<p>Africa’s vast genetic diversity poses challenges for optimising drug treatments in the continent, which is exacerbated by the fact that drug discovery and development efforts have historically been performed outside Africa. This has led to suboptimal therapeutic outcomes in African populations and overall scarcity of relevant pharmacogenetic data, including characteristic genotypes as well as drugs prescribed in the continent to treat infectious diseases. Here, we propose a general approach to identify drug-gene pairs with potential pharmacogenetic interest. Our pipeline couples machine learning and artificial intelligence with physiologically-based pharmacokinetic (PBPK) and non-linear mixed effects (NLME) modelling to hypothesize which pharmacogenes could be of potential clinical interest, and which dose adjustments could be made to provide better treatment outcomes for African populations. Drug-gene pairs are first ranked with the latest knowledge embedding techniques, based on public structural and bioactivity data for drugs and genes, followed by a large language model-based refinement. Selected genes are then evaluated for their sensitivity in PBPK analysis, and relevant variants subsequently inspected with NLME for dose optimization. The analysis is focused on genes with potential clinical relevance in Africa. We delve deeper into malaria and tuberculosis therapies, many of which remain uncharacterised from a pharmacogenetic perspective.</p>