Development of a unique model to assess the impact of interventions in the control of trypanosomiasis in humans and livestock
Combining gene expression and machine learning to estimate individual age in tsetse flies.
Trypanosomiases are deadly diseases of humans and livestock transmitted by tsetse flies in Africa. The human form of the disease (sleeping sickness) is a direct threat to human life, while the animal form (nagana) presents a major economic burden by killing livestock.
Neither sleeping sickness nor nagana can be eliminated through treatment of the disease alone, it also requires effective control of tsetse populations to prevent reinfection. However, at this stage current methods of evaluating the success of control measures are insufficient. A sensitive means of estimating changes in mortality is through recording shifts in the fly population's age distribution, but age is notoriously difficult to estimate in the field. Age is also an important determining factor in the ability of tsetse flies to transmit nagana, since older flies are more likely to be infective.
We will apply a unique combined analysis of gene expression and Near Infra-Red Spectroscopy to obtain estimates of age in tsetse flies, using machine learning algorithms to provide accurate estimates of age, which can then be used in the field to assess the impact of tsetse control interventions and predict the ability of a population to transmit trypanosomiases.