Predicting antibody-antigen docking and structure-based design represent significant long-term and therapeutically important challenges in computational biology. We present SAGERank, a general, configurable deep learning framework for antibody design using Graph Sample and Aggregate Networks. SAGERank successfully predicted majority epitopes in a cancer target dataset. In nanobody-antigen structure prediction, SAGERank coupled with a protein dynamics structure prediction algorithm slightly outperform Alphafold3. Most importantly, our study demonstrated the real potential of inductive deep learning to overcome small dataset problem in molecular science. The SAGERank models trained for antibody-antigen docking can be used to examine generally protein-protein interaction tasks, such as TCR-pMHC recognition, classification of biological versus crystal interfaces, and prediction of ternary complex of molecular glue. In the cases of ranking docking decoys and identifying biological interfaces, SAGERank is competitive with or outperforms, state-of-the-art methods.
