Sorbonne Université, Inserm, Institut Pierre-Louis d'Epidémiologie et de Santé Publique, IPLESP, AP-HP, Groupe Hospitalier Pitié-Salpêtrière, Service de Parasitologie-Mycologie, 75013 Paris, France.
Laboratoire d'Ecologie Vectorielle et Parasitaire (LEVP), Faculté des Sciences et Techniques, Université Cheikh Anta Diop de Dakar, BP 5005 Dakar, Senegal.
Sci Adv. 2024 May 10;10(19):eadj6990. doi: 10.1126/sciadv.adj6990.
Mosquito-borne diseases like malaria are rising globally, and improved mosquito vector surveillance is needed. Survival of mosquitoes is key for epidemiological monitoring of malaria transmission and evaluation of vector control strategies targeting mosquito longevity, as the risk of pathogen transmission increases with mosquito age. However, the available tools to estimate field mosquito age are often approximate and time-consuming. Here, we show a rapid method that combines matrix-assisted laser desorption/ionization-time-of-flight mass spectrometry with deep learning for mosquito age prediction. Using 2763 mass spectra from the head, legs, and thorax of 251 field-collected mosquitoes, we developed deep learning models that achieved a best mean absolute error of 1.74 days. We also demonstrate consistent performance at two ecological sites in Senegal, supported by age-related protein changes. Our approach is promising for malaria control and the field of vector biology, benefiting other disease vectors like mosquitoes.
蚊媒疾病（如疟疾）在全球范围内呈上升趋势，因此需要改进蚊媒监测。蚊子的存活是疟疾传播的流行病学监测和针对蚊子寿命的媒介控制策略评估的关键，因为随着蚊子年龄的增长，病原体传播的风险会增加。然而，目前用于估计野外蚊子年龄的工具通常是近似的，而且费时。在这里，我们展示了一种快速的方法，该方法将基质辅助激光解吸/电离飞行时间质谱与深度学习相结合，用于预测蚊子的年龄。使用 251 只野外采集的蚊子的头部、腿部和胸部的 2763 个质谱，我们开发了深度学习模型，最佳平均绝对误差为 1.74 天。我们还在塞内加尔的两个生态地点证明了一致的性能，这得到了与年龄相关的蛋白质变化的支持。我们的方法有望用于疟疾控制和媒介生物学领域，也有益于其他疾病媒介，如蚊子。
