Alzheimer’s Disease (AD) is a neurodegenerative disease and the leading form of dementia around the world. While significant research has gone into understanding its pathogenesis and developing potential therapeutics, effective treatments remain limited, and many aspects of its pathophysiology are still not fully understood. To identify the molecular changes related to the progression of Alzheimer’s Disease, recent research has utilized “omics” approaches, where hundreds or thousands of molecules (e.g., transcripts, proteins, metabolites) can be measured simultaneously. This research has identified certain genes and proteins as potential biomarkers of AD. However, the high-dimensionality and complexity of these data often preclude further interrogation by standard statistical analysis methods. As such, there is a necessity for the development of computational tools that can make accurate and robust predictions from these data.

This Topical Collection includes computational tools for omics data analysis, including machine learning and artificial intelligence models and their applications, multi-omics integration frameworks, and feature selection/biomarker discovery workflows. We also welcome methods focused on statistical and network-based analysis, pathway analysis, longitudinal and time-series analysis, causal inference, model interpretation, and robustness assessment. The goal of these methodological advances is to improve the analysis, visualization, and interpretability of omics datasets and advance our understanding of the molecular mechanisms underlying AD.