In 2021, Plasmodium falciparum was responsible for 619,000 reported malaria-related deaths. Resistance has been detected to every clinically used antimalarial, urging the development of novel antimalarials with uncompromised mechanisms of actions. High-content imaging allows researchers to collect and quantify numerous phenotypic properties at the single-cell level, and machine learning-based approaches enable automated classification and clustering of cell populations. By combining these technologies, we developed a method capable of robustly differentiating and quantifying P. falciparum asexual blood stages. These phenotypic properties also allow for the quantification of changes in parasite morphology. Here, we demonstrate that our analysis can be used to quantify schizont nuclei, a phenotype that previously had to be enumerated manually. By monitoring stage progression and quantifying parasite phenotypes, our method can discern stage specificity of new compounds, thus providing insight into the compound's mode of action.
Keywords: Plasmodium falciparum; drug discovery; drug resistance; high-content imaging; machine learning; malaria; parasites.
© 2023 The Authors.