MolecRank: A Specificity-Based Network Analysis Algorithm
Biomedical scientists often search databases of therapeutic molecules to answer a set of drug-related queries. In this paper, we present a novel network algorithm called MolecRank that is specialized in searching and ranking molecules using a biomedical literature. Starting with a disease-related set of publications (e.g., depression), a feature extraction step is performed to identify the biological features associated with the drugs of study. The MolecRank is a network centrality algorithm that is specialized in deriving a rank when specificity is in question. The algorithm’s promise is two folds (a) an interesting search-and-rank tool that demonstrated its importance in the drug discovery research, (b) a theoretical network centrality measure that is based on the notion of specificity. We performed our experiments against a depression-related literature dataset. The results shows an interesting order that is significantly different from well-advertised drugs (e.g., Cymbalta#10 though well-advertised). We conclude that not all well-advertised drugs are most specific. This striking evidence highlights the significance of specificity as an important measure in discovering new drugs.
KeywordsSpecificity centrality Ranking algorithms Therapeutic molecules Literature mining
The authors would like thank Greg Temsi, Ramiro Barrantes for their valuable discussions. The authors also greatly appreciate the tremendous feedback on this work giving by Dr. Barabasi and his lab members. We also thank Dr. Karin Verspoor of University of Melbourne for the valuable discussions.
- 2.Winter, C., Kristiansen, G., Kersting, S., Roy, J., Aust, D., Knösel, T., Rümmele, P., Jahnke, B., Hentrich, V., Rückert, F., Niedergethmann, M., Weichert, W., Bahra, M., Schlitt, H.J., Settmacher, U., Friess, H., Büchler, M., Saeger, H.-D., Schroeder, M., Pilarsky, C., Grützmann, R.: Google goes cancer: improving outcome prediction for cancer patients by network-based ranking of marker genes. PLOS Comput. Biol. 8(5), 1–16 (2012)CrossRefGoogle Scholar
- 11.Lehninger, A., Nelson, D.L., Cox, M.M.: Lehninger Principles of Biochemistry, 5th edn. W. H. Freeman, San Francisco (2008)Google Scholar
- 12.Wood, E.J.: Harper’s Biochemistry 24th edition by R.K. Murray, D.K. Granner, P.A. Mayes and V.W Rodwell. pp 868. Appleton & Lange, Stamford, CT (1996). £ 28.95 isbn 0-8385-3612-3. Biochem. Educ. 24(4), 237–237 (1996)Google Scholar
- 18.Strovel, J., Sittampalam, S., Coussens, N.P., Hughes, M., Inglese, J., Kurtz, A., Andalibi, A., Patton, L., Austin, C., Baltezor, M., et al.: Early drug discovery and development guidelines: for academic researchers, collaborators, and start-up companies (2016)Google Scholar
- 22.Carpenter, B.: Lingpipe for 99.99% recall of gene mentions. In: Proceedings of the Second BioCreative Challenge Evaluation Workshop, vol. 23, pp. 307–309 (2007)Google Scholar
- 25.Koschützki, D., Schreiber, F.: Centrality analysis methods for biological networks and their application to gene regulatory networks. Gene Regul. Syst. Biol. 2, 193 (2008)Google Scholar
- 32.Page, L., Brin, S., Motwani, R., Winograd, T.: The pagerank citation ranking: bringing order to the web. Technical report, Stanford InfoLab (1999)Google Scholar
- 33.Pretto, L.: A theoretical analysis of google’s pagerank. In: String Processing and Information Retrieval, pp. 125–136. Springer (2002)Google Scholar