Whole genome sequencing and other studies of Alzheimer’s disease (AD) genetics are identifying more and more candidate regions of the genome that influence disease predisposition. However, we still lack an understanding of what these regions are doing in the context of Alzheimer’s disease, which involves a complex interplay of different biological processes and cell types. Our approach uses a combination of laboratory and computational research to disentangle this complexity. First, we used epigenetic analysis to find a new network of Alzheimer’s-associated genes that only emerge during the course of disease progression in oligodendrocyte cells, which make up the brain’s “white matter.” Next, we built sophisticated machine learning models that predict how mutations in the human genome influence different cell types. These models demonstrate the importance of the brain immune cells, microglia, as well as peripheral immune cells that circulate in the bloodstream. Finally, we conducted a set of experiments where we synthesized hundreds of fragments of the human genome associated with Alzheimer’s disease and studied them in the context of the mouse brain. Our results thus far identified a mutation that is likely to impact the regulation of the gene PTK2B, influencing how sensitive neurons are to the buildup of amyloid protein during Alzheimer’s disease. We have shared these resources with consortium collaborators, who are using them to find pathways for potential therapeutics that may be selectively active across different cell types.