Function-preserving watermarking of AI-generated proteins

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 of "Function-preserving watermarking of AI-generated proteins" by Stutz D, Cowen-Rivers AI, Ortiz-Jimenez G et al., https://doi.org/10.1038/s41586-026-10965-y, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified.