Rational drug design for Alzheimer's disease: from approved therapies to next-generation clinical candidates and AI-guided innovation.
TL;DR
The incorporation of artificial intelligence (AI) and machine learning (ML) is expected to enhance the prediction of pharmacokinetic, pharmacodynamic, and toxicity parameters in AD drug design.
Abstract
Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by multifactorial pathology, including amyloid-β (Aβ) aggregation, tau hyperphosphorylation, oxidative stress, neuroinflammation, and synaptic dysfunction. Despite extensive research, currently approved treatment provides only symptomatic relief, while recently approved disease-modifying monoclonal antibodies have shown limited benefits. Ongoing clinical investigations have shifted toward multi-target directed ligands (MTDLs), RNA-based therapies, immunotherapies, and vaccines. Some approved drugs that have established safety profiles are being repurposed to address the disease's neuropsychiatric symptoms or modulate AD pathological changes. Integrating diverse pharmacophores, such as curcumin, resveratrol, chromone, and indole, within a single skeleton is anticipated to exert multi-modal modifying properties. In parallel, optimization of ADME properties, particularly blood-brain barrier (BBB) permeation and efflux modulation, remains a major obstacle in AD drug design. The incorporation of artificial intelligence (AI) and machine learning (ML) is expected to enhance the prediction of pharmacokinetic, pharmacodynamic, and toxicity parameters.