Predictive Modeling Of Concentration-Dependent Viscosity Behavior Of Monoclonal Antibody Solutions

Solutions of monoclonal antibodies can show increased viscosity at high concentration, which can be a disadvantage during protein purification, filling, and administration. We present a modeling approach employing artificial neural networks (ANNs) using experimental factors combined with simulation-derived parameters plus viscosity data from 27 highly concentrated (180 mg/mL) mAbs. These ANNs can be used to predict if mAbs exhibit problematic viscosity at distinct concentrations or to model viscosity-concentration-curves.