AI-redesigned starting points and outcomes enhance protein evolution | Nature
A workflow using artificial intelligence-redesigned starting points to evolve enzymes with improved properties compared with those evolved from natural proteins is established.
Download PDF Subjects Molecular engineering Protein design Abstract Engineered or laboratory-evolved proteins often have suboptimal stability, activity or specificity. Here we applied artificial intelligence (AI)-based protein sequence design to address challenges in experimental enzyme evolution. Using the model ProteinMPNN, we redesigned three distinct botulinum neurotoxin (BoNT) proteases, generating variants with improved stability and full catalytic efficiency 1 . We hypothesized that redesigned enzymes may be more mutationally robust than their wild-type (WT) counterparts, and therefore
related reading
- Miniaturizing and modifying natural proteins with Raygun | Naturenature.com
- Self-driving laboratories to autonomously navigate the protein fitness landscapenature.com
- Evo 2 Can Design Entire Genomesasimov.press
- AlphaProteo generates novel proteins for biology and health researchdeepmind.google
- AI identifies interactions in CRISPR complexes to improve specificity of DNA editingnature.com
- Engineering Plastic-Degrading Enzymes and PCSK9 Binders with Protein AI Toolsblog.latch.bio
- How AI Revolutionized Protein Science, but Didn’t End It | Quanta Magazinequantamagazine.org
- DISCO — Teaching AI to Invent Enzymes Nature Never Imagineddisco-design.github.io
- ‘Set it and forget it’: automated lab uses AI and robotics to improve proteinsnature.com
- Proto: A programming language for generative biology | Arc Institutearcinstitute.org
- Protein design - Wikipediaen.wikipedia.org
- Protein World Model | Biohubbiohub.ai