Development of machine learning-based tools for the discovery of new Malaria drug candidates

• Grant number: 19/27790-8
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: September 01, 2020
• End date: August 31, 2023
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Rafael Victorio Carvalho Guido
• Grantee: Alexandre Victor Fassio
• Host Institution: Instituto de Física de São Carlos (IFSC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 13/07600-3 - CIBFar - Center for Innovation in Biodiversity and Drug Discovery, AP.CEPID

Abstract

Malaria is an infectious disease caused by protozoa of the genus Plasmodium that has a prominent position among tropical diseases, due, among other factors, to the high mortality rate, the low socioeconomic development of the affected communities, and the enormous impact on the health and productivity of the populations living in endemic regions of the disease. The disease transmission occurs in 87 countries and is endemic in tropical and subtropical regions of Africa, Southeast Asia, and Latin America. Almost half of the world's population (3.2 billion people) is exposed to Malaria transmission in risk areas. In 2017, there were 219 million cases and 435,000 deaths, with Africa being the most affected region. In recent decades, worldwide efforts to eradicate Malaria have caused a significant reduction in the number of cases. However, the emergence and spread of drug-resistant parasites make the search for new chemotherapy agents against the disease critical. This project is divided into two fronts. In the first, we will develop algorithms, models, and computational tools to predict novel promising compounds capable of inhibiting multiple protein targets in P. falciparum strains. To do so, we propose the use of machine learning techniques, virtual screening, and molecular docking for the training of computational models based on known protein-ligand complexes and subsequent prediction and experimental validation of new drug candidates based on the prospective results obtained with the constructed models. The later consists of the development of a web platform to assist and streamline the process of creating a database of microscopic images that will be made available to the scientific community. To thoroughly conduct the proposal, we established an international partnership between researchers from the Institute of Physics of San Carlos (IFSC-USP) and the University of California San Francisco (UCSF). The IFSC-USP research group has extensive experience in medicinal chemistry for the discovery of new bioactive compounds. Our laboratory is home to the Center for Research and Innovation in Biodiversity and Pharmaceuticals (CIBFar-CEPID) and has facilities and equipment suitable for the discovery of new drug candidates. Also, our research group is a center of excellence of the nonprofit Medicines for Malaria Venture (MMV) for the evaluation of antiMalarial drug candidate compounds. In its turn, the research group coordinated by Prof. Michael Keiser (UCSF) has extensive experience in chemoinformatics, polypharmacology, computer vision, and machine learning techniques for new drug discovery and image processing. Therefore, this proposal offers the opportunity for our research team to take effective action in science and technology in the fields of Medicinal Chemistry, Bioinformatics, Chemoinformatics, Biochemistry, and Data Science for the discovery of new candidates for antimalarial drugs. (AU)