# Function-preserving watermarking of AI-generated proteins

Article · Stutz D, Cowen-Rivers AI, Ortiz-Jimenez G, Ratcliff J, Zambaldi V, Willmore L, Abramson J, Patani H, Kouridi C, Stimberg F, Vecerik M, Chu A, Singh S, Dathathri S, Papa E, De Bortoli V, Doucet A, Hassabis D, Wang J, Gowal S, Kohli P

- Archive id: doi:10.1038/s41586-026-10965-y
- Published: 2026-09-30
- Venue: Nature
- DOI: https://doi.org/10.1038/s41586-026-10965-y
- PMID: 42816606
- Citations: 0
- Source URL: https://doi.org/10.1038/s41586-026-10965-y
- Provenance: europepmc

## Abstract

Generative artificial intelligence (AI) models are revolutionizing biology, with tools such as AlphaFold 3 and protein design models accelerating breakthroughs in protein structure prediction and the creation of new functional proteins 1 . Tracking and establishing the provenance of AI-generated protein sequences and structures is becoming increasingly important to tackle a range of emerging challenges, including biosecurity and concerns about information veracity 2-4 . Here we introduce SynthIDBio, a family of methods for watermarking protein sequences and structures to establish the provenance of those generated with AI. SynthIDBio-sequence actively embeds a watermark into protein sequences while preserving function. We demonstrate this by creating watermarked, functional designed protein binders with binding affinity comparable with non-watermarked counterparts and near-perfect watermark detection accuracy. Furthermore, SynthIDBio-structure, a fine-tuned AlphaFold3 model, embeds an imperceptible watermark into biomolecular structures. Our work is a proof-of-concept that function-preserving biological watermarking is feasible, introducing a potential tool for provenance in the rapidly expanding era of AI-driven biological engineering.

_Abstract reproduced under CC-BY (article license as recorded by Europe PMC; abstract reproduced unmodified apart from markup removal)._

Topics: [AI Protein Design & Structure Prediction](https://space-kitty.com/topics/protein-design)

---
Space Kitty Archive · https://space-kitty.com · API: https://space-kitty.com/api/v1 · MCP: https://space-kitty.com/mcp · Premium: $0.20/request via x402 (Base Sepolia (testnet)). Metadata: arXiv (CC0), OpenAlex (CC0), Europe PMC (CC BY/CC0 works), ClinicalTrials.gov.