Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences & Engineering Division, King Abdullah University of Science and Technology, 4700 King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia.
Bioinformatics. 2021 Dec 11;37(24):4835-4843. doi: 10.1093/bioinformatics/btab548.
In silico drug-target interaction (DTI) prediction is important for drug discovery and drug repurposing. Approaches to predict DTIs can proceed indirectly, top-down, using phenotypic effects of drugs to identify potential drug targets, or they can be direct, bottom-up and use molecular information to directly predict binding affinities. Both approaches can be combined with information about interaction networks.
We developed DTI-Voodoo as a computational method that combines molecular features and ontology-encoded phenotypic effects of drugs with protein-protein interaction networks, and uses a graph convolutional neural network to predict DTIs. We demonstrate that drug effect features can exploit information in the interaction network whereas molecular features do not. DTI-Voodoo is designed to predict candidate drugs for a given protein; we use this formulation to show that common DTI datasets contain intrinsic biases with major effects on performance evaluation and comparison of DTI prediction methods. Using a modified evaluation scheme, we demonstrate that DTI-Voodoo improves significantly over state of the art DTI prediction methods.
DTI-Voodoo source code and data necessary to reproduce results are freely available at https://github.com/THinnerichs/DTI-VOODOO.
Supplementary data are available at Bioinformatics online.
计算药物-靶标相互作用（DTI）预测对于药物发现和药物再利用非常重要。预测 DTIs 的方法可以间接、自上而下进行，使用药物的表型效应来识别潜在的药物靶点，也可以直接、自下而上，利用分子信息直接预测结合亲和力。这两种方法都可以与关于相互作用网络的信息相结合。
我们开发了 DTI-Voodoo 作为一种计算方法，它将药物的分子特征和本体编码的表型效应与蛋白质-蛋白质相互作用网络相结合，并使用图卷积神经网络来预测 DTI。我们证明药物效应特征可以利用相互作用网络中的信息，而分子特征则不能。DTI-Voodoo 旨在预测给定蛋白质的候选药物；我们使用这种配方表明，常见的 DTI 数据集包含内在偏差，对性能评估和 DTI 预测方法的比较有重大影响。使用修改后的评估方案，我们证明 DTI-Voodoo 显著优于最先进的 DTI 预测方法。
DTI-Voodoo 的源代码和重现结果所需的数据可在 https://github.com/THinnerichs/DTI-VOODOO 上免费获得。
补充数据可在生物信息学在线获得。
