TY - JOUR T1 - A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding JF - bioRxiv DO - 10.1101/759498 SP - 759498 AU - Rahmad Akbar AU - Philippe A. Robert AU - Milena Pavlović AU - Jeliazko R. Jeliazkov AU - Igor Snapkov AU - Andrei Slabodkin AU - Cédric R. Weber AU - Lonneke Scheffer AU - Enkelejda Miho AU - Ingrid Hobæk Haff AU - Dag Trygve Tryslew Haug AU - Fridtjof Lund-Johansen AU - Yana Safonova AU - Geir K. Sandve AU - Victor Greiff Y1 - 2020/01/01 UR - http://biorxiv.org/content/early/2020/03/04/759498.abstract N2 - 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 the largest set of non-redundant antibody-antigen structures, we identified 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 (i) is compact, less than 104 motifs, (ii) distinct from non-immune protein-protein interactions, and (iii) mediates specific oligo- and polyreactive interactions between paratope-epitope pairs. Our work successfully leveraged combined structure- and sequence-based learning showing that machine-learning-driven predictive paratope and epitope engineering is feasible. ER -