AI-assisted multi-OMICS analysis reveals new markers for the prediction of AD.

Alzheimer's Disease (AD) is the most prevalent neurodegenerative disorder, characterized by progressive cognitive decline. Early and accurate diagnosis is crucial for improving patient outcomes, yet current diagnostic methods remain invasive, costly, and limited in accessibility. This study leverages artificial intelligence (AI) and machine learning approaches to perform a multi-omics analysis, integrating proteomics and transcriptomics data to identify potential biomarkers for early AD prediction. Using multiple AD-related databases and AI-powered literature review tools, we extracted and analyzed gene expression profiles from various tissues, including brain, cerebrospinal fluid (CSF), and plasma. A protein-protein interaction (PPI) network was reconstructed to determine key hub genes using centrality analysis. Our findings revealed 13 common hub genes, including APP, YWHAE, YWHAH, SOD1, UQCRFS1, ATP5F1B, AP2M1, MMAB, INA, RPL6, HADHB, CD63, and CTNNB1, that are significantly implicated in both early and advanced AD. Furthermore, pathway enrichment analysis identified critical pathways such as oxidative phosphorylation, metabolic pathways, and synaptic transmission, which are associated with AD progression. Additionally, nine common miRNAs and eight key molecular axes were determined, highlighting potential mechanistic links between early and advanced AD. These findings offer novel insights into AD pathophysiology and provide a foundation for developing non-invasive biomarkers for early detection. Future experimental validation of these biomarkers is essential to translate these findings into clinical applications.