Computational approaches for understanding compound-protein interactions (CPIs) can greatly facilitate drug development. Recently, a number of deep-learning-based methods have been proposed to predict binding affinities and attempt to capture local interaction sites in compounds and proteins through neural attentions (i.e., neural network architectures that enable the interpretation of feature importance). Here, we compiled a benchmark dataset containing the inter-molecular non-covalent interactions for more than 10,000 compound-protein pairs and systematically evaluated the interpretability of neural attentions in existing models. We also developed a multi-objective neural network, called MONN, to predict both non-covalent interactions and binding affinities between compounds and proteins. Comprehensive evaluation demonstrated that MONN can successfully predict the non-covalent interactions between compounds and proteins that cannot be effectively captured by neural attentions in previous prediction methods. Moreover, MONN outperforms other state-of-the-art methods in predicting binding affinities. Source code for MONN is freely available for download at https://github.com/lishuya17/MONN.

了解化合物-蛋白质相互作用（CPI）的计算方法可以极大地促进药物开发。最近，已经提出了许多基于深度学习的方法来预测结合亲和力，并试图通过神经注意（即能够解释特征重要性的神经网络体系结构）来捕获化合物和蛋白质中的局部相互作用位点。在这里，我们编辑了一个基准数据集，其中包含超过10,000种化合物-蛋白质对的分子间非共价相互作用，并系统地评估了现有模型中神经注意力的可解释性。我们还开发了一个称为MONN的多目标神经网络，以预测化合物与蛋白质之间的非共价相互作用和结合亲和力。综合评估表明，MONN可以成功预测化合物和蛋白质之间的非共价相互作用，而以前的预测方法无法通过神经注意力有效捕获该相互作用。此外，在预测结合亲和力方面，MONN优于其他最新技术。MONN的源代码可从https://github.com/lishuya17/MONN免费下载。