MONN: A Multi-objective Neural Network for Predicting Compound-Protein Interactions and Affinities
MONN: A Multi-objective Neural Network for Predicting Compound-Protein Interactions and Affinities
复制标题
MONN：用于预测复合蛋白质相互作用和亲和力的多目标神经网络
DOI：
10.1016/j.cels.2020.03.002
复制
发表时间：
2020-04-22
期刊：
影响因子：
9.3
通讯作者：
Zeng, Jianyang
中科院分区：
文献类型：
--
作者：
Li, Shuya;Wan, Fangping;Zeng, Jianyang
理解化合物-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，并试图通过神经关注（即能够解释特征重要性的神经网络架构）捕获化合物和蛋白质中的局部相互作用位点。在这里，我们编制了一个包含超过10,000个化合物-蛋白质对的分子间非共价相互作用的基准数据集，并系统地评估了现有模型中神经注意的可解释性。我们还开发了一个多目标神经网络，称为MONN，以预测化合物和蛋白质之间的非共价相互作用和结合亲和力。综合评价表明，MONN可以成功预测化合物与蛋白质之间的非共价相互作用，而在以往的预测方法中，神经注意力无法有效捕获这些相互作用。此外，MONN在预测结合亲和力方面优于其他最先进的方法。MONN的源代码可从https://github.com/lishuya17/MONN免费下载。
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.