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
- AI identifies interactions in CRISPR complexes to improve specificity of DNA editingnature.com
- Precise DNA base editing using AlphaFold3-based contact modelling | Naturenature.com
- Evolutionary Scale · ESM3: Simulating 500 million years of evolution with a language modelevolutionaryscale.ai
- One-shot design of functional protein binders with BindCraftnature.com
- Advancing regulatory variant effect prediction with AlphaGenomenature.com
- Highly accurate protein structure prediction with AlphaFoldnature.com
- Language models of protein sequences at the scale of evolution enable accurate structure predictionbiorxiv.org
- Evo 2 Can Design Entire Genomesasimov.press
- Towards the explainability of protein language modelsnature.com
- LLMs can invent their own compression - Rajan Agarwalrajan.sh
- Anthrogenanthrogen.com
- How AI Revolutionized Protein Science, but Didn’t End It | Quanta Magazinequantamagazine.org