The application of support vector regression for prediction of the antiallodynic effect of drug combinations in the mouse model of streptozocin-induced diabetic neuropathy

Drug interactions are an important issue of efficacious and safe pharmacotherapy. Although the use of drug combinations carries the potential risk of enhanced toxicity, when carefully introduced it enables to optimize the therapy and achieve pharmacological effects at doses lower than those of single agents. In view of the development of novel analgesic compounds for the neuropathic pain treatment little is known about their influence on the efficacy of currently used analgesic drugs.Below we describe the preliminary evaluation of support vector machine in the regression mode (SVR) application for the prediction of maximal antiallodynic effect of a new derivative of dihydrofuran-2-one (LPP1) used in combination with pregabalin (PGB) in the streptozocin-induced neuropathic pain model in mice. Based on SVR the most effective doses of co-administered LPP1 (4 mg/kg) and PGB (1 mg/kg) were predicted to cause the paw withdrawal threshold at 6.7 g in the von Frey test. In vivo for the same combination of doses the paw withdrawal was observed at 6.5 g, which confirms good predictive properties of SVR.