Alzheimer’s disease (AD) is a complex neurodegenerative disorder influenced by intricate interactions among genetic, molecular, and clinical factors. This dissertation advances AD research by employing informatics strategies within the Genomics, Molecular Multiomics, Biomarkers, and Outcomes (GMBO) framework to integrate large-scale biobank data and uncover key disease mechanisms. Through computational approaches, this work bridges genetic, molecular, and neuroimaging data to address critical challenges in understanding AD heterogeneity and progression. A central contribution of this dissertation is the development of biologically informed models that enhance the identification of causal pathways linking genetic variants to neuroanatomical changes and clinical outcomes. In this dissertation, we integrate brain imaging genomics data to create a genetically informed brain atlas for enhancing the discovery power for brain imaging genomics studies. With the development of the structural Bayesian factor analysis model, we further add the molecular multiomics data besides the brain imaging genomics to discover the common informative information for AD diagnosis. To establish the putative causal pathways for AD from genomics to molecular signatures, to neuroimaging biomarkers, and eventually to AD onset, we further investigate a brain-wide genome-wide colocalization framework to integrate GWAS, tissue-specific gene expression, and imaging biomarkers. The findings underscore the importance of integrating diverse data modalities and incorporating domain knowledge to improve precision in AD biomarker discovery and risk prediction. Looking forward, future directions encompass extending our integrative framework to address the problem of complex chronic diseases and multimorbidity by developing scalable deep learning and large language models for multi-modal integration, refining advanced imputation methods to manage incomplete data, and incorporating spatial and single-cell multi-omics data. These strategies promise to unravel the complex biological networks underlying complex chronic diseases and their co-occurring chronic conditions, thereby paving the way for more personalized diagnostics and targeted therapeutic interventions.