Phase 2a results for a drug whose target and molecule both came from AI
Phase 2a results for a drug whose target and molecule both came from AI is graded peer reviewed on whataifound.org, with the AI's role graded search scaffold.
Rentosertib, a TNIK inhibitor whose target was picked by one AI system and whose molecule was generated by another, improved forced vital capacity by 98.4 mL at the top dose against a 20.3 mL decline on placebo in a 71-patient randomised trial.
- Verification
- Peer reviewed
- Autonomy
- Search scaffold
- Lab
- Insilico Medicine
- Model
- PandaOmics (target) + Chemistry42 (molecule)
- Field
- Medicine
- Date
- 2025-06-03
What was found
TNIK was prioritised as a fibrosis target by PandaOmics from omics and literature data; the inhibitor was generated and optimised by Chemistry42. GENESIS-IPF was a 12-week double-blind placebo-controlled Phase 2a across 22 sites in China, randomising 71 idiopathic pulmonary fibrosis patients across placebo and three dose arms. The 60 mg once-daily arm showed the largest lung-function improvement, and the drug was generally well tolerated. Published in Nature Medicine.
Novelty check
AI-generated molecules had reached the clinic before, and AI-nominated targets had been published before, but this is the first randomised placebo-controlled efficacy signal for a compound where both the target and the molecule came from generative systems. TNIK's role in fibrosis was not an established target hypothesis when it was nominated.
Caveats
Phase 2a is small, short and exploratory: 71 patients over 12 weeks, single-country sites, not powered for efficacy, with FVC change over 12 weeks not a registrational endpoint. The sponsor designed, ran, analysed and published the trial. "AI-discovered" covers target selection and generative chemistry; the medicinal chemistry, preclinical work and trial conduct were conventional. A Phase 3 was subsequently initiated, which does not retrospectively strengthen this readout.
Sources
How this is graded
whataifound.org grades every entry on two axes: verification (how solid the result is, from a machine-checked proof down to refuted) and autonomy (how much the AI did versus its human collaborators). This finding is peer reviewed and search scaffold. Full definitions are in the methodology.
Cite this entry
whataifound.org (2025). Phase 2a results for a drug whose target and molecule both came from AI. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2025-06-03-rentosertib-phase2a