School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, 510006, China.
Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, 510006, China.
Brief Bioinform. 2022 Sep 20;23(5). doi: 10.1093/bib/bbac162.
The identification of active binding drugs for target proteins (referred to as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential role in drug discovery. Although recent deep learning-based approaches achieve better performance than molecular docking, existing models often neglect topological or spatial of intermolecular information, hindering prediction performance. We recognize this problem and propose a novel approach called the Intermolecular Graph Transformer (IGT) that employs a dedicated attention mechanism to model intermolecular information with a three-way Transformer-based architecture. IGT outperforms state-of-the-art (SoTA) approaches by 9.1% and 20.5% over the second best option for binding activity and binding pose prediction, respectively, and exhibits superior generalization ability to unseen receptor proteins than SoTA approaches. Furthermore, IGT exhibits promising drug screening ability against severe acute respiratory syndrome coronavirus 2 by identifying 83.1% active drugs that have been validated by wet-lab experiments with near-native predicted binding poses. Source code and datasets are available at https://github.com/microsoft/IGT-Intermolecular-Graph-Transformer.
鉴定靶蛋白的活性结合药物（称为药物-靶标相互作用预测）是虚拟筛选的关键挑战，在药物发现中起着至关重要的作用。尽管最近基于深度学习的方法比分子对接具有更好的性能，但现有的模型往往忽略了分子间的拓扑或空间信息，从而阻碍了预测性能。我们认识到这个问题，并提出了一种名为分子间图转换器（IGT）的新方法，该方法采用专用注意力机制，通过基于三向的架构来对分子间信息进行建模。IGT 在结合活性和结合构象预测方面分别比第二好的方法高出 9.1%和 20.5%，并且比 SoTA 方法表现出更好的对未见受体蛋白的泛化能力。此外，IGT 通过识别 83.1%已通过湿实验室实验验证的活性药物，并预测接近天然的结合构象，显示出有希望的针对严重急性呼吸综合征冠状病毒 2 的药物筛选能力。源代码和数据集可在 https://github.com/microsoft/IGT-Intermolecular-Graph-Transformer 上获得。
