RT Journal Article SR Electronic T1 A Network Integration Approach for Drug-Target Interaction Prediction and Computational Drug Repositioning from Heterogeneous Information JF bioRxiv FD Cold Spring Harbor Laboratory SP 100305 DO 10.1101/100305 A1 Yunan Luo A1 Xinbin Zhao A1 Jingtian Zhou A1 Jinling Yang A1 Yanqing Zhang A1 Wenhua Kuang A1 Jian Peng A1 Ligong Chen A1 Jianyang Zeng YR 2017 UL http://biorxiv.org/content/early/2017/01/13/100305.abstract AB The emergence of large-scale genomic, chemical and pharmacological data provides new opportunities for drug discovery and repositioning. Systematic integration of these heterogeneous data not only serves as a promising tool for identifying new drug-target interactions (DTIs), which is an important step in drug development, but also provides a more complete understanding of the molecular mechanisms of drug action. In this work, we integrate diverse drug-related information, including drugs, proteins, diseases and side-effects, together with their interactions, associations or similarities, to construct a heterogeneous network with 12,015 nodes and 1,895,445 edges. We then develop a new computational pipeline, called DTINet, to predict novel drug-target interactions from the constructed heterogeneous network. Specifically, DTINet focuses on learning a low-dimensional vector representation of features for each node, which accurately explains the topological properties of individual nodes in the heterogeneous network, and then predicts the likelihood of a new DTI based on these representations via a vector space projection scheme. DTINet achieves substantial performance improvement over other state-of-the-art methods for DTI prediction. Moreover, we have experimentally validated the novel interactions between three drugs and the cyclooxygenase (COX) protein family predicted by DTINet, and demonstrated the new potential applications of these identified COX inhibitors in preventing inflammatory diseases. These results inculcate that DTINet can provide a practically useful tool for integrating heterogeneous information to predict new drug-target interactions and repurpose existing drugs. The source code of DTINet and the input heterogeneous network data can be downloaded from http://github.com/luoyunan/DTINet.