Department of Control Engineering, Northeastern University, Qinhuangdao, Hebei, 066001, PR China.
Department of Control Engineering, Northeastern University, Qinhuangdao, Hebei, 066001, PR China.
Comput Biol Chem. 2021 Jun;92:107476. doi: 10.1016/j.compbiolchem.2021.107476. Epub 2021 Mar 18.
Drug discovery processes require drug-target interaction (DTI) prediction by virtual screenings with high accuracy. Compared with traditional methods, the deep learning method requires less time and domain expertise, while achieving higher accuracy. However, there is still room for improvement for higher performance with simplified structures. Meanwhile, this field is calling for multi-task models to solve different tasks. Here we report the GanDTI, an end-to-end deep learning model for both interaction classification and binding affinity prediction tasks. This model employs the compound graph and protein sequence data. It only consists of a graph neural network, an attention module and a multiple-layer perceptron, yet outperforms the state-of-the art methods to predict binding affinity and interaction classification on the DUD-E, human, and bindingDB benchmark datasets. This demonstrates our refined model is highly effective and efficient for DTI prediction and provides a new strategy for performance improvement.
药物发现过程需要通过虚拟筛选以高精度预测药物-靶点相互作用（DTI）。与传统方法相比，深度学习方法所需的时间和领域专业知识更少，同时实现更高的准确性。然而，对于更简化的结构，仍有提高性能的空间。同时，该领域呼吁使用多任务模型来解决不同的任务。在这里，我们报告了 GanDTI，这是一种用于交互分类和结合亲和力预测任务的端到端深度学习模型。该模型采用化合物图和蛋白质序列数据。它仅由图神经网络、注意力模块和多层感知机组成，但在 DUD-E、人类和 bindingDB 基准数据集上的结合亲和力和交互分类预测方面优于最先进的方法。这表明我们的精细化模型对于 DTI 预测非常有效且高效，并为性能提升提供了新的策略。
