Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2024 Mar;20(3):162-169.
doi: 10.1038/s44320-024-00016-x. Epub 2024 Jan 30.

Deep learning for protein structure prediction and design-progress and applications

Jürgen Jänes  1   2 , Pedro Beltrao  3   4
Affiliations
Review

Deep learning for protein structure prediction and design-progress and applications

Jürgen Jänes et al. Mol Syst Biol. 2024 Mar.

Abstract

Proteins are the key molecular machines that orchestrate all biological processes of the cell. Most proteins fold into three-dimensional shapes that are critical for their function. Studying the 3D shape of proteins can inform us of the mechanisms that underlie biological processes in living cells and can have practical applications in the study of disease mutations or the discovery of novel drug treatments. Here, we review the progress made in sequence-based prediction of protein structures with a focus on applications that go beyond the prediction of single monomer structures. This includes the application of deep learning methods for the prediction of structures of protein complexes, different conformations, the evolution of protein structures and the application of these methods to protein design. These developments create new opportunities for research that will have impact across many areas of biomedical research.

Keywords: AlphaFold2; Protein Conformations; Protein Design; Structural Bioinformatics; Structural Systems Biology.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1. Example applications of AlphaFold2 beyond single protein structure prediction.
(A) Alphafold2 has shown to be capable of predicting structures for binary protein complexes but predicting structures for larger assemblies remains challenging. A suggested procedure has been to predict the structures for possible sub-complexes and then combine them using superimposition of common subunits (see main text). (B) While AlphaFold2 is trained to predict a single conformation, it has been shown that subsampling of the alignment that serves as the main input, can result in the prediction of different conformations that sometimes resemble known conformations.
Figure 2
Figure 2. Proteome-wide structural systems biology.
Structural details for the initial steps of EFG pathway activation. For representation, the AlphaFold2 predicted structures of pathway components were combined with experimental structures from years of study of this pathway, including PDB ids: 1egf, 1nql, 1m17, 2jwa, 3njp, 2gs6, 1gri, 1xd2, 3ksy, 5p21, 6xi7, 6q0j, 2y4i, 1pme. The AlphaFold2 models help complete the missing protein sequence information not represented in the experimental results, in particular for the long unstructured regions. The example is inspired by similar visualization in PDB-101 (https://pdb101.rcsb.org/learn/exploring-the-structural-biology-of-cancer). It may become possible to use the protein sequences and structures to derive reaction parameters that would allow us to better understand the mechanisms underlying a system of interest.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Ahdritz G, Bouatta N, Kadyan S, Xia Q, Gerecke W, O’Donnell TJ, Berenberg D, Fisk I, Zanichelli N, Zhang B et al (2022) OpenFold: retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. Preprint at bioRxiv 10.1101/2022.11.20.517210 - PubMed
    1. Akdel M, Pires DEV, Pardo EP, Jänes J, Zalevsky AO, Mészáros B, Bryant P, Good LL, Laskowski RA, Pozzati G, et al. A structural biology community assessment of AlphaFold2 applications. Nat Struct Mol Biol. 2022;29:1056–1067. doi: 10.1038/s41594-022-00849-w. - DOI - PMC - PubMed
    1. AlQuraishi M. End-to-end differentiable learning of protein structure. Cell Syst. 2019;8:292–301.e3. doi: 10.1016/j.cels.2019.03.006. - DOI - PMC - PubMed
    1. AlQuraishi M. Machine learning in protein structure prediction. Curr Opin Chem Biol. 2021;65:1–8. doi: 10.1016/j.cbpa.2021.04.005. - DOI - PubMed
    1. Anand N, Eguchi R, Mathews II, Perez CP, Derry A, Altman RB, Huang P-S. Protein sequence design with a learned potential. Nat Commun. 2022;13:746. doi: 10.1038/s41467-022-28313-9. - DOI - PMC - PubMed