to predict the activity of newly designed compounds with reasonable accuracy within the applicability domain (q2 = 0.70–0.74). The models were applied to screen a virtual chemical library of imidazole derivatives, which was designed to have antiviral activity. The six most promising compounds were identified, synthesized and their antiviral activities against HCMV were evaluated in vitro. However, only
使用在线
化学建模环境 (OCH
EM) 解决了设计针对人类巨细胞病毒 (HCMV) 的新抗病毒药物的问题。从文献中收集化合物对人类
生物体的抗病毒活性数据并上传到 OCH
EM 数据库。通过交叉验证测试回归模型的预测能力,确定系数 q 2 = 0.71–0.76。使用外部测试集对模型的验证证明,这些模型可用于预测新设计化合物的活性,在适用范围内具有合理的准确性(q 2 = 0.70–0.74)。该模型用于筛选具有抗病毒活性的
咪唑衍
生物虚拟
化学库。鉴定、合成了六种最有希望的化合物,并在体外评估了它们对 HCMV 的抗病毒活性。然而,其中只有两个显示出对 HCMV AD169 菌株的一些活性。