September 8, 2026, (Inside AI) — A drug candidate designed with artificial intelligence has shown early signs of reducing biological age in patients with a chronic lung disease. The molecule, called rentosertib, lowered age markers across six different AI-powered aging clocks during a clinical trial run by Insilico Medicine.
The results appeared Monday in Nature Biotechnology. They mark one of the first times a clinical trial has linked an AI-generated drug to measurable reductions in predicted biological age. The trial involved 43 patients with idiopathic pulmonary fibrosis, or IPF, a scarring lung disease that can be fatal within years.
Insilico, founded in 2014 by Alex Zhavoronkov, built rentosertib using two neural network systems. One analyzed health records, blood proteins, and academic papers to identify disease targets. The other generated new molecular structures that could bind to those targets and neutralize them.
"It is like scanning a lock and generating a key that fits the lock," Zhavoronkov said in an interview.
The new analysis focused on aging clocks, AI models that estimate biological age from cellular and organ function. After 12 weeks of treatment, all six clocks showed reductions in predicted age for the IPF patients.
"This is the first study that shows, very clearly, that predicted biological age can be reduced," Vadim Gladyshev, a Harvard Medical School professor who helped build one of these aging clocks.
Gladyshev cautioned that the sample was small and aging clocks are not always reliable. The drug has not been tested in healthy people, so the effect may be specific to IPF patients.
"This drug looks encouraging," Eric Topol, a cardiologist and the author of the book "Super Agers." "But we do not yet have a definitive trial to make the final judgment."
Rentosertib is still years away from regulatory approval, even for IPF. But some longevity researchers see the trial design as a template for future studies.
"These are methods we will use in future trials," Evelyne Bischof, a professor of medicine at Tel Aviv University who specializes in longevity.
The trial underscores a broader shift. AI techniques behind chatbots and image generators are now accelerating drug discovery and longevity research. Insilico is one of many companies using neural networks to identify disease proteins and design new molecules.
Still, the gap between biological age reduction and real-world health outcomes remains wide. Aging clocks are predictive tools, not direct measures of lifespan extension. No trial has yet shown that lowering a clock score translates into longer, healthier lives.
Insilico's approach could accelerate early-stage drug development. But the company must still prove rentosertib's safety and efficacy in larger, more diverse populations. The anti-aging claim, for now, rests on a single small study in sick patients.
The IPF trial itself showed the drug could expand lung air capacity. That was the primary endpoint. The aging clock analysis was a secondary, exploratory measure.
The findings arrive as regulators and researchers debate how to validate AI-derived drugs. The U.S. Food and Drug Administration has not yet established formal guidelines for aging clocks as clinical endpoints.
Insilico's dual-system approach mirrors techniques used by other AI drug discovery firms. But the company's willingness to publish aging clock data sets it apart, even if the clinical meaning remains uncertain.
