ARID-sf: A Physics-Informed Deep Learning Scoring Function to Improve Antibody-Antigen Docking Model Ranking

Accurate prediction of antibody-antigen (Ab-Ag) complexation is crucial for understanding immune responses, diagnostics, and the development of therapeutic antibodies. While molecular docking generates conformations, current scoring functions struggle to identify near-native poses, particularly for Ab-Ag interactions. We present ARID-sf (Antibody-antigen Residue Interface Docking scoring function), which combines classical force fields with structural features and protein language model embeddings through a self-attention-based neural network architecture. ARID-sf was trained on >1.5 million docking models and evaluated across four independent test sets comprising 806 cases and 700,000+ docking models. ARID-sf consistently outperforms other functions on increasingly challenging docking scenarios. Critically, ARID-sf maintains performance across diverse sequence identities and increasing conformational change required to reach the bound state, starting with unbound components, demonstrating robust generalization. ARID-sf is parallelizable and can process thousands of docking models per minute, enabling practical application in computational Ab engineering pipelines. The code, trained network, and complete pipeline are freely available at https://github.com/DSIMB/ARID-sf.git.