Prediction of Potential Kinase Inhibitors in Leishmania spp. through a Machine Learning and Molecular Docking Approach
Currently, tropical diseases are a major research objective in biomedical sciences due to the overall impact on vulnerable populations ignored by pharmaceutical companies. For that reason, the search for new therapeutic treatments is essential in the fight against tropical parasites such as Leishmania spp. The proposed approach will involve collecting the set of kinases from both the parasite and other organisms (except human), attempting to identify compounds and approved drugs, which are selective to the parasite, based on in silico methodologies. ChEMBL, Therapeutic Target Database (TTD) and DrugBank were used as sources for a list of compounds and kinase drug targets, which were represented using fingerprints based on patterns detected in the protein sequence, and a set of descriptors based on physic-chemical properties of the catalytic domains. The enzymes were used as a training set for a Support Vector Machine in conjunction with Feature Selection techniques, looking to predict druggable kinases, found in five sequenced Leishmania species. Following the target selection, a list of compounds was inferred and filtered according to some cheminformatics protocols. Finally, to support the predictions, some Leishmania kinases and their associated compounds were 3D modeled, and docked to each other according to a consensus docking schema based on the open packages AutoDock 4, AutoDockVina and DOCK.
KeywordsBioinformatics Docking Machine Learning Leishmania Kinases
Unable to display preview. Download preview PDF.
- 1.World Health Organization: Leishmaniasis: worldwide epidemiological and drug access update (2012) Google Scholar
- 2.Maltezou, H.: Drug resistance in visceral leishmaniasis. J. Biomed. Biotechnol. 2010 (2010)Google Scholar
- 7.Ochoa, R., Florez, A., Muskus, C.: Detección in silico de segundos usos de medicamentos con potencial acción leishmanicida. Ingeniería Biomédica 10, 10–16 (2011)Google Scholar
- 8.Knox, C., Law, V., Jewison, T., Liu, P., Ly, S., Frolkis, A., Pon, A., et al.: DrugBank 3.0: a comprehensive resource for “omics” research on drugs. Nucleic. Acids. Res. 39, D1035–D1041 (2011)Google Scholar
- 9.Zhu, F., Shi, Z., Qin, C., Tao, L., Liu, X., Xu, F., Zhang, L., et al.: Therapeutic target database update 2012: a resource for facilitating target-oriented drug discovery. Nucleic. Acids. Res. 40, D1128–D1136 (2012)Google Scholar
- 10.Gaulton, A., Bellis, L., Bento, P., Chambers, J., Davies, M., Hersey, A., Light, Y., et al.: ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic. Acids. Res. 40, D1100–D1107 (2012)Google Scholar
- 11.Altschup, S., Gish, W., Pennsylvania, T., Park, U.: Basic Local Alignment Search Tool. J. Mol. Biol. 215, 403–410 (1990)Google Scholar
- 13.Flicek, P., Aken, B.L., Beal, K., Ballester, B., Caccamo, M., Chen, Y., Clarke, L., et al.: Ensembl 2008. Nucleic. Acids. Res. 36, D707–D714 (2008)Google Scholar
- 17.Pieper, U., Eswar, N., Braberg, H., Madhusudhan, M., Davis, F., Stuart, A., Mirkovic, N., et al.: MODBASE, a database of annotated comparative protein structure models, and associated resources. Nucleic. Acid. Res. 32, D217–D222 (2004)Google Scholar
- 19.Trott, O., Olson, A.: AutoDockVina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J. Comput. Chem. 31(2), 455–461 (2010)Google Scholar
- 22.Eswar, N., Webb, B., Marti-Renom, M., Madhusudhan, M., Eramian, D., Shen, M., Pieper, U., et al.: Comparative protein structure modeling using MODELLER. Current protocols in Bioinformatics 2(15), 1–30 (2007)Google Scholar