Ensemble-Based Methodology for the Prediction of Drug-Target Interactions

Antibacterial resistance has been progressively increasing mostly due to selective antibiotic pressure, forcing pathogens to either adapt or die. The development of antibacterial resistance to last-line antibiotics urges the formulation of alternative strategies for drug discovery. Recently, attention has been devoted to the development of computational methods to predict drug-target interactions (DTIs). Here we present a computational strategy to predict proteome-scale DTIs based on the combination of the drugs' chemical features and substructural fingerprints, and on the structural information and physicochemical properties of the proteins. We propose an ensemble learning combination of Support-Vector Machine and Random Forest to deal with the complexity of DTI classification. Two distinct classification models were developed to ascertain whether taking the type of protein target (i.e., enzymes, g-protein-coupled receptors, ion channels and nuclear receptors) into account improves classification performance. External validation analysis was consistent with internal five-fold cross-validation, with an AUC of 0.87. This strategy was applied to the proteome of methicillin-resistant Staphylococcus aureus COL (MRSA COL, taxonomy id: 93062), a major nosocomial pathogen worldwide whose antimicrobial resistance and incidence rate keeps steadily increasing.