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

TL;DR

DecoyDB is a large, structure-aware dataset designed for graph contrastive learning in protein-ligand binding affinity prediction, enabling improved model pre-training and fine-tuning for drug discovery tasks.

Contribution

The paper introduces DecoyDB, a novel large-scale dataset with diverse decoy structures for self-supervised graph contrastive learning in protein-ligand affinity prediction.

Findings

Pre-trained models with DecoyDB outperform baselines in accuracy.

DecoyDB enhances label efficiency in affinity prediction.

Models generalize better across different datasets.

Abstract

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 pre-training 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 (less than 2.5 Angstrom) and diverse decoy structures with computationally generated binding poses that range from realistic to suboptimal (negative pairs). Each decoy is annotated with a Root Mean Squared Deviation (RMSD) from the native pose. We further design a customized GCL framework to pre-train graph neural networks based on DecoyDB and fine-tune the models with labels from PDBbind. Extensive experiments confirm that models pre-trained with DecoyDB achieve superior accuracy, label efficiency, and generalizability.