Computational approaches to therapeutic antibody design: established methods and emerging trends

Abstract

Antibodies are proteins that recognize the molecular surfaces of potentially noxious molecules to mount an adaptive immune response or, in the case of autoimmune diseases, molecules that are part of healthy cells and tissues. Due to their binding versatility, antibodies are currently the largest class of biotherapeutics, with five monoclonal antibodies ranked in the top 10 blockbuster drugs. Computational advances in protein modelling and design can have a tangible impact on antibody-based therapeutic development. Antibody-specific computational protocols currently benefit from an increasing volume of data provided by next generation sequencing and application to related drug modalities based on traditional antibodies, such as nanobodies. Here we present a structured overview of available databases, methods and emerging trends in computational antibody analysis and contextualize them towards the engineering of candidate antibody therapeutics.

Engineering Stability, Viscosity, and Immunogenicity of Antibodies by Computational Design

“…However, because of recent advances in computational power and algorithms, computational design is becoming an alternative method in antibody engineering. [13][14][15][16][17][18] One of the advantages to computational methods is that their use can be a rational approach when combined with a structure. Antibodies and their structures should be governed by physical laws, and based on physical principles, we should be able to predict behavior of antibodies in solution and in our body.…”

Designing Feature-Controlled Humanoid Antibody Discovery Libraries Using Generative Adversarial Networks

“…52,54,55,56,60 Peptide-MHCII binding is the first step in the T-cell-mediated immune response and the clearest handle available for practically mitigating immunogenicity risk. 7,22 The GAN library, with only a 2% difference from OAS in predicted immunogenicity, is statistically indistinguishable (at p<0.0001) from the human repertoire training set, whereas PFA shows a statistically significant 11% shift towards higher immunogenicity. The GAN -I library, using a similar transfer learning approach to the one described above, shows a total 76% shift to lower predicted MHCII binding than human repertoire.…”

“…While many papers have been published trying to develop a predictable connection between an antibody's sequence and/or computed molecular structure and the molecule's various physical characteristics, the connection is elusive as it involves complex nonlinear interactions between the constituent amino acid residues. 11,[22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37] Frequently, such work involves an exceptionally small number of molecules, frequently under 200 and often under 50, from a non-diverse set of sequences -a small number of parental sequences, several parents with a small number of highly-related sequence variants, or a single antibody with mutational scanning. Such approaches give information on an individual antibody or small group, but are highly unlikely to generalize the complexity of residue interactions to other antibodies.…”

Machine Learning-Guided Prediction of Antigen-Reactive In Silico Clonotypes Based on Changes in Clonal Abundance through Bio-Panning

“…Based on rapid advances in next-generation sequencing (NGS) technology, various methodologies for analyzing NGS data have been developed to decode the antibody repertoire from diverse sources such as the natural B cell receptor of animals and humans as well as recombinant antibody libraries that can be synthetically designed and constructed [12][13][14]. Furthermore, combining surface display technology and NGS analysis offers synergistic advantages in identifying antigen-reactive clones in silico over the laborious in vitro screening process, which is frequently overwhelmed by dominant antibody clones [15].…”