Zhao Kai, So Hon-Cheong
School of Biomedical Sciences, The Chinese University of Hong Kong, Shatin, Hong Kong.
KIZ-CUHK Joint Laboratory of Bioresources and Molecular Research of Common Diseases, Kunming Zoology Institute of Zoology, Kunming, China.
Methods Mol Biol. 2019;1903:219-237. doi: 10.1007/978-1-4939-8955-3_13.
The cost of new drug development has been increasing, and repurposing known medications for new indications serves as an important way to hasten drug discovery. One promising approach to drug repositioning is to take advantage of machine learning (ML) algorithms to learn patterns in biological data related to drugs and then link them up to the potential of treating specific diseases. Here we give an overview of the general principles and different types of ML algorithms, as well as common approaches to evaluating predictive performances, with reference to the application of ML algorithms to predict repurposing opportunities using drug expression data as features. We will highlight common issues and caveats when applying such models to repositioning. We also introduce resources of drug expression data and highlight recent studies employing such an approach to repositioning.
新药研发成本一直在增加，将已知药物用于新适应症的重新利用是加速药物发现的重要途径。一种有前景的药物重新定位方法是利用机器学习（ML）算法来学习与药物相关的生物数据中的模式，然后将它们与治疗特定疾病的潜力联系起来。在此，我们概述ML算法的一般原理和不同类型，以及评估预测性能的常用方法，并参考使用药物表达数据作为特征来预测重新定位机会的ML算法应用。我们将强调将此类模型应用于重新定位时的常见问题和注意事项。我们还介绍了药物表达数据的资源，并重点介绍了最近采用这种方法进行重新定位的研究。
