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.

MACHINE LEARNING FOR BIOLOGY

Protein structure prediction beyond AlphaFold

Nature Machine Intelligence volume 1, pages 336–337 (2019)Cite this article

Subjects

DeepMind’s AlphaFold recently demonstrated the potential of deep learning for protein structure prediction. DeepFragLib, a new protein-specific fragment library built using deep neural networks, may have advanced the field to the next stage.

There are currently two main categories of protein structure prediction techniques: template-based models and template-free models, depending on whether or not an existing template structure is employed. Template-based modelling is typically more accurate if a good template can be found, as it exploits existing protein structures. Technically, this approach is relatively mature and can be used by non-experts. However, for a protein without any existing template, template-free modelling has to be employed to construct its structure. There are two significant types of template-free modelling approaches: fragment-based assembly and ab initio or de novo folding. The latter seeks to build 3D structures ‘from scratch’ using physical principles. The success of de novo methods depends crucially on an accurate energy function, an efficient conformational search algorithm for identifying low-energy states, and the ability to discriminate native-like structures from decoys. However, fragment-based assembly is the dominant technique due to its higher accuracy and higher capability whenever a good template is difficult to identify or otherwise unavailable.

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

Relevant articles

Open Access articles citing this article.

Access options

Rent or buy this article

Get just this article for as long as you need it

$39.95

Learn more

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

References

  1. AlQuraishi, M. Bioinformatics https://doi.org/10.1093/bioinformatics/btz422 (2019).

  2. Moult, J., Fidelis, K., Kryshtafovych, A., Schwede, T. & Tramontano, A. Proteins 86, 7–15 (2018).

    Article  Google Scholar 

  3. Wang, T. et al. Nat. Mach. Intell. https://doi.org/10.1038/s42256-019-0075-7 (2019).

  4. Wang, S., Sun, S., Li, Z., Zhang, R. & Xu, J. PLoS Comput. Biol. 13, e1005324 (2017).

    Article  Google Scholar 

  5. Zhou, Y., Zhou, H., Zhang, C. & Liu, S. Cell Biochem. Biophys. 46, 165–174 (2006).

    Article  Google Scholar 

  6. Chandonia, J.-M., Fox, N. K. & Brenner, S. E. J. Mol. Biol. 429, 348–355 (2017).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics, Michigan State University, East Lansing, MI, USA

    Guo-Wei Wei

  2. Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, MI, USA

    Guo-Wei Wei

  3. Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA

    Guo-Wei Wei

Authors
  1. Guo-Wei Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Guo-Wei Wei.

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

Wei, GW. Protein structure prediction beyond AlphaFold. Nat Mach Intell 1, 336–337 (2019). https://doi.org/10.1038/s42256-019-0086-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-019-0086-4

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