Google DeepMind Unveils SynthID Bio to Watermark AI-Generated Proteins and Biological Code

Google DeepMind Unveils SynthID Bio to Watermark AI-Generated Proteins and Biological Code Google DeepMind has introduced SynthID Bio, a watermarking method designed to embed imperceptible, verifiable signatures directly into biological data such as protein sequences and 3D structures without diminishing biological function. SynthID Bio adjusts amino acid selection for sequences and fine-tunes atomic coordinates in 3D structures to embed detectable watermarks. Wet-lab experiments demonstrated that watermarked protein binders targeting VEGF-A, SARS-CoV-2 spike RBD, and PD-L1 matched the binding affinity and hit rates of unwatermarked equivalents. By fine-tuning AlphaFold 3's diffusion network weights, predicted 3D coordinates automatically embed a detectable signature resilient to minor noise without sacrificing accuracy. The technology aims to aid DNA synthesis screening by providing automated provenance verification and to help public databases such as GenBank and UniProt flag synthetic entries. DeepMind is collaborating with the Hie lab to extend SynthID Bio to bacteriophage genomes designed with the Evo 2 model, and is open-sourcing its code, weights, and in vitro data. Watermarking Mechanisms and Wet-Lab Verification SynthID Bio adapts to different biological data modalities by subtly guiding amino acid choices in generated sequences and adjusting atomic coordinates in predicted 3D structures. Using AlphaProteo together with a modified version of ProteinMPNN, researchers generated watermarked protein binders against three target proteins: VEGF-A, the SARS-CoV-2 spike protein RBD, and PD-L1. In vitro laboratory testing showed that these watermarked proteins retained the binding affinity (KD), hit rate, and natural sequence diversity of unwatermarked designs, establishing physically functional watermarked proteins. Integration with AlphaFold 3 For structural predictions, SynthID Bio incorporates watermarking directly into AlphaFold 3 by fine-tuning a small portion of its diffusion network weights. As a result, the model's predicted 3D coordinates automatically carry an identifiable signature regardless of the user running the model. This embedded signature offers near-perfect detectability and resists digital noise or minor coordinate perturbations while preserving AlphaFold 3's baseline structural prediction accuracy. Applications to Biosecurity and Database Integrity The framework functions as an embedded verification layer within biosecurity's layered defense model. In DNA synthesis screening, novel AI-designed sequences often lack resemblance to cataloged hazards, forcing time-consuming manual evaluations. SynthID Bio provides an automated signal confirming an order stems from an authorized model with built-in safeguards. Additionally, it offers a mechanism for public repositories like the Protein Data Bank, UniProt, and GenBank to detect and label AI-generated submissions, preventing data pollution and mislabeling. Future Developments and Open-Source Release Ongoing research addresses challenges such as hardening watermarks against deliberate tampering and combining them with metadata standards like C2PA or central AI data repositories. In collaboration with the Hie lab at Stanford University and the Arc Institute, DeepMind integrated SynthID Bio into the Evo 2 genomic model to watermark the genome of synthetic bacteriophages, which preliminary bacterial culture tests confirmed remain functional. DeepMind is open-sourcing the method's code, model weights, and in vitro data alongside a methods paper.

Google DeepMind 推出 SynthID Bio：为 AI 生成蛋白质嵌入生物水印且不损功能 Google DeepMind 宣布推出 SynthID Bio，这是一种专门用于合成生物学的水印技术。该技术可将难以察觉的签名直接嵌入生物代码中，不仅能在数字模型中读取，也能在合成后的实体蛋白质中进行验证，同时在湿实验中保持其生物功能。 SynthID Bio 通过调整氨基酸选择或 3D 结构原子坐标嵌入水印，湿实验验证其不损害蛋白质功能。 在针对 VEGF-A、SARS-CoV-2 刺突蛋白 RBD 和 PD-L1 的测试中，带水印的蛋白结合剂在命中率和结合亲和力上与未加水印版本一致。 通过微调 AlphaFold 3 扩散网络的部分权重，使预测的 3D 坐标自带高检出率的水印且保持预测精度。 该技术旨在协助 DNA 合成机构进行自动化生物安全筛查，并防止 AI 生成的错误标签数据污染公共生物数据库。 技术机制与湿实验功能验证 SynthID Bio 针对不同数据形态采用适配方法：在序列设计中微调氨基酸选择，在预测 3D 结构时微调原子坐标。团队结合 AlphaProteo 与支持 SynthID Bio 的 ProteinMPNN，在 VEGF-A、新冠刺突蛋白 RBD 及 PD-L1 三个靶点上进行了湿实验，证实带水印分子的命中率、结合亲和力与序列多样性均不受影响。此外，通过微调 AlphaFold 3 扩散网络的小部分权重，模型生成的 3D 坐标原生附带水印信号，既能抵御数字噪声，又维持了原有预测精度。 赋能 DNA 合成筛查与公共数据完整性 AI 设计的全新序列往往与已知危害物差异极大，传统筛查容易因无法判定风险而引发耗时的人工审核。SynthID Bio 可作为自动化凭证，向 Twist Bioscience 等 DNA 合成服务商证明订单来源于具备安全机制的受信模型，从而加速安全筛查流程。同时，该水印还可应用于 Protein Data Bank、UniProt 和 GenBank 等公开数据库，标记或拦截错误标注的 AI 生成结构，防止公共科研资源受污染。 复杂生物对象扩展与开源计划 针对未来防御蓄意篡改的需求，SynthID Bio 计划与类似 C2PA 的元数据溯源方法或中央数据库结合。DeepMind 还与斯坦福大学及 Arc 研究所的 Hie 实验室合作，将技术整合至基因组模型 Evo 2 中，成功对设计的噬菌体基因组嵌入水印，初步培养实验已证实其具备功能。团队已公布方法论文，并开源了代码、体外实验数据和模型权重以推动社区合作。

