AI-designed IPF drug enters Phase III trial, a first for generative AI
New CapabilitiesRentosertib targets TNIK, a kinase AI linked to fibrosis; 52-week readout to come
Yesterday: Insilico announces Phase III initiationNew here? Follow stories to track developments over time. Create a free account to get updates when stories you care about change.
Overview
Updated YesterdayInsilico Medicine dosed the first patient this week in a Phase III trial of Rentosertib, a drug for the progressive lung disease idiopathic pulmonary fibrosis. It's the first medicine with both an AI-identified target and an AI-designed molecule to reach this stage of testing.
The 320-patient, 52-week study runs at 47 hospitals across China and compares Rentosertib against placebo on the rate of lung-function decline. The outcome will test the core claim of AI drug discovery: that generative models can find treatments faster and cheaper than traditional chemistry.
Rentosertib inhibits TNIK, a kinase no one had previously tied to fibrosis. Insilico's PandaOmics platform flagged the target by scoring genes with multi-omics data from fibrotic tissue — a target class not previously associated with the disease.
Why it matters
If Rentosertib succeeds, it validates that generative AI can discover viable medicines — a claim the industry has made for years without proof.
Questions about this story
Free account needed to ask — your question is kept and asked for you right after sign-up. Answers are public.
No questions yet — be the first to ask.
Key Indicators
Voices
Curated perspectives — historical figures and your fellow readers.
Play
Exploring all sides of a story is often best achieved with Play.
Higher or Lower
A number from this story, against one from elsewhere in the news — guess which is bigger, then keep the chain going. 5 rounds, 3 strikes; a miss costs a strike and resets your streak.
Keyboard: ↓/L lower · ↑/H higher
0 points — sign up to put that on the leaderboard.
Connections
Sixteen names from the news. Find the four hidden groups of four. Four mistakes max.
Sign up to keep a daily streak — a new puzzle lands every day.
Exit debate?
Your progress in this debate will be lost.
- 1 Two AI personas square off on this story.
- 2 You predict who'll win each round — correct picks earn XP.
- 3 One crossfire question is yours to fire. Pick it carefully.
Couldn't generate a topic
Select Your Champions
Choose one persona for each side of the debate
DEBATE TOPIC
Choose personas with different perspectives for a more dynamic debate.
Select debater for this side:
No debate personas available right now.
Select debater for this side:
No debate personas available right now.
Who's Got This Round?
Make your prediction before the referee scores
The referee scores both sides on
Round Results
Set the Crossfire
Pick the question both personas must answer in the final round
Debate Oracle! You called every round!
Sharp Instincts! You know your debaters!
The Coin Flip Strategist! Perfectly balanced!
The Contrarian! Bold predictions!
Inverse Genius! Try betting the opposite next time!
XP Breakdown
Prediction History
People Involved
Organizations Involved
A generative-AI-powered biotech that identified TNIK as a fibrosis target through its PandaOmics platform.
The hospital where the first Phase III patient was dosed, under the direction of Leading PI Zuojun Xu.
Timeline
February 2023 September 2026
-
Insilico announces Phase III initiation
Latest AnnouncementCompany confirms Rentosertib is the first generative-AI-driven drug to enter Phase III testing.
-
First patient dosed in Phase III
Clinical TrialPeking Union Medical College Hospital doses first GENESIS-IPF-3 patient; Shanghai Pulmonary Hospital enrolls its first the same day.
-
CDE clears IND for inhaled formulation
RegulatoryChina approves a Phase I study of inhaled Rentosertib in healthy volunteers and IPF patients.
-
Phase IIa results published in Nature Medicine
Publication71 patients showed +98.4 mL FVC change at 12 weeks in the 60 mg arm versus -20.3 mL placebo.
-
China CDE grants Breakthrough Therapy Designation
RegulatoryChina's Center for Drug Evaluation fast-tracks Rentosertib for IPF.
-
FDA grants Orphan Drug Designation
RegulatoryUS Food and Drug Administration designates Rentosertib as an orphan drug for IPF.
Historical Context
3 moments from history that rhyme with this story — and how they unfolded.
Nintedanib's path to IPF approval (2014)
Boehringer Ingelheim's nintedanib (Ofev) became the second approved IPF drug in 2014, after years of failed candidates in a disease where trials have one of the highest failure rates in drug development.
Nintedanib and pirfenidone became the standard of care, slowing FVC decline without reversing fibrosis.
They set the regulatory precedent: FVC decline rate is the accepted endpoint for IPF trials, which is exactly what GENESIS-IPF-3 measures.
IPF's brutal trial history is why Rentosertib's Phase III readout carries so much weight — positive Phase II signals have failed here before.
AlphaFold 2 (2020)
DeepMind's AlphaFold 2 won the CASP14 protein-folding competition, predicting protein structures with accuracy near experimental methods. The problem had stood unsolved for 50 years.
AlphaFold's predictions were released openly, and the database now covers hundreds of millions of proteins used by researchers worldwide.
It established AI as a legitimate tool for fundamental biology, not just a laboratory curiosity.
AlphaFold proved AI could predict biology; Rentosertib tests whether AI can deliver a marketable medicine. Both are 'firsts' for AI in their respective domains.
Computational drug discovery's unfulfilled promise (1990s–2010s)
Computer-aided drug design methods like molecular docking promised in the 1990s to speed drug discovery. They improved efficiency at the margins but produced few breakthrough drugs.
In silico methods became standard tools, but the industry's core pipeline remained chemistry-driven.
The gap between promise and delivery left the field skeptical of computational claims, a skepticism now aimed at generative AI.
Rentosertib is the first genuine late-stage test of whether AI delivers where earlier computational waves fell short.
