Miniaturizing, Modifying, and Augmenting Nature’s Proteins with Raygun

Proteins are nature’s versatile nanomachines, but engineering them for enhanced function or novel applications remains challenging. Current methods for protein modification struggle to design sequence alterations, especially insertions and deletions, that preserve structure. Here, we introduce Raygun, a template-guided protein design framework that unlocks efficient miniaturization, modification, and augmentation of existing proteins. Using a novel probabilistic encoding of protein sequences constructed from language model embeddings, Raygun is able to generate diverse candidates with deletions, insertions, and substitutions while maintaining core structural elements. We show that Raygun can shrink proteins by 10-25% (sometimes over 50%) while preserving predicted structural integrity and fidelity, introduce extensive sequence diversity while preserving functional sites, and even expand proteins beyond their natural size. In experimental validation, we successfully miniaturize the fluorescent proteins eGFP and mCherry to synthesize functional variants, two of which are smaller than 96% of fluorescent proteins reported in FPbase. Raygun’s conceptual innovations in template-based protein design open new avenues for protein engineering, potentially catalyzing the development of more efficient molecular tools and therapeutics.