Adaptive Sparse Multiple Canonical Correlation Analysis With Application to Imaging (Epi)Genomics Study of Schizophrenia

• Published in: IEEE transactions on biomedical engineering Vol. 65; no. 2; pp. 390 - 399
• Main Authors: Hu, Wenxing, Lin, Dongdong, Cao, Shaolong, Liu, Jingyu, Chen, Jiayu, Calhoun, Vince D., Wang, Yu-Ping
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Algorithms; Biomarkers; Brain; canonical correlation analysis; Computer Simulation; Correlation; Correlation analysis; Data analysis; data fusion; Data integration; Data processing; Datasets; Diseases; DNA Methylation; Epigenomics - methods; Feature extraction; Genetic diversity; Genetic variance; Genetics; genomic data analysis; Genomics; Humans; Image Processing, Computer-Assisted; Imaging; Imaging genomics; Linear programming; Mathematical models; Mental disorders; Models, Statistical; multi-omics data integration; Neural tube; Neuroimaging; Neuroimaging - methods; ROC Curve; Schizophrenia; Schizophrenia - diagnostic imaging; Schizophrenia - genetics
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2017.2771483

Finding correlations across multiple data sets in imaging and (epi)genomics is a common challenge. Sparse multiple canonical correlation analysis (SMCCA) is a multivariate model widely used to extract contributing features from each data while maximizing the cross-modality correlation. The model is achieved by using the combination of pairwise covariances between any two data sets. However, the scales of different pairwise covariances could be quite different and the direct combination of pairwise covariances in SMCCA is unfair. The problem of "unfair combination of pairwise covariances" restricts the power of SMCCA for feature selection. In this paper, we propose a novel formulation of SMCCA, called adaptive SMCCA, to overcome the problem by introducing adaptive weights when combining pairwise covariances. Both simulation and real-data analysis show the outperformance of adaptive SMCCA in terms of feature selection over conventional SMCCA and SMCCA with fixed weights. Large-scale numerical experiments show that adaptive SMCCA converges as fast as conventional SMCCA. When applying it to imaging (epi)genetics study of schizophrenia subjects, we can detect significant (epi)genetic variants and brain regions, which are consistent with other existing reports. In addition, several significant brain-development related pathways, e.g., neural tube development, are detected by our model, demonstrating imaging epigenetic association may be overlooked by conventional SMCCA. All these results demonstrate that adaptive SMCCA are well suited for detecting three-way or multiway correlations and thus can find widespread applications in multiple omics and imaging data integration.