High-Throughput Self-Interaction Chromatography: Applications in Protein Formulation Prediction

Purpose Demonstrate the ability of an artificial neural network (ANN), trained on a formulation screen of measured second virial coefficients to predict protein self-interactions for untested formulation conditions. Materials and Methods Protein self-interactions, quantified by the second virial coefficient, B ₂₂, were measured by self-interaction chromatography (SIC). The B ₂₂ values of lysozyme were measured for an incomplete factorial distribution of 81 formulation conditions of the screen components. The influence of screen parameters (pH, salt and additives) on B ₂₂ value was modeled by training an ANN using B ₂₂ value measurements. After training, the ANN was asked to predict the B ₂₂ value for the complete factorial of parameters screened (12,636 conditions). Twenty of these predicted values (distributed throughout the range of predictions) were experimentally measured for comparison. Results The ANN was able to predict lysozyme B ₂₂ values with a significance of p < 0.0001 and RMSE of 2.6 x 10⁻⁴ mol ml/g². Conclusions The results indicate that an ANN trained on measured B ₂₂ values for a small set of formulation conditions can accurately predict B ₂₂ values for untested formulation conditions. As a measure of protein-protein interactions correlated with solubility, B ₂₂ value predictions based on a small screen may enable rapid determination of high solubility formulations.