Drug-Target Interaction Prediction via an Ensemble of Weighted Nearest Neighbors with Interaction Recovery

Predicting drug-target interactions (DTI) via reliable computational methods is an effective and efficient way to mitigate the enormous costs and time of the drug discovery process. Structure-based drug similarities and sequence-based target protein similarities are the commonly used information for DTI prediction. Among numerous computational methods, neighborhoodbased chemogenomic approaches that leverage drug and target similarities to perform predictions directly are simple but promising ones. However, most existing similarity-based methods follow the transductive setting. These methods cannot directly generalize to unseen data because they should be re-built to predict the interactions for new arriving drugs, targets, or drug-target pairs. Besides, many similarity-based methods, especially neighborhood-based ones, cannot handle directly all three types of interaction prediction involving new drugs and/or new targets. Furthermore, a large amount of missing (undetected) interactions in current DTI datasets hinders most DTI prediction methods. To address these issues, we propose a new method denoted as Weighted k Nearest Neighbor with Interaction Recovery (WkNNIR). Not only can WkNNIR estimate interactions of any new drugs and/or new targets Bin Liu School of Informatics, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece E-mail: binliu@csd.auth.gr Konstantinos Pliakos KU Leuven, Campus KULAK, Faculty of Medicine, Kortrijk, Belgium ITEC, imec research group at KU Leuven E-mail: konstantinos.pliakos@kuleuven.be Celine Vens KU Leuven, Campus KULAK, Faculty of Medicine, Kortrijk, Belgium ITEC, imec research group at KU Leuven E-mail: celine.vens@kuleuven.be Grigorios Tsoumakas School of Informatics, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece E-mail: greg@csd.auth.gr ar X iv :2 01 2. 12 32 5v 1 [ cs .L G ] 2 2 D ec 2 02 0