September 30, 2026 Science Pushmeet Kohli, David Stutz, Ali Cowen-Rivers and Jeremy Ratcliff Proof of concept for watermarking AI-generated proteins while preserving biological function. Today, we’re introducing SynthID Bio to bring watermarking technology to synthetic biology. SynthID Bio embeds an imperceptible signature directly into the biological code, ensuring the watermark is verifiable not just on a digital model but on the synthesized, physical protein itself – all while preserving its biological function in laboratory testing. Generative AI is helping scientists address critical biological challenges, from predicting the structure of proteins ( AlphaFold ) to designing entirely new proteins ( AlphaProteo , and ProteinMPNN ), and more recently, developing new bacteriophages , viruses that infect bacteria. Yet these tools also present new challenges: novel AI designs can bypass traditional DNA synthesis screening, while mislabeled synthetic 3D structures risk polluting public databases and misleading downstream research. How SynthID Bio works SynthID Bio is a family of watermarking methods developed specifically for synthetic biology to strengthen biosecurity and scientific integrity. It adapts its approach depending on the type of data, subtly guiding the choice of amino acids for sequences and adjusting atomic coordinates for predicted 3D structures, creating a reliable signal for detection. In experiments, these adjustments did not compromise the protein’s biological function, which is essential to effectively treat disease and advance scientific research. Visualization of the predicted structure of our watermarked VEGF-A protein binder with watermark signal indicated by color for each amino acid. We verified our approach for watermarking protein binders, i.e. molecules built to selectively latch onto other proteins, by using our binder design method AlphaProteo alongside a SynthID Bio-enabled version of ProteinMPNN, the commonly used protein sequence generation method. In wet-lab testing across three target proteins (VEGF-A, the SARS-CoV-2 spike protein RBD, and PD-L1), our watermarked designs matched the hit rate, binding affinity, and natural sequence diversity of unwatermarked versions, successfully creating the first-ever watermarked and biologically functional protein binders. Binding affinity, measured as KD, comparing non-watermarked and watermarked protein designs across three targets. Lower indicates stronger binders. For protein folding, SynthID Bio fine-tunes a small part of AlphaFold 3’s diffusion network, building the ability to watermark directly into the model’s weights. This ensures that the predicted 3D coordinates inherently carry a detectable signature regardless of who runs the model. SynthID Bio preserves AlphaFold 3 prediction accuracy while offering near-perfect detectability, maintaining key structural feature distributions, and holding up against digital noise or minor coordinate changes. On 7PPA, we show the AF3 predicted structure (left), the ground truth structure (middle), and the watermarked structure (right). Strengthening biosecurity and information integrity Biosecurity relies on layered defenses – think of it like a “Swiss cheese” defense model, where multiple independent safety measures work in tandem to cover each other’s blind spots. Safeguards like model-level mitigations and customer vetting each represent critical layers with potential gaps. As a part of our broader vision for bioresilience , SynthID Bio’s watermarking approach serves as an important, tangible verification layer embedded in the biological design itself. “SynthID Bio is an important piece of the puzzle for tracking the provenance of biological designs,” said Sarah Carter, a biosecurity policy expert and Principal at Science Policy Consulting who reviewed the work. “By linking designs to the model developer, these watermarks empower developers to lead on safety and allow synthesis providers to streamline screening for customers who have used those models.” That layer is especially vital to DNA synthesis screening, which sits on the frontlines of biosecurity. Converting digital protein designs into physical molecules requires placing an order with DNA synthesis providers, who screen requests against databases of known threats. For example, historically, an unfamiliar sequence may have been safely assumed to be an undiscovered natural organism. But because AI can create entirely new sequences with little resemblance to known hazards, screeners can no longer make that assumption. Verifying that an unfamiliar order isn't an engineered threat requires exhaustive manual reviews that can stall vital research. Here, SynthID