Recent advancements in computational tools have allowed protein structure prediction with high accuracy. Computational prediction methods have been used for modeling many soluble and membrane proteins, but the performance of these methods in modeling peptide structures has not yet been systematically investigated. We benchmarked the accuracy of AlphaFold2 in predicting 588 peptide structures between 10 and 40 amino acids using experimentally determined NMR structures as reference. Our results showed AlphaFold2 predicts $\alpha$-helical, $\beta$-hairpin, and disulfide-rich peptides with high accuracy. AlphaFold2 performed at least as well if not better than alternative methods developed specifically for peptide structure prediction. AlphaFold2 showed several shortcomings in predicting $\Phi$/$\Psi$ angles, disulfide bond patterns, and the lowest RMSD structures failed to correlate with lowest pLDDT ranked structures. In summary, computation can be a powerful tool to predict peptide structures, but additional steps may be necessary to analyze and validate the results.
%0 Journal Article
%1 McDonald2023-ds
%A McDonald, Eli Fritz
%A Jones, Taylor
%A Plate, Lars
%A Meiler, Jens
%A Gulsevin, Alican
%D 2023
%I Elsevier BV
%J Structure
%K AlphaFold2; benchmark; bonds; disulfide folding; pLDDT; peptides; prediction protein structure topic_lifescience
%N 1
%P 111--119.e2
%T Benchmarking AlphaFold2 on peptide structure prediction
%V 31
%X Recent advancements in computational tools have allowed protein structure prediction with high accuracy. Computational prediction methods have been used for modeling many soluble and membrane proteins, but the performance of these methods in modeling peptide structures has not yet been systematically investigated. We benchmarked the accuracy of AlphaFold2 in predicting 588 peptide structures between 10 and 40 amino acids using experimentally determined NMR structures as reference. Our results showed AlphaFold2 predicts $\alpha$-helical, $\beta$-hairpin, and disulfide-rich peptides with high accuracy. AlphaFold2 performed at least as well if not better than alternative methods developed specifically for peptide structure prediction. AlphaFold2 showed several shortcomings in predicting $\Phi$/$\Psi$ angles, disulfide bond patterns, and the lowest RMSD structures failed to correlate with lowest pLDDT ranked structures. In summary, computation can be a powerful tool to predict peptide structures, but additional steps may be necessary to analyze and validate the results.
@article{McDonald2023-ds,
abstract = {Recent advancements in computational tools have allowed protein structure prediction with high accuracy. Computational prediction methods have been used for modeling many soluble and membrane proteins, but the performance of these methods in modeling peptide structures has not yet been systematically investigated. We benchmarked the accuracy of AlphaFold2 in predicting 588 peptide structures between 10 and 40 amino acids using experimentally determined NMR structures as reference. Our results showed AlphaFold2 predicts $\alpha$-helical, $\beta$-hairpin, and disulfide-rich peptides with high accuracy. AlphaFold2 performed at least as well if not better than alternative methods developed specifically for peptide structure prediction. AlphaFold2 showed several shortcomings in predicting $\Phi$/$\Psi$ angles, disulfide bond patterns, and the lowest RMSD structures failed to correlate with lowest pLDDT ranked structures. In summary, computation can be a powerful tool to predict peptide structures, but additional steps may be necessary to analyze and validate the results.},
added-at = {2024-09-10T10:41:24.000+0200},
author = {McDonald, Eli Fritz and Jones, Taylor and Plate, Lars and Meiler, Jens and Gulsevin, Alican},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/280b31fd244a9c8f1ffa430c241793f11/scadsfct},
copyright = {http://www.elsevier.com/open-access/userlicense/1.0/},
interhash = {add17c841dae548ca61ae91e790a676f},
intrahash = {80b31fd244a9c8f1ffa430c241793f11},
journal = {Structure},
keywords = {AlphaFold2; benchmark; bonds; disulfide folding; pLDDT; peptides; prediction protein structure topic_lifescience},
language = {en},
month = jan,
number = 1,
pages = {111--119.e2},
publisher = {Elsevier BV},
timestamp = {2024-09-10T12:00:15.000+0200},
title = {Benchmarking {AlphaFold2} on peptide structure prediction},
volume = 31,
year = 2023
}
