Multi-objective optimization with majority voting ensemble of classifiers for prediction of HIV-1 protease cleavage site

HIV-1 protease cleavage site prediction of an amino acid sequence Human Immune Deficiency Virus (HIV-1) type 1 has been the subject intense research for decades to increase AUC value without placing much attention accuracy metric by many researchers. Knowledge substrate specificity significant application in inhibitors development and studying novel drug targets. Motivated this, a multi-objective optimization (MOO)-based majority voting ensemble framework combining outputs from multiple classifiers proposed current paper both values simultaneously. The optimal set that are considered purposes at time is determined automatically using search capability MOO. Comparatively better results have attained various benchmark data sets with average (area under ROC curve) 0.92 0.96, respectively.