Similarity-based machine learning support vector machine predictor of drug-drug interactions with improved accuracies.

WHAT IS KNOWN AND OBJECTIVE: Drug-drug interactions (DDI) are frequent causes of adverse clinical drug reactions. Efforts have been directed at the early stage to achieve accurate identification of DDI for drug safety assessments, including the development of in silico predictive methods. In particular, similarity-based in silico methods have been developed to assess DDI with good accuracies, and machine learning methods have been employed to further extend the predictive range of similarity-based approaches. However, the performance of a developed machine learning method is lower than expectations partly because of the use of less diverse DDI training data sets and a less optimal set of similarity measures. METHOD: In this work, we developed a machine learning model using support vector machines (SVMs) based on the literature-reported established set of similarity measures and comprehensive training data sets. The established similarity measures include the 2D molecular structure similarity, 3D pharmacophoric similarity, interaction profile fingerprint (IPF) similarity, target similarity and adverse drug effect (ADE) similarity, which were extracted from well-known databases, such as DrugBank and Side Effect Resource (SIDER). A pairwise kernel was constructed for the known and possible drug pairs based on the five established similarity measures and then used as the input vector of the SVM. RESULT: The 10-fold cross-validation studies showed a predictive performance of AUROC >0.97, which is significantly improved compared with the AUROC of 0.67 of an analogously developed machine learning model. Our study suggested that a similarity-based SVM prediction is highly useful for identifying DDI. CONCLUSION: in silico methods based on multifarious drug similarities have been suggested to be feasible for DDI prediction in various studies. In this way, our pairwise kernel SVM model had better accuracies than some previous works, which can be used as a pharmacovigilance tool to detect potential DDI.

A Pharmacokinetic-Pharmacodynamic Model of Tamoxifen and Endoxifen to Predict Their Distribution and Effects on Inhibition of Tumor Growth.

BACKGROUND: Tamoxifen is widely used in the therapy for breast cancer and has three major metabolites, N-desmethyltamoxifen, 4-hydroxytamoxifen, and endoxifen. Endoxifen has played a major role in the inhibition of tumor growth of breast cancer and the tumor growth is related to endoxifen concentration. OBJECTIVES: The aim of this study was to develop a pharmacokinetic-pharmacodynamic model to predict the distribution of tamoxifen and endoxifen quantitatively, and to discover the anti-tumor effect patterns of tamoxifen and endoxifen. METHODS: The pharmacokinetic-pharmacodynamic model was established by integrating a four compartments pharmacokinetics model and a pharmacodynamic model, the first one include central compartment and peripheral compartment both of which contain tamoxifen and endoxifen. The parameters of the model were calculated by the values of plasma concentrations and the tumor growth data before and after the administration of tamoxifen. RESULTS: The transport rate k42 (6.0003) of endoxifen from the peripheral compartment to the central compartment and the metabolism rate k34 (0.0031) from tamoxifen to endoxifen in the peripheral compartment were proven to be significant, which showed that tamoxifen and endoxifen are mainly distributed in the central compartment. The model provided reasonable predictions of tumor growth, which was inhibited after the administration and varies with the concentration of endoxifen. CONCLUSION: We established a PK-PD model of tamoxifen and endoxifen to predict the tumor growth. The parameters of the pharmacodynamic model, which characterized the tumor growth, revealed the patterns of tamoxifen's anti-tumor functions. The PK-PD model successfully provided illustration for the pharmacokinetics of tamoxifen and endoxifen, and predicted the inhibition effect of endoxifen on the tumor growth.