DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction

Yupu Zhang (University of Florida) · Zelin Xu (University of Florida) · Tingsong Xiao (University of Florida) · Gustavo Seabra (University of Florida) · Yanjun Li (University of Florida) · Chenglong Li (Anhui University) · Zhe Jiang (University of Florida)

binding affinitycomputationally generated binding posesdecoydbdrug discoverygcl algorithmsgeneralizability graph contrastive learning graph neural networkspositive/negative complex pairsprotein-ligand complexesroot mean square deviationsample efficiency self-supervised learningstructure-aware datasetunlabeled complexes

Predicting the binding affinity of protein-ligand complexes plays a vital role in drug discovery. Unfortunately, progress has been hindered by the lack of large-scale and high-quality binding affinity labels. The widely used PDBbind dataset has fewer than 20K labeled complexes. Self-supervised learning, especially graph contrastive learning (GCL), provides a unique opportunity to break the barrier by pretraining graph neural network models based on vast unlabeled complexes and fine-tuning the models on much fewer labeled complexes. However, the problem faces unique challenges, including a lack of a comprehensive unlabeled dataset with well-defined positive/negative complex pairs and the need to design GCL algorithms that incorporate the unique characteristics of such data. To fill the gap, we propose DecoyDB, a large-scale, structure-aware dataset specifically designed for self-supervised GCL on protein–ligand complexes. DecoyDB consists of high-resolution ground truth complexes and diverse decoy structures with computationally generated binding poses that range from realistic to suboptimal. Each decoy is annotated with a Root Mean Square Deviation (RMSD) from the native pose. We further design a customized GCL framework to pretrain graph neural networks based on DecoyDB and fine-tune the models with labels from PDBbind. Extensive experiments confirm that models pretrained with DecoyDB achieve superior accuracy, sample efficiency, and generalizability.