Integrative Multi-Omics and Machine Learning Analysis Identifies Therapeutic Targets and Drug Repurposing Candidates for Alzheimer’s Disease

Background/Objectives: Alzheimer’s disease (AD) remains a progressive neurodegenerative disorder with limited therapeutic options. This study aimed to develop an integrative multi-omics computational pipeline to identify diagnostic biomarkers and prioritize druggable therapeutic targets for AD. Methods: We integrated transcriptomic data from 1047 samples (547 AD, 500 controls) using weighted gene co-expression network analysis (WGCNA) and three machine learning algorithms (LASSO, Random Forest, SVM) with strict separation of training, feature selection, and evaluation. Single-cell RNA sequencing of 48,481 nuclei from entorhinal cortex, two-sample Mendelian randomization (MR) with Bayesian colocalization, and structure-based molecular docking with triplicate 500 ns molecular dynamics (MD) simulations were also employed. Results: Machine learning identified 10 consensus biomarker genes involved in synaptic vesicle cycling, ion transport, and calcium homeostasis (internal test AUC = 0.891, 95% CI: 0.836–0.946; external validation on GSE48350: AUC = 0.847, 95% CI: 0.798–0.896). Covariate-adjusted differential expression and MR with Bayesian colocalization converged on eight immune-related therapeutic targets including APOE, TREM2, and TYROBP (p<0.05; Bonferroni-corrected threshold p<0.00625). Single-cell analysis revealed oligodendrocyte expansion in AD (28.5% versus 24.8%), with target genes predominantly expressed in microglia and astrocytes. Virtual screening of 2634 FDA-approved drugs prioritized 10 exploratory repurposing candidates; indomethacin–TREM2 and celecoxib–CSF1R are primary exploratory candidates given structurally validated binding pockets. Triplicate MD simulations (15 μs aggregate) showed force-field-consistent structural stability (RMSD ≤ 3.2 Å). A quantitative multi-omics convergence framework identified four Tier 1 targets (APOE, TREM2, TYROBP, CX3CR1) supported by ≥5 analytical layers (Pperm=0.0003; note: three of five layers share the same transcriptomic input). Conclusions: These findings provide a multi-evidence computational framework linking diagnostic biomarkers and druggable neuroinflammatory targets for AD. All predictions require experimental validation in biochemical and cellular models before clinical conclusions can be drawn.