基于支持向量回归和分子对接技术的中药CYP450 2E1抑制剂筛选

细胞色素P450酶(CYP450)的抑制是药物相互作用最常见的原因,对CYPs抑制剂早期预测的研究有助于减少药物相互作用导致的不良反应。CYP450 2E1(CYP2E1)是CYP450酶系中参与药物体内代谢的主要酶,具有广泛的药物代谢底物谱。该研究以CYP2E1为研究对象,基于32个CYP2E1抑制剂,建立支持向量回归模型(support vector regression,SVR),并用测试集数据对CYP2E1定量模型进行验证,获得CYP2E1抑制剂最优预测模型。该研究同时利用CDOCKER分析阳性化合物与活性口袋相互作用模式及氨基酸,建立CYP2E1抑制剂最优筛选模型。综合利用支持向量回归模型和分子对接预测模型筛选中药化学成分数据库(traditional Chinese medicine database,TCMD),提高了计算效率和结果的准确性。SVR预测模型初步得到6 376个中药化合物,通过分子对接进一步验证,最终获得247个对CYP2E1具有潜在抑制活性的中药化合物,其中部分已有实验证实其的确对CYP2E1具有抑制作用。该研究对CYP2E1酶抑制剂的研究可为CYP450抑制剂的虚拟筛选及其介导的药物不良反应预测提供指导,对临床合理用药提供一定的参考。

Screen potential CYP450 2E1 inhibitors from Chinese herbal medicine based on support vector regression and molecular docking method

Inhibition of cytochrome P450 (CYP450) enzymes is the most common reasons for drug interactions, so the study on early prediction of CYPs inhibitors can help to decrease the incidence of adverse reactions caused by drug interactions.CYP450 2E1(CYP2E1), as a key role in drug metabolism process, has broad spectrum of drug metabolism substrate. In this study, 32 CYP2E1 inhibitors were collected for the construction of support vector regression (SVR) model. The test set data were used to verify CYP2E1 quantitative models and obtain the optimal prediction model of CYP2E1 inhibitor. Meanwhile, one molecular docking program, CDOCKER, was utilized to analyze the interaction pattern between positive compounds and active pocket to establish the optimal screening model of CYP2E1 inhibitors.SVR model and molecular docking prediction model were combined to screen traditional Chinese medicine database (TCMD), which could improve the calculation efficiency and prediction accuracy. 6 376 traditional Chinese medicine (TCM) compounds predicted by SVR model were obtained, and in further verification by using molecular docking model, 247 TCM compounds with potential inhibitory activities against CYP2E1 were finally retained. Some of them have been verified by experiments. The results demonstrated that this study could provide guidance for the virtual screening of CYP450 inhibitors and the prediction of CYPs-mediated DDIs, and also provide references for clinical rational drug use.