Insilico Medicine has initiated a Phase III clinical trial for Rentosertib, a potentially first-in-class oral small-molecule inhibitor targeting TNIK for the treatment of idiopathic pulmonary fibrosis (IPF). The trial represents a significant milestone in AI-driven drug discovery, advancing a medicine whose target and chemical structure were identified using generative AI. The study aims to address the high unmet medical need in IPF, a progressive, age-related fibrotic lung disease with limited treatment options.

Rentosertib, formerly known as ISM001-055 / INS018_055, was discovered and designed through Insilico's Pharma.AI platform. The program integrates a novel fibrosis target prioritized by Biology42: PandaOmics and a small molecule generated via Chemistry42. The discovery-to-clinic path was documented in Nature Biotechnology, while Phase IIa results were published in Nature Medicine. The upcoming Phase III trial is a prospective, randomized, double-blind, placebo-controlled, parallel-group study expected to enroll 320 patients with IPF.

Phase IIa Results and Rationale

The GENESIS-IPF Phase IIa study demonstrated manageable safety and tolerability, with the 60 mg once-daily arm showing a mean forced vital capacity (FVC) improvement of +98.4 mL at 12 weeks, compared to -20.3 mL in the placebo group. These results provided the confidence to proceed with larger-scale testing. The Phase III trial will assess whether the safety profile and lung-function signal observed in Phase IIa can translate into clinically meaningful benefit.

Trial Design and Leadership

The Phase III trial will be led by Professor Zuojun Xu of Peking Union Medical College Hospital as the Leading Principal Investigator. Academician Nanshan Zhong and President Chang Chen of Shanghai Pulmonary Hospital will serve as Co-Leading Principal Investigators. The study is designed to systematically evaluate the efficacy and safety of once-daily Rentosertib administered over 52 weeks across 47 centers in China. The primary endpoint is the annual rate of decline in FVC, with a key secondary endpoint measuring time to first disease progression event.

Scientific and Pipeline Context

TNIK is a serine/threonine kinase implicated in fibrosis-driving and inflammation-related pathways. Insilico identified TNIK as a high-priority target using PandaOmics by integrating multi-omics data and aging-relevant target scoring. Rentosertib is the lead program in Insilico's pipeline, which includes 31 preclinical candidate nominations, 13 IND clearances, and 8 ongoing Phase I trials. The company's end-to-end AI platform, Pharma.AI, integrates Biology42, Chemistry42, and Medicine42 to accelerate drug discovery and development.

Insilico Medicine announced a strategic collaboration with Takeda to utilize its proprietary end-to-end platform, Pharma.AI, for advancing drug candidates across Takeda's therapeutic areas. The partnership aims to identify clinically differentiated drug candidates for promising therapeutic targets by using advanced generative models from the earliest stages of design. This collaboration is designed to improve the quality of candidate molecules and optimize them to achieve best-in-class efficacy and safety criteria.

Under the agreement, Insilico will lead AI-driven discovery to identify molecules meeting predefined scientific and early development criteria, while Takeda will apply its global development capabilities to advance selected candidates through clinical validation. The agreement grants Takeda exclusive worldwide rights to develop, manufacture, and commercialize novel therapeutics selected through the collaboration.

"I am excited to partner with one of the top leaders in the biopharmaceutical industry with massive competence in generative AI," said Alex Zhavoronkov, Ph.D., founder, CEO and CBO of Insilico Medicine. "As we deepen the integration of generative AI into every stage of the pharma value chain, I believe the future of pharmaceutical superintelligence has the potential to deliver the highest quality and differentiated drugs. This is a fundamental step on our journey toward extension of healthy productive life."

"By combining Takeda's deep disease biology expertise with Insilico's AI-enabled discovery capabilities, this collaboration seeks to deliver meaningful treatment options for patients by identifying clinically differentiated therapies," said Chris Arendt, Ph.D., Chief Scientific Officer and Head of Research at Takeda. "The partnership also supports Takeda's transition to an AI-native discovery model, as we integrate automation, robotics, and generative AI to advance high-quality candidates more efficiently."

Financial Terms

The financial structure of the agreement includes immediate and future payments based on project milestones and success. Insilico stands to receive significant compensation if the collaboration meets its scientific and commercial objectives.

Insilico Medicine is a clinical-stage generative AI drug discovery company listed on the Main Board of the Hong Kong Stock Exchange under the stock code 03696.HK. Takeda is a values-based, R&D-driven biopharmaceutical company headquartered in Japan.