Wu Yuyuan, Ma Lijing, Li Xinyi, Yang Jingpeng, Rao Xinyu, Hu Yiru, Xi Jingyi, Tao Lin, Wang Jianjun, Du Lailing, Chen Gongxing, Liu Shuiping
School of Pharmacy, Hangzhou Normal University, Hangzhou, Zhejiang, China.
Key Laboratory of Elemene Class Anti-Cancer Chinese Medicines, Engineering Laboratory of Development and Application of Traditional Chinese Medicines, Collaborative Innovation Center of Traditional Chinese Medicines of Zhejiang Province, Hangzhou Normal University, Hangzhou, Zhejiang, China.
Front Pharmacol. 2024 Nov 29;15:1459954. doi: 10.3389/fphar.2024.1459954. eCollection 2024.
The role of computational tools in drug discovery and development is becoming increasingly important due to the rapid development of computing power and advancements in computational chemistry and biology, improving research efficiency and reducing the costs and potential risks of preclinical and clinical trials. Machine learning, especially deep learning, a subfield of artificial intelligence (AI), has demonstrated significant advantages in drug discovery and development, including high-throughput and virtual screening, design of drug molecules, and solving difficult organic syntheses. This review summarizes AI technologies used in drug discovery and development, including their roles in drug screening, design, and solving the challenges of clinical trials. Finally, it discusses the challenges of drug discovery and development based on AI technologies, as well as potential future directions.
由于计算能力的迅速发展以及计算化学和生物学的进步，计算工具在药物发现和开发中的作用变得越来越重要，这提高了研究效率，降低了临床前和临床试验的成本及潜在风险。机器学习，尤其是作为人工智能（AI）一个子领域的深度学习，在药物发现和开发中已展现出显著优势，包括高通量和虚拟筛选、药物分子设计以及解决困难的有机合成问题。本综述总结了用于药物发现和开发的人工智能技术，包括它们在药物筛选、设计以及解决临床试验挑战方面的作用。最后，讨论了基于人工智能技术的药物发现和开发所面临的挑战以及未来潜在的发展方向。