Bio can provide an automated verification signal, proving an order originated from a trusted model with built-in safeguards. "AI is expanding what scientists can design, and DNA synthesis companies have an important role in helping that innovation scale responsibly,” said James Diggans, Vice President, Policy and Biosecurity at Twist Bioscience, who provided early feedback on the paper. “For Twist, watermarking offers a promising new addition to the biosecurity toolbox that could strengthen screening, focus resources on sequences that warrant closer review and make biosecurity more efficient as AI-designed biology continues to advance." Similarly, SynthID Bio could help maintain the integrity of databases such as the Protein Data Bank, UniProt, and GenBank. These databases, many of which are open to public submission, play a vital role in scientific advancements – but mislabeled entries can have an outsized negative impact in biosecurity decision-making , a challenge that may only grow with the addition of AI-generated biological data. As a part of the submission process, SynthID Bio could help ensure synthetic entries are properly labeled or flagged for further review. Looking ahead While no single biosecurity intervention is a silver bullet, SynthID Bio brings SynthID , our tried and tested watermarking tool, to synthetic biology. It’s an important first step toward reliably identifying and tracking AI-generated biological sequences and structures. Moving forward, key challenges include making the watermark more robust against deliberate tampering. SynthID Bio can also be paired with provenance metadata approaches – similar to C2PA for digital media – or central repositories of AI-generated biological data to better identify and track AI-generated proteins. To match the growing capabilities of frontier AI technology, we’re also researching how to apply watermarking to more complex biological objects. In ongoing work with the Hie lab at Stanford University and Arc Institute, we integrated SynthID Bio into Evo 2, an advanced genomic model, to watermark the genome of an Evo 2 designed bacteriophage . Early laboratory testing in bacteria cultures has confirmed these watermarked bacteriophages are functional. We believe this work has the potential to address some of the biosecurity risks associated with genome design and will share more details in a technical manuscript soon. Realizing the full biosecurity benefits of this work will require community collaboration and further research. As part of our commitment to responsible innovation, we are publishing our methods paper and open-sourcing the code and in vitro data, and releasing the weights to the research community, so we can build on this work. By working openly with partners across biosecurity, gene synthesis, and policy, we can ensure safety and responsibility keeps pace with AI-driven discovery. To reach out about partnering with us on this important topic, please contact us at synthidbio@google.com with a high level proposal. Please do not disclose any confidential or proprietary information. Acknowledgements This project was initiated by Pushmeet Kohli. The research and technical development was led by Alexander I. Cowen-Rivers and David Stutz and was advised by Pushmeet Kohli. Key engineering and research contributions were made by Guillermo Ortiz-Jimenez, Jeremy Ratcliff, Vinicius Zambaldi, Lindsay Willmore, Josh Abramson, Harshnira Patani, Christina Kouridi, Florian Stimberg, Mel Vecerik, Alex Chu, Sukhdeep Singh, Sumanth Dathathri, Eliseo Papa, Valentin De Bortoli, Arnaud Doucet, Jue Wang, and Sven Gowal. We thank Adaptyv Bio for help with in vitro validation. The extension of this work to watermark DNA of bacteriophages is a collaboration between Google DeepMind and the Hie lab at Stanford and Arc Institute with key contributions from Jeremy Ratcliff, Aleks Petrov, Alexander I. Cowen-Rivers, David Stutz, Elisa L. H. Wong, Victor Martin Palacios, Francesca Pietra, Alfred Piccioni, Tristan Oliver Kwan, Tor Lattimore, Sumanth Dathathri, and Pushmeet Kohli from Google DeepMind and Brian Hie, Samuel King, and Aditi Merchant from Arc Institute and Stanford. We further thank Rudy Bunel, Anna Cupani, Rob Fergus, Thomas Frerix, Sahra Ghalebikesabi, John Jumper, Jacob Kelly, David La, Victor Martin, Sebastian Nowozin, Stig Petersen, Aleks Petrov, Uchechi Okereke, Sylvestre-Alvise Rebuffi, Rosalia Schneider, Armin Senoner, Richard Shuai, Ashok Thillaisundaram, Elisa L. H. Wong, Zachary Wu, and Augustin Žídek for their contributions to the research article, and Julien Bergeron for contributions to the 3D rendering. Finally, we thank Demis Hassabis for his encouragement and support of this project.