He Shuai-Bing, Li Man-Man, Zhang Bai-Xia, Ye Xiao-Tong, Du Ran-Feng, Wang Yun, Qiao Yan-Jiang
Key Laboratory of Traditional Chinese Medicine-Information Engineer of State Administration of Traditional Chinese Medicine, School of Chinese Pharmacy, Beijing University of Chinese Medicine, Beijing 100102, China.
College of Chinese Medicine, Hebei University, Baoding 071002, China.
Int J Mol Sci. 2016 Oct 9;17(10):1686. doi: 10.3390/ijms17101686.
During the past decades, there have been continuous attempts in the prediction of metabolism mediated by cytochrome P450s (CYP450s) 3A4, 2D6, and 2C9. However, it has indeed remained a huge challenge to accurately predict the metabolism of xenobiotics mediated by these enzymes. To address this issue, microsomal metabolic reaction system (MMRS)-a novel concept, which integrates information about site of metabolism (SOM) and enzyme-was introduced. By incorporating the use of multiple feature selection (FS) techniques (ChiSquared (CHI), InfoGain (IG), GainRatio (GR), Relief) and hybrid classification procedures (Kstar, Bayes (BN), K-nearest neighbours (IBK), C4.5 decision tree (J48), RandomForest (RF), Support vector machines (SVM), AdaBoostM1, Bagging), metabolism prediction models were established based on metabolism data released by Sheridan et al. Four major biotransformations, including aliphatic -hydroxylation, aromatic -hydroxylation, -dealkylation and -dealkylation, were involved. For validation, the overall accuracies of all four biotransformations exceeded 0.95. For receiver operating characteristic (ROC) analysis, each of these models gave a significant area under curve (AUC) value >0.98. In addition, an external test was performed based on dataset published previously. As a result, 87.7% of the potential SOMs were correctly identified by our four models. In summary, four MMRS-based models were established, which can be used to predict the metabolism mediated by CYP3A4, 2D6, and 2C9 with high accuracy.
在过去几十年中，人们不断尝试预测由细胞色素P450（CYP450）3A4、2D6和2C9介导的代谢过程。然而，准确预测这些酶介导的外源化合物代谢仍然是一个巨大的挑战。为了解决这个问题，引入了微粒体代谢反应系统（MMRS）——一个整合了代谢位点（SOM）和酶信息的新概念。通过结合使用多种特征选择（FS）技术（卡方检验（CHI）、信息增益（IG）、增益率（GR）、Relief）和混合分类程序（Kstar、贝叶斯（BN）、K近邻（IBK）、C4.5决策树（J48）、随机森林（RF）、支持向量机（SVM）、AdaBoostM1、Bagging），基于谢里丹等人发布的代谢数据建立了代谢预测模型。该模型涉及四种主要的生物转化，包括脂肪族α-羟基化、芳香族α-羟基化、N-脱烷基化和O-脱烷基化。为了进行验证，所有四种生物转化的总体准确率均超过0.95。对于受试者工作特征（ROC）分析，这些模型中的每一个都给出了显著的曲线下面积（AUC）值>0.98。此外，基于先前发布的数据集进行了外部测试。结果，我们的四个模型正确识别了87.7%的潜在SOM。总之，建立了四个基于MMRS的模型，可用于高精度预测由CYP3A4、2D6和2C9介导的代谢。
