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
. 2023 Jun 22:10:1208810.
doi: 10.3389/fmolb.2023.1208810. eCollection 2023.

AI-based protein models enhance the accuracy of experimentally determined protein crystal structures

Ki Hyun Nam  1   2
Affiliations

AI-based protein models enhance the accuracy of experimentally determined protein crystal structures

Ki Hyun Nam. Front Mol Biosci. .
No abstract available

Keywords: AlphaFold; artificial intelligence; model structure; protein structure; re-refinement.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

FIGURE 1
FIGURE 1
Improvement of experimentally determined the lumenal domains of Calnexin (PDB code: 1JHN) and Delta-aminolevulinic acid dehydratase (ALAD) (PDB code: 2Z1B) by using the AI system AlphaFold. The regions Asn262–Pro270 of the lumenal domain and Val121–Leu142 of ALAD were reconstructed using the AI model structure. (A) Experimentally determined structures (B) Superimposition of the AI models on the experimentally determined model structures (C) COOT program-based real-space refinement of the Al model structure followed by a subsequent re-refinement using the phenix.refine software. The 2Fo-Fc (blue, 1 σ) and Fo-Fc (green for 3 σ and red for −3 σ) electron density maps are illustrated in mesh. (D) Cartoon representation of the experimentally determined and improved model structures in accordance with the AI model structure. The regions where amino acid model building was not performed are indicated by white arrows or dotted lines.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Baek M., DiMaio F., Anishchenko I., Dauparas J., Ovchinnikov S., Lee G. R., et al. (2021). Accurate prediction of protein structures and interactions using a three-track neural network. Science 373 (6557), 871–876. 10.1126/science.abj8754 - DOI - PMC - PubMed
    1. Bittrich S., Bhikadiya C., Bi C., Chao H., Duarte J. M., Dutta S., et al. (2023). RCSB protein Data Bank: Efficient searching and simultaneous access to one million computed structure models alongside the PDB structures enabled by architectural advances. J. Mol. Biol., 167994. 10.1016/j.jmb.2023.167994 - DOI - PubMed
    1. Blakeley M. P., Hasnain S. S., Antonyuk S. V. (2015). Sub-atomic resolution X-ray crystallography and neutron crystallography: Promise, challenges and potential. IUCrJ 2 (4), 464–474. 10.1107/s2052252515011239 - DOI - PMC - PubMed
    1. Bornscheuer U. T., Huisman G. W., Kazlauskas R. J., Lutz S., Moore J. C., Robins K. (2012). Engineering the third wave of biocatalysis. Nature 485 (7397), 185–194. 10.1038/nature11117 - DOI - PubMed
    1. Callaway E. (2020). ‘It will change everything’: DeepMind’s AI makes gigantic leap in solving protein structures. Nature 588 (7837), 203–204. 10.1038/d41586-020-03348-4 - DOI - PubMed

Grants and funding

This work was funded by the National Research Foundation of Korea (NRF) (NRF-2017M3A9F6029736 and NRF-2021R1I1A1A01050838) and Korea Initiative for Fostering University of Research and Innovation (KIURI) Program of the NRF (NRF-2020M3H1A1075314). This study was supported by ProGen.

LinkOut - more resources

-