CovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions

2025-06-26

AI Summary

Existing covalent docking methods struggle to model covalent bond formation and associated conformational changes, and lack systematic benchmarking frameworks. To address this, we propose CovDocker—the first comprehensive benchmark framework specifically designed for covalent drug discovery. It decomposes covalent docking into three distinct tasks: reactive site prediction, covalent reaction prediction, and covalent pose docking. We construct the first high-quality, multi-target, multi-reaction-type dataset and adapt state-of-the-art models—including Uni-Mol and Chemformer—to enable end-to-end modeling of both chemical transformations and conformational rearrangements during covalent binding. Extensive experiments demonstrate substantial improvements over baseline methods: notably, a +12.3% gain in F1 score for reactive site identification and significant advances in molecular transformation modeling. These results validate CovDocker’s effectiveness in accelerating covalent inhibitor discovery.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Molecular docking plays a crucial role in predicting the binding mode of ligands to target proteins, and covalent interactions, which involve the formation of a covalent bond between the ligand and the target, are particularly valuable due to their strong, enduring binding nature. However, most existing docking methods and deep learning approaches hardly account for the formation of covalent bonds and the associated structural changes. To address this gap, we introduce a comprehensive benchmark for covalent docking, CovDocker, which is designed to better capture the complexities of covalent binding. We decompose the covalent docking process into three main tasks: reactive location prediction, covalent reaction prediction, and covalent docking. By adapting state-of-the-art models, such as Uni-Mol and Chemformer, we establish baseline performances and demonstrate the effectiveness of the benchmark in accurately predicting interaction sites and modeling the molecular transformations involved in covalent binding. These results confirm the role of the benchmark as a rigorous framework for advancing research in covalent drug design. It underscores the potential of data-driven approaches to accelerate the discovery of selective covalent inhibitors and addresses critical challenges in therapeutic development.

Problem

• Predicting covalent bond formation in molecular docking
• Addressing limitations in current covalent docking methods
• Establishing benchmarks for covalent drug design tasks

Innovation

• Benchmark for covalent docking tasks
• Adapts Uni-Mol and Chemformer models
• Predicts interaction sites and transformations