Autor: |
Akbar R; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway., Robert PA; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway., Weber CR; Department of Biosystems Science and Engineering, ETH Zürich, Basel, Switzerland., Widrich M; Ellis Unit Linz and Lit Ai Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria., Frank R; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway., Pavlović M; Department of Informatics, University of Oslo, Oslo, Norway., Scheffer L; Department of Informatics, University of Oslo, Oslo, Norway., Chernigovskaya M; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway., Snapkov I; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway., Slabodkin A; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway., Mehta BB; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway., Miho E; Institute of Medical Engineering and Medical Informatics, School of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern Switzerland, Muttenz, Switzerland., Lund-Johansen F; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway., Andersen JT; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway.; Institute of Clinical Medicine, Department of Pharmacology, University of Oslo, Oslo, Norway., Hochreiter S; Ellis Unit Linz and Lit Ai Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria.; Institute of Advanced Research in Artificial Intelligence (IARAI), Austria., Hobæk Haff I; Department of Mathematics, University of Oslo, Oslo, Norway., Klambauer G; Ellis Unit Linz and Lit Ai Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria., Sandve GK; Department of Informatics, University of Oslo, Oslo, Norway., Greiff V; Department of Immunology, Oslo University Hospital Rikshospitalet and University of Oslo, Norway. |
Abstrakt: |
Generative machine learning (ML) has been postulated to become a major driver in the computational design of antigen-specific monoclonal antibodies (mAb). However, efforts to confirm this hypothesis have been hindered by the infeasibility of testing arbitrarily large numbers of antibody sequences for their most critical design parameters: paratope, epitope, affinity, and developability. To address this challenge, we leveraged a lattice-based antibody-antigen binding simulation framework, which incorporates a wide range of physiological antibody-binding parameters. The simulation framework enables the computation of synthetic antibody-antigen 3D-structures, and it functions as an oracle for unrestricted prospective evaluation and benchmarking of antibody design parameters of ML-generated antibody sequences. We found that a deep generative model, trained exclusively on antibody sequence (one dimensional: 1D) data can be used to design conformational (three dimensional: 3D) epitope-specific antibodies, matching, or exceeding the training dataset in affinity and developability parameter value variety. Furthermore, we established a lower threshold of sequence diversity necessary for high-accuracy generative antibody ML and demonstrated that this lower threshold also holds on experimental real-world data. Finally, we show that transfer learning enables the generation of high-affinity antibody sequences from low-N training data. Our work establishes a priori feasibility and the theoretical foundation of high-throughput ML-based mAb design. |