Back

Rapid ageing and species identification of natural mosquitoes for malaria surveillance

Siria, D. J.; Sanou, R.; Mitton, J.; Mwanga, E.; Niang, A.; Sare, I.; Johnson, P. C. D.; Foster, G.; Belem, A.; Wynne, K.; Murray-Smith, R.; Ferguson, H. M.; Gonzalez Jimenez, M.; Babayan, S.; Diabate, A.; Okumu, F. O.; Baldini, F.

2020-06-12 zoology
10.1101/2020.06.11.144253 bioRxiv
Show abstract

The malaria parasite, which is transmitted by several Anopheles mosquito species, requires more time to reach its human-transmissible stage than the average lifespan of a mosquito. Monitoring the species-specific age structure of mosquito populations is critical to evaluating the impact of vector control interventions on malaria risk. We developed a rapid, cost-effective surveillance method based on deep learning of mid-infrared spectra of mosquitoes cuticle that simultaneously identifies the species and the age of three main malaria vectors, in natural populations. Using over 40,000 ecologically and genetically diverse females, we could speciate and age grade An. gambiae, An. arabiensis, and An. coluzzii with up to 95% accuracy. Further, our model learned the age of new populations with minimal sampling effort and detected the impact of control interventions on simulated mosquito populations, measured as a shift in their age structures. We anticipate our method to be applied to other arthropod vector-borne diseases.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.