EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Geometric epitope and paratope prediction

Marco Pegoraro iD, Clémentine Dominé iD, Emanuele Rodolà, Petar Veličković, Andreea Deac

Bioinformatics · 01.07.2024 · 40 (7)

DOI: 10.1093/bioinformatics/btae405 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 10.07.2024. Verfasst von Marco Pegoraro und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Sapienza University of Rome, 00185, Italy. Hauptthemen laut MEDLINE: Deep Learning, Epitopes. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ERC, Sapienza University of Rome.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Identifying the binding sites of antibodies is essential for developing vaccines and synthetic antibodies. In this article, we investigate the optimal representation for predicting the binding sites in the two molecules and emphasize the importance of geometric information. Results Specifically, we compare different geometric deep learning methods applied to proteins’ inner (I-GEP) and outer (O-GEP) structures. We incorporate 3D coordinates and spectral geometric descriptors as input features to fully leverage the geometric information. Our research suggests that different geometrical representation information is useful for different tasks. Surface-based models are more efficient in predicting the binding of the epitope, while graph models are better in paratope prediction, both achieving significant performance improvements. Moreover, we analyze the impact of structural changes in antibodies and antigens resulting from conformational rearrangements or reconstruction errors. Through this investigation, we showcase the robustness of geometric deep learning methods and spectral geometric descriptors to such perturbations. Availability and Implementation The python code for the models, together with the data and the processing pipeline, is open-source and available at https://github.com/Marco-Peg/GEP.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningEpitopesComputational BiologyProtein ConformationAntibodiesSoftwareBinding Sites

Substanzen

EpitopesAntibodies

Autor:innen und Institutionen

  • Department of Computer Science, Sapienza University of Rome, 00185, Italy.
  • Gatsby Computational Neuroscience Unit, University College London, W1T 4JG, United-Kingdom.
  • Google-DeepMind, 6-8 Handyside Street, London N1C 4UZ, UK.
  • Département d'informatique et de recherche opérationelle, Université de Montréal, QC H2S 3H1, Canada.

ORCID-Profile: Marco Pegoraro, Clémentine Dominé

Förderung

  • ERC
  • Sapienza University of Rome

Zitieren

APA

Pegoraro, M., Dominé, C., Rodolà, E., Veličković, P., & Deac, A. (2024). Geometric epitope and paratope prediction. Bioinformatics, 40(7). https://doi.org/10.1093/bioinformatics/btae405

Vancouver

Pegoraro M, Dominé C, Rodolà E, Veličković P, Deac A. Geometric epitope and paratope prediction. Bioinformatics. 2024;40(7). doi:10.1093/bioinformatics/btae405

BibTeX
@article{Pegoraro2024,
  author = {Pegoraro, Marco and Dominé, Clémentine and Rodolà, Emanuele and Veličković, Petar and Deac, Andreea},
  title = {Geometric epitope and paratope prediction},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {7},
  doi = {10.1093/bioinformatics/btae405}
}
Kostenlos starten →