Computational Discovery of Putative Leads for Drug Repositioning through Drug-Target Interaction Prediction

摘要

De novo experimental drug discovery is an expensive and time-consuming task. It requiresthe identification of drug-target interactions (DTIs) towards targets of biological interest,either to inhibit or enhance a specific molecular function. Dedicated computational modelsfor protein simulation and DTI prediction are crucial for speed and to reduce the costs associated with DTI identification. In this paper we present a computational pipeline that enablesthe discovery of putative leads for drug repositioning that can be applied to any microbialproteome, as long as the interactome of interest is at least partially known. Network metricscalculated for the interactome of the bacterial organism of interest were used to identifyputative drug-targets. Then, a random forest classification model for DTI prediction was constructed using known DTI data from publicly available databases, resulting in an area underthe ROC curve of 0.91 for classification of out-of-sampling data. A drug-target network wascreated by combining 3,081 unique ligands and the expected ten best drug targets. This network was used to predict new DTIs and to calculate the probability of the positive class,allowing the scoring of the predicted instances. Molecular docking experiments were performed on the best scoring DTI pairs and the results were compared with those of the sameligands with their original targets. The results obtained suggest that the proposed pipelinecan be used in the identification of new leads for drug repositioning. The proposed classification model is available at http://bioinformatics.ua.pt/software/dtipred/.