Development of Predictive Classification Models for Whole Cell Antimycobacterial Activity of Benzothiazinones
作者:Sebastian Schieferdecker、Freddy A. Bernal、K. Philip Wojtas、François Keiff、Yan Li、Hans-Martin Dahse、Florian Kloss
DOI:10.1021/acs.jmedchem.2c00098
日期:2022.5.12
against Mycobacterium tuberculosis. However, relationships between their structural properties and whole cell activity remain poorly predictable. Herein, we present the synthesis and antimycobacterial evaluation of a diverse set of BTZs. High potency was predominantly achieved by piperidine and piperazine substitutions, whereupon three compounds were identified as promising candidates, showing preferable
硝基苯并噻嗪酮 (BTZ) 是一类非常有效的抗结核分枝杆菌的抗生素. 然而,它们的结构特性和全细胞活性之间的关系仍然很难预测。在此,我们介绍了多种 BTZ 的合成和抗分枝杆菌评估。高效力主要通过哌啶和哌嗪取代来实现,因此三种化合物被确定为有希望的候选物,显示出较好的代谢稳定性。效力和计算的结合能之间缺乏相关性表明靶抑制不是获得合适的抗分枝杆菌剂的唯一要求。相比之下,通过广泛验证的机器学习模型成功地完成了全细胞活动类别的预测。通过对大量报告的 BTZ 进行 >70% 的正确类别预测,进一步验证了卓越模型的性能。