Brain connectome mapping of complex human traits and their polygenic architecture using machine learning

Background: Mental disorders and individual characteristics such as intelligence and personality are complex traits sharing a largely unknown neuronal basis. Their genetic architectures are highly polygenic and overlapping, which is supported by heterogeneous phenotypic expression and substantial clinical overlap. Brain network analysis provides a non-invasive means of dissecting biological heterogeneity yet its sensitivity, specificity and validity in assessing individual characteristics relevant for brain function and mental health and their genetic underpinnings in clinical applications remains a challenge. Methods: In a machine learning approach, we predicted individual scores for educational attainment, fluid intelligence and dimensional measures of depression, anxiety and neuroticism using fMRI-based static and dynamic temporal synchronization between large-scale brain network nodes in 10,343 healthy individuals from the UK Biobank. In addition to age and sex to serve as our reference point, we also predicted individual polygenic scores for related phenotypes, and 13 different neuroticism traits and schizophrenia. Results: Beyond high accuracy for age and sex, supporting the biological sensitivity of the connectome-based features, permutation tests revealed above chance-level prediction accuracy for trait-level educational attainment and fluid intelligence. Educational attainment and fluid intelligence were mainly negatively associated with static brain connectivity in frontal and default mode networks, whereas age showed positive correlations with a more widespread pattern. In contrast, prediction accuracy was at chance level for depression, anxiety, neuroticism and polygenic scores across traits. Conclusion: These novel findings provide a benchmark for future studies linking the genetic architecture of individual and mental health traits with fMRI-based brain connectomics.