Automation and Active Learning for the Multi-Objective Optimization of Antibody Formulations.

Over the last forty years, monoclonal antibodies have become increasingly important therapeutic agents, with most manufactured as preformulated solutions. However, bioformulation of complex proteins is a difficult engineering challenge; formulations must be tailored to individual therapies, necessitating time- and material-intensive campaigns to select combinations of excipients to simultaneously optimize various design criteria. These additives complicate formulation design with unintuitive and non-linear relationships, creating a vast multidimensional design space that is intrinsically difficult to optimize using traditional techniques. To address this challenge, we investigated a high-throughput discovery pipeline using machine learning to model and predict the effects of GRAS excipients on formulation behavior of a model antibody. This was supported by automation-assisted "on-demand" formulation to produce dozens of uniquely formulated antibody solutions for downstream evaluation and biophysical characterization. This pipeline was then integrated into an iterative closed-loop cycle of automated Design-Build-Test-Learn (DBTL), where new rounds of experiments are designed by the model. The process yielded both improved formulations and accurate predictive models of formulation behavior across multiple target objectives (melting temperature, diffusivity, and high-concentration viscosity). This validates the utility of this technique to both map the underlying property-function landscape and effectively guide formulation development while balancing multiple competing design requirements.