School of Science, Monash University Malaysia, 47500, Bandar Sunway, Selangor Darul Ehsan, Malaysia.
School of Information Technology, Monash University Malaysia, 47500, Bandar Sunway, Selangor Darul Ehsan, Malaysia.
Curr Genet. 2021 Jun;67(3):421-429. doi: 10.1007/s00294-021-01156-5. Epub 2021 Feb 13.
Antimicrobial resistance (AMR) in bacteria is a global health crisis due to the rapid emergence of multidrug-resistant bacteria and the lengthy development of new antimicrobials. In light of this, artificial intelligence in the form of machine learning has been viewed as a potential counter to delay the spread of AMR. With the aid of AI, there are possibilities to predict and identify AMR in bacteria efficiently. Furthermore, a combination of machine learning algorithms and lab testing can help to accelerate the process of discovering new antimicrobials. To date, many machine learning algorithms for antimicrobial-resistance discovery had been created and vigorously validated. Most of these algorithms produced accurate results and outperformed the traditional methods which relied on sequence comparison within a database. This mini-review will provide an updated overview of antimicrobial design workflow using the latest machine-learning antimicrobial discovery algorithms in the last 5 years. With this review, we hope to improve upon the current AMR identification and antimicrobial development techniques by introducing the use of AI into the mix, including how the algorithms could be made more effective.
细菌中的抗微生物药物耐药性（AMR）是一个全球性的健康危机，因为多药耐药菌的迅速出现和新抗菌药物的漫长研发过程。有鉴于此，人工智能以机器学习的形式被视为延缓 AMR 传播的一种潜在手段。借助人工智能，可以有效地预测和识别细菌中的 AMR。此外，机器学习算法和实验室测试的结合可以帮助加速发现新抗菌药物的过程。迄今为止，已经创建并大力验证了许多用于发现抗微生物药物耐药性的机器学习算法。这些算法中的大多数都产生了准确的结果，并且优于传统的方法，传统方法依赖于数据库内的序列比较。这篇小型综述将提供过去 5 年中使用最新机器学习抗菌药物发现算法进行抗菌设计工作流程的最新概述。通过这篇综述，我们希望通过将人工智能引入其中，包括如何使算法更有效，来改进当前的 AMR 识别和抗菌药物开发技术。
