Skip to main content
World Today News
  • Home
  • News
  • World
  • Sport
  • Entertainment
  • Business
  • Health
  • Technology
Menu
  • Home
  • News
  • World
  • Sport
  • Entertainment
  • Business
  • Health
  • Technology
AI-Designed Drug Enters Final Human Trial Phase

AI-Designed Drug Enters Final Human Trial Phase

November 17, 2026 Health Desk Health

A drug designed end to end by artificial intelligence has reached Phase III testing — the final stage of human trials — for the first time, Ziarul Lumina reported.

The drug, rentosertib, entered Phase III on July 7, 2026, with 320 patients across 47 medical centers in China.

Key Clinical Takeaways:

  • Rentosertib, developed by Insilico Medicine with algorithms identifying both the drug target and the molecule, is the first AI-designed drug to reach Phase III testing.
  • In a Phase II study of 71 patients published in Nature Medicine in 2025, those taking 60 mg daily gained an average of 98 ml in forced vital capacity after 12 weeks, while the placebo group lost 20 ml.
  • Approval, if the Phase III results hold, could still be three to four years away.

Why the milestone matters

Developing a new medicine takes 10 to 15 years on average and costs more than a billion dollars, Ziarul Lumina reported, citing material produced by the Center for Innovation and e-Health at Carol Davila University of Medicine and Pharmacy in Bucharest. Researchers must identify the mechanism of a disease and a molecule that blocks it without harmful effects; thousands of candidates are screened, and most fail.

Algorithms shorten the search. By analyzing large volumes of data on genes, diseases, and molecules, artificial intelligence can flag plausible therapeutic targets and promising compounds far faster than conventional screening. What it cannot shorten is verification: every candidate still has to be tested for toxicity and efficacy in humans.

How rentosertib was built

The company Insilico Medicine used algorithms to identify the protein TNIK as a possible therapeutic target in pulmonary fibrosis, then to design the molecule that blocks it. That two-step process — machine-discovered target, machine-designed compound — is what makes the drug a test case for the entire approach.

The Phase II results, published in 2025 in Nature Medicine, covered 71 patients. After 12 weeks, participants receiving 60 mg daily recorded a mean increase in forced vital capacity of 98 ml, against a decline of 20 ml in the placebo group. The trial was randomized and placebo-controlled, but Ziarul Lumina reported the caution that such results do not by themselves prove efficacy.

The trial now underway

Phase III began on July 7, 2026, with 320 patients at 47 medical centers in China, followed for one year. It is the first drug designed in this way to reach that stage. The current study can confirm or refute the earlier results; rentosertib is not yet approved, and any approval could come in three to four years.

Where algorithms have helped — and failed

The track record shows both sides. In 2025, the same team designed new molecules against gonorrhea and methicillin-resistant Staphylococcus aureus (MRSA) — but those have so far been tested only in the laboratory and in animals.

The filtering is steep. Of 80 molecules the MIT algorithms proposed against gonorrhea, only two could actually be synthesized, Ziarul Lumina reported. The quality of the data the programs are trained on matters as much as the computing power behind them.

What it changes, and for whom

For drug developers, the Phase III trial is the first real-world test of whether algorithm-driven discovery can survive the full weight of clinical validation — the stage where most candidates, however promising their early data, fail.

For patients with pulmonary fibrosis, a progressive disease in which lung scarring steadily erodes breathing capacity, a positive Phase III result would add a candidate to a therapeutic area with limited options. Nothing is approved yet, and the 98 ml figure from Phase II remains provisional until the larger trial reads out.

The open question

Algorithms accelerate the search for molecules; they do not accelerate the verification. That distinction, drawn by the Bucharest university center’s material, frames what the next year of the Chinese trial will test. The final decision on administering any medicine rests with physicians acting on scientific evidence — and the evidence here is still being gathered.


Disclaimer: The information provided in this article is for educational and scientific communication purposes only and does not constitute medical advice. Always consult with a qualified healthcare provider regarding any medical condition, diagnosis, or treatment plan.

More on this story: AI Co-Scientists to Accelerate Breakthroughs in Cancer Research via Project AURORA

Share this:

  • Share on Facebook (Opens in new window) Facebook
  • Share on X (Opens in new window) X

Keep reading

  • Catching Three Fish with One Hand Trailer Reveals Complex Romance and Family Conflict
  • Godzilla Minus Zero Is Fastest Japanese Film to Reach 10 Billion Yen

Related

Search:

World Today News

World Today News is your trusted source for global journalism — breaking headlines, in-depth analysis, and reporting from around the world.

Quick Links

  • Privacy Policy
  • About Us
  • Accessibility statement
  • California Privacy Notice (CCPA/CPRA)
  • Contact
  • Cookie Policy
  • Disclaimer
  • DMCA Policy
  • Do not sell my info
  • EDITORIAL TEAM
  • Terms & Conditions

Browse by Location

  • GB
  • NZ
  • US

Connect With Us

© 2026 World Today News. All rights reserved. Your trusted global news source directory.
For contact, advertising, copyright, issues email: [email protected]

Privacy Policy Terms of Service