Insilico Medicine has achieved a significant milestone in AI-driven drug discovery with the publication of Phase IIa results for Rentosertib, a novel TNIK inhibitor for idiopathic pulmonary fibrosis (IPF), in Nature Medicine. The study represents the first clinical proof-of-concept validation of a drug where both the target identification and molecular design were powered by artificial intelligence.
Clinical Trial Results Demonstrate Efficacy
The Phase IIa GENESIS-IPF trial, a double-blind, placebo-controlled study, enrolled 71 patients with IPF across 22 sites in China. Participants were randomly assigned to receive either placebo, 30 mg Rentosertib once daily, 30 mg twice daily, or 60 mg once daily for 12 weeks.
The results showed that patients receiving 60 mg daily of Rentosertib experienced the greatest mean improvement in lung function, with a mean forced vital capacity (FVC) increase of +98.4 mL compared to a mean decline of -20.3 mL in the placebo group. This dose-dependent improvement in FVC, the gold-standard metric for assessing lung function in IPF patients, represents a promising secondary efficacy endpoint.
Safety Profile and Tolerability
Rentosertib met its primary endpoint of safety and tolerability across all treatment groups. The drug exhibited a manageable safety profile with similar rates of treatment-emergent adverse events observed across all dosage levels. Most adverse events were mild to moderate in severity, with serious adverse events being rare. Notably, all adverse events resolved following discontinuation of treatment.
Biomarker Analysis Validates Mechanism
Exploratory biomarker analyses provided additional validation of Rentosertib's biological mechanism. The study revealed dose- and time-dependent changes in serum protein levels after 12 weeks of treatment, supporting the drug's anti-fibrotic and anti-inflammatory effects. In the high-dose group, profibrotic proteins such as COL1A1, MMP10, and FAP were significantly reduced, while the anti-inflammatory marker IL-10 was increased. These protein changes correlated with improvements in FVC.
AI-Driven Discovery Process
The development of Rentosertib began with Insilico Medicine's PandaOmics platform, which analyzed extensive datasets to identify TNIK (TRAF2 and NCK-interacting kinase) as a promising target for IPF treatment. The company's Chemistry42 platform then designed and optimized small-molecule compounds targeting TNIK, ultimately leading to Rentosertib's nomination as a preclinical candidate.
This AI-driven approach significantly accelerated the drug discovery timeline, reducing the process from target identification to preclinical candidate selection to just 18 months. According to the company, their 22 nominated candidate drugs from 2021 to 2024 took only 12-18 months on average to progress from project initiation to nomination of preclinical candidates, compared to the typical 2.5-4 years required in traditional drug discovery.
Regulatory Path Forward
Following these encouraging Phase IIa results, Insilico Medicine has begun discussions with regulatory authorities to facilitate the evaluation of Rentosertib in larger cohorts of patients. The company is engaging with global regulatory authorities to initiate larger pivotal trials.
"These results not only suggest that Rentosertib has a manageable safety and tolerability profile, but also warrants further investigation in larger-scale clinical trials of longer duration, demonstrating the transformative potential of AI in drug discovery and development," said Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine.
Disease Background and Unmet Need
Idiopathic pulmonary fibrosis is a chronic, scarring lung disease characterized by progressive and irreversible decline in lung function. The condition affects approximately 5 million people worldwide and carries a poor prognosis, with a median survival of 3 to 4 years. Current approved treatments, including antifibrotic drugs, can slow disease progression but do not stop or reverse it, leaving a significant unmet need for more effective, disease-modifying therapies.
The United States Adopted Names Council has officially named the compound Rentosertib, making it the first drug in which both the target and compound were identified through generative AI. If successful in larger trials, Rentosertib could become the first AI-discovered therapy to reach patients, potentially transforming the treatment landscape for IPF.
