First Generative AI-Discovered Drug Advances to Phase III Human Studies

Insilico Medicine has dosed the first patient in GENESIS-IPF-3 (NCT07687459; CTR20262475), a Phase III study evaluating rentosertib, also known as ISM001-055 or INS018_055, in patients with IPF. The first patient was dosed at Peking Union Medical College Hospital, while Shanghai Pulmonary Hospital enrolled its first patient on the same day. Insilico describes rentosertib as the world’s first drug candidate discovered and developed using generative AI, with AI used to identify its target and support the design of the molecule.

Unlike a conventional drug-development story in which AI is used primarily to optimize established discovery processes, rentosertib represents an end-to-end AI-enabled program that moved from target identification and molecular design into human clinical testing and now Phase III development.

GENESIS-IPF-3 to Evaluate Rentosertib Over 52 Weeks

GENESIS-IPF-3 is a prospective, multicenter, randomized, double-blind, placebo-controlled, parallel-group Phase III trial designed to evaluate the efficacy and safety of once-daily oral rentosertib over 52 weeks.

The study is expected to enroll 320 participants across 47 centers in China. The primary endpoint is the annual rate of decline in forced vital capacity (FVC) over 52 weeks, while a key secondary endpoint is the time to first occurrence of a disease-progression event.

Prof. Zuojun Xu of Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, is the Leading Principal Investigator. Academician Nanshan Zhong and President Chang Chen of Shanghai Pulmonary Hospital are serving as Co-Leading Principal Investigators.

The Phase III study follows a 12-week Phase IIa trial in 71 patients with IPF. That study reported a promising dose-dependent lung-function signal, with the 60-mg once-daily group showing a mean FVC change of +98.4 mL at 12 weeks compared with a decline of 20.3 mL in the placebo group. The Phase IIa findings provided the basis for evaluating rentosertib in a larger population and over a longer treatment period.

Targeting TNIK in IPF

Rentosertib is a potentially first-in-class small molecule targeting TRAF2- and NCK-interacting kinase (TNIK). Insilico identified TNIK through its AI-enabled biology platform and subsequently used generative chemistry to design and optimize the drug candidate.

The development hypothesis is that TNIK signaling contributes to pathological fibrosis and that inhibiting the kinase could potentially modify the fibrotic process. This mechanism remains investigational and is now being tested in a larger clinical population.

The U.S. Food and Drug Administration granted rentosertib Orphan Drug Designation for IPF in February 2023.

IPF is a progressive and irreversible scarring lung disease affecting approximately 5 million people worldwide. Median survival is reported at approximately three to four years. Existing antifibrotic therapies can slow lung-function decline but do not reverse established fibrosis, leaving a substantial need for additional treatment approaches.

The rentosertib program has been documented in peer-reviewed publications spanning AI-driven discovery, medicinal chemistry and Phase IIa clinical development. A 2026 Nature Biotechnology study also reported reductions in predicted biological age across six proteomic aging-clock models following rentosertib treatment.

With GENESIS-IPF-3 now underway, the key question is whether the promising clinical signals observed in Phase IIa can translate into clinically meaningful benefits during longer-term treatment. Rentosertib remains investigational and has not been approved by any regulatory authority.

Reference

Insilico Medicine Doses First Patient in GENESIS-IPF-3, the World’s First Phase III Trial of a Generative AI-Driven Innovative Drug, Insilico Medicine, 10 September 2026