Modeling analgesic drug interactions using support vector regression: a new approach to isobolographic analysis

Background: Modeling drug interactions is important for illustrating combined drug actions and for predicting the pharmacological and/or toxicological effects that can be obtained using combined drug therapy.

Aim: In this study, we propose a new and universal support vector regression (SVR)-based method for the analysis of drug interactions that significantly accelerates the isobolographic analysis.

Methods: Using SVR, a theoretical model of the dose-effect relationship was built to simulate various dose ratios of two drugs. Using the model could then rapidly determine the combinations of doses that elicited equivalent effects compared with each drug used alone.

Results: The model that was built can be used for any level of drug effect and can generate classical isobolograms to determine the nature of drug interactions (additivity, subadditivity or synergy), which is of particular importance in the case of novel compounds endowed with a high biological activity for which the mechanism of action is unknown. In addition, this method is an interesting alternative allowing for a meaningful reduction in the number of animals used for in vivo studies.

Conclusions: In a mouse model of toxic peripheral neuropathy induced by a single intraperitoneal dose of oxaliplatin, the usefulness of this SVR method for modeling dose-effect relationships was confirmed. This method may also be applicable during preliminary investigations regarding the mechanism of action of novel compounds.