Evaluating AlphaFold Tools and Related Scoring Functions for Protein–peptide Complex Prediction
Genomics, Proteomics & Bioinformatics · 2026
DOI: 10.1093/gpbjnl/qzag026 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift Genomics, Proteomics & Bioinformatics, 2026. Verfasst von Negin Manshour und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, Christopher S. Bond Life Sciences Center, NextGen Precision Health, University of Missouri…. Hauptthemen laut MEDLINE: Proteins, Peptides, Software, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS.
Abstract (Originalsprache)
Determining the three-dimensional structures of protein–peptide complexes is crucial for elucidating biological processes and designing peptide-based drugs. Protein–peptide docking has become essential for predicting complex structures. AlphaFold-Multimer, ColabFold, and AlphaFold3 are groundbreaking tools that enhance protein–peptide docking accuracy. In this study, we evaluated these three tools for predicting protein–peptide complex structures in both template-based (TB) and template-free (TF) modes. AlphaFold-Multimer excels in TB predictions and performs moderately in TF scenarios in the prediction pool; however, TF outperforms TB in the first-ranked models. ColabFold demonstrates versatility in both TB and TF settings. AlphaFold3 generates high-quality structures for more proteins, but its medium-accuracy predictions are not as good as those of AlphaFold-Multimer using a large model pool. We also assessed the performance of various scoring functions in ranking predicted protein–peptide complex structures. While the scoring function built in AlphaFold demonstrates the best performance, some other scoring functions, e.g., FoldX-Stability and HADDOCK-mdscore, provide complementary information for model ranking. These findings suggest the potential for enhancing scoring functions targeting AlphaFold-based predictions by combining multiple scoring functions or using a consensus approach from many prediction models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Electrical Engineering and Computer Science, Christopher S. Bond Life Sciences Center, NextGen Precision Health, University of Missouri, Columbia, MO 65211, USA.
- Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD 21218, USA.
ORCID-Profile: Negin Manshour, Jarett Zida Ren, Farzaneh Esmaili, Erik Bergstrom, Dong Xu 许东
Förderung
- NIGMS NIH HHS
Zitieren
APA
Manshour, N., Ren, J. Z., Esmaili, F., Bergstrom, E., & Xu 许东, D. (2026). Evaluating AlphaFold Tools and Related Scoring Functions for Protein–peptide Complex Prediction. Genomics, Proteomics & Bioinformatics. https://doi.org/10.1093/gpbjnl/qzag026
Vancouver
Manshour N, Ren JZ, Esmaili F, Bergstrom E, Xu 许东 D. Evaluating AlphaFold Tools and Related Scoring Functions for Protein–peptide Complex Prediction. Genomics, Proteomics & Bioinformatics. 2026. doi:10.1093/gpbjnl/qzag026
BibTeX
@article{Manshour2026,
author = {Manshour, Negin and Ren, Jarett Zida and Esmaili, Farzaneh and Bergstrom, Erik and Xu 许东, Dong},
title = {Evaluating AlphaFold Tools and Related Scoring Functions for Protein–peptide Complex Prediction},
journal = {Genomics, Proteomics & Bioinformatics},
year = {2026},
doi = {10.1093/gpbjnl/qzag026}
}
EUVIMED