the algorithm. The focus of each task is to determine the genotype-phenotype pattern guided by the diagnostic team to discover the association with SNP/gene and brain region changes. Besides, the Laplacian matrices of three kinds of data are added as prior knowledge to the algorithm penalty item so that the algorithm can analyze the correlation between different features. Compared with other SCCA methods, our algorithm has improved noise resistance and stability, and found some diagnostic-specific SNP/gene-ROI specific to the two diagnostic groups of MCI and AD. Significance: This method provides a way to further study the association of multi-modal biological data and identify the complex association patterns of diseases.

Brain imaging genetics can demonstrate the complicated relationship between genetic factors and the structure or function of the humankind brain. Therefore, it has become an important research topic and attracted more and more attention from scholars. The structured sparse canonical correlation analysis (SCCA) model has been widely used to identify the association between brain image data and genetic data in imaging genetics. To investigate the intricate genetic basis of cerebrum imaging phenotypes, a great deal of other standard SCCA methods combining different interested structed have now appeared. For example, some models use group lasso penalty, and some use the fused lasso or the graph/network guided fused lasso for feature selection. However, prior knowledge may not be completely available and the group lasso methods have limited capabilities in practical applications. The graph/network guided approaches can use sample correlation to define constraints, thereby overcoming this problem. Unfortunately, this also has certain limitations. The graph/network conducted methods are susceptible to the sign of the sample correlation of the data, which will affect the stability of the model. To improve the efficiency and stability of SCCA, a sparse canonical correlation analysis model with GraphNet regularization (FGLGNSCCA) is proposed in this manuscript. Based on the FGLSCCA model, the GraphNet regularization penalty is imposed in our study and an optimization algorithm is presented to optimize the model. The structural Magnetic Resonance Imaging (sMRI) and gene expression data are used in this study to find the genotype and characteristics of brain regions associated with Alzheimer’s disease (AD). Experiment results shown that the new FGLGNSCCA model proposed in this manuscript is superior or equivalent to traditional methods in both artificially synthesized neuroimaging genetics data or actual neuroimaging genetics data. It can select essential features more powerfully compared with other multivariate methods and identify significant canonical correlation coefficients as well as captures more significant typical weight patterns which demonstrated its excellent ability in finding biologically important imaging genetic relations.