Tech
Researchers use AI to design proteins that cut up other proteins
Publication: Ars Technica - All content
Author: John Timmer
Source published: 14/10/2026, 17:10:15 UTC
Briefing created: 15/10/2026, 04:04:54 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 14/10/2026, 19:43:23 UTC.
Briefings
Researchers replaced the catalytic core of two protease enzymes with AI-designed proteins to create new enzymes that specifically cut peptide bonds, potentially shortening the half-life of proteins from hundreds of years to a fraction of a second. The team successfully demonstrated this capability by using the new enzymes to degrade proteins linked to neurological diseases, proving the method works in biological contexts. The study highlights how AI can bypass natural evolutionary diversification to engineer precise molecular tools.
Key points
- Researchers replaced the catalytic core of two protease enzymes with AI-designed proteins to create new enzymes that specifically cut peptide bonds.
- The new enzymes were successfully demonstrated to degrade proteins associated with neurological diseases, proving the method works in biological contexts.
Context and limitations
The study's effectiveness was demonstrated only on proteins linked to neurological diseases; the long-term stability and broader applicability of the engineered enzymes remain to be tested in other environmental or clinical settings.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 15/10/2026, 04:04:54 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeihjbavkzm2feqt6pixhkqy5wuwuylhsw2pwzy53qmbdsqzgfmgese