Miniaturizing and modifying natural proteins with Raygun
6 affiliations
- 1Department of Biostatistics and Bioinformatics, Duke University, Durham, NC, USA
- 2Department of Cell Biology, Duke University, Durham, NC, USA
- 3Department of Chemistry and Biochemistry, University of California San Diego, San Diego, CA, USA
- 4Department of Cell Biology, Duke University, Durham, NC, USA. [email protected]
- 5Department of Biostatistics and Bioinformatics, Duke University, Durham, NC, USA. [email protected]
- 6Department of Cell Biology, Duke University, Durham, NC, USA. [email protected]
Abstract
Proteins have evolved over billions of years through extensive and coordinated substitutions, insertions and deletions (indels). Computational protein design cannot yet fully mimic nature’s ability to engineer new proteins from existing templates. Protein language models generate informative per-residue representations, but leveraging them to execute large-scale, function-preserving mutations and indels has remained beyond reach. We introduce Raygun, a generative AI framework that unlocks efficient miniaturization, modification, and augmentation of proteins, using a novel probabilistic encoding of protein sequences constructed from language model embeddings. Emulating evolution, Raygun shrinks proteins by 10-25% (sometimes over 50%) while preserving predicted structural integrity and fidelity, introduces extensive sequence diversity while preserving functional sites, and can expand proteins beyond their natural size. These capabilities unlock new opportunities in gene therapy and biotechnology. In cell-based validation, Raygun successfully miniaturized fluorescent proteins, two of which are smaller than 96% of fluorescent proteins reported in FPbase, as well as TurboID, a synthetic biotin ligase widely adopted for proteomics. It also successfully expanded Epidermal Growth Factor (EGF), a natural binding partner to the EGFR protein, generating EGF variants with higher binding affinity than the wildtype. Raygun’s conceptual innovations in template-based protein design reveal that protein function can be encoded in a length-independent space. This fundamental insight bridges protein representation learning with evolutionary biology and could unlock the development of more efficient molecular tools and biological therapeutics.
Related
- Programmable design of functional proteins from natural language
- StrucNS reveals interaction-weighted network topology as the driving predictor of absolute stability of natural and de novo proteins
- Chromatin-modifying Complex Component Nurf55/p55 Associates with Histones H3 and H4 and Polycomb Repressive Complex 2 Subunit Su(z)12 through Partially Overlapping Binding Sites
- Methylglyoxal hampers the angiogenic capacity of human retinal endothelial cells modifying cell transcriptome with the contribution of NRSF/REST
- Improving plant photosynthesis by modifying Rubisco and its chaperones
BibTeX
@article{devkota2026miniaturizing,
title = {{Miniaturizing and modifying natural proteins with Raygun}},
author = {Kapil Devkota and Daichi Shonai and Yiwei Mao and Young Su Ko and Wei Wang and Scott H. Soderling and Rohit Singh},
journal = {Nature},
year = {2026},
month = jul,
doi = {10.1038/s41586-026-10842-8},
url = {https://doi.org/10.1038/s41586-026-10842-8},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Miniaturizing and modifying natural proteins with Raygun
AU - Kapil Devkota
AU - Daichi Shonai
AU - Yiwei Mao
AU - Young Su Ko
AU - Wei Wang
AU - Scott H. Soderling
AU - Rohit Singh
PY - 2026
DA - 2026/07/29
JO - Nature
DO - 10.1038/s41586-026-10842-8
UR - https://doi.org/10.1038/s41586-026-10842-8
AB - Proteins have evolved over billions of years through extensive and coordinated substitutions, insertions and deletions (indels). Computational protein design cannot yet fully mimic nature’s ability to engineer new proteins from existing templates. Protein language models generate informative per-residue representations, but leveraging them to execute large-scale, function-preserving mutations and indels has remained beyond reach. We introduce Raygun, a generative AI framework that unlocks efficient miniaturization, modification, and augmentation of proteins, using a novel probabilistic encoding of protein sequences constructed from language model embeddings. Emulating evolution, Raygun shrinks proteins by 10-25% (sometimes over 50%) while preserving predicted structural integrity and fidelity, introduces extensive sequence diversity while preserving functional sites, and can expand proteins beyond their natural size. These capabilities unlock new opportunities in gene therapy and biotechnology. In cell-based validation, Raygun successfully miniaturized fluorescent proteins, two of which are smaller than 96% of fluorescent proteins reported in FPbase, as well as TurboID, a synthetic biotin ligase widely adopted for proteomics. It also successfully expanded Epidermal Growth Factor (EGF), a natural binding partner to the EGFR protein, generating EGF variants with higher binding affinity than the wildtype. Raygun’s conceptual innovations in template-based protein design reveal that protein function can be encoded in a length-independent space. This fundamental insight bridges protein representation learning with evolutionary biology and could unlock the development of more efficient molecular tools and biological therapeutics.
SN - 0028-0836
SN - 1476-4687
ER -