EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Towards the accurate modelling of antibody−antigen complexes from sequence using machine learning and information-driven docking

Marco Giulini iD, Constantin Schneider, Daniel Cutting, Nikita Desai, Charlotte M Deane, Alexandre M J J Bonvin iD

Bioinformatics · 2024

DOI: 10.1093/bioinformatics/btae583 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Marco Giulini und 5 weiteren Autor:innen. Beteiligte Einrichtung: Bijvoet Centre for Biomolecular Research, Faculty of Science-Chemistry, Utrecht University, Utrecht CH 3584, The Netherlands. Hauptthemen laut MEDLINE: Molecular Docking Simulation, Antigen-Antibody Complex, Machine Learning. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union Horizon 2020, EGI-ACE, Netherlands e-Science Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Antibody−antigen complex modelling is an important step in computational workflows for therapeutic antibody design. While experimentally determined structures of both antibody and the cognate antigen are often not available, recent advances in machine learning-driven protein modelling have enabled accurate prediction of both antibody and antigen structures. Here, we analyse the ability of protein−protein docking tools to use machine learning generated input structures for information-driven docking. Results In an information-driven scenario, we find that HADDOCK can generate accurate models of antibody−antigen complexes using an ensemble of antibody structures generated by machine learning tools and AlphaFold2 predicted antigen structures. Targeted docking using knowledge of the complementary determining regions on the antibody and some information about the targeted epitope allows the generation of high-quality models of the complex with reduced sampling, resulting in a computationally cheap protocol that outperforms the ZDOCK baseline. Availability and implementation The source code of HADDOCK3 is freely available at github.com/haddocking/haddock3. The code to generate and analyse the data is available at github.com/haddocking/ai-antibodies. The full runs, including docking models from all modules of a workflow have been deposited in our lab collection (data.sbgrid.org/labs/32/1139) at the SBGRID data repository.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Molecular Docking SimulationAntigen-Antibody ComplexMachine LearningSoftwareAntibodiesAntigensEpitopes

Substanzen

Antigen-Antibody ComplexAntibodiesAntigensEpitopes

Autor:innen und Institutionen

  • Bijvoet Centre for Biomolecular Research, Faculty of Science-Chemistry, Utrecht University, Utrecht CH 3584, The Netherlands.
  • Exscientia Plc, Oxford OX4 4GE, United Kingdom.

ORCID-Profile: Marco Giulini, Alexandre M J J Bonvin

Förderung

  • European Union Horizon 2020
  • EGI-ACE
  • Netherlands e-Science Center

Zitieren

APA

Giulini, M., Schneider, C., Cutting, D., Desai, N., Deane, C. M., & Bonvin, A. M. J. J. (2024). Towards the accurate modelling of antibody−antigen complexes from sequence using machine learning and information-driven docking. Bioinformatics. https://doi.org/10.1093/bioinformatics/btae583

Vancouver

Giulini M, Schneider C, Cutting D, Desai N, Deane CM, Bonvin AMJJ. Towards the accurate modelling of antibody−antigen complexes from sequence using machine learning and information-driven docking. Bioinformatics. 2024. doi:10.1093/bioinformatics/btae583

BibTeX
@article{Giulini2024,
  author = {Giulini, Marco and Schneider, Constantin and Cutting, Daniel and Desai, Nikita and Deane, Charlotte M and Bonvin, Alexandre M J J},
  title = {Towards the accurate modelling of antibody−antigen complexes from sequence using machine learning and information-driven docking},
  journal = {Bioinformatics},
  year = {2024},
  doi = {10.1093/bioinformatics/btae583}
}
Kostenlos starten →