From parasite proteins to candidate drug targets: where AlphaFold can help malaria research
Predicted protein structures can widen the search for antimalarial targets. The useful question is not whether AlphaFold makes a protein 'druggable', but how structural evidence can improve target prioritization.
Why structure matters here
GAYAR's confirmed malaria scope is identifying target proteins for antimalarial drug combinations. Protein structure is highly relevant to that problem because a candidate target must be more than biologically interesting: researchers also need evidence that it can be engaged selectively and usefully by a molecule.
AlphaFold provides predicted protein structures at a scale that was previously impossible to obtain experimentally. AlphaFold 3 extends that idea to interactions involving proteins, nucleic acids, small molecules and other biomolecules.
A malaria example already exists
A 2025 study revisited the Plasmodium falciparum druggable genome using predicted structures together with essentiality, ligand-binding and other biological evidence. The authors identified hundreds of candidate proteins and, after additional filtering and expert review, prioritized 27 high-priority antimalarial targets. AlphaFold-derived structures and AlphaFill ligand information were part of that evidence stack.
That is a useful model for how structure prediction could support GAYAR's malaria direction: not by declaring a target valid, but by helping prioritize which proteins deserve deeper computational and experimental investigation.
What structure prediction does not solve
A convincing structural model is not proof of druggability. Binding pockets may be misleading, predicted regions may have low confidence, and a protein can look chemically tractable while failing on essentiality, parasite-stage expression, human selectivity, resistance risk or pharmacology. Drug combinations add another layer because interaction between two interventions cannot be inferred from a single static structure.
The sensible role for AlphaFold is therefore triage and hypothesis generation: reduce a huge target space to a smaller set worth testing.
Sources: Google DeepMind — AlphaFold, the AlphaFold 3 Nature paper, and the 2025 P. falciparum druggable-genome study.