VN-EGNN: E(3)- and SE(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification

We present VN-EGNN, a novel approach to binding site identification that significantly advances predictive performance. By integrating virtual nodes into E(n)– and SE(n)-equivariant graph neural networks (EGNNs) and extending the message-passing scheme, we address limitations of traditional GNNs in modeling complex geometric entities such as binding pockets and at the same time get neural representations of binding sites. Our extensive experiments demonstrate that VN-EGNN sets a new state-of-the-art in locating binding site centers on the COACH420, HOLO4K, and PDBbind2020 datasets, showcasing a marked improvement in the DCC/DCA success rates over existing methods. These results underscore the potential of VN-EGNN in drug discovery and protein-ligand interaction studies. We extend E(n)-equivariant graph neural networks (EGNNs) for binding site prediction by introducing spatially distributed virtual nodes into protein graphs and adapting the message passing scheme accordingly. The virtual nodes serve as dedicated entities for learning representations of potential binding regions. Our approach showed strong predictive performance on several benchmark datasets and provides a targeted framework for binding site identification.