DrugNet: Network-based drug–disease prioritization by integrating heterogeneous data

• Published in: Artificial intelligence in medicine Vol. 63; no. 1; pp. 41 - 49
• Main Authors: Martínez, Víctor, Navarro, Carmen, Cano, Carlos, Fajardo, Waldo, Blanco, Armando
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 2015
• Subjects: Area Under Curve; Computational Biology; Computer Simulation; Data integration; Data Mining; Databases, Factual; Disease networks; Diseases; Drug repositioning; Drug Repositioning - methods; Drugs; Flow propagation; Humans; Internal Medicine; Matlab; Medical research; Methodology; Models, Theoretical; Network-based prioritization; Networks; Other; Reproducibility of Results; ROC Curve; Source code; Systems Integration; Tasks; Drug repositioning; Flow propagation; Network-based prioritization; Data integration; Disease networks
• ISSN: 0933-3657; 1873-2860
• DOI: 10.1016/j.artmed.2014.11.003

Abstract Objective Computational drug repositioning can lead to a considerable reduction in cost and time in any drug development process. Recent approaches have addressed the network-based nature of biological information for performing complex prioritization tasks. In this work, we propose a new methodology based on heterogeneous network prioritization that can aid researchers in the drug repositioning process. Methods We have developed DrugNet, a new methodology for drug–disease and disease-drug prioritization. Our approach is based on a network-based prioritization method called ProphNet which has recently been developed by the authors. ProphNet is able to integrate data from complex networks involving a wide range of types of elements and interactions. In this work, we built a network of interconnected drugs, proteins and diseases and applied DrugNet to different types of tests for drug repositioning. Results We tested the performance of our approach on different validation tests, including cross validation and tests based on real clinical trials. DrugNet achieved a mean AUC value of 0.9552 ± 0.0015 in 5-fold cross validation tests, and a mean AUC value of 0.8364 for tests based on recent clinical trials (phases 0–4) not present in our data. These results suggest that DrugNet could be very useful for discovering new drug uses. We also studied specific cases of particular interest, proving the benefits of heterogeneous data integration in this problem. Conclusions Our methodology suggests that new drugs can be repositioned by generating ranked lists of drugs based on a given disease query or vice versa. Our study shows that the simultaneous integration of information about diseases, drugs and targets can lead to a significant improvement in drug repositioning tasks. DrugNet is available as a web tool from http://genome2.ugr.es/drugnet/ (accessed 23.09.14). Matlab source code is also available on the website.