China approves first AI-assisted Class 1 innovative drug Mprosevir
New CapabilitiesCOVID-19 treatment went from candidate discovery to conditional approval in 3.5 years, about a third of the traditional timeline
2 days ago: NMPA grants conditional approval to MprosevirNew here? Follow stories to track developments over time. Create a free account to get updates when stories you care about change.
Overview
Updated 1 hour agoChina's drug regulator granted conditional approval to Mprosevir, a COVID-19 treatment, on September 2. It is the country's first 'Class 1' innovative drug developed with AI assistance—the highest classification in China's drug registration system, reserved for drugs never marketed domestically or abroad.
Mprosevir took 3.5 years from candidate discovery to clinical trial completion, about a third of the traditional decade-long pipeline. Researchers screened 49 billion compounds in a DNA-encoded library (DEL), with AI narrowing more than 100 candidates to nine molecules within days. It is the first small-molecule drug approved worldwide using DEL technology, a concept proposed 34 years ago.
Why it matters
AI-assisted drug development can compress a decade-long pipeline into years, changing how quickly new medicines reach patients.
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
China's national drug regulator, equivalent to the US Food and Drug Administration.
Private research university in Hangzhou founded by structural biologist Shi Yigong.
Pharmaceutical company affiliated with the Westlake ecosystem in Hangzhou.
Research institute in Hangzhou affiliated with Westlake University.
Timeline
January 1992 September 2026
-
NMPA grants conditional approval to Mprosevir
Latest Regulatory ApprovalChina approves first AI-assisted Class 1 innovative drug for mild-to-moderate COVID-19 in adults.
-
Two-year AI-guided optimization completed
DevelopmentTeam improves potency, pharmacology, and toxicity. Progresses from cell assays through mouse studies toward clinical trials.
-
AI narrows candidates; WLU6937 selected
DiscoveryAI filters 100+ candidates to nine in days; six show strong activity. WLU6937 chosen as lead.
-
Westlake team begins DEL screening campaign
DiscoveryResearchers screen 49 billion compounds in a DEL library targeting the 3CLpro coronavirus protease.
-
DNA-encoded library concept proposed
Scientific ContextSydney Brenner and Richard Lerner introduce the DEL concept, enabling compound screening at massive scale.
Historical Context
3 moments from history that rhyme with this story — and how they unfolded.
COVID-19 mRNA vaccines (2020-2021)
Operation Warp Speed and the new mRNA platform compressed vaccine development from the typical 10-15 years to under a year. Pfizer-BioNTech and Moderna moved from sequence to emergency authorization in about 11 months, a process that normally takes a decade.
Billions of doses delivered worldwide within 18 months of the pandemic's start.
Demonstrated that regulatory flexibility plus platform innovation can compress biological product timelines dramatically, reshaping vaccine development norms.
The same dynamic is at work with Mprosevir: a new discovery platform (DEL plus AI) combined with regulatory adaptation compresses a decade-long process into years.
AlphaFold protein structure breakthrough (2020-2021)
DeepMind's AlphaFold solved the 50-year protein folding problem, predicting protein structures with atomic accuracy. In 2021, AlphaFold released structures for nearly all of the 200 million proteins cataloged in science—work that would have taken researchers centuries.
Structural biologists gained instant access to predictions for proteins they had spent years trying to crystallize.
Established that AI can outperform traditional experimental methods in biological discovery, fueling investment in AI-driven drug development.
Mprosevir builds directly on this precedent: AI applied to biological problems changes what's possible, and what was a research tool in 2021 is now producing approved drugs.
Drug development's 'three tens' rule
The pharmaceutical industry's long-standing benchmark: 10 years of development, $1 billion in investment, and less than 10% probability of success for a new drug. This baseline has held for decades despite advances in chemistry, genomics, and screening technology.
High development costs and failure rates have kept drug prices high and limited innovation to well-capitalized firms.
The rule set expectations for how long patients wait for new treatments and how much risk investors accept.
Mprosevir challenges the baseline directly—3.5 years versus 10, with AI handling screening and optimization that historically consumed years of medicinal chemistry effort.
