Key facts
- Google's DeepMind developed a protein watermarking system.
- The system uses a cryptographic key to embed watermarks.
- Watermarked proteins remain functional and can bind to intended targets.
- The technology aims to improve biosecurity by identifying AI-designed proteins.
- DNA synthesizers can use the system to screen for unknown or potentially threatening protein sequences.
Google's DeepMind has introduced a novel method for watermarking AI-designed proteins, a development aimed at bolstering biosecurity. The system, an adaptation of Google's SynthID technology, embeds an invisible watermark directly into the protein sequence without compromising its biological function. This innovation allows for the identification of proteins designed by trusted researchers, thereby enabling closer scrutiny of unknown or potentially hazardous sequences.
The challenge in watermarking proteins lies in their fundamental structure. Unlike digital images with millions of pixels, proteins are composed of only 20 amino acids, with limited room for subtle alterations. Any change must not disrupt the protein's structural integrity or catalytic activity. Google's approach, detailed in a recent research paper, integrates with popular AI protein design tools like ProteinMPNN. During the design process, SynthIDBio, a variant of SynthID, suggests amino acids that are consistent with the watermark, provided they do not inactivate the protein. This ensures that the resulting watermarked proteins remain functional.
The system works by using a cryptographic key to influence the AI's amino acid selection. When the AI encounters a position where multiple chemically similar amino acids would function, it prioritizes one that aligns with the watermark. This process distributes the watermark randomly throughout the protein sequence, making it detectable only with the correct key and difficult to remove. The team demonstrated that watermarked proteins successfully bind to their intended targets, suggesting the method is viable for complex design tasks.
This technology is intended to assist DNA synthesizers, which currently screen ordered sequences for known threats. However, AI-designed proteins can be novel and uncharacterized, making their potential threat level difficult to assess. By using keys provided by trusted organizations, synthesizers can quickly identify AI-designed proteins from known sources, allowing them to focus resources on evaluating truly unknown sequences.