Disorders of mood and psychosis such as schizophrenia, bipolar disorder, and unipolar depression are incredibly complex, influenced by both genetic and environmental factors, and the clinical characterizations are primarily based on symptoms rather than biological information. Current diagnostic approaches are based on symptoms, which overlap extensively in some cases, and there is growing consensus that we should approach mental illness as a continuum, rather than as a categorical entity. Since both genetic and environmental factors play a large role in mental illness, the combination of brain imaging and genomic data are poised to play an important role is clarifying our understanding of mental illness. However, both imaging and genomic data are high dimensional and include complex relationships that are poorly understood. To characterize the available information, we are in need of approaches that can deal with high-dimensional data exhibiting interactions at multiple levels (i.e., data fusion), while providing interpretable solutions (i.e., a focus on brain and genomic networks). An additional challenge exists because the available data has mixed temporal dimensionality, e.g., single nucleotide polymorphisms (SNPs) do not change over time, brain structure changes slowly over time, while fMRI changes rapidly over time. To address these challenges, we introduce a new unified framework called flexible subspace analysis (FSA) that can automatically identify subspaces (groupings of unimodal or multimodal components) in joint multimodal data. Our approach leverages the interpretability of source separation approaches and can include additional flexibility by allowing for a combination of shallow and ?deep? subspaces, thus leveraging the power of deep learning. We will apply the developed models to a large (N>60,000) dataset of individuals along the mood and psychosis spectrum to evaluate the important question of disease categorization. We will compute fully cross-validated genomic-neuro-behavioral profiles of individuals including a comparison of the predictive accuracy of 1) standard categories from the diagnostic and statistical manual of mental disorders (DSM), 2) data-driven subgroups, and 3) dimensional relationships. We will also evaluate the single subject predictive power of these profiles in independent data to maximize generalization. All methods and results will be shared with the community. The combination of advanced algorithmic approach plus the large N data promises to advance our understanding of the nosology of mood and psychosis disorders in addition to providing new tools that can be widely applied to other studies of complex disease.
It is clear that mood and psychosis disorders, largely diagnosed without biological criteria, include a multitude of inter-related genetic and environmental factors. We propose to develop new flexible models to capture multiscale (dynamic) brain imaging and genomics data, which we will use to study individuals along the mood and psychosis spectrum using a large aggregated dataset including a comparison of the predictive accuracy of two dichotomous approaches (standard diagnostic categories and unsupervised/data-driven) as well as a dimensional approach to diagnosis.
