Lungs and chest · Drug discovery
An AI-designed drug for lung scarring (rentosertib)
Rentosertib, a drug whose target and molecule were found using generative AI by Insilico Medicine, was tested in 71 people with idiopathic pulmonary fibrosis in a 12-week phase 2a trial. It looked safe enough to keep testing, though some people stopped because of liver problems or diarrhoea. Lung function (FVC) improved at the top dose, but that was an exploratory measure in a small, short, company-run safety trial in China only. It's years from approval.
How far away is this?
It's in registered human trials (NCT05938920), but only a small, short, early-phase one. Larger, longer trials are needed.
Where is it approved?
| Region | Regulator | Status | Notes |
|---|---|---|---|
| United States | FDA | Not approved | Phase 2a trial only; no marketing approval. |
| European Union | CE mark / EMA | Not approved | Phase 2a trial only; no marketing approval. |
| United Kingdom | MHRA | Not approved | Phase 2a trial only; no marketing approval. |
| Australia | TGA | Not approved | Phase 2a trial only; no marketing approval. |
Not approved anywhere. The phase 2a trial was run at sites in China. "Unknown" means we haven't verified it, not that it's unavailable. Approval in one country isn't approval in another.
What is it?
Idiopathic pulmonary fibrosis (IPF) is scarring of the lungs that gets worse over time. Insilico used AI to pick a new drug target (a protein called TNIK) and to design a molecule to block it.
What's the evidence?
The randomised, double-blind, placebo-controlled phase 2a trial enrolled 71 patients for 12 weeks (published in Nature Medicine, June 2025).[1]
Evidence stage: In clinical trials · #c1
The main goal was safety: rates of side effects were similar across drug and placebo groups. Discontinuations were most often due to liver problems or diarrhoea.[2]
Evidence stage: In clinical trials · #c2
At the highest dose (60 mg once daily), lung capacity (FVC) rose by an average 98.4 mL versus a 20.3 mL fall on placebo. Groups were small (about 18 people each), so this is a signal, not proof.[1]
Evidence stage: In clinical trials · #c3
The trial was run by the company that developed the drug: ClinicalTrials.gov lists InSilico Medicine Hong Kong Limited as lead sponsor.[3]
Evidence stage: In clinical trials · #c4
What does it mean for me?
If you or someone you love has IPF, this isn't a treatment you can get. It's one of the first signs that AI-discovered drugs can make it into patient trials.
What could I ask my doctor?
- Are there clinical trials for IPF I might be eligible for where I live?
- What treatments are available for me now?
- How would I know if a trial is legitimate?
These are general starting points, not a recommendation to choose any particular test or treatment.
Change history
- : First published.
- : Updated after independent fact-check and clinical review
- : Review label corrected: this page was not clinically reviewed. Earlier labels saying 'independent fact-check' and 'clinical review' were wrong; checks so far were AI-assisted source checks only.
General information only, not medical advice. Talk to your doctor about your situation. AI-assisted source check. Not clinically reviewed.
References
- Xu et al., Nature Medicine (2025). nature.com (2025). Peer-reviewed randomised trial. https://www.nature.com/articles/s41591-025-03743-2
- PubMed 40461817. pubmed.ncbi.nlm.nih.gov. Abstract. https://pubmed.ncbi.nlm.nih.gov/40461817/
- ClinicalTrials.gov NCT05938920. clinicaltrials.gov. Trial registry. https://clinicaltrials.gov/study/NCT05938920
- Insilico Medicine announcement. insilico.com. Company document (claim). https://insilico.com/news/tnrecuxsc1-insilico-announces-nature-medicine-publi
Publisher shown as the website hosting each source. Dates are given where the source label includes them.