AIMaR: Combating Antimalarial Resistance: An AI-Driven Approach to Identify and Prioritize Key Parasite Mutations
Started: December 2025 · Ends: November 2028
Project Description
The AIMaR project aims to tackle the growing challenge of malaria drug resistance, which heavily impacts millions of people, especially young children and pregnant women across Africa. While traditional surveillance methods have laid a vital foundation for tracking malaria, relying on manual observation falls short when trying to stay ahead of rapidly evolving parasite mutations. Because predicting drug resistance and identifying immune evasion effectively relies heavily on finding specific genetic variations before they spread, a faster and more predictive approach is urgently needed. To fix this, the AIMaR project integrates malaria genomics, epidemiological data, and laboratory testing with the Evolutionary Variant Effect (EVE) framework and AlphaFold's highly accurate protein structure predictions. By combining these advanced computational models, the project accelerates how we identify, model, and prioritize novel Plasmodium falciparum variants at an unprecedented pace. Ultimately, this work builds strong local capacity for early detection, giving researchers the high-quality insights needed to keep current malaria treatments effective while driving progress toward total malaria elimination.
This project is led by Daudi Jjingo, PhD (Director ).
Relevance to the Sector
This project addresses a critical gap in malaria eradication that conventional methods have not yet solved. By predicting and characterizing drug resistance mutations before they spread, it strengthens malaria control and elimination efforts. It provides much-needed molecular markers for tracking resistance to key antimalarial drugs, including lumefantrine; a cornerstone of artemisinin-based combination therapies. The findings will also guide vaccine design by identifying mutations that affect efficacy, particularly relevant given the recent rollout of the R21/Matrix-M vaccine in Uganda. The open-source, Python-based nature of the tools ensures they are suitable for sustainable local capacity building in low-resource settings. Furthermore, the scalable AI pipeline can be adapted to study genetic resistance in other high-priority pathogens such as TB and HIV. Finally, by using local clinical samples collected across Uganda, the research ensures findings are relevant to global populations.
Timeline
Start Date
December 1, 2025
End Date
November 30, 2028