Abstract
Identification of interactions of drugs and proteins is an essential step in the early stages of drug discovery and in finding new drug uses. Traditional experimental identification and validation of these interactions are still time-consuming, expensive, and do not have a high success rate. To improve this identification process, development of computational methods to predict and rank likely drug-target interactions (DTI) with minimum error rate would be of great help. In this work, we propose a computational method for (Drug-Target interaction prediction using Graph Embedding and graph Mining), DTiGEM. DTiGEM models identify novel DTIs as a link prediction problem in a heterogeneous graph constructed by integrating three networks, namely: drug-drug similarity, target-target similarity, and known DTIs. DTiGEM combines different techniques, including graph embeddings (e.g., node2vec), graph mining (e.g., path scores between drugs and targets), and machine learning (e.g., different classifiers). DTiGEM achieves improvement in the prediction performance compared to other state-of-the-art methods for computational prediction of DTIs on four benchmark datasets in terms of area under precision-recall curve (AUPR). Specifically, we demonstrate that based on the average AUPR score across all benchmark datasets, DTiGEM achieves the highest average AUPR value (0.831), thus reducing the prediction error by 22.4% relative to the second-best performing method in the comparison.