An Efficient Drug-Target Interaction Mining Algorithm in Heterogeneous Biological Networks
The identification of interactions between drugs and targets is a key area in drug research. Exploring targets can help identify potential side effects and toxicities for drugs, as well as new applications of existing drugs. Because of the enormous scale of biological dataset, most of the existing algorithms for drug-target mining are time-consuming. In this paper, we proposed an optimization algorithm called LSH-HeteSim to mine the drug-target interaction in heterogeneous biological networks, where the relationship between drugs and targets is various. It means drugs and targets are connected with complicated semantic path. In practice, the similarity measure used for semantic path is a path-dependent method, called HeteSim, which had been utilized in some previous studies of relevance search. Experiment results in real biological networks show that our algorithm can effectively predict drug-target interaction with the AUC measure achieving 0.943. Simultaneously, the running time of our algorithm is much less than the state-of-art methods.
KeywordsDrug target Link prediction Heterogeneous biological networks Meta-path Similarity measure
The work was supported in part by the National Natural Science Foundation Project of China under Grant. No. 61170096 and Research Program of Shanghai Science and Technology Committee under Grant. No. 12511502403. The authors gratefully acknowledge the support of SA-SIBS Scholarship Program.
- 8.Fakhraei, S., Louiqa, L., Lise, G.: Drug-target interaction prediction for drug repurposing with probabilistic similarity logic. In: Proceedings of the 12th International Workshop on Data Mining in Bioinformatics. ACM (2013)Google Scholar
- 9.Sun, Y.Z., Han, J.W., Yan, X.F., et al.: PathSim: meta path-based top-k similarity search in heterogeneous information networks. In: VLDB’11 (2011)Google Scholar
- 10.Shi, C., Kong, X.N., Yu, P.S., et al.: Relevance search in heterogeneous networks. In: Proceedings of the 15th International Conference on Extending Database Technology. ACM (2012)Google Scholar
- 11.Palma, G., Viadl, M.-E., Haag, L., et al.: Measuring relatedness between scientific entities in annotation datasets. In: Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics. ACM (2013)Google Scholar
- 14.Datar, M., Immorlica, N., Indyk, P., et al.: Locality-sensitive hashing scheme based on p-stable distributions. In: Proceedings of the Twentieth Annual Symposium on Computational Geometry. ACM (2004)Google Scholar
- 16.Kishore, S.: Accelerated clustering through locality-sensitive hashing. Diss. Massachusetts Institute of Technology (2012)Google Scholar
- 17.Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In: Proceedings of the thirty-fourth annual ACM symposium on Theory of computing. ACM (2002)Google Scholar
- 18.SLAP for Drug Target Prediction. http://cheminfov.informatics.indiana.edu:8080/slap
- 22.Lv, Q., Josephson, W., Wang, Z., et al.: Multi-probe LSH: efficient indexing for high-dimensional similarity search. VLDB Endowment, pp. 950–961 (2007)Google Scholar