A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding

Rahmad Akbar; Philippe A Robert; Milena Pavlović; Jeliazko R Jeliazkov; Igor Snapkov; Andrei Slabodkin; Cédric R Weber; Lonneke Scheffer; Enkelejda Miho; Ingrid Hobæk Haff; Dag Trygve Tryslew Haug; Fridtjof Lund-Johansen; Yana Safonova; Geir K Sandve; Victor Greiff

doi:10.1016/j.celrep.2021.108856

A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding

Cell Rep. 2021 Mar 16;34(11):108856. doi: 10.1016/j.celrep.2021.108856.

Authors

Affiliations

¹ Department of Immunology, University of Oslo, Oslo, Norway. Electronic address: [email protected].
² Department of Immunology, University of Oslo, Oslo, Norway.
³ Department of Informatics, University of Oslo, Oslo, Norway; Centre for Bioinformatics, University of Oslo, Norway; K.G. Jebsen Centre for Coeliac Disease Research, Institute of Clinical Medicine, University of Oslo, Oslo, Norway.
⁴ Department of Biochemistry, University of Zürich, Zürich, Switzerland.
⁵ Department of Biosystems Science and Engineering, ETH Zürich, Basel, Switzerland.
⁶ Department of Informatics, University of Oslo, Oslo, Norway; Centre for Bioinformatics, University of Oslo, Norway.
⁷ Institute of Medical Engineering and Medical Informatics, School of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern Switzerland, Muttenz, Switzerland.
⁸ Department of Mathematics, University of Oslo, Oslo, Norway.
⁹ Department of Philosophy, Classics, History of Arts and Ideas, Oslo, Norway.
¹⁰ Computer Science and Engineering Department, University of California, San Diego, La Jolla, CA, USA.
¹¹ Department of Immunology, University of Oslo, Oslo, Norway. Electronic address: [email protected].

PMID: 33730590
DOI: 10.1016/j.celrep.2021.108856

Abstract

Antibody-antigen binding relies on the specific interaction of amino acids at the paratope-epitope interface. The predictability of antibody-antigen binding is a prerequisite for de novo antibody and (neo-)epitope design. A fundamental premise for the predictability of antibody-antigen binding is the existence of paratope-epitope interaction motifs that are universally shared among antibody-antigen structures. In a dataset of non-redundant antibody-antigen structures, we identify structural interaction motifs, which together compose a commonly shared structure-based vocabulary of paratope-epitope interactions. We show that this vocabulary enables the machine learnability of antibody-antigen binding on the paratope-epitope level using generative machine learning. The vocabulary (1) is compact, less than 10⁴ motifs; (2) distinct from non-immune protein-protein interactions; and (3) mediates specific oligo- and polyreactive interactions between paratope-epitope pairs. Our work leverages combined structure- and sequence-based learning to demonstrate that machine-learning-driven predictive paratope and epitope engineering is feasible.

Keywords: antibody; antigen; deep learning; epitope; machine learning; paratope; prediction; structure.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Amino Acid Motifs
Amino Acid Sequence
Antibodies / chemistry
Antibodies / immunology
Antigen-Antibody Reactions / immunology*
Binding Sites, Antibody / immunology*
Complementarity Determining Regions / chemistry
Epitopes / chemistry
Epitopes / immunology*
Machine Learning
Protein Binding

Substances

Antibodies
Complementarity Determining Regions
Epitopes