Last Updated: 29/05/2025

Integrated genomics and AI as a tool for eliminating malaria in Brazil (I-GAME)

Objectives

*Original title in Portuguese: Genômica integrada e IA como ferramenta para eliminação da malária no Brasil (I-GAME)

The project involves performing whole genome sequencing (WGS)/ amplicon sequencing (AMP-SEQ) in different malaria hotspots in Brazil to increase understanding of genetic diversity and improve strategies for disease control and elimination in the country.

Principal Investigators / Focal Persons

Claudio Romero Farias Marinho

Partner Investigators

Taane Gregory Clark

Rationale and Abstract

Malaria remains a significant global health problem, with millions of cases and hundreds of thousands of deaths per year, caused primarily by Plasmodium falciparum (Pf) and Plasmodium vivax (Pv). Efforts to control the disease have been challenged by emerging drug resistance, particularly to artemisinin-based therapies (ACTs). Although artemisinin resistance is primarily observed in Southeast Asia, the risk exists in other regions with similar transmission dynamics, including parts of South America, such as the Guiana Shield. The importance of genomic data in malaria control is highlighted, particularly for identifying drug resistance (DR) mutations and tracking transmission patterns. Whole genome sequencing (WGS) of the parasite and targeted amplicon sequencing (AMP-SEQ) are employed to detect species, DR mutations, and genetic diversity. These technologies, supported by platforms such as Oxford Nanopore and Illumina, enable accurate epidemiological insights and aid in surveillance strategies. However, effective utilization of genomic data is hampered by challenges such as the need for advanced informatics tools. The development of AI-driven tools, such as the Malaria-Profiler software, facilitates the analysis and rapid interpretation of sequencing data, providing actionable insights into species identification, DR profiles, and geographic origins. These tools are essential to inform clinical management, surveillance efforts, and public health interventions, especially in data-poor regions such as Brazil. LSHTM and ICB-USP aim to further enhance these informatics tools by integrating AI models to continuously update mutation libraries and improve predictive accuracy for species and DR profile, as well as other genomic information that can assist the National Malaria Control Program. Integrating AI with genomic data promises to revolutionize malaria control by enabling proactive surveillance, personalized treatment strategies, and timely response to emerging threats such as drug resistance. This approach not only improves clinical care but also strengthens public health systems through informed decision-making and collaborative data sharing among researchers and health care providers worldwide.

Date

Feb 2025 — Jan 2028

Project Site

Brazil

SHARE
SHARE