Kleandrova Valeria V, Scotti Marcus T, Scotti Luciana, Speck-Planche Alejandro
Laboratory of Fundamental and Applied Research of Quality and Technology of Food Production, Moscow State University of Food Production, Volokolamskoe Shosse 11, 125080, Moscow, Russian Federation.
Postgraduate Program in Natural and Synthetic Bioactive Products, Federal University of Paraíba, João Pessoa 58051-900, Brazil.
Curr Top Med Chem. 2021;21(7):661-675. doi: 10.2174/1568026621666210119112845.
Cyclin-dependent kinase 4 (CDK4) and the human epidermal growth factor receptor 2 (HER2) are two of the most promising targets in oncology research. Thus, a series of computational approaches have been applied to the search for more potent inhibitors of these cancerrelated proteins. However, current approaches have focused on chemical analogs while predicting the inhibitory activity against only one of these targets, but never against both.
We report the first perturbation model combined with machine learning (PTML) to enable the design and prediction of dual inhibitors of CDK4 and HER2.
Inhibition data for CDK4 and HER2 were extracted from ChEMBL. The PTML model relied on artificial neural networks to allow the classification/prediction of molecules as active or inactive against CDK4 and/or HER2.
The PTML model displayed sensitivity and specificity higher than 80% in the training set. The same statistical metrics had values above 75% in the test set. We extracted several molecular fragments and estimated their quantitative contributions to the inhibitory activity against CDK4 and HER2. Guided by the physicochemical and structural interpretations of the molecular descriptors in the PTML model, we designed six molecules by assembling several fragments with positive contributions. Three of these molecules were predicted as potent dual inhibitors of CDK4 and HER2, while the other three were predicted as inhibitors of at least one of these proteins. All the molecules complied with Lipinski's rule of five and its variants.
The present work represents an encouraging alternative for future anticancer chemotherapies.
细胞周期蛋白依赖性激酶4（CDK4）和人表皮生长因子受体2（HER2）是肿瘤学研究中最具潜力的两个靶点。因此，一系列计算方法已被应用于寻找这些与癌症相关蛋白的更有效抑制剂。然而，目前的方法仅专注于化学类似物，且仅预测对其中一个靶点的抑制活性，而从未针对两个靶点同时进行预测。
我们报告了首个结合机器学习的扰动模型（PTML），以实现CDK4和HER2双重抑制剂的设计与预测。
从ChEMBL中提取CDK4和HER2的抑制数据。PTML模型依靠人工神经网络对分子针对CDK4和/或HER2的活性或非活性进行分类/预测。
PTML模型在训练集中显示出高于80%的敏感性和特异性。在测试集中，相同的统计指标值高于75%。我们提取了几个分子片段，并估计了它们对CDK4和HER2抑制活性的定量贡献。在PTML模型中分子描述符的物理化学和结构解释的指导下，我们通过组装几个具有正向贡献的片段设计了六个分子。其中三个分子被预测为CDK4和HER2的有效双重抑制剂，而另外三个被预测为这些蛋白中至少一种的抑制剂。所有分子均符合Lipinski的五规则及其变体。
本研究为未来的抗癌化疗提供了一个令人鼓舞的选择。
