Abstract
BackgroundComputational prediction of the interaction between drugs and protein targets is very important for the new drug discovery, as the experimental determination of drug-target interaction (DTI) is expensive and time-consuming. However, different protein targets are with very different numbers of interactions. Specifically, most interactions focus on only a few targets. As a result, targets with larger numbers of interactions could own enough positive samples for predicting their interactions but the positive samples for targets with smaller numbers of interactions could be not enough. Only using a classification strategy may not be able to deal with the above two cases at the same time. To overcome the above problem, in this paper, a drug-target interaction prediction method based on multiple classification strategies (MCSDTI) is proposed. In MCSDTI, targets are firstly divided into two parts according to the number of interactions of the targets, where one part contains targets with smaller numbers of interactions (TWSNI) and another part contains targets with larger numbers of interactions (TWLNI). And then different classification strategies are respectively designed for TWSNI and TWLNI to predict the interaction. Furthermore, TWSNI and TWLNI are evaluated independently, which can overcome the problem that result could be mainly determined by targets with large numbers of interactions when all targets are evaluated together.ResultsWe propose a new drug-target interaction (MCSDTI) prediction method, which uses multiple classification strategies. MCSDTI is tested on five DTI datasets, such as nuclear receptors (NR), ion channels (IC), G protein coupled receptors (GPCR), enzymes (E), and drug bank (DB). Experiments show that the AUCs of our method are respectively 3.31%, 1.27%, 2.02%, 2.02% and 1.04% higher than that of the second best methods on NR, IC, GPCR and E for TWLNI; And AUCs of our method are respectively 1.00%, 3.20% and 2.70% higher than the second best methods on NR, IC, and E for TWSNI.ConclusionMCSDTI is a competitive method compared to the previous methods for all target parts on most datasets, which administrates that different classification strategies for different target parts is an effective way to improve the effectiveness of DTI prediction.
Highlights
Computational prediction of the interaction between drugs and protein targets is very important for the new drug discovery, as the experimental determination of drug-target interaction (DTI) is expensive and time-consuming
In multiple classification strategies based drug-target interaction (MCSDTI), targets are firstly divided into targets with larger numbers of interactions (TWLNI) and targets with smaller numbers of interactions (TWSNI)
To verify the effectiveness of our proposed multiple classification strategies, our method are compared with the following methods, such as decision tree (DT)[36], random forest (RF) [36], nearest profile (NP) [31], weighted profile (WP) [31], network-based inference (NBI) [37], regularized least squares-avg (RLS) [38], regularized least squares-kron (RK) [9], ensemble decision tree (EDT) [19], ensemble kernel ridge regression ensemble (EKRR) [19] and so on
Summary
Computational prediction of the interaction between drugs and protein targets is very important for the new drug discovery, as the experimental determination of drug-target interaction (DTI) is expensive and time-consuming. To overcome the above problem, in this paper, a drug-target interaction prediction method based on multiple classification strategies (MCSDTI) is proposed. TWSNI and TWLNI are evaluated independently, which can overcome the problem that result could be mainly determined by targets with large numbers of interactions when all targets are evaluated together. Drug development is a time-consuming and expensive process that is plagued with the problem known as the high attrition rate. Mongia et al proposed a multi-graph regularized nuclear norm minimization based method for DTI, which predicts the interactions between drugs and target proteins from three inputs [4]. Wang et al proposed an effective computational model of dual Laplacian graph regularized matrix completion, where the drug and the target similarities can be fully exploited by using a dual Laplacian graph regularization term [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
