A Drug-Side Effect Context-Sensitive Network approach for drug target prediction

Abstract

Summary: Computational drug target prediction has become an important process in drug discovery. Network-based approaches are commonly used in computational drug-target interaction (DTI) prediction. Existing network-based approaches are limited in capturing the contextual information on how diseases, drugs and genes are connected. Here, we proposed a context-sensitive network (CSN) model for DTI prediction by modeling contextual drug phenotypic relationships. We constructed a Drug-Side Effect Context-Sensitive Network (DSE-CSN) of 139 760 drug-side effect pairs, representing 1480 drugs and 5868 side effects. We also built a protein-protein interaction network (PPIN) of 15 267 gene nodes and 178 972 weighted edges. A heterogeneous network was built by connecting the DSE-CSN and the PPIN through 3684 known DTIs. For each drug on the DSE-CSN, its genetic targets were predicted and prioritized using a network-based ranking algorithm. Our approach was evaluated in both de novo and leave-one-out cross-validation analysis using known DTIs as the gold standard. We compared our DSE-CSN-based model to the traditional similarity-based network (SBN)-based prediction model. The results suggested that the DSE-CSN-based model was able to rank known DTIs highly. In a de novo cross-validation, the area under the receiver operating characteristic (ROC) curve was 0.95. In a leave-one-out cross-validation, the average rank was top 3.2% for known DTIs. When it was compared to the SBN-based model using the Precision-Recall curve, our CSN-based model achieved a higher mean average precision (MAP) (0.23 versus 0.19, P-value<1e-4) in a de novo cross-validation analysis. We further improved the CSN-based DTI prediction by differentially weighting the drug-side effect pairs on the network and showed a significant improvement of the MAP (0.29 versus 0.23, P-value<1e-4). We also showed that the CSN-based model consistently achieved better performances than the traditional SBN-based model across different drug classes. Moreover, we demonstrated that our novel DTI predictions can be supported by published literature. In summary, the CSN-based model, by modeling the context-specific inter-relationships among drugs and side effects, has a high potential in drug target prediction.

Availability and implementation: nlp/case/edu/public/data/DSE/CSN_DTI.

Fig. 1.

(a) Different relationships among drugs, diseases and genes. (b) The visualization of the integrated context-sensitive network

Fig. 2.

(a) Drug nodes from a traditional similarity-based network (SBN), where drugs are connected based on the side effect similarity scores. (b) Drug nodes from a novel context-sensitive network (CSN), where drugs are directly connected through specific side effects

Fig. 3.

The outline of the DSE-CSN-based approach: (a) Construct a DSE-CSN and a PPIN. (b) Integrate the DSE-CSN and the PPIN. (c) Prioritize the genes by a network-based algorithm

Fig. 4.

(a) Mean average precision versus the transition probabilities and (b) mean average precision versus the probability of restarting from the seed

Fig. 5.

ROC curves for the DSE-CSN-based approach and the DSE-SBN-based approach

Fig. 6.

(a) Comparison between the Unweighted DSE-CSN and the Random DSE-CSN; (b) Comparison between Unweighted the DSE-CSN and the DSE-SBN

Fig. 7.

(a) Comparison between the Frequency-based DSE-CSN and the Unweighted DSE-CSN; (b) Comparison between the Information-content-based DSE-CSN and the Unweighted DSE-CSN

Fig. 8.

The number of successfully predicted drug–target interactions for the DSE-CSN-based model and the DSE-SBN-based model

Fig. 9.

PR curves for the DSE-CSN approach across different ATC class in de novo cross-validation