Progress and challenges for the machine learning-based design of fit-for-purpose monoclonal antibodies

mAbs

Robert Frank¹  Talip Zengin¹  Puneet Rawat¹  Brij Bhushan Mehta¹  Karine Flem-Karlsen¹  Rahmad Akbar¹  Philippe A. Robert¹  Jan Terje Andersen¹  Victor Greiff¹  Fridtjof Lund-Johansen¹  Tudor-Stefan Cotet²  Mai Ha Vu³  Eva Smorodina⁴  Jose Gutierrez-Marcos⁵  Habib Bashour⁵ 

[1] Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway;Department of Life Sciences, Imperial College London, UK;Department of Linguistics and Scandinavian Studies, University of Oslo, Norway;Faculty of Bioengineering and Bioinformatics, Lomonosov Moscow State University, Russia;School of Life Sciences, University of Warwick, Coventry, UK;

关键词: Machine learning;    artificial intelligence;    antibody;    antigen;    developability;    drug design;   

DOI  :  10.1080/19420862.2021.2008790

来源: DOAJ

【 摘 要 】

Although the therapeutic efficacy and commercial success of monoclonal antibodies (mAbs) are tremendous, the design and discovery of new candidates remain a time and cost-intensive endeavor. In this regard, progress in the generation of data describing antigen binding and developability, computational methodology, and artificial intelligence may pave the way for a new era of in silico on-demand immunotherapeutics design and discovery. Here, we argue that the main necessary machine learning (ML) components for an in silico mAb sequence generator are: understanding of the rules of mAb-antigen binding, capacity to modularly combine mAb design parameters, and algorithms for unconstrained parameter-driven in silico mAb sequence synthesis. We review the current progress toward the realization of these necessary components and discuss the challenges that must be overcome to allow the on-demand ML-based discovery and design of fit-for-purpose mAb therapeutic candidates.

【 授权许可】

Unknown