Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Comment
  • Published:

Structure prediction and materials design with generative neural networks

Nature Computational Science volume 3, pages 572–574 (2023)Cite this article

Subjects

The prediction of stable crystal structures is an important part of designing solid-state crystalline materials with desired properties. Recent advances in structural feature representations and generative neural networks promise the ability to efficiently create new stable structures to use for inverse design and to search for materials with tailored functionalities.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Material property prediction and inverse design.

References

  1. Chen, W.-C., Schmidt, J. N., Yan, D., Vohra, Y. K. & Chen, C.-C. npj Comput. Mater. 7, 114 (2021).

    Article  Google Scholar 

  2. Peng, F. et al. Phys. Rev. Lett. 119, 107001 (2017).

    Article  Google Scholar 

  3. Chen, L., Zhang, W., Nie, Z., Li, S. & Pan, F. J. Mater. Inform. 1, 4 (2021).

    Google Scholar 

  4. Noh, J., Gu, G. H., Kim, S. & Jung, Y. Chem. Sci. 11, 4871–4881 (2020).

    Article  Google Scholar 

  5. Kim, S., Noh, J., Gu, G. H., Aspuru-Guzik, A. & Jung, Y. ACS Cent. Sci. 6, 1412–1420 (2020).

    Article  Google Scholar 

  6. Nouira, A., Sokolovska, N. & Crivello, J.-C. CrystalGAN: learning to discover crystallographic structures with generative adversarial networks. Preprint at https://arxiv.org/abs/1810.11203 (2018).

  7. Geiger, M. & Smidt, T. e3nn: Euclidean neural networks. Preprint at https://arxiv.org/abs/2207.09453 (2022).

  8. Levin, I. NIST Inorganic Crystal Structure Database (ICSD) (National Institute of Standards and Technology, 2018).

  9. Jain, A. et al. APL Mater. 1, 011002 (2013).

    Article  Google Scholar 

  10. Kim, Y. et al. npj Comput. Mater. 7, 140 (2021).

    Article  Google Scholar 

  11. Noh, J. et al. Matter 1, 1370–1384 (2019).

    Article  Google Scholar 

  12. Ren, Z. et al. Matter 5, 314–335 (2022).

    Article  Google Scholar 

  13. Long, T. et al. npj Comput. Mater. 7, 66 (2021).

    Article  Google Scholar 

  14. Xie, T. & Grossman, J. C. Phys. Rev. Lett. 120, 145301 (2018).

    Article  Google Scholar 

  15. Sanchez-Lengeling, B. & Aspuru-Guzik, A. Science 361, 360–365 (2018).

    Article  Google Scholar 

  16. Dieb, T. M. et al. Sci. Technol. Adv. Mater. 18, 498–503 (2017).

    Article  Google Scholar 

Download references

Acknowledgements

D.Y. acknowledges support from ARDEF 1ARDEF21 03 (ADECA) and from National Science Foundation (NSF) Award OAC-2106461. A.D.S. and C.-C.C. are supported by NSF Award RII Track-1 Future Technologies and Enabling Plasma Processes Project OIA-2148653. C.-C.C. also acknowledges support from NSF Award DMR-2142801.

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Alabama at Birmingham, Birmingham, AL, USA

    Da Yan

  2. Department of Physics, University of Alabama at Birmingham, Birmingham, AL, USA

    Adam D. Smith & Cheng-Chien Chen

Authors
  1. Da Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Adam D. Smith
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Cheng-Chien Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors developed the content outline, wrote the manuscript, and created the figure.

Corresponding authors

Correspondence to Da Yan, Adam D. Smith or Cheng-Chien Chen.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yan, D., Smith, A.D. & Chen, CC. Structure prediction and materials design with generative neural networks. Nat Comput Sci 3, 572–574 (2023). https://doi.org/10.1038/s43588-023-00471-w

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s43588-023-00471-w

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing