GIaNt: Protein-Ligand Binding Affinity Prediction via Geometry-Aware Interactive Graph Neural Network
Shuangli Li, Jingbo Zhou, Tong Xu, Liang Huang, Fan Wang, Haoyi Xiong, Weili Huang, Dejing Dou, Hui Xiong
Abstract
Drug discovery often relies on the successful prediction of protein-ligand binding affinity. Recent advances have shown great promise in applying graph neural networks (GNNs) for better affinity prediction by learning the representations of protein-ligand complexes. However, existing solutions usually treat protein-ligand complexes as topological graph data, thus the 3D geometry-based biomolecular structural information is not fully utilized. The essential intermolecular interactions with long-range dependencies, including type-wise interactions and molecule-wise interactions, are also neglected in GNN models. To this end, we propose a geometry-aware interactive graph neural network ( <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GIaNt</small> ) which consists of two components: 3D geometric graph learning network ( <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3DG-Net</small> ) and pairwise interactive learning network ( <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Pi-Net</small> ). Specifically, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3DG-Net</small> iteratively performs the node-edge interaction process to update embeddings of nodes and edges in a unified framework while preserving the 3D geometric factors among atoms, including spatial distance, polar angle and dihedral angle information in 3D space. Moreover, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Pi-Net</small> is adopted to incorporate both element type-level and molecule-level interactions. Specially, interactive edges are gathered with a subsequent reconstruction loss to reflect the global type-level interactions. Meanwhile, a pairwise attentive pooling scheme is designed to identify the critical interactive atoms for complex representation learning from a semantic view. An exhaustive experimental study on two benchmarks verifies the superiority of <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GIaNt</small> .