UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection

TL;DR

UniSite introduces a novel protein-centric dataset and an end-to-end detection framework for ligand binding sites, improving accuracy and addressing biases in existing methods and datasets.

Contribution

The paper presents the first UniProt-centric ligand binding site dataset and an end-to-end detection framework with set prediction loss, advancing the field of binding site prediction.

Findings

UniSite-DS has 4.81 times more multi-site data than previous datasets.

UniSite outperforms existing methods in ligand binding site detection.

IoU-based Average Precision is a more accurate evaluation metric.

Abstract

The detection of ligand binding sites for proteins is a fundamental step in Structure-Based Drug Design. Despite notable advances in recent years, existing methods, datasets, and evaluation metrics are confronted with several key challenges: (1) current datasets and methods are centered on individual protein-ligand complexes and neglect that diverse binding sites may exist across multiple complexes of the same protein, introducing significant statistical bias; (2) ligand binding site detection is typically modeled as a discontinuous workflow, employing binary segmentation and subsequent clustering algorithms; (3) traditional evaluation metrics do not adequately reflect the actual performance of different binding site prediction methods. To address these issues, we first introduce UniSite-DS, the first UniProt (Unique Protein)-centric ligand binding site dataset, which contains 4.81 times more multi-site data and 2.08 times more overall data compared to the previously most widely used datasets. We then propose UniSite, the first end-to-end ligand binding site detection framework supervised by set prediction loss with bijective matching. In addition, we introduce Average Precision based on Intersection over Union (IoU) as a more accurate evaluation metric for ligand binding site prediction. Extensive experiments on UniSite-DS and several representative benchmark datasets demonstrate that IoU-based Average Precision provides a more accurate reflection of prediction quality, and that UniSite outperforms current state-of-the-art methods in ligand binding site detection. The dataset and codes will be made publicly available at https://github.com/quanlin-wu/unisite.