The widespread use of monoclonal antibodies for therapeutic applications has led to intense interest in optimizing several of their natural properties (affinity, specificity, stability, solubility and effector functions) as well as introducing non-natural activities (bispecificity and cytotoxicity mediated by conjugated drugs). A common challenge during antibody optimization is that improvements in one property (e.g., affinity) can lead to deficits in other properties (e.g., stability). Here we review recent advances in understanding trade-offs between different antibody properties, including affinity, specificity, stability and solubility. We also review new approaches for co-optimizing multiple antibody properties and discuss how these methods can be used to rapidly and systematically generate antibodies for a wide range of applications.

Therapeutic antibody development requires selection and engineering of molecules with high affinity and other drug-like biophysical properties. Co-optimization of multiple antibody properties remains a difficult and time-consuming process that impedes drug development. Here we evaluate the use of machine learning to simplify antibody co-optimization for a clinical-stage antibody (emibetuzumab) that displays high levels of both on-target (antigen) and off-target (non-specific) binding. We mutate sites in the antibody complementarity-determining regions, sort the antibody libraries for high and low levels of affinity and non-specific binding, and deep sequence the enriched libraries. Interestingly, machine learning models trained on datasets with binary labels enable predictions of continuous metrics that are strongly correlated with antibody affinity and non-specific binding. These models illustrate strong tradeoffs between these two properties, as increases in affinity along the co-optimal (Pareto) frontier require progressive reductions in specificity. Notably, models trained with deep learning features enable prediction of novel antibody mutations that co-optimize affinity and specificity beyond what is possible for the original antibody library. These findings demonstrate the power of machine learning models to greatly expand the exploration of novel antibody sequence space and accelerate the development of highly potent, drug-like antibodies.

The ability of antibodies to recognize their target antigens with high specificity is fundamental to their natural function. Nevertheless, therapeutic antibodies display variable and difficult-to-predict levels of nonspecific and self-interactions that can lead to various drug development challenges, including antibody aggregation, abnormally high viscosity, and rapid antibody clearance. Here we report a method for predicting the overall specificity of antibodies in terms of their relative risk for displaying high levels of nonspecific or self-interactions at physiological conditions. We find that individual and combined sets of chemical rules that limit the maximum and minimum numbers of certain solvent-exposed amino acids in antibody variable regions are strong predictors of specificity for large panels of preclinical and clinical-stage antibodies. We also demonstrate how the chemical rules can be used to identify sites that mediate nonspecific interactions in suboptimal antibodies and guide the design of targeted sublibraries that yield variants with high antibody specificity. These findings can be readily used to improve the selection and engineering of antibodies with drug-like specificity.