In Silico Prediction of CYP2C8 Inhibition with Machine-Learning Methods

Abstract

Cytochrome P450 2C8 (CYP2C8) is a major drug-metabolizing enzyme in humans and is responsible for the metabolism of ∼5% drugs in clinical use. Thus, inhibition of CYP2C8, which causes potential adverse drug events, cannot be neglected. The in vitro drug interaction studies guidelines for industry issued by the FDA also point out that it needs to be determined whether investigated drugs are CYP2C8 inhibitors before clinical trials. However, current studies mainly focus on predicting the inhibitors of other major P450 enzymes, and the importance of CYP2C8 inhibition has been overlooked. Therefore, there is a need to develop models for identifying potential CYP2C8 inhibition. In this study, in silico classification models for predicting CYP2C8 inhibition were built by five machine-learning methods combined with nine molecular fingerprints. The performance of the models built was evaluated by test and external validation sets. The best model had AUC values of 0.85 and 0.90 for the test and external validation sets, respectively. The applicability domain was analyzed based on the molecular similarity and exhibited an impact on the improvement of prediction accuracy. Furthermore, several representative privileged substructures such as 1H-benzo­[d]­imidazole, 1-phenyl-1H-pyrazole, and quinoline were identified by information gain and substructure frequency analysis. Overall, our results would be helpful for the prediction of CYP2C8 inhibition.

IDL-PPBopt: A Strategy for Prediction and Optimization of Human Plasma Protein Binding of Compounds via an Interpretable Deep Learning Method

“…As shown in Figure S3, the detected PSubs for Ames mutagenicity 49 and hERG blockers 50 were consistent with the structural alerts (SAs) reported in the literature. In addition, for the other end points with known PSubs, including HIV-1 protease inhibitors, 51 CYP2C8 inhibitors, 52 and ROCK inhibitors, 53 the newly detected PSubs also shared similar structural features. The results demonstrated that our detection protocol combined with interpretable deep learning models could indeed extract task-related substructures.…”

In Silico Prediction of Human and Rat Liver Microsomal Stability via Machine Learning Methods

“…The grid search and Bayesian optimization approaches were used to perform hyper-parameter optimization for the machine learning and deep learning methods, respectively, and then, the model performance was evaluated using the 10-fold cross-validation. The parameter settings of the conventional machine learning algorithms refer to the previous studies. , The detailed optimal parameters of the top five models and D-MPNN obtained by 10-fold cross-validation are provided in the Supporting Information (data.xlsx).…”

“…SVM , is one of the most commonly used machine learning algorithms for binary classification models, which can also be used for multiclassification and quantitative regression models. The core idea of SVM is to find the optimal hyperplane in the sample space, and the samples in the space are separated by the hyperplane according to their properties.…”

“…The parameter settings of the conventional machine learning algorithms refer to the previous studies. 36,39 The detailed optimal parameters of the top five models and D-MPNN obtained by 10-fold cross-validation are provided in the Supporting Information (data.xlsx).…”

Identification of Pharmacophoric Fragments of DYRK1A Inhibitors Using Machine Learning Classification Models

“…Recently, machine learning (ML) methods have been considered as powerful tools to build robust and predictive classification models [ 17 , 18 ]. Without the limitation of data samples in one certain chemical scaffold, classification studies of machine learning methods along with molecular features [ 19 , 20 ] are applicable for DYRK1A inhibitors with diverse heterocyclic scaffolds and broad-spectrum bioactivities.…”