Paper Information | SBC BOOKS

Fill in your paper information

Language (*)

Title (*)

Keywords (*)

Abstract (*)

The chemogenomics computational methods use chemical and biological information about drugs and therapeutic targets to predict new interactions. The independence of protein structures and the ability to explore large sets of targets and drugs simultaneously are advantages of these approaches (Ezzat et al., 2019). In addition, these methodologies allow the prediction of new interactions from a group of drugs and targets (Reker et al., 2017). There are several chemogenomics methodologies, such as techniques based on networks, machine learning, and based on matrix factorization. Thus, in the search for new therapies, it is relevant to explore the therapeutic potential of different groups of compounds and identify new drug-target interactions. In this work, we applied different chemogenomic methodologies to a group of natural products from Brazilian plants and to a group of hallucinogens. We observed differences in the results of predictions of new interactions between the methodology based on networks (Cheng et al., 2012) and the one based on matrix factorization (Zheng et al., 2013). Therefore, we proposed a heterogeneous ensemble based on the two evaluated methodologies, offering robustness to the results. As a result, we identified two new drug-target interactions from natural plant products (Martins et al., 2022). Subsequently, we applied the same strategy of the heterogeneous ensemble in the hallucinogen group, and we identified two new interactions. From the predicted interactions, it was possible to correlate the two natural products of plants with different diseases, including breast cancer, mammary tumor, and syndrome of Cushing. On the other hand, the two hallucinogens obtained from the predicted interactions were correlated with several diseases, including epilepsy and Parkinson's. Currently, we are applying the heterogeneous ensemble strategy in other drug groups to identify other potential therapeutics.

Pages (*)

File Link

English Information

Title

Keywords

Abstract

(*) To change the order drag the item to the new position.

Authors

#	Name
1	Ronald Martins(ronaldmartins@aluno.fiocruz.br)
2	Marcelo Gomes(marcelo.gomes@fiocruz.br)
3	Ernesto Caffarena(ernesto.caffarena@fiocruz.br)

(*) To change the order drag the item to the new position.

Reference

#	Reference
1	Cheng, F., Liu, C., Jiang, J., Lu, W., Li, W., Liu, G., Zhou, W., Huang, J., Tang, Y., 2012. Prediction of Drug-Target Interactions and Drug Repositioning via Network-Based Inference. PLoS Comput. Biol. 8, e1002503. https://doi.org/10.1371/journal.pcbi.1002503 Ezzat, A., Wu, M., Li, X.-L., Kwoh, C.-K., 2019. Computational prediction of drug–target interactions using chemogenomic approaches: an empirical survey. Brief. Bioinform. 20, 1337–1357. https://doi.org/10.1093/bib/bby002 Martins, S.R., da Costa Gomes, M.F., Caffarena, R.E., 2022. Combining network-based and matrix factorization to predict novel drug-target interactions: A case study using the Brazilian natural chemical database. Curr. Bioinforma. 17, 1–1. https://doi.org/10.2174/1574893617666220820105258 Reker, D., Schneider, P., Schneider, G., Brown, J., 2017. Active learning for computational chemogenomics. Future Med. Chem. 9, 381–402. https://doi.org/10.4155/fmc-2016- 0197 Zheng, X., Ding, H., Mamitsuka, H., Zhu, S., 2013. Collaborative matrix factorization with multiple similarities for predicting drug-target interactions, in: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, Chicago Illinois USA, pp. 1025–1033. https://doi.org/10.1145/2487575.2487670

Paper Registration

Fill in your paper information

English Information

Authors

Reference