An experimental drug created with the help of artificial intelligence has shown early signs of reversing biological aging in a small clinical trial, according to findings published this week in the journal Nature Biotechnology.
The drug, called rentosertib, was developed by Insilico Medicine, a biotechnology company that uses AI to design molecular structures for potential treatments. Researchers tested the drug on 42 patients with idiopathic pulmonary fibrosis, a progressive lung disease, over a 12-week period. Using six different AI-based «aging clocks» — tools that estimate how quickly a person's body is aging based on biological, physiological, and psychological markers — the scientists found that all six clocks predicted lower biological ages for every participant at the end of the trial compared with their starting measurements.
Participants who received a placebo or no treatment saw their predicted ages either increase or remain unchanged during the same period. The results offer a glimpse of what could become a new class of therapies aimed not at a single disease but at the underlying process of aging itself.
The concept of using AI to accelerate drug discovery has generated considerable excitement in the medical and technology communities. Executives such as OpenAI CEO Sam Altman and Anthropic CEO Dario Amodei have publicly speculated about AI-driven cures for major diseases, though no such breakthrough has yet reached the market. Rentosertib represents one of the more concrete advances in this direction, with the AI assistance used specifically in designing the drug's molecular structure.
However, researchers caution that the results should be interpreted carefully. The scientific community remains divided over the accuracy and usefulness of aging clocks, and there is no universally agreed-upon method for measuring biological age. The trial was also designed primarily to test rentosertib as a treatment for idiopathic pulmonary fibrosis, meaning all participants had that condition; the drug has not yet been studied in healthy individuals.
The sample size was small and highly specific, which limits how broadly the findings can be applied. Even if the drug proves effective in larger studies, it remains years away from regulatory approval. Insilico Medicine has not yet announced plans for follow-up trials in healthy populations, and questions about long-term safety and efficacy remain unanswered.
Despite these caveats, the publication in a peer-reviewed journal marks a notable step for AI-assisted drug development. If further research confirms that rentosertib can meaningfully slow or reverse biological aging, the implications would extend far beyond the lung disease it was originally designed to treat. For now, the results offer a cautious reason for optimism — and a reminder that the promised era of AI-driven medicine may be closer than it appears.