Protein-ligand binding representation learning from fine-grained interactions
This work addresses a key bottleneck in drug discovery by improving binding prediction accuracy, though it appears incremental as it builds on existing deep learning approaches with a novel focus on interactions.
The paper tackles the problem of poor generalization in protein-ligand binding prediction due to limited supervised data by proposing a self-supervised learning method that learns representations from fine-grained interactions, achieving superior performance across tasks like affinity prediction, virtual screening, and docking.
The binding between proteins and ligands plays a crucial role in the realm of drug discovery. Previous deep learning approaches have shown promising results over traditional computationally intensive methods, but resulting in poor generalization due to limited supervised data. In this paper, we propose to learn protein-ligand binding representation in a self-supervised learning manner. Different from existing pre-training approaches which treat proteins and ligands individually, we emphasize to discern the intricate binding patterns from fine-grained interactions. Specifically, this self-supervised learning problem is formulated as a prediction of the conclusive binding complex structure given a pocket and ligand with a Transformer based interaction module, which naturally emulates the binding process. To ensure the representation of rich binding information, we introduce two pre-training tasks, i.e.~atomic pairwise distance map prediction and mask ligand reconstruction, which comprehensively model the fine-grained interactions from both structure and feature space. Extensive experiments have demonstrated the superiority of our method across various binding tasks, including protein-ligand affinity prediction, virtual screening and protein-ligand docking.