Xuan Ping, Cui Hui, Shen Tonghui, Sheng Nan, Zhang Tiangang
School of Computer Science and Technology, Heilongjiang University, Harbin, China.
Department of Computer Science and Information Technology, La Trobe University, Bundoora, VIC, Australia.
Front Pharmacol. 2019 Nov 8;10:1301. doi: 10.3389/fphar.2019.01301. eCollection 2019.
Identifying new treatments for existing drugs can help reduce drug development costs and explore novel indications of drugs. The prediction of associations between drugs and diseases is challenging because their similarities and relations are complicated and non-linear. We propose a HeteroDualNet model to address this issue. Firstly, three types of matrices are extracted to represent intra-drug similarities, intra-disease similarity and drug-disease associations. The intra-drug similarities consider three drug features and a newly introduced drug-related disease correlation. Secondly, an embedding mechanism is proposed to integrate these matrices in a heterogenous drug-disease association layer (hetero-layer). Further, a neighbouring heterogeneous layer (hetero-layer-N) is constructed to incorporate the biological premise that similar drugs can often treat related diseases. Finally, a dual convolutional neural network is built with hetero-layer and hetero-layer-N as two branches to learn from characteristics of drug-disease and the relations of their neighbours simultaneously. HeteroDualNet outperformed the other four methods in comparison over a public dataset of 763 drugs and 681 diseases in terms of Areas Under the Curves of Receiver Operating Characteristics and Precision-Recall, and recall rate at top . Case study of five drugs further proved the capacity of HeteroDualNet in finding reliable disease candidates of drugs as validated by database records or literature. Our findings show that the embedded heterogenous layers of original and neighbouring drug-disease representations in a dual neural network improved the association prediction performance.
识别现有药物的新疗法有助于降低药物研发成本并探索药物的新适应症。药物与疾病之间关联的预测具有挑战性，因为它们的相似性和关系复杂且呈非线性。我们提出了一种异质对偶网络（HeteroDualNet）模型来解决这个问题。首先，提取三种类型的矩阵来表示药物内相似性、疾病内相似性和药物 - 疾病关联。药物内相似性考虑了三种药物特征以及新引入的与药物相关的疾病相关性。其次，提出了一种嵌入机制，以在异质药物 - 疾病关联层（异质层）中整合这些矩阵。此外，构建了一个相邻异质层（异质层 - N），以纳入相似药物通常可治疗相关疾病这一生物学前提。最后，构建了一个对偶卷积神经网络，以异质层和异质层 - N 作为两个分支，同时从药物 - 疾病特征及其邻居关系中学习。在一个包含763种药物和681种疾病的公共数据集上，就受试者工作特征曲线下面积和精确率 - 召回率以及前 召回率而言，异质对偶网络（HeteroDualNet）在比较中优于其他四种方法。对五种药物的案例研究进一步证明了异质对偶网络（HeteroDualNet）在寻找经数据库记录或文献验证的药物可靠疾病候选方面的能力。我们的研究结果表明，在对偶神经网络中嵌入原始和相邻药物 - 疾病表示的异质层提高了关联预测性能。
