a Sheffield Institute for Translational Neuroscience (SITraN) , University of Sheffield , Sheffield , United Kingdom.
Expert Opin Drug Discov. 2018 Nov;13(11):1015-1025. doi: 10.1080/17460441.2018.1533953. Epub 2018 Oct 13.
Amyotrophic lateral sclerosis (ALS) is a rapid adult-onset neurodegenerative disorder characterised by the progressive loss of upper and lower motor neurons. Current treatment options are limited for ALS, with very modest effects on survival. Therefore, there is a unmet need for novel therapeutics to treat ALS. Areas covered: This review highlights the many diverse high-throughput screening platforms that have been implemented in ALS drug discovery. The authors discuss cell free assays including in silico and protein interaction models. The review also covers classical in vitro cell studies and new cell technologies, such as patient derived cell lines. Finally, the review looks at novel in vivo models and their use in high-throughput ALS drug discovery Expert opinion: Greater use of patient-derived in vitro cell models and development of better animal models of ALS will improve translation of lead compounds into clinic. Furthermore, AI technology is being developed to digest and interpret obtained data and to make 'hidden knowledge' usable to researchers. As a result, AI will improve target selection for high-throughput drug screening (HTDS) and aid lead compound optimisation. Furthermore, with greater genetic characterisation of ALS patients recruited to clinical trials, AI may help identify responsive genetic subtypes of patients from clinical trials.
肌萎缩侧索硬化症（ALS）是一种快速发作的成年起病的神经退行性疾病，其特征是上下运动神经元的进行性丧失。目前针对 ALS 的治疗选择有限，对生存的影响非常有限。因此，需要新型疗法来治疗 ALS。
本文重点介绍了在 ALS 药物发现中实施的许多不同的高通量筛选平台。作者讨论了无细胞测定法，包括计算机模拟和蛋白质相互作用模型。该综述还涵盖了经典的体外细胞研究和新的细胞技术，如患者来源的细胞系。最后，本文探讨了新型体内模型及其在高通量 ALS 药物发现中的应用。
更多地使用基于患者的体外细胞模型和开发更好的 ALS 动物模型将有助于将先导化合物转化为临床应用。此外，人工智能技术正在被开发出来，以消化和解释所获得的数据，并使“隐藏的知识”可供研究人员使用。因此，人工智能将改进高通量药物筛选（HTDS）的靶点选择，并有助于优化先导化合物。此外，随着对参与临床试验的 ALS 患者进行更多的遗传特征分析，人工智能可能有助于从临床试验中识别出对治疗有反应的遗传亚型患者。
