Sparse generalized canonical correlation analysis for biological model integration: A genetic study of psychiatric disorders

In the post-genomic era, unveiling causal traits in the complex mechanisms that involve a number of diseases has been highlighted as one of the key goals. Much research has recently suggested integrative approaches of both genomewide association studies (GWAS) and gene expression profiling-based studies provide greater insight of the mechanism than utilizing only one. In this paper, we propose a novel method, sparse generalized canonical correlation analysis (SGCCA), to integrate multiple biological data such as genetic markers, gene expressions, and disease phenotypes. The proposed method provides a powerful approach to comprehensively analyze complex biological mechanism while utilizing the multiple data simultaneously. The new method is also designed to identify a few of the elements significantly involved in the system among a large number of elements within the variable sets. The advantage of the method as well lies in the output of easily interpretable solutions. To verify the performance of SGCCA, we performed experiments with simulation data and human brain data of psychiatric diseases. Its capability to detect significant elements of the sets and the relations of the complex system is assessed.