Computational and artificial intelligence-based methods for antibody development. (March 2023)

• Record Type: Journal Article
• Authors: Kim, Jisun; McFee, Matthew; Fang, Qiao; Abdin, Osama; Kim, Philip M.
• Is Part Of: Trends in pharmacological sciences. Volume 44:Number 3(2023)
• Page Start: 175
• Page End: 189
• Publication Date: 2023-03
• Subjects: antibody development -- computational engineering -- deep learning -- artificial intelligence; Pharmacology -- Periodicals; Pharmacology -- trends -- Periodicals; Pharmacologie -- Périodiques; Pharmacology; Electronic journals; Periodicals; 615.1
• DOI: 10.1016/j.tips.2022.12.005
• Languages: English
• ISSNs: 0165-6147

Abstract

Highlights: Recent advances in computational/artificial intelligence (AI)-based methodologies for antibody engineering and discovery hold great promise for accelerating and improving the development of therapeutic antibodies. Databases hold large repertoires of antibody sequences, but only limited structural data; data on biophysical properties is also available. A large suite of predictors of different biophysical and other properties of antibodies have been developed. Deep learning approaches are improving the performance of structure prediction of antibodies, including CDRs, while de novo design remains a challenging problem. Protein language models are showing very promising results for the improvement of antibody activity and properties. Abstract: Due to their high target specificity and binding affinity, therapeutic antibodies are currently the largest class of biotherapeutics. The traditional largely empirical antibody development process is, while mature and robust, cumbersome and has significant limitations. Substantial recent advances in computational and artificial intelligence (AI) technologies are now starting to overcome many of these limitations and are increasingly integrated into development pipelines. Here, we provide an overview of AI methods relevant for antibody development, including databases, computational predictors of antibody properties and structure, and computational antibody design methods with an emphasis on machine learning (ML) models, and the design of complementarity-determining region (CDR) loops, antibody structural components critical for binding.