Prediction of Paratope–Epitope Pairs Using Convolutional Neural Networks
International Journal of Molecular Sciences · 16.05.2024 · 25 (10) · 5434
DOI: 10.3390/ijms25105434 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 16.05.2024. Verfasst von Dong Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: Computational Biology and Bioinformatics, Université Libre de Bruxelles, 1050 Brussels, Belgium. Hauptthemen laut MEDLINE: Epitopes, Neural Networks, Computer. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FNRS, Chinese Scholarship Council, FNRS-Belgian Fund.
Abstract (Originalsprache)
Antibodies play a central role in the adaptive immune response of vertebrates through the specific recognition of exogenous or endogenous antigens. The rational design of antibodies has a wide range of biotechnological and medical applications, such as in disease diagnosis and treatment. However, there are currently no reliable methods for predicting the antibodies that recognize a specific antigen region (or epitope) and, conversely, epitopes that recognize the binding region of a given antibody (or paratope). To fill this gap, we developed ImaPEp, a machine learning-based tool for predicting the binding probability of paratope–epitope pairs, where the epitope and paratope patches were simplified into interacting two-dimensional patches, which were colored according to the values of selected features, and pixelated. The specific recognition of an epitope image by a paratope image was achieved by using a convolutional neural network-based model, which was trained on a set of two-dimensional paratope–epitope images derived from experimental structures of antibody–antigen complexes. Our method achieves good performances in terms of cross-validation with a balanced accuracy of 0.8. Finally, we showcase examples of application of ImaPep, including extensive screening of large libraries to identify paratope candidates that bind to a selected epitope, and rescoring and refining antibody–antigen docking poses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Computational Biology and Bioinformatics, Université Libre de Bruxelles, 1050 Brussels, Belgium.
- Interuniversity Institute of Bioinformatics in Brussels, 1050 Brussels, Belgium.
ORCID-Profile: Dong Li
Förderung
- FNRS
- Chinese Scholarship Council
- FNRS-Belgian Fund
- China Scholarship Council
Zitieren
APA
Li, D., Pucci, F., & Rooman, M. (2024). Prediction of Paratope–Epitope Pairs Using Convolutional Neural Networks. International Journal of Molecular Sciences, 25(10), 5434. https://doi.org/10.3390/ijms25105434
Vancouver
Li D, Pucci F, Rooman M. Prediction of Paratope–Epitope Pairs Using Convolutional Neural Networks. International Journal of Molecular Sciences. 2024;25(10):5434. doi:10.3390/ijms25105434
BibTeX
@article{Li2024,
author = {Li, Dong and Pucci, Fabrizio and Rooman, Marianne},
title = {Prediction of Paratope–Epitope Pairs Using Convolutional Neural Networks},
journal = {International Journal of Molecular Sciences},
year = {2024},
volume = {25},
number = {10},
pages = {5434},
doi = {10.3390/ijms25105434}
}
EUVIMED