Scoring functions for the prediction of protein-ligand binding affinity have seen renewed interest in recent years when novel machine learning and deep learning methods started to consistently outperform classical scoring functions. Here we explore the use of atomic environment vectors (AEVs) and feed-forward neural networks, the building blocks of several neural network potentials, for the prediction of protein-ligand binding affinity. The AEV-based scoring function, which we term AEScore, is shown to perform as well or better than other state-of-the-art scoring functions on binding affinity prediction, with an RMSE of 1.22 pK units and a Pearson’s correlation coefficient of 0.83 for the CASF-2016 benchmark. However, AEScore does not perform as well in docking and virtual screening tasks, for which it has not been explicitly trained. Therefore, we show that the model can be combined with the classical scoring function AutoDock Vina in the context of $$\Delta$$ -learning, where corrections to the AutoDock Vina scoring function are learned instead of the protein-ligand binding affinity itself. Combined with AutoDock Vina, $$\Delta$$ -AEScore has an RMSE of 1.32 pK units and a Pearson’s correlation coefficient of 0.80 on the CASF-2016 benchmark, while retaining the docking and screening power of the underlying classical scoring function.

中文翻译：

---

学习与原子环境载体的蛋白质-配体结合亲和力

近年来，当新型机器学习和深度学习方法开始持续优于经典评分函数时，用于预测蛋白质-配体结合亲和力的评分函数重新引起人们的兴趣。在这里，我们探索使用原子环境向量 (AEV) 和前馈神经网络（几种神经网络电位的构建块）来预测蛋白质-配体结合亲和力。基于 AEV 的评分函数（我们称为 AEScore）在结合亲和力预测方面表现得与其他最先进的评分函数一样好或更好，RMSE 为 1.22 pK 单位，皮尔逊相关系数为 0.83用于 CASF-2016 基准测试。然而，AEScore 在对接和虚拟筛选任务中表现不佳，因为它没有经过明确的训练。所以，我们展示了该模型可以在 $$\Delta$$ 学习的背景下与经典评分函数 AutoDock Vina 相结合，其中学习对 AutoDock Vina 评分函数的校正而不是蛋白质-配体结合亲和力本身。结合 AutoDock Vina，$$\Delta$$ -AEScore 在 CASF-2016 基准上的 RMSE 为 1.32 pK 单位，皮尔逊相关系数为 0.80，同时保留了底层经典评分函数的对接和筛选能力。