Multi-modal fusion is an effective approach in biomedical imaging which combines multiple data types in a joint analysis and overcomes the problem that each modality provides a limited view of the brain. In this paper, we propose an exploratory fusion model, we term "mCCA+jICA", by combining two multivariate approaches: multi-set canonical correlation analysis (mCCA) and joint independent component analysis (jICA). This model can freely combine multiple, disparate data sets and explore their joint information in an accurate and effective manner, so that high decomposition accuracy and valid modal links can be achieved simultaneously. We compared mCCA+jICA with its alternatives in simulation and applied it to real fMRI-DTI-methylation data fusion, to identify brain abnormalities in schizophrenia. The results replicate previous reports and add to our understanding of the neural correlates of schizophrenia, and suggest more generally a promising approach to identify potential brain illness biomarkers.