University of Cape Town Secures Google Grant for AI-Powered African Pharmacogenomics Platform

The University of Cape Town (UCT) has received a significant $1.6 million grant from Google.org to develop an artificial intelligence platform. This platform aims to map the genetic variations within African populations that influence how individuals metabolize various medicines. This initiative addresses a critical gap in global pharmacogenomics, as current guidelines are predominantly based on European and East Asian data, leaving African clinicians without population-specific evidence for prescribing medications.
The project, part of the Google.org Impact Challenge: AI for Science, will catalogue genetic diversity across over 50 drug-metabolizing genes. It will use AI to predict which genetic variants are most likely to alter drug processing, with these predictions then being experimentally validated in the laboratory. The initial focus will be on tuberculosis, HIV, and malaria, diseases that disproportionately affect the continent and for which existing dosing guidelines are often inadequate.
A key aspect of this research is its commitment to open science. All software, AI models, and curated datasets will be openly published, and findings will be shared through international research databases. Furthermore, the decision-support tools developed will be designed for low-bandwidth environments, ensuring they are accessible and usable in district clinics across Africa, not just well-resourced teaching hospitals. This approach aims to maximize the real-world impact of the research.
Beyond its immediate applications, the project is designed to be adaptable, allowing its methods to be extended to other underrepresented populations and a broader range of medical treatments, including cancer and cardiovascular conditions. The grant also includes a strong capacity-building component, funding the training of African postdoctoral fellows and students in AI, bioinformatics, and pharmacogenomics, thereby fostering local expertise and leadership in this crucial field. This UCT-led initiative, spearheaded by African scientists, underscores a significant step towards equitable and effective medicine use on the continent.
Source
More in research
AI Models Systematically Undervalue African Time, New Research Reveals
A global study on how large language models (LLMs) value human time found that these AI systems consistently recommend the lowest compensation for users in Africa when simulating…
New Speech Synthesizer Preserves Nuances of Yoruba Language
TTSYoruba is a new speech synthesizer specifically designed for the Yoruba language, a significant step in developing AI tools for low-resource African languages. It is deployed…
New 'Nufo' Benchmark Advances Ewe Language AI Speech Recognition
A new 174-hour Ewe ASR benchmark, 'Nufo', has been released, providing a crucial resource for developing speech recognition technology for this major West African language. This…
AI Model Enhances West African Rainfall Prediction by Downscaling Climate Data
This research applies AI, specifically U-Net and GAN architectures, to statistically downscale climate data, providing higher-resolution daily precipitation forecasts for West…
The dispatch
One email a day. The AI stories shaping Africa.
Rewritten for clarity, sourced always. No spam; unsubscribe anytime.
