Deep Learning-driven research for drug discovery: Tackling Malaria

Author(s)

Neves, Bruno J. ^{[1, 2]} ; Braga, Rodolpho C. ^[3] ; Alves, Vinicius M. ^{[4, 1]} ; Lima, Marilia N. N. ^[1] ; Cassiano, Gustavo C. ^{[5, 6]} ; Muratov, Eugene N. ^{[7, 4]} ; Costa, Fabio T. M. ^[5] ; Andrade, Carolina Horta ^{[5, 1]}

Affiliation

^[1] Univ Fed Goias, LabMol Lab Mol Modeling & Drug Design, Fac Pharm, Goiania, Go - Brazil

^[2] Univ Ctr Anapolis, UniEVANGELICA, Lab Cheminformat, Anapolis, Go - Brazil

^[3] InsilicAll, Sao Paulo, SP - Brazil

^[4] Univ N Carolina, UNC Eshelman Sch Pharm, Lab Mol Modeling, Chapel Hill, NC 27515 - USA

^[5] Univ Estadual Campinas, Dept Genet Evolut Microbiol & Immunol, Inst Biol, Lab Trop Dis Prof Dr Luiz Jacintho da Silva, Campinas, SP - Brazil

^[6] Univ Nova Lisboa, IHMT, GHTM, Lisbon - Portugal

^[7] Odessa Natl Polytech Univ, Dept Chem Technol, Odessa - Ukraine

• Document type: Journal article
• Source: PLOS COMPUTATIONAL BIOLOGY; v. 16, n. 2 FEB 2020.
• Web of Science Citations: 0

Abstract

Malaria is an infectious disease that affects over 216 million people worldwide, killing over 445,000 patients annually. Due to the constant emergence of parasitic resistance to the current antimalarial drugs, the discovery of new drug candidates is a major global health priority. Aiming to make the drug discovery processes faster and less expensive, we developed binary and continuous Quantitative Structure-Activity Relationships (QSAR) models implementing deep learning for predicting antiplasmodial activity and cytotoxicity of untested compounds. Then, we applied the best models for a virtual screening of a large database of chemical compounds. The top computational predictions were evaluated experimentally against asexual blood stages of both sensitive and multi-drug-resistant Plasmodium falciparum strains. Among them, two compounds, LabMol-149 and LabMol-152, showed potent antiplasmodial activity at low nanomolar concentrations (EC50 < 500 nM) and low cytotoxicity in mammalian cells. Therefore, the computational approach employing deep learning developed here allowed us to discover two new families of potential next generation antimalarial agents, which are in compliance with the guidelines and criteria for antimalarial target candidates. (AU)

• FAPESP's process: 17/02353-9 - Bioinformatics, Chemiogenomics and Chemioinformatics applied to the Discovery of New Drugs and Biotechnological Products
• Grantee: Fabio Trindade Maranhão Costa
• Support Opportunities: Research Grants - Visiting Researcher Grant - Brazil
• FAPESP's process: 17/18611-7 - Development of new tools for search and validation of molecular targets for therapy against Plasmodium vivax
• Grantee: Fabio Trindade Maranhão Costa
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 15/20774-6 - Identifying protein kinase inhibitors as antimalarial agents using chemogenomic, bioinfomatics and phenotypic strategies: focus in Plasmodium vivax.
• Grantee: Gustavo Capatti Cassiano
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 12/16525-2 - Plasmodium vivax: pathogenesis and infectivity
• Grantee: Fabio Trindade Maranhão Costa
• Support Opportunities: Research Projects - Thematic Grants