Skip to main content

Thank you for visiting 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.


Neural networks learn the motions of molecular machines

New computational approaches capture molecular motion from cryo-EM images and provide a more complete understanding of protein dynamics.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Two possible motions of the yeast spliceosome, a highly dynamic complex.


  1. 1.

    Zhong, E. D., Bepler, T., Berger, B. & Davis, J. H. Nat. Methods 18, 176–185 (2021).

    CAS  Article  Google Scholar 

  2. 2.

    Chen, M. & Ludtke, S. Nat. Methods (2021).

  3. 3.

    Yip, K. M., Fischer, N., Paknia, E., Chari, A. & Stark, H. Nature 587, 157–161 (2020).

    CAS  Article  Google Scholar 

  4. 4.

    Nakane, T. et al. Nature 587, 152–156 (2020).

    CAS  Article  Google Scholar 

  5. 5.

    Cheng, Y., Grigorieff, N., Penczek, P. A. & Walz, T. Cell 161, 438–449 (2015).

    CAS  Article  Google Scholar 

  6. 6.

    Punjani, A. & Fleet, D. J. Preprint at bioRxiv (2021).

Download references

Author information



Corresponding author

Correspondence to Timothy Grant.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Grant, T. Neural networks learn the motions of molecular machines. Nat Methods 18, 869–871 (2021).

Download citation


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