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 C-hydroxylation, aromatic C-hydroxylation, N-dealkylation and O-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.

Objective: Cell co-culture technology has been widely used to analyze the effects of drugs on cell proliferation and the expression of some proteins in cells, especially in the field of traditional Chinese medicine (TCM); however, the interactions between cells and the transmission of TCM effects between cells have not been adequately studied. Materials and Methods: Using data on gene transcription regulation, biological response, signal channel, and cell-specific expression protein, we built a network for cell types based on entity grammar. Through the correspondence and location information of signal molecules and receptors, type-specific networks of single cells were connected and a multicellular network of smooth muscle cells, neurons, and vascular endothelial cells was constructed. The mechanism of action of nimodipine was analyzed based on the multicellular communication network and its simulation capability was evaluated. Results: The outputs generated by the model developed in this study showed that nimodipine inhibited smooth muscle contraction, due to the overload of Ca²⁺ and the toxicity of excitatory amino acids, and protected neurons and vascular endothelial cells by supporting cell proliferation and inhibiting cell apoptosis. These results were consistent with the known mechanism of nimodipine action, thus confirming that the multicellular network can be used to study the transmission of drug effects among cells. Conclusions: This study lays a foundation for the analysis of the transmission of drug effects in multi-cells, tissues, organs, and other spatial scales through multicellular co-culture experiments, based on a multicellular communication network. In addition, it provides a biological network model for the analysis of TCM action mechanisms.