Graph Convolutional Neural Networks for Predicting Drug-Target Interactions

Accurate determination of target-ligand interactions is crucial in the drug discovery process. In this paper, we propose a graph-convolutional (Graph-CNN) framework for predicting protein-ligand interactions. First, we built an unsupervised graph-autoencoder to learn fixed-size representations of protein pockets from a set of representative druggable protein binding sites. Second, we trained two Graph-CNNs to automatically extract features from pocket graphs and 2D ligand graphs, respectively, driven by binding classification labels. We demonstrate that graph-autoencoders can learn fixed-size representations for protein pockets of varying sizes and the Graph-CNN framework can effectively capture protein-ligand binding interactions without relying on target-ligand co-complexes. Across several metrics, Graph-CNNs achieved better or comparable performance to 3DCNN ligand-scoring, AutoDock Vina, RF-Score, and NNScore on common virtual screening benchmark datasets. Visualization of key pocket residues and ligand atoms contributing to the classification decisions confirms that our networks recognize meaningful interactions between pockets and ligands. <br/><br/>This project includes the following software/data packages: <br/> <ul> <li> <a href="https://simtk.org/frs?group_id=1752#pack_2138">Graph_CNN </a> </li> <li> <a href="https://simtk.org/frs?group_id=1752#pack_2202">README </a> </li> </ul>

在药物发现过程中，准确确定靶标-配体相互作用至关重要。本文提出了一种图卷积（Graph-CNN）框架，用于预测蛋白质-配体相互作用。首先，我们构建了一个无监督的图自动编码器，从一组代表性可药蛋白质结合位点中学习蛋白质口袋的固定大小表示。其次，我们训练了两个Graph-CNN，分别自动从口袋图和二维配体图中提取特征，由结合分类标签驱动。我们证明，图自动编码器可以学习不同大小的蛋白质口袋的固定大小表示，而Graph-CNN框架能够有效捕捉蛋白质-配体结合相互作用，而无需依赖于靶标-配体共复合物。在多个指标上，Graph-CNN的性能优于或与3DCNN配体评分、AutoDock Vina、RF-Score和NNScore在常见的虚拟筛选基准数据集上相当。关键口袋残基和配体原子的可视化确认了我们的网络识别了口袋与配体之间的有意义相互作用。该项目包括以下软件/数据包：
<ul>
<li><a href="https://simtk.org/frs?group_id=1752#pack_2138">Graph_CNN</a></li>
<li><a href="https://simtk.org/frs?group_id=1752#pack_2202">README</a></li>
</ul>