AI Identifies Repurposed Drug Candidates for Liver Fibrosis
Stanford geneticist Gary Peltz used Google's Co-Scientist AI to identify existing drugs that could be repurposed to treat liver fibrosis, a condition causing over 1.4 million deaths annually. In a study published in Advanced Science, Peltz asked Co-Scientist to propose three drug candidates and explain its reasoning, while he selected two himself based on literature prominence. All five were tested on live human liver cells. Peltz's picks showed no benefit, but two of Co-Scientist's candidates blocked fibrosis and promoted liver cell regeneration. One had only been linked to fibrosis in a few papers. The standout was cancer drug vorinostat, which blocked 91% of a damage response driving liver scarring. Co-Scientist's suggestions targeted drugs that reshape gene activity rather than single pathways. Peltz argues such drugs could launch a new generation of anti-fibrotic medicines.
Key facts
- Liver fibrosis causes over 1.4 million deaths each year.
- Gary Peltz is a geneticist at Stanford University School of Medicine.
- The research was published in Advanced Science.
- Co-Scientist proposed three drug candidates; Peltz selected two.
- Peltz's two picks showed no benefit against fibrosis.
- Two of Co-Scientist's three candidates blocked fibrosis and promoted liver cell regeneration.
- One Co-Scientist pick had only been linked to fibrosis in a handful of papers.
- Vorinostat blocked 91% of a damage response that can drive liver scarring.
Entities
Institutions
- Stanford University School of Medicine
- Google DeepMind
- Advanced Science
Locations
- Stanford
- United States