Evidence Passport
AI designs protein-cutting enzymes from scratch
Top story 5 in the issue of 22 October 2026, in 32 AI Biotechnology.
Original source
AI designs protein-cutting enzymes from scratch
Of 135 designed metalloproteases, 36% were active, with rate gains above 10^8-fold; a companion paper made cysteine proteases with a 19% success rate.
Evidence
Evidence: Peer-reviewed (evidence step 5 of 6)
Published after review by independent experts.
Bottleneck: Designing enzymes with new catalytic activity Progress
The story in three lines
- Key finding
- 36% of 135 computer-designed metalloproteases were active, speeding reactions by more than 10^8-fold.
- Significance
- Technical: designing enzymes that cut proteins has been a long-standing hurdle for protein design.
- Takeaway
- A major laboratory advance; therapeutic or industrial use still needs stability and safety work.
Later coverage in the journal
No later coverage in the journal yet.
Corrections and updates
No corrections or updates recorded for this item.
This page is generated from the issue and stays at the same address. It adds nothing that is not in the issue, the source link or the corrections log.