GAABind: A Geometry-Aware Attention-Based Network for Accurate Protein-Ligand Binding Pose and Binding Affinity Prediction

The preprocessed dataset for paper "GAABind: A Geometry-Aware Attention-Based Network for Accurate Protein-Ligand Binding Pose and Binding Affinity Prediction" with associated code at https://github.com/Mercuryhs/GAABind. The dataset files are saved as .pkl file for the convenience of use. Paper Abstract: Protein-ligand interactions are increasingly profiled at high-throughput, playing a vital role in lead compound discovery and drug optimization. Accurate prediction of binding pose and binding affinity constitutes a pivotal challenge in advancing our computational understanding of protein-ligand interactions. However, inherent limitations still exist, including high computational cost for conformational search sampling in traditional molecular docking tools, and the unsatisfactory molecular representation learning and intermolecular interaction modeling in deep learning-based methods. Here we propose a geometry-aware attention-based deep learning model, GAABind, which effectively predicts the pocket- ligand binding pose and binding affinity within a multi-task learning framework. Specifically, GAABind comprehensively captures the geometric and topological properties of both binding pockets and ligands, and employs expressive molecular representation learning to model intramolecular interactions. Moreover, GAABind proficiently learns the intermolecular many-body interactions and simulates the dynamic conformational adaptations of the ligand during its interaction with the protein through meticulously designed networks. We trained GAABind on the PDBbindv2020 and evaluated it on the CASF2016 dataset, the results indicate that GAABind achieves state-of-the-art performance in binding pose prediction and shows comparable binding affinity prediction performance. Notably, GAABind achieves a success rate of 82.8% in binding pose prediction, and the Pearson correlation between predicted and experimental binding affinities reaches up to 0.803. Additionally, we assessed GAABind's performance on the SARS-CoV-2 main protease cross-docking dataset. In this evaluation, GAABind demonstrates a notable success rate of 76.5% in binding pose prediction and achieves the highest Pearson correlation coefficient in binding affinity prediction compared with all baseline methods.本数据集为论文《GAABind：一款面向精准蛋白质-配体（protein-ligand）结合姿态（binding pose）与结合亲和力预测的几何感知注意力网络》的预处理数据集，配套开源代码地址为https://github.com/Mercuryhs/GAABind。为便于使用，数据集文件均以.pkl格式存储。 论文摘要： 蛋白质-配体相互作用的高通量表征研究日益增多，其在先导化合物发现与药物优化领域发挥着至关重要的作用。精准预测结合姿态与结合亲和力，是深化蛋白质-配体相互作用计算认知研究的关键挑战。但现有方法仍存在固有局限：传统分子对接工具需进行构象搜索采样，计算成本高昂；而基于深度学习的方法在分子表征学习与分子间相互作用建模方面表现欠佳。 为此，我们提出一款几何感知注意力深度学习模型GAABind，其可在多任务学习框架下精准预测结合口袋-配体的结合姿态与结合亲和力。具体而言，GAABind可全面捕捉结合口袋与配体的几何与拓扑特性，并通过高效的分子表征学习对分子内相互作用进行建模。此外，GAABind通过精心设计的网络结构，高效学习分子间多体相互作用，并模拟配体与蛋白质相互作用过程中的动态构象适配行为。 我们在PDBbindv2020数据集上训练GAABind，并在CASF2016数据集上开展评估，结果显示GAABind在结合姿态预测任务上达到当前最优性能，在结合亲和力预测任务上也表现出可媲美的水准。值得注意的是，GAABind在结合姿态预测任务中达到82.8%的成功率，预测结合亲和力与实验值之间的皮尔逊相关系数最高可达0.803。 此外，我们在SARS-CoV-2主蛋白酶交叉对接数据集上评估了GAABind的性能。在该评估中，GAABind在结合姿态预测任务上达到76.5%的显著成功率，且相较于所有基线方法，其在结合亲和力预测任务中取得了最高的皮尔逊相关系数。