Computational strategies for identifying new drug–target interactions (DTIs) can guide the process of drug discovery, reduce the cost and time of drug development, and thus promote drug development. Most recently proposed methods predict DTIs via integration of heterogeneous data related to drugs and proteins. However, previous methods have failed to deeply integrate these heterogeneous data and learn deep feature representations of multiple original similarities and interactions related to drugs and proteins. We therefore constructed a heterogeneous network by integrating a variety of connection relationships about drugs and proteins, including drugs, proteins, and drug side effects, as well as their similarities, interactions, and associations. A DTI prediction method based on random walk and convolutional neural network was proposed and referred to as DTIPred. DTIPred not only takes advantage of various original features related to drugs and proteins, but also integrates the topological information of heterogeneous networks. The prediction model is composed of two sides and learns the deep feature representation of a drug–protein pair. On the left side, random walk with restart is applied to learn the topological vectors of drug and protein nodes. The topological representation is further learned by the constructed deep learning frame based on convolutional neural network. The right side of the model focuses on integrating multiple original similarities and interactions of drugs and proteins to learn the original representation of the drug–protein pair. The results of cross-validation experiments demonstrate that DTIPred achieves better prediction performance than several state-of-the-art methods. During the validation process, DTIPred can retrieve more actual drug–protein interactions within the top part of the predicted results, which may be more helpful to biologists. In addition, case studies on five drugs further demonstrate the ability of DTIPred to discover potential drug–protein interactions.

中文翻译：

---

基于随机游走和卷积神经网络推断药物-靶标相互作用

识别新药物-靶点相互作用（DTI）的计算策略可以指导药物发现过程，降低药物开发的成本和时间，从而促进药物开发。最近提出的方法通过整合与药物和蛋白质相关的异构数据来预测 DTI。然而，以前的方法未能深入整合这些异构数据，并无法学习与药物和蛋白质相关的多个原始相似性和相互作用的深度特征表示。因此，我们通过整合关于药物和蛋白质的各种连接关系，包括药物、蛋白质和药物副作用，以及它们的相似性、相互作用和关联性，构建了一个异构网络。提出了一种基于随机游走和卷积神经网络的DTI预测方法，称为DTIPred。DTIPred不仅利用了与药物和蛋白质相关的各种原始特征，还整合了异构网络的拓扑信息。预测模型由两侧组成，学习药物-蛋白质对的深度特征表示。在左侧，使用带重启的随机游走来学习药物和蛋白质节点的拓扑向量。通过基于卷积神经网络构建的深度学习框架进一步学习拓扑表示。模型右侧侧重于整合药物和蛋白质的多个原始相似性和相互作用，以学习药物-蛋白质对的原始表示。交叉验证实验的结果表明，DTIPred 比几种最先进的方法实现了更好的预测性能。在验证过程中，DTIPred 可以在预测结果的顶部检索到更多实际的药物-蛋白质相互作用，这可能对生物学家更有帮助。此外，对五种药物的案例研究进一步证明了 DTIPred 发现潜在药物-蛋白质相互作用的能力。