B1484
Title: Dimension reduction and regression modelling for imaging genetics
Authors: Farouk Nathoo - University of Victoria (Canada) [presenting]
Abstract: Recent advances in technology for brain imaging and high-throughput genotyping have motivated studies examining the influence of genetic variation on brain structure. We describe approaches for the analysis of imaging genetic studies using penalized multi-task regression with priors that provide structured sparsity at both the gene level and SNP level using multivariate Laplace formulations. The model is specified as a three-level Gaussian scale-mixture and we consider both spatial and non-spatial models and Bayesian implementations based on both MCMC and variational Bayes. We also describe an approach for disease-directed dimension reduction of neuroimaging phenotypes based on neural networks. The approaches are evaluated using both simulations as well as test data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI).
