Skip to main content
Any publication that discloses findings arising from using AlphaFold 3 source code, model parameters, or outputs must cite the AlphaFold 3 paper.

Citation Requirement

If you use AlphaFold 3 in your research, you must cite the following paper: Accurate structure prediction of biomolecular interactions with AlphaFold 3 Published in Nature, Volume 630, Issue 8016, Pages 493-500 (2024) DOI: 10.1038/s41586-024-07487-w

BibTeX Format

For LaTeX and BibTeX users, use the following citation:

Text Citation Formats

APA Style

MLA Style

Chicago Style

Nature Style


Authors

Lead Authors

Josh Abramson, Jonas Adler, Jack Dunger, Richard Evans, Tim Green, Alexander Pritzel, Olaf Ronneberger, Lindsay Willmore

Contributing Authors

Andrew J. Ballard, Joshua Bambrick, Sebastian W. Bodenstein, David A. Evans, Chia-Chun Hung, Michael O’Neill, David Reiman, Kathryn Tunyasuvunakool, Zachary Wu, Akvilė Žemgulytė, Eirini Arvaniti, Charles Beattie, Ottavia Bertolli, Alex Bridgland, Alexey Cherepanov, Miles Congreve, Alexander I. Cowen-Rivers, Andrew Cowie, Michael Figurnov, Fabian B. Fuchs, Hannah Gladman, Rishub Jain, Yousuf A. Khan, Caroline M. R. Low, Kuba Perlin, Anna Potapenko, Pascal Savy, Sukhdeep Singh, Adrian Stecula, Ashok Thillaisundaram, Catherine Tong, Sergei Yakneen, Ellen D. Zhong, Michal Zielinski, Augustin Žídek

Senior Authors

Victor Bapst, Pushmeet Kohli, Max Jaderberg, Demis Hassabis, John M. Jumper

What to Cite

You must cite AlphaFold 3 if you use any of the following:

Source Code

  • The AlphaFold 3 GitHub repository
  • Any code derived from AlphaFold 3
  • Modified versions of AlphaFold 3

Model Parameters

  • Pre-trained model weights
  • Fine-tuned models based on AlphaFold 3

Outputs

  • Predicted structures (CIF files)
  • Confidence scores
  • Any analysis or findings derived from AlphaFold 3 predictions

Methods

  • If AlphaFold 3 was used in your methodology
  • Even if results are not shown but informed the research

Additional References

Supplementary Information

For detailed method descriptions, please also refer to the Supplementary Information of the AlphaFold 3 paper:
  • Detailed architecture descriptions
  • Training procedures
  • Validation benchmarks
  • Limitations and caveats
If you also use AlphaFold 2, cite:

License Information

AlphaFold 3 is licensed for non-commercial use only.

Source Code License

The AlphaFold 3 source code is licensed under: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC-BY-NC-SA 4.0)
  • Attribution: Must cite the paper
  • NonCommercial: No commercial use
  • ShareAlike: Derivative works must use the same license
License text: https://github.com/google-deepmind/alphafold3/blob/main/LICENSE

Model Parameters License

The AlphaFold 3 model parameters are subject to separate terms: AlphaFold 3 Model Parameters Terms of Use
  • You may only use parameters received directly from Google
  • Non-commercial use only
  • Additional restrictions apply
Terms: https://github.com/google-deepmind/alphafold3/blob/main/WEIGHTS_TERMS_OF_USE.md

Acknowledgments in Publications

Suggested Acknowledgment Text

Consider including an acknowledgment like:
“Structure predictions were performed using AlphaFold 3 (Abramson et al., Nature 2024). We thank Google DeepMind for making the AlphaFold 3 code and model parameters available for non-commercial use.”

Funding and Support

If appropriate, acknowledge:
  • Google DeepMind and Isomorphic Labs for developing AlphaFold 3
  • Computational resources used for running predictions
  • Any grants or funding that supported the research

Questions About Citation

If you have questions about how to cite AlphaFold 3 or licensing: Email: alphafold@google.com

Disclaimer

AlphaFold 3 and its outputs are for theoretical modeling only. Not intended, validated, or approved for clinical use.
AlphaFold 3 outputs are predictions with varying confidence levels and should be interpreted carefully. Always:
  • Validate predictions experimentally when possible
  • Check confidence scores (pLDDT, ranking scores)
  • Use discretion before relying on predictions
  • Do not use for clinical or medical decisions
  • Clearly communicate prediction uncertainty in publications