AlphaFold Models of Small Proteins Rival the Accuracy of Solution NMR Structures
- PMID: 35769913
- PMCID: PMC9234698
- DOI: 10.3389/fmolb.2022.877000
AlphaFold Models of Small Proteins Rival the Accuracy of Solution NMR Structures
Abstract
Recent advances in molecular modeling using deep learning have the potential to revolutionize the field of structural biology. In particular, AlphaFold has been observed to provide models of protein structures with accuracies rivaling medium-resolution X-ray crystal structures, and with excellent atomic coordinate matches to experimental protein NMR and cryo-electron microscopy structures. Here we assess the hypothesis that AlphaFold models of small, relatively rigid proteins have accuracies (based on comparison against experimental data) similar to experimental solution NMR structures. We selected six representative small proteins with structures determined by both NMR and X-ray crystallography, and modeled each of them using AlphaFold. Using several structure validation tools integrated under the Protein Structure Validation Software suite (PSVS), we then assessed how well these models fit to experimental NMR data, including NOESY peak lists (RPF-DP scores), comparisons between predicted rigidity and chemical shift data (ANSURR scores), and 15N-1H residual dipolar coupling data (RDC Q factors) analyzed by software tools integrated in the PSVS suite. Remarkably, the fits to NMR data for the protein structure models predicted with AlphaFold are generally similar, or better, than for the corresponding experimental NMR or X-ray crystal structures. Similar conclusions were reached in comparing AlphaFold2 predictions and NMR structures for three targets from the Critical Assessment of Protein Structure Prediction (CASP). These results contradict the widely held misperception that AlphaFold cannot accurately model solution NMR structures. They also document the value of PSVS for model vs. data assessment of protein NMR structures, and the potential for using AlphaFold models for guiding analysis of experimental NMR data and more generally in structural biology.
Keywords: AlphaFold; X-ray crystal structure analysis; artificial inteligence; automated structure determination; protein NMR; protein structure prediction; structure validation.
Copyright © 2022 Tejero, Huang, Ramelot and Montelione.
Conflict of interest statement
GTM is a founder of Nexomics Biosciences, Inc. The remaining 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](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/9234698/bin/fmolb-09-877000-g001.gif)
![FIGURE 2](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/9234698/bin/fmolb-09-877000-g002.gif)
![FIGURE 3](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/9234698/bin/fmolb-09-877000-g003.gif)
![FIGURE 4](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/9234698/bin/fmolb-09-877000-g004.gif)
![FIGURE 5](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/9234698/bin/fmolb-09-877000-g005.gif)
![FIGURE 6](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/9234698/bin/fmolb-09-877000-g006.gif)
![FIGURE 7](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/9234698/bin/fmolb-09-877000-g007.gif)
Similar articles
-
Blind Assessment of Monomeric AlphaFold2 Protein Structure Models with Experimental NMR Data.bioRxiv [Preprint]. 2023 Jan 22:2023.01.22.525096. doi: 10.1101/2023.01.22.525096. bioRxiv. 2023. Update in: J Magn Reson. 2023 Jul;352:107481. doi: 10.1016/j.jmr.2023.107481. PMID: 36712039 Free PMC article. Updated. Preprint.
-
Blind assessment of monomeric AlphaFold2 protein structure models with experimental NMR data.J Magn Reson. 2023 Jul;352:107481. doi: 10.1016/j.jmr.2023.107481. Epub 2023 May 20. J Magn Reson. 2023. PMID: 37257257 Free PMC article.
-
The accuracy of protein structures in solution determined by AlphaFold and NMR.Structure. 2022 Jul 7;30(7):925-933.e2. doi: 10.1016/j.str.2022.04.005. Epub 2022 May 9. Structure. 2022. PMID: 35537451 Free PMC article.
-
AlphaFold 2 and NMR Spectroscopy: Partners to Understand Protein Structure, Dynamics and Function.Front Mol Biosci. 2022 May 17;9:906437. doi: 10.3389/fmolb.2022.906437. eCollection 2022. Front Mol Biosci. 2022. PMID: 35655760 Free PMC article. Review.
-
Prediction of protein structure and AI.J Hum Genet. 2024 Jan 4. doi: 10.1038/s10038-023-01215-4. Online ahead of print. J Hum Genet. 2024. PMID: 38177398 Review.
Cited by
-
Insights into AlphaFold's breakthrough in neurodegenerative diseases.Ir J Med Sci. 2024 Jun 4. doi: 10.1007/s11845-024-03721-6. Online ahead of print. Ir J Med Sci. 2024. PMID: 38833116
-
The 100-protein NMR spectra dataset: A resource for biomolecular NMR data analysis.Sci Data. 2024 Jan 4;11(1):30. doi: 10.1038/s41597-023-02879-5. Sci Data. 2024. PMID: 38177162 Free PMC article.
-
How accurately can one predict drug binding modes using AlphaFold models?Elife. 2023 Dec 22;12:RP89386. doi: 10.7554/eLife.89386. Elife. 2023. PMID: 38131311 Free PMC article.
-
Exposing the small protein load of bacterial life.FEMS Microbiol Rev. 2023 Nov 1;47(6):fuad063. doi: 10.1093/femsre/fuad063. FEMS Microbiol Rev. 2023. PMID: 38012116 Free PMC article. Review.
-
Modelling peptide-protein complexes: docking, simulations and machine learning.QRB Discov. 2022 Sep 19;3:e17. doi: 10.1017/qrd.2022.14. eCollection 2022. QRB Discov. 2022. PMID: 37529282 Free PMC article.
References
Grants and funding
LinkOut - more resources
Full Text Sources