Drug Discovery & Research

AI-Designed Drug Reaches Landmark Phase III Trial for Fatal Lung Disease

Insilico Medicine's rentosertib becomes the first AI-developed therapeutic to enter late-stage testing for idiopathic pulmonary fibrosis, a condition with few treatment options and a median survival of just 3-4 years.

2 min read
HA
Health AI Central Editorial Team
Editorial standards & disclosures
September 28, 2026
2 min read
Share:
AI-Designed Drug Reaches Landmark Phase III Trial for Fatal Lung Disease

Artificial intelligence has moved from the laboratory to the clinic in a significant milestone for computational drug discovery. Insilico Medicine has dosed the first patient in a Phase III trial of rentosertib, an AI-designed drug targeting idiopathic pulmonary fibrosis (IPF), marking the first time an AI-developed therapeutic has reached this advanced stage of clinical testing. The trial, which began September 10 in China, will enroll 320 patients across 47 medical centers to evaluate whether the drug can improve lung function in a disease that affects approximately 5 million people worldwide.

A New Approach to a Deadly Disease

Idiopathic pulmonary fibrosis is a progressive and fatal lung condition with a median survival of just 3-4 years following diagnosis. Current treatments can slow the disease's progression but cannot restore lost lung function, leaving patients with severely limited therapeutic options. Rentosertib represents a potential shift in this landscape, with Phase II data suggesting the drug may actually improve lung capacity rather than merely delay decline.

In the earlier Phase II study involving 71 patients, those receiving the highest dose of rentosertib gained an average of 98.4 ml in lung capacity over 12 weeks, while patients in the placebo group experienced a decline. The upcoming Phase III trial will extend treatment to 12 months of daily dosing, providing a more comprehensive assessment of the drug's efficacy and safety profile.

Validating the AI Drug Discovery Model

Insilico Medicine's achievement comes as the AI drug discovery sector seeks to demonstrate that computational approaches can deliver clinically viable candidates, not just promising molecules. The company has built a pipeline that extends beyond rentosertib: in January, it dosed the first patient with garutadustat for inflammatory bowel diseases, moving from program initiation to preclinical candidate selection in just 12 months while synthesizing approximately 115 compounds.

The broader industry context suggests momentum is building. More than 170 AI-created molecules are currently in various stages of clinical trials, and Generate:Biomedicines is conducting two Phase III trials of GB-0895, an antibody for severe asthma, with plans to enroll approximately 1,600 participants. These developments indicate that AI-designed therapeutics are transitioning from experimental curiosities to serious contenders in pharmaceutical development.

Implications for Patients and the Industry

For patients with IPF, rentosertib's progression to Phase III testing offers hope for a disease-modifying therapy that could restore function rather than simply slow deterioration. For the AI drug discovery sector, this milestone provides critical validation that computational approaches can produce candidates capable of advancing through the rigorous clinical trial process. The trial's results, expected after the 12-month dosing period concludes, will offer important insights into whether AI-designed drugs can deliver on their promise of faster, more efficient therapeutic development for complex diseases with significant unmet medical needs.

Sources

  1. China starts Phase III trial of AI drug for pulmonary fibrosis — ua.news

Companies in this article

Reporting & accountability

How we maintain accuracy

Health AI Central separates reported facts, analysis, and public-source data. Readers can review our standards, request a correction, or consult the relevant research methodology before relying on a claim.

Share: