Evaluating Zero-Shot Scoring for In Vitro Antibody Binding Prediction with Experimental Validation
This work addresses the challenge of efficiently screening antibody candidates for therapeutic development, though it is incremental as it analyzes existing methods on new data.
The study evaluated eight open-source scoring methods for predicting antibody binding in vitro, finding that existing methods struggle to detect binders and performance varies across antigens, with flexibly docked complexes and ensemble scores showing more robustness.
The success of therapeutic antibodies relies on their ability to selectively bind antigens. AI-based antibody design protocols have shown promise in generating epitope-specific designs. Many of these protocols use an inverse folding step to generate diverse sequences given a backbone structure. Due to prohibitive screening costs, it is key to identify candidate sequences likely to bind in vitro. Here, we compare the efficacy of 8 common scoring paradigms based on open-source models to classify antibody designs as binders or non-binders. We evaluate these approaches on a novel surface plasmon resonance (SPR) dataset, spanning 5 antigens. Our results show that existing methods struggle to detect binders, and performance is highly variable across antigens. We find that metrics computed on flexibly docked antibody-antigen complexes are more robust, and ensembles scores are more consistent than individual metrics. We provide experimental insight to analyze current scoring techniques, highlighting that the development of robust, zero-shot filters is an important research gap.