• Towards the accurate modelling...

*Result*: Towards the accurate modelling of antibody-antigen complexes from sequence using machine learning and information-driven docking.

Title:
Towards the accurate modelling of antibody-antigen complexes from sequence using machine learning and information-driven docking.
Authors:
Giulini M; Bijvoet Centre for Biomolecular Research, Faculty of Science-Chemistry, Utrecht University, Utrecht CH 3584, The Netherlands., Schneider C; Exscientia Plc, Oxford OX4 4GE, United Kingdom., Cutting D; Exscientia Plc, Oxford OX4 4GE, United Kingdom., Desai N; Exscientia Plc, Oxford OX4 4GE, United Kingdom., Deane CM; Exscientia Plc, Oxford OX4 4GE, United Kingdom., Bonvin AMJJ; Bijvoet Centre for Biomolecular Research, Faculty of Science-Chemistry, Utrecht University, Utrecht CH 3584, The Netherlands.
Source:
Bioinformatics (Oxford, England) [Bioinformatics] 2024 Oct 01; Vol. 40 (10).
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Oxford University Press Country of Publication: England NLM ID: 9808944 Publication Model: Print Cited Medium: Internet ISSN: 1367-4811 (Electronic) Linking ISSN: 13674803 NLM ISO Abbreviation: Bioinformatics Subsets: MEDLINE
Imprint Name(s):
Original Publication: Oxford : Oxford University Press, c1998-
MeSH Terms:
Antigen-Antibody Complex*/chemistry , Molecular Docking Simulation* , Machine Learning*, Antibodies/chemistry ; Antigens/chemistry ; Antigens/immunology ; Epitopes/chemistry ; Epitopes/immunology ; Software
References:
Nature. 2021 Aug;596(7873):590-596. (PMID: 34293799)
Science. 2021 Aug 20;373(6557):871-876. (PMID: 34282049)
Proteins. 2012 Jul;80(7):1810-7. (PMID: 22489062)
J Am Chem Soc. 1988 Mar 1;110(6):1657-66. (PMID: 27557051)
N Biotechnol. 2011 Sep;28(5):435-47. (PMID: 21477671)
Proteins. 2023 Dec;91(12):1658-1683. (PMID: 37905971)
Proteins. 2017 Mar;85(3):417-423. (PMID: 27802573)
Proteins. 2021 Dec;89(12):1800-1823. (PMID: 34453465)
Proteins. 2003 Jul 1;52(1):2-9. (PMID: 12784359)
PLoS Comput Biol. 2017 Jul 26;13(7):e1005659. (PMID: 28746339)
Proteins. 2003 Jul 1;52(1):51-67. (PMID: 12784368)
Proteins. 2003 Jul 1;52(1):88-91. (PMID: 12784372)
Structure. 2020 Jan 7;28(1):119-129.e2. (PMID: 31727476)
J Am Chem Soc. 2003 Feb 19;125(7):1731-7. (PMID: 12580598)
Trends Pharmacol Sci. 2023 Mar;44(3):175-189. (PMID: 36669976)
Nat Commun. 2023 Apr 25;14(1):2389. (PMID: 37185622)
Commun Biol. 2023 May 29;6(1):575. (PMID: 37248282)
Science. 2023 Mar 17;379(6637):1123-1130. (PMID: 36927031)
Nat Commun. 2016 Mar 07;7:10882. (PMID: 26947396)
Curr Opin Struct Biol. 2023 Jun;80:102594. (PMID: 37060758)
PLoS One. 2016 Aug 25;11(8):e0161879. (PMID: 27560519)
Dev Comp Immunol. 2003 Jan;27(1):55-77. (PMID: 12477501)
Bioinformatics. 2022 Mar 28;38(7):1877-1880. (PMID: 35099535)
MAbs. 2021 Jan-Dec;13(1):1923122. (PMID: 34030577)
Proteins. 2003 Jul 1;52(1):80-7. (PMID: 12784371)
Nature. 2021 Aug;596(7873):583-589. (PMID: 34265844)
Antib Ther. 2022 Sep 06;5(4):233-257. (PMID: 36213257)
Comput Struct Biotechnol J. 2017 Feb 01;15:222-231. (PMID: 28228926)
J Mol Biol. 2004 Jan 16;335(3):843-65. (PMID: 14687579)
Bioinformatics. 2022 Jan 3;38(2):377-383. (PMID: 34546288)
Proteins. 2023 Dec;91(12):1724-1733. (PMID: 37578163)
J Mol Biol. 2015 Sep 25;427(19):3031-41. (PMID: 26231283)
Nucleic Acids Res. 2022 Jan 7;50(D1):D1368-D1372. (PMID: 34986602)
Commun Biol. 2024 Jan 8;7(1):62. (PMID: 38191620)
Curr Opin Struct Biol. 2022 Jun;74:102379. (PMID: 35490649)
Protein Sci. 2024 Jan;33(1):e4865. (PMID: 38073135)
Grant Information:
823830 European Union Horizon 2020; 101017567 EGI-ACE; 027.020.G13 Netherlands e-Science Center
Substance Nomenclature:
0 (Antigen-Antibody Complex)
0 (Antibodies)
0 (Antigens)
0 (Epitopes)
Entry Date(s):
Date Created: 20240930 Date Completed: 20241016 Latest Revision: 20241018
Update Code:
20260130
PubMed Central ID:
PMC11483107
DOI:
10.1093/bioinformatics/btae583
PMID:
39348157
Database:
MEDLINE

*Further Information*

*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.
(© The Author(s) 2024. Published by Oxford University Press.)*