AlphaFold 2, but not AlphaFold 3, predicts confident but unrealistic β-solenoid structures for repeat proteins
Computational and Structural Biotechnology Journal · 01.01.2025 · 27 · 467-477
DOI: 10.1016/j.csbj.2025.01.016 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 25.01.2025. Verfasst von Olivia S Pratt und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biochemistry, Cell and Systems, Biology, Institute of Structural, Molecular and Integrative Biology, University of Liverpool, Crown Str…. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Biotechnology and Biological Sciences Research Council.
Abstract (Originalsprache)
AlphaFold 2 (AF2) has revolutionised protein structure prediction but, like any new tool, its performance on specific classes of targets, especially those potentially under-represented in its training data, merits attention. Prompted by a highly confident prediction for a biologically meaningless, randomly permuted repeat sequence, we assessed AF2 performance on sequences composed of perfect repeats of random sequences of different lengths. AF2 frequently folds such sequences into β-solenoids which, while ascribed high confidence, contain unusual and implausible features such as internally stacked and uncompensated charged residues. A number of sequences confidently predicted as β-solenoids are predicted by other advanced methods as intrinsically disordered. The instability of some predictions is demonstrated by molecular dynamics. Importantly, other deep learning-based structure prediction tools predict different structures or β-solenoids with much lower confidence suggesting that AF2 alone has an unreasonable tendency to predict confident but unrealistic β-solenoids for perfect repeat sequences. The potential implications for structure prediction of natural (near-)perfect sequence repeat proteins are also explored.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biochemistry, Cell and Systems, Biology, Institute of Structural, Molecular and Integrative Biology, University of Liverpool, Crown Street, Liverpool L69 7ZB, United Kingdom.
- Department of Chemistry, University of Liverpool, Crown Street, Liverpool L69 7ZD, United Kingdom.
- Computational Biology Facility, MerseyBio,University of Liverpool, Crown Street, Liverpool L69 7ZB, United Kingdom.
Förderung
- Biotechnology and Biological Sciences Research Council
Zitieren
APA
Pratt, O. S., Elliott, L. G., Haon, M., Mesdaghi, S., Price, R. M., Simpkin, A. J., & Rigden, D. J. (2025). AlphaFold 2, but not AlphaFold 3, predicts confident but unrealistic β-solenoid structures for repeat proteins. Computational and Structural Biotechnology Journal, 27, 467-477. https://doi.org/10.1016/j.csbj.2025.01.016
Vancouver
Pratt OS, Elliott LG, Haon M, Mesdaghi S, Price RM, Simpkin AJ, et al. AlphaFold 2, but not AlphaFold 3, predicts confident but unrealistic β-solenoid structures for repeat proteins. Computational and Structural Biotechnology Journal. 2025;27:467-477. doi:10.1016/j.csbj.2025.01.016
BibTeX
@article{Pratt2025,
author = {Pratt, Olivia S and Elliott, Luc G and Haon, Margaux and Mesdaghi, Shahram and Price, Rebecca M and Simpkin, Adam J and Rigden, Daniel J},
title = {AlphaFold 2, but not AlphaFold 3, predicts confident but unrealistic β-solenoid structures for repeat proteins},
journal = {Computational and Structural Biotechnology Journal},
year = {2025},
volume = {27},
pages = {467--477},
doi = {10.1016/j.csbj.2025.01.016}
}
EUVIMED