red blood cells

Malaria is one of the epidemics that can cause human death. Accurate and rapid diagnosis of malaria is important for treatment. Due to the limited number of data and human factors, the prediction performance and reliability of traditional classification methods are often affected. In this study, we propose an efficient and novel classification network named Attentive Dense Circular Net (ADCN) which based on Convolutional Neural Networks (CNN).

FIKK kinases in the human malaria parasite Plasmodium falciparum are attractive targets for new anti‐malaria drugs, as they have no orthologues in humans and have been linked to disease severity. Six FIKKs are known to be exported into red blood cells (RBCs) where they mediate dramatic structural and functional changes to RBCs that are central to pathogenesis. Eleven members of this family, which are predicted to be exported into infected RBCs (iRBCs), remain uncharacterised.

In this work, we developed two types of cell model, one with an included parasite, and the other without an included parasite. The former is a representation of real malaria-infected RBCs, in which the parasite is treated as a rigid body.