Independent project. Not a U.S. government website.

Support our project (opens Buy Me a Coffee)
USASI
SoftwareFramework

SynthID Bio

SynthID Bio is a framework maintained by Google DeepMind12, released Sep 30, 2026. Its source code is public1 under the Apache License 2.021.

SynthID Bio is a set of methods from Google DeepMind for watermarking AI-generated protein sequences and biomolecular structures so that their AI origin can later be detected. SynthID Bio-sequence adds watermarked sampling to the ProteinMPNN inverse-folding model, and SynthID Bio-structure is a fine-tuned AlphaFold 3 model that embeds a watermark in generated structures. The public repository contains the sequence watermarking code, a standalone detection script, and data supporting the paper.16Fact reviewed Oct 4, 2026

Last reviewedEntry updated Documented release Sep 30, 2026

Availability and license

Overall availability

Public

The sequence watermarking code, bundled ProteinMPNN parameters, and paper data are on GitHub. For the structure watermarking model, the README refers users to the AlphaFold 3 repository for downloading weights, which are governed by the AlphaFold 3 Model Parameters Terms of Use; this catalog did not confirm how the fine-tuned SynthID Bio-structure parameters are obtained.1

Availability fact review: Oct 4, 2026

Availability is separate from permission: read the license before using or redistributing.

The README states that all software is under Apache 2.0, that the ProteinMPNN model parameters are redistributed under their original MIT License, and that the data directory is under CC-BY 4.0. AlphaFold 3 model parameters are covered by the separate AlphaFold 3 Model Parameters Terms of Use, which the repository references rather than reproduces. The README also states that software, parameters, and outputs are for theoretical modeling only and not for clinical use.15Fact reviewed Oct 4, 2026

Component reuse rights

A readable or downloadable component is not automatically reusable. These indicators concern recorded license evidence, not system certification.
weights
Reviewed qualifying license recorded — check scope and conditions
code
Reviewed qualifying license recorded — check scope and conditions
data
Reviewed qualifying license recorded — check scope and conditions
documentation
Unknown — no complete fact-level rights review

No complete system-rights review is recorded for this release.

Public materials checklist

Items for a framework under USASI rubric v0.2. Unknown means unassessed or insufficient evidence.
Public materials checklist for SynthID Bio
ItemStatusNotes and evidence
Source codeIs the source code publicly readable?PublicPublic on GitHub, including a modified copy of ProteinMPNN with watermarking added (the README lists the changes and notes that ProteinMPNN's training code was removed) and a vendored copy of SynthID Text.1
DocumentationIs user documentation published?PublicThe README documents setup, watermarked and unwatermarked generation examples, and detection.1
InstallationAre installation instructions or packages publicly available?PublicThe README gives steps using uv or venv with Python 3.9, a requirements file, and an editable install of the bundled SynthID Text package.1
Supported platformsAre supported operating systems or hardware documented?PartialThe README's setup steps are written for Linux; other platforms are not documented.1
Release statusAre versioned releases published?Not publicThe repository listed no releases or tags at review; the code is used from the main branch. It was published alongside the paper (Nature, online 2026-09-30).16

What it is useful for

Generating watermarked protein sequences with ProteinMPNN and computing detection scores for existing sequences in FASTA files, for research on the provenance of AI-designed proteins. The paper describes the work as a proof of concept.16Fact reviewed Oct 4, 2026

Organization context

Provenance and derivatives

SynthID Bio-sequence modifies ProteinMPNN, an existing open-source inverse-folding model, and uses Google DeepMind's SynthID Text watermarking package. SynthID Bio-structure is a fine-tune of AlphaFold 3.16

  • Derived from: ProteinMPNN — Vendored and modified in synthidbio_sequence/third_party/ProteinMPNN (MIT License).
  • Derived from: SynthID Text — Vendored in synthidbio_sequence/third_party/synthid-text (Apache-2.0).
  • Derived from: AlphaFold 3 — Base model for SynthID Bio-structure.

In the news

Dated, sourced updates in this catalog's news that mention this entry.
  1. · Research

    Google DeepMind introduces SynthID Bio and open-sources code for watermarking AI-designed proteins

    On September 30, 2026 Google DeepMind introduced SynthID Bio, a family of watermarking methods for AI-generated protein sequences and 3D structures, which it describes as a proof of concept. The repository README says SynthID Bio-sequence adds watermarked sampling to ProteinMPNN, and the announcement says SynthID Bio-structure fine-tunes a small part of AlphaFold 3's diffusion network so that predicted coordinates carry a detectable signature. Google DeepMind says it is publishing a methods paper, open-sourcing the code and in vitro data, and releasing weights to the research community. In the public repository, the software is licensed under Apache 2.0, the in vitro validation data supporting the paper is licensed under CC BY 4.0, and AlphaFold 3 model parameters remain under the AlphaFold 3 terms of use. USASI has not tested SynthID Bio.

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S.-governed project

The repository is published in Google DeepMind's GitHub organization and its licensing section states copyright 2026 Google LLC. See the google-deepmind organization record, which is assessed under U.S. control as part of Google.12

Assessed Oct 4, 2026

Sources

  1. 1.
    google-deepmind/synthidbio repository and README (external site: github.com)

    Google DeepMind (GitHub) · Repository · accessed Oct 4, 2026

  2. 2.
  3. 3.
    synthidbio ProteinMPNN LICENSE (MIT) (external site: raw.githubusercontent.com)

    Google DeepMind (GitHub) · License · accessed Oct 4, 2026

  4. 4.
    synthidbio data LICENSE (external site: raw.githubusercontent.com)

    Google DeepMind (GitHub) · License · accessed Oct 4, 2026

  5. 5.
  6. 6.
    Function-preserving watermarking of AI-generated proteins (external site: nature.com)

    Nature · Paper · published Sep 30, 2026 · accessed Oct 4, 2026

Share or cite this page

Cite this page

APA style

USASI. (2026, October 4). SynthID Bio. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/open/synthid-bio/

BibTeX

@misc{usasi_synthid_bio,
  author = {{USASI}},
  title = {SynthID Bio},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/open/synthid-bio/}},
  note = {United States of America Superintelligence. Last updated 2026-10-04}
}

The date is when this page was last updated. Add the date you read it if your style needs one.

For maintainers: a “Listed in USASI” badge

Listed in the USASI catalogLinks to this page. It says the entry is listed, not endorsed or rated. About the badge

Markdown (for a README)

[![Listed in the USASI catalog](https://unitedstatesofamericasuperintelligence.com/badges/listed.svg)](https://unitedstatesofamericasuperintelligence.com/open/synthid-bio/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/open/synthid-bio/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/listed.svg" alt="Listed in the USASI catalog" height="20"></a>

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project