Appearance
Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 1: Ways to make an impact, and why we are not there yet.
文献信息
| DOI | 10.1016/j.drudis.2020.12.009 |
|---|---|
| PMID | 33346134 |
| 期刊 | Drug discovery today |
| 影响因子 | 7.5 |
| JCR 分区 | Q1 |
| 发表年份 | 2021 |
| 被引次数 | 77 |
| 关键词 | 人工智能, 药物发现, 临床成功率, 决策质量 |
| 文献类型 | Journal Article, Review |
| ISSN | 1359-6446 |
| 页码 | 511-524 |
| 期号 | 26(2) |
| 作者 | Andreas Bender, Isidro Cortés-Ciriano |
一句话小结
本文探讨了人工智能在药物发现中的应用,指出提高临床成功率比加速开发流程或降低成本更为关键,强调了选择合成化合物的重要性。研究认为,目前对药物体内疗效和安全性相关数据的关注不足,未来需优化数据生成和建模,以提升临床决策质量,充分发挥AI的潜力。
在麦伴科研 (maltsci.com) 搜索更多文献
摘要
尽管人工智能(AI)在图像识别等领域产生了深远的影响,但在药物发现方面,类似的进展却相对罕见。本文量化了药物发现过程中在哪些阶段提高所需时间、成功率或可负担性将对新药上市产生最深远的整体影响。临床成功率的变化将对提高药物发现的成功率产生最显著的影响;换句话说,关于选择哪个化合物进行开发(以及如何进行临床试验)的决策质量比速度或成本更为重要。尽管当前的AI进展主要集中于如何合成特定化合物,但关于应合成哪个化合物的问题,尤其是基于临床疗效和安全性相关终点的选择,却受到了显著较少的关注。因此,当前的代理测量方法和可用数据无法充分发挥AI在药物发现中的潜力,特别是在药物的体内疗效和安全性方面。因此,确定生成哪些数据以及建模哪些终点的问题,将成为未来改善临床相关决策的重要关键。
英文摘要
Although artificial intelligence (AI) has had a profound impact on areas such as image recognition, comparable advances in drug discovery are rare. This article quantifies the stages of drug discovery in which improvements in the time taken, success rate or affordability will have the most profound overall impact on bringing new drugs to market. Changes in clinical success rates will have the most profound impact on improving success in drug discovery; in other words, the quality of decisions regarding which compound to take forward (and how to conduct clinical trials) are more important than speed or cost. Although current advances in AI focus on how to make a given compound, the question of which compound to make, using clinical efficacy and safety-related end points, has received significantly less attention. As a consequence, current proxy measures and available data cannot fully utilize the potential of AI in drug discovery, in particular when it comes to drug efficacy and safety in vivo. Thus, addressing the questions of which data to generate and which end points to model will be key to improving clinically relevant decision-making in the future.
麦伴智能科研服务
主要研究问题
- 在药物发现过程中,AI如何具体提高临床试验的成功率?
- 目前有哪些具体的AI技术可以应用于药物选择的决策过程?
- 在药物发现的不同阶段,AI的应用潜力是否存在显著差异?
- 如何评估AI在药物发现中的实际效果与其宣传的能力之间的差距?
- 除了AI,药物发现领域还有哪些技术或方法可以显著提高成功率?
核心洞察
1. 研究背景和目的
人工智能(AI)在许多领域(如图像识别)取得了显著进展,但在药物发现领域的应用尚未达到同样的水平。药物发现过程复杂且耗时,涉及多个阶段,从化合物筛选到临床试验,成功率和成本控制至关重要。本研究旨在探讨AI在药物发现中的实际应用潜力,识别可产生重大影响的阶段,并分析当前AI应用的局限性,特别是在决策质量和临床成功率方面。
2. 主要方法和发现
文章通过量化药物发现的不同阶段,评估在提高药物上市效率、成功率和降低成本方面的潜在影响。研究发现,临床成功率的提升对药物发现的整体成功具有最深远的影响。这表明,关于选择哪种化合物进行开发及如何设计临床试验的决策质量,比单纯追求速度或降低成本更为重要。尽管当前AI的进展主要集中在化合物的合成上,但对选择合适化合物的关注明显不足,尤其是在临床疗效和安全性等关键指标的建模上。
3. 核心结论
研究指出,当前药物发现中AI的应用尚未充分发挥其潜力,尤其是在临床相关决策方面。现有的代理测量和数据无法有效支持AI在药物疗效和安全性评估中的应用。这表明,在未来的发展中,必须重点考虑生成哪种数据以及如何建模临床终点,以便改善药物发现过程中的决策能力。
4. 研究意义和影响
本研究的意义在于识别AI在药物发现中的应用瓶颈,为未来的研究方向提供了重要的指导。通过强调临床成功率和决策质量的重要性,研究为药物开发领域的决策者提供了新的视角,提示他们在AI应用中应更多关注选择合适的化合物,而不仅仅是化合物的合成过程。这将有助于加速新药的研发,提高成功率,最终促进更多安全有效药物的上市,造福患者和社会。
引用本文的文献
- Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 2: a discussion of chemical and biological data. - Andreas Bender;Isidro Cortes-Ciriano - Drug discovery today (2021)
- Deep Learning in Virtual Screening: Recent Applications and Developments. - Talia B Kimber;Yonghui Chen;Andrea Volkamer - International journal of molecular sciences (2021)
- Resources and computational strategies to advance small molecule SARS-CoV-2 discovery: Lessons from the pandemic and preparing for future health crises. - Natesh Singh;Bruno O Villoutreix - Computational and structural biotechnology journal (2021)
- AI-based language models powering drug discovery and development. - Zhichao Liu;Ruth A Roberts;Madhu Lal-Nag;Xi Chen;Ruili Huang;Weida Tong - Drug discovery today (2021)
- AI in drug development: a multidisciplinary perspective. - Víctor Gallego;Roi Naveiro;Carlos Roca;David Ríos Insua;Nuria E Campillo - Molecular diversity (2021)
- Structure-based in silico approaches for drug discovery against Mycobacterium tuberculosis. - Alexander D H Kingdon;Luke J Alderwick - Computational and structural biotechnology journal (2021)
- Mechanism of activation and the rewired network: New drug design concepts. - Ruth Nussinov;Mingzhen Zhang;Ryan Maloney;Chung-Jung Tsai;Bengi Ruken Yavuz;Nurcan Tuncbag;Hyunbum Jang - Medicinal research reviews (2022)
- Potential of artificial intelligence to accelerate diagnosis and drug discovery for COVID-19. - Indira Mikkili;Abraham Peele Karlapudi;T C Venkateswarulu;Vidya Prabhakar Kodali;Deepika Sri Singh Macamdas;Krupanidhi Sreerama - PeerJ (2021)
- Applications of Artificial Intelligence in Drug Design: Opportunities and Challenges. - Morgan Thomas;Andrew Boardman;Miguel Garcia-Ortegon;Hongbin Yang;Chris de Graaf;Andreas Bender - Methods in molecular biology (Clifton, N.J.) (2022)
- Artificial intelligence for the discovery of novel antimicrobial agents for emerging infectious diseases. - Adam Bess;Frej Berglind;Supratik Mukhopadhyay;Michal Brylinski;Nicholas Griggs;Tiffany Cho;Chris Galliano;Kishor M Wasan - Drug discovery today (2022)
... (67 更多 篇文献)
© 2025 MaltSci 麦伴科研 - 我们用人工智能技术重塑科研
