Predicting brain age and associated structural networks in mouse models with humanized APOE alleles using integrative and interpretable graph neural networks
Alzheimer's disease (AD), a prevalent neurodegenerative disorder, is influenced by an intricate mix of risk factors including age, genetics, and environmental variables. In our study, we employed mouse models with human APOE alleles and nitric oxide synthase 2, and adjusted environmental factors like diet, to replicate controlled genetic risk and innate immune response associated with AD in human subjects. We utilized a Feature Attention Graph Neural Network (FAGNN), integrating brain structural connectomes, genetic traits, environmental factors, and behavioral data, to estimate brain age. Our method demonstrated improved accuracy in age prediction over other methods and highlighted age-associated brain connections. The most impactful connections included the cingulum, striatum, corpus callosum, and hippocampus. We further investigated these findings through fractional anisotropy in different age groups of mice, and our results underlined the significance of white matter degradation in aging. Our results underscore the effectiveness of integrative graph neural networks in predicting brain age and delineating important neural connections associated with brain aging.
