A high-throughput platform for biophysical antibody developability assessment to enable AI/ML model training

Antibodies must bind their targets with high affinity and specificity to achieve useful therapeutic activity. They must also possess additional properties - collectively referred to as developability properties - that ensure favorable production, formulation, and in vivo performance. Both types of properties - comprising a dozen interacting but distinct attributes - are inherent to an antibody amino acid sequence. Identification or selection of antibodies possessing suitable binding characteristics is now routine, and de novo computational design models, trained on extensive complementarity-determining region sequence and structural data, are rapidly improving. Developability properties, by way of contrast, remain difficult to predict - largely due to insufficient training data - with empirical testing being used heavily to avoid challenges in late-stage antibody development. To fill this gap, we built a high-throughput antibody developability assay platform designed to generate the large datasets needed to train improved machine learning (ML) models. We optimized and automated known developability assays [Jain et al., 2017], and developed a robust integrated data analytics pipeline. Here we report data on 246 antibodies - representing approved, clinical-stage, and preregistration molecules - across a panel of 10 developability assays, in a tidy data format suitable for AI/ML modeling. We used these data to propose updated developability warning thresholds based on 106 approved antibodies, and to confirm preliminarily that predictive models do improve with more training data. Our high-throughput platform PROPHET-Ab enables data generation at the scale needed to develop improved ML models to predict antibody developability.