Miniaturizing and modifying natural proteins with Raygun | Nature
Probabilistic sequence encoding from language model embeddings within a generative AI framework enables protein miniaturization, modification and augmentation while maintaining native architecture and functional integrity.
Download PDF Abstract Proteins have evolved over billions of years through coordinated substitutions, insertions and deletions, yet computational protein design cannot fully replicate nature’s ability to engineer new proteins from existing templates. Protein language models 1 , 2 , 3 generate informative per-residue representations, but harnessing them for large-scale, function-preserving sequence modifications has remained beyond reach. Here we introduce Raygun, a generative artificial intelligence framework that enables miniaturization, modification and augmentation of proteins, using a prob
saved by
related reading
- Evolutionary Scale · ESM3: Simulating 500 million years of evolution with a language modelevolutionaryscale.ai
- One-shot design of functional protein binders with BindCraftnature.com
- Language models of protein sequences at the scale of evolution enable accurate structure predictionbiorxiv.org
- Anthrogenanthrogen.com
- Protein World Model | Biohubbiohub.ai
- Highly accurate protein structure prediction with AlphaFoldnature.com
- Evo 2 Can Design Entire Genomesasimov.press
- Evo 2: DNA Foundation Model | Arc Institutearcinstitute.org
- Fast and Ultra-Capable Protein Design: Advancing the Frontier Through Atomistic SE(3)-Equivariance with Genie 3biorxiv.org
- A socratic dialogue over the utility of DNA language models (Part 1 of 2)owlposting.com
- AI-redesigned starting points and outcomes enhance protein evolution | Naturenature.com
- Publications - Debbie Marks Labdeboramarkslab.com