# DeepMind Watermarks AI-Designed Proteins Without Measurable Loss of Binding Function

Wet-lab tests against VEGF-A, the SARS-CoV-2 spike receptor-binding domain and PD-L1 found marked designs matched unmarked ones on hit rate and affinity.

- Published: 2026-10-01T06:20:51.871Z
- Canonical: https://polylog.news/ai/2026-10-01/deepmind-watermarks-ai-designed-proteins-without-measurable
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Google DeepMind](https://deepmind.google/blog/introducing-synthid-bio/), [Google](https://blog.google/innovation-and-ai/models-and-research/google-deepmind/synthid-bio/)

Google DeepMind published SynthID Bio, a family of watermarking methods that embed verifiable signatures into AI-designed protein sequences and predicted three-dimensional structures. The sequence method biases amino acid choices during gen…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-01/deepmind-watermarks-ai-designed-proteins-without-measurable (subscription information: https://polylog.news/pricing).