AI-enabled drug repurposing in Alzheimer’s disease: from computational nomination to pharmacological proof
- 1School of Health and Life Sciences, Teesside University
- 2The Elton Laboratory for Molecular Neuroendocrinology, Department of Human Genetics and Computational Medicine, Gray Faculty of Medical and Health Sciences, Sagol School of Neuroscience and Adams Super Center for Brain Studies, Tel Aviv University
Abstract
Artificial intelligence (AI) has expanded the scale and speed of drug repurposing in Alzheimer’s disease (AD). Transcriptomic signature matching, network-based systems pharmacology, real-world data pharmacoepidemiology and multi-omics machine learning have generated hundreds of candidate drugs, while repurposed agents account for 35% (56 of 158) of drugs and 42% (15 of 36) of Phase 3 agents in the 2026 AD pipeline. Clinical translation, however, remains unproven. Randomised trials of GLP-1 receptor agonists illustrate the gap between prioritisation and therapeutic proof: semaglutide did not slow clinical progression in evoke and evoke+, while liraglutide did not improve the primary FDG-PET endpoint in ELAD. We examine four complementary evidence domains, defining what each can and cannot establish, and position large language models as a cross-cutting tool for evidence synthesis and knowledge-graph reasoning rather than an independent source of biological evidence. Rather than cataloguing methods and candidates, we appraise leading drugs at the individual-molecule level and propose explicit criteria for progression from computational nomination to clinical testing. The framework defines seven requirements for clinical progression: disease-stage matching, adequate site-of-action exposure, including CNS exposure for central mechanisms, mechanistic validation in human-relevant models, biomarker-stratified trial design, convergence across independent evidence domains, causal inference with explicit boundary conditions, and mechanism-aligned endpoints with predefined stopping rules. AI has improved candidate prioritisation in AD, but clinical value will depend on converting ranked hypotheses into pharmacologically plausible and prospectively testable programmes.
Related
- Senescence-Associated Transcriptome Reversal Prioritizes Repurposing Candidates for Diabetic Kidney Disease: A Computational Study
- Nutritional profiling and pharmacological investigation of Baccaurea motleyana peel and seed through experimental and computational approach
- Gastrodin alleviates mild cognitive impairment and Alzheimer’s disease via candidate targeting of ACHE, S1PR5, SERPINE1, and TOP2A: an integrative computational and cellular study
- Disease-associated myeloid states in cardiac remodeling: A new era of cardiac inflammation research enabled by computational biology.
- 3D-Fiber Mapping in Biological Tissues with Computational Scattered Light Imaging Enabled Through 3D-Nanoprinting.
BibTeX
@article{li2026aienabled,
title = {{AI-enabled drug repurposing in Alzheimer’s disease: from computational nomination to pharmacological proof}},
author = {Xinzhong Li and Illana Gozes},
journal = {Frontiers in Pharmacology},
year = {2026},
month = oct,
doi = {10.3389/fphar.2026.1999276},
url = {https://www.frontiersin.org/articles/10.3389/fphar.2026.1999276/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - AI-enabled drug repurposing in Alzheimer’s disease: from computational nomination to pharmacological proof
AU - Xinzhong Li
AU - Illana Gozes
PY - 2026
DA - 2026/10/28
JO - Frontiers in Pharmacology
DO - 10.3389/fphar.2026.1999276
UR - https://www.frontiersin.org/articles/10.3389/fphar.2026.1999276/full
AB - Artificial intelligence (AI) has expanded the scale and speed of drug repurposing in Alzheimer’s disease (AD). Transcriptomic signature matching, network-based systems pharmacology, real-world data pharmacoepidemiology and multi-omics machine learning have generated hundreds of candidate drugs, while repurposed agents account for 35% (56 of 158) of drugs and 42% (15 of 36) of Phase 3 agents in the 2026 AD pipeline. Clinical translation, however, remains unproven. Randomised trials of GLP-1 receptor agonists illustrate the gap between prioritisation and therapeutic proof: semaglutide did not slow clinical progression in evoke and evoke+, while liraglutide did not improve the primary FDG-PET endpoint in ELAD. We examine four complementary evidence domains, defining what each can and cannot establish, and position large language models as a cross-cutting tool for evidence synthesis and knowledge-graph reasoning rather than an independent source of biological evidence. Rather than cataloguing methods and candidates, we appraise leading drugs at the individual-molecule level and propose explicit criteria for progression from computational nomination to clinical testing. The framework defines seven requirements for clinical progression: disease-stage matching, adequate site-of-action exposure, including CNS exposure for central mechanisms, mechanistic validation in human-relevant models, biomarker-stratified trial design, convergence across independent evidence domains, causal inference with explicit boundary conditions, and mechanism-aligned endpoints with predefined stopping rules. AI has improved candidate prioritisation in AD, but clinical value will depend on converting ranked hypotheses into pharmacologically plausible and prospectively testable programmes.
SN - 1663-9812
ER -