Discovery of senolytics using machine learning
Problem
Only a few senolytics (drugs eliminating senescent cells) are known, and experimental screening for new ones is costly.
Why it matters
Senescent cells drive ageing and diseases including cancer, type-2 diabetes, and osteoarthritis, yet drug discovery is expensive.
What the AI did
Machine learning trained solely on published screening data computationally screened chemical libraries, yielding three candidate senolytics that were validated in human cell lines.
Results
Three senolytics (ginkgetin, periplocin, oleandrin) validated in human cell lines across senescence modalities; potency comparable to known senolytics; several hundred-fold reduction in screening costs.
Impact
AI-driven screening produced validated senolytic candidates at a fraction of conventional screening cost.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Vanessa Smer-Barreto, Andrea Quintanilla, Richard J. R. Elliott, John C. Dawson, Jiugeng Sun, Víctor M. Campa, Álvaro Lorente‐Macías, Asier Unciti‐Broceta et al. |
| Citations | 130 (OpenAlex, at import time) |
| References | 81 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-023-39120-1 |
| Open access | gold |
| Keywords | senolytics, senescence, drug discovery, machine learning, oleandrin |
Importance rating
major — millions of lives, an industry or a field
Abstract states senescence is involved in ageing and diverse diseases including cancer, type-2 diabetes, osteoarthritis, and viral infection; senolytic discovery targets major age-related disease burden, though no numbers given.