Computational Drug Repositioning by Ranking and Integrating Multiple Data Sources
· Chemical data source: Drug and PubChem chemical substructures relationships
It includes 122,022 associations between 1007 drugs and 881 PubChem chemical substructures.
The descriptions of the 881 chemical substructures found here.
Generated from fingerprints of PubChem1.
· Protein data source: Drug and UniProt target proteins relationships
It includes 3,152 associations between 1007 drugs and 775 target proteins.
Generated from targets of DrugBank2.
· Side-effect data source: Drug and SIDER side-effect keywords relationships
It includes 61,102 associations between 888 drugs and 1385 side-effect terms.
Generated from SIDER3.
· Drug-disease treatment data source: Drug and therapeutic indication relationships
It includes 3,250 treatment relationships between 799 drugs and 719 diseases.
Generated from Li and Lu4.
· Predicted drug-disease associations by our method
It includes 3,870 predicted drug-disease associations by our method.
1. Wang Y, Xiao J, Suzek TO, Zhang J, Wang J, Bryant SH. PubChem: a public information system for analyzing bioactivities of small molecules. Nucleic Acids Res. 2009;37(Web Server Issue):W623-W633.
2. Wishart DS, Knox C, Guo AC, Cheng D, Shrivastava S, Tzur D, Gautam B, Hassanali M. DrugBank: a knowledgebase for drugs, drug actions and drug targets. Nucleic Acids Res. 2008;36(Database Issue):D901-D906.
3. Kuhn M, Campillos M, Letunic I, Jensen LJ, Bork P. A side effect resource to capture phenotypic effects of drugs. Molecular Systems Biology 2010;6:343.
4. Li J, Lu Z. A New Method for Computational Drug Repositioning Using Drug Pairwise Similarity. In Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine 2012.