Abstract
Mitochondrial dysfunction is implicated across a spectrum of neurological diseases, yet its causal role and mechanistic specificity remain unclear. This study employed a multi-modal integrative analysis of mitochondrial gene expression in Alzheimer's Disease (AD), Amyotrophic Lateral Sclerosis (ALS), Multiple Sclerosis (MS), and Parkinson's Disease (PD) to address these gaps. We combined machine learning for predictive modeling with genetic causal inference methods (Mendelian Randomization, colocalization, PheWAS), followed by drug enrichment analysis and molecular docking. Our machine learning models, particularly Support Vector Machine and Multi-layer Perceptron, effectively classified these conditions, with MS exhibiting the highest predictability (mean Accuracy: 0.758). Causal inference analyses identified specific gene-disease links; for instance, genetically predicted increased expression of PDK1 was causally associated with an elevated risk for both AD (OR = 1.041) and ALS (OR = 1.037), identifying pyruvate metabolism as a shared vulnerability. In contrast, genes like SLC25A38 emerged as highly predictive specifically for PD. We also observed evidence of potential brain-periphery interaction, such as a bidirectional causal relationship between red blood cell indices and MS risk. Finally, drug enrichment analysis highlighted Celecoxib, and subsequent molecular docking predicted a strong binding affinity to PDK1 (docking score S = -6.522 kcal/mol), generating hypotheses for potential metabolic modulation. Taken together, this study provides a computational hypothesis framework suggesting mitochondrial pathways and targets that warrant future biological validation. This study provides specific, genetically supported evidence for the causal role of mitochondrial pathways in neurological diseases and identifies tangible targets for future therapeutic development.