Applied Artificial Intelligence Institute, Deakin University, Geelong, VIC, 3216, Australia.
Faculty of Information Technology, Nha Trang University, Nha Trang, Khanh Hoa, Viet Nam.
Bioinformatics. 2021 May 23;37(8):1140-1147. doi: 10.1093/bioinformatics/btaa921.
The development of new drugs is costly, time consuming and often accompanied with safety issues. Drug repurposing can avoid the expensive and lengthy process of drug development by finding new uses for already approved drugs. In order to repurpose drugs effectively, it is useful to know which proteins are targeted by which drugs. Computational models that estimate the interaction strength of new drug-target pairs have the potential to expedite drug repurposing. Several models have been proposed for this task. However, these models represent the drugs as strings, which is not a natural way to represent molecules. We propose a new model called GraphDTA that represents drugs as graphs and uses graph neural networks to predict drug-target affinity. We show that graph neural networks not only predict drug-target affinity better than non-deep learning models, but also outperform competing deep learning methods. Our results confirm that deep learning models are appropriate for drug-target binding affinity prediction, and that representing drugs as graphs can lead to further improvements.
The proposed models are implemented in Python. Related data, pre-trained models and source code are publicly available at https://github.com/thinng/GraphDTA. All scripts and data needed to reproduce the post hoc statistical analysis are available from https://doi.org/10.5281/zenodo.3603523.
Supplementary data are available at Bioinformatics online.
新药的开发既昂贵又耗时，而且往往伴随着安全问题。药物重定位可以通过寻找已批准药物的新用途来避免昂贵和漫长的药物开发过程。为了有效地进行药物重定位，了解哪些蛋白质是哪些药物的靶点是很有用的。估计新药靶对相互作用强度的计算模型有可能加速药物重定位。已经提出了几种用于该任务的模型。然而，这些模型将药物表示为字符串，这不是表示分子的自然方式。我们提出了一个名为 GraphDTA 的新模型，它将药物表示为图，并使用图神经网络来预测药物-靶标亲和力。我们表明，图神经网络不仅比非深度学习模型更好地预测药物-靶标亲和力，而且优于竞争的深度学习方法。我们的结果证实，深度学习模型适用于药物-靶标结合亲和力预测，并且将药物表示为图可以进一步提高预测性能。
所提出的模型是用 Python 实现的。相关数据、预训练模型和源代码可在 https://github.com/thinng/GraphDTA 上获得。重现事后统计分析所需的所有脚本和数据可从 https://doi.org/10.5281/zenodo.3603523 获得。
补充数据可在生物信息学在线获得。
