We present here a device built to facilitate error-free pipetting of samples from individual barcoded tubes to a multi-well plate or between multi-well plates (both 96 and 384 wells are supported). The device is programmable, modular and easily customizable to accommodate plates with different form-factors, and different protocols. The main components are only a 12.3” touch screen, a small form-factor PC, and a barcode scanner, combined with custom-made parts can be easily fabricated with a laser cutter and a hobby-grade 3D printer. The total cost is between approximately US$550 and US$600, depending on the configuration.
Although qualitative rapid diagnostic tests (RDTs) and PCR-based assays for malaria detection have existed for many years, in most malaria-endemic countries manual counting by microscopy remains the dominant modality for assessment of infection. This method involves smearing, fixation, staining, and manual inspection of blood smears—a practice that is time-consuming, labor-intensive, error-prone, and has varied little in over a century. Similarly, for laboratories around the world that grow P. falciparum for research, the process of assessing different stages of parasite growth is a daily ritual. Here, we provide rigorous evidence that live, unstained parasites can be automatically distinguished and sub-categorized from a healthy background in the context of laboratory cell culture, by applying deep learning to ordinary microscopy images, with high-sensitivity and low false-positive rates.