{"version":1,"type":"story","url":"https://digestai.news/story/ai-designed-enzymes-cut-proteins-linked-to-neurological-diseases","json":"https://digestai.news/story/ai-designed-enzymes-cut-proteins-linked-to-neurological-diseases.json","markdown":"https://digestai.news/story/ai-designed-enzymes-cut-proteins-linked-to-neurological-diseases.md","slug":"ai-designed-enzymes-cut-proteins-linked-to-neurological-diseases","headline":"UW researchers design AI-built proteases targeting disease proteins","summary":"Two teams at the University of Washington’s Institute for Protein Design published papers in *Nature* on October 14, 2026, detailing AI-designed proteases that cleave specific disease-linked proteins. The studies report zinc-based metalloproteases and cysteine-based proteases, both engineered from scratch using computational methods like RFdiffusion and RFD2-MI. One metalloprotease design achieved a **10¹⁰-fold** acceleration in peptide-bond hydrolysis, while cysteine proteases showed up to **3 × 10⁷-fold** improvements over uncatalyzed reactions.\n\nThe proteases target proteins like TDP-43 (linked to ALS), amyloid-β (Alzheimer’s), and serum amyloid A (inflammation). The team also designed caged cytokines and receptor antagonists, enabling programmable control of cell states. Crystal structures and data are deposited in the Protein Data Bank, with code available on Zenodo and GitHub. Funding came from sources including the Howard Hughes Medical Institute, Gates Foundation, and NIH.","keyPoints":["AI-designed proteases cleave disease-linked proteins TDP-43, amyloid-β, and serum amyloid A with up to **10¹⁰-fold** acceleration","Two protease families: zinc-based metalloproteases (36% success rate) and cysteine-based proteases (19% success rate)","Structures and code publicly available; funding from HHMI, Gates Foundation, NIH, and others"],"whyItMatters":"These AI-designed enzymes could advance therapeutics for neurodegenerative diseases and inflammation by selectively targeting problematic proteins without disrupting essential functions. The programmable nature may also enable new biotech applications like bioorthogonal drug delivery.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["University of Washington","ETH Zurich"],"models":["RFdiffusion","RFD2-MI","AlphaFold 3","ProteinMPNN"],"people":["David Baker","Donald Hilvert","Anqi Chen","Kejia Wu","Hojae Choi","Brian Coventry"]},"firstPublishedAt":"2026-10-14T17:10:15Z","updatedAt":"2026-10-14T17:35:11Z","sourceCount":2,"hasPrimarySource":false,"sources":[{"outlet":"Unite.AI","title":"Baker Lab Designs AI Proteases That Cleave Disease-Linked Proteins","url":"https://unite.ai/baker-lab-designs-ai-proteases-that-cleave-disease-linked-proteins","publishedAt":"2026-10-14T17:35:11Z","type":"press","primary":false,"lead":true},{"outlet":"Ars Technica AI","title":"Researchers use AI to design proteins that cut up other proteins","url":"https://arstechnica.com/science/2026/10/researchers-use-ai-to-design-proteins-that-cut-up-other-proteins","publishedAt":"2026-10-14T17:10:15Z","type":"press","primary":false,"lead":false}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"UW researchers design AI-built proteases targeting disease proteins\", 14 October 2026, https://digestai.news/story/ai-designed-enzymes-cut-proteins-linked-to-neurological-diseases","publisher":"Digest AI","title":"UW researchers design AI-built proteases targeting disease proteins","datePublished":"2026-10-14T17:10:15Z","url":"https://digestai.news/story/ai-designed-enzymes-cut-proteins-linked-to-neurological-diseases"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}