SynthID Bio watermarks sequences and 3D structures, open for research use
GoogleDeepMind · x · 2026-10-01
DeepMind's blog details SynthID Bio: the approach adapts to data type, subtly guiding amino acid choices for sequences and adjusting atomic coordinates for predicted 3D structures to create a reliable detection signal. Experiments show watermarked designs (e.g., a VEGF-A protein binder) retain biological function. Motivation: novel AI designs can bypass traditional DNA synthesis screening, and mislabeled synthetic 3D structures risk polluting public databases. Tools are released openly for research use.
More from Research
- Argus open-sources a VLM-powered robotics data annotation and quality pipeline — k7agar · 2026-10-02
- Mathematician Kevin Buzzard: math community is 'grieving' through five stages over AI — littmath · 2026-10-02
- MINTEval, accepted at NeurIPS, shows LLM agents fail at tracking evolving contexts — EliasEskin · 2026-10-02
- MazeBench goes free online: agents prefer top-down views and stall in 3D puzzles — patience_cave · 2026-10-02
- Aleph Alpha Details MoE Pre-training Scaling: 30B-A3B on 16-512 B200s at 35% MFU — CatAstro_Piyush · 2026-10-02
- Cohere Labs' World Model from Scratch session 3 covers post-training and fine-tuning — Cohere_Labs · 2026-10-02