Computational prediction of the interaction between drugs and targets is a standing challenge in drug discovery. High performance on binary drug-target benchmark datasets was reported for a number of methods. A possible drawback of binary data is that missing values and non-interacting drug-target pairs are not differentiated. In this paper, we present a method called SimBoost that predicts the continuous binding affinities of drugs and targets and thus incorporates the whole interaction spectrum from true negative to true positive interactions in the learning phase. Additionally, we propose a version called SimBoostQuant which computes a prediction interval in order to assess the confidence of the predicted affinity. We evaluate SimBoost and SimBoostQuant on three continuous drug-target datasets and show that our methods outperform the state-of-the-art models.
Copyright is held by the author.
This thesis may be printed or downloaded for non-commercial research and scholarly purposes.
Supervisor or Senior Supervisor
Thesis advisor: Ester, Martin
Member of collection