Prediction of malaria mosquito species and population age structure using mid-infrared spectroscopy and supervised machine learning
Prediction of malaria mosquito species and population age structure using mid-infrared spectroscopy and supervised machine learning
复制标题
使用中红外光谱和监督机器学习预测疟疾蚊子种类和种群年龄结构
DOI：
10.1101/414342
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
González-Jiménez M
中科院分区：
文献类型：
--
作者：
González-Jiménez M
尽管在防治疟疾方面作出了全球努力，但这一疾病正在死灰复燃。其中一个主要原因是疟疾病媒按蚊对杀虫剂产生了抗药性。按蚊必须存活至少12天才有可能传播疟疾。因此，为了评估和改进疟疾病媒控制干预措施，必须监测和准确估计蚊子种群的年龄分布以及总种群规模。然而，目前估计蚊子年龄是一个缓慢、不精确且劳动密集型的过程，只能区分四天大以下和四天大以上的雌性蚊子。在这里，我们展示了一种基于机器学习的方法，该方法利用蚊子的中红外光谱同时表征疟疾媒介冈比亚按蚊和安的雌性的年龄和物种身份，并且具有前所未有的准确性。在各自的人群中。年龄结构的预测在统计上与真实的模型分布没有区别。该方法每只蚊子的成本可以忽略不计，不需要训练有素的人员，比目前的技术快得多，因此可以很容易地应用于实验室和现场环境。我们的研究结果表明，通过更大的中红外光谱数据集，这项技术可以进一步改进并扩展到其他疾病的载体，如寨卡病毒和登革热。
Despite the global efforts made in the fight against malaria, the disease is resurging. One of the main causes is the resistance thatAnophelesmosquitoes, vectors of the disease, have developed to insecticides.Anophelesmust survive for at least 12 days to possibly transmit malaria. Therefore, to evaluate and improve malaria vector control interventions, it is imperative to monitor and accurately estimate the age distribution of mosquito populations as well as total population sizes. However, estimating mosquito age is currently a slow, imprecise, and labour-intensive process that can only distinguish under-from over-four-day-old female mosquitoes. Here, we demonstrate a machine-learning based approach that utilizes mid-infrared spectra of mosquitoes to characterize simultaneously, and with unprecedented accuracy, both age and species identity of females of the malaria vectorsAnopheles gambiaeandAn. arabiensismosquitoes within their respective populations. The prediction of the age structures was statistically indistinguishable from true modelled distributions. The method has a negligible cost per mosquito, does not require highly trained personnel, is substantially faster than current techniques, and so can be easily applied in both laboratory and field settings. Our results show that, with larger mid-infrared spectroscopy data sets, this technique can be further improved and expanded to vectors of other diseases such as Zika and Dengue.
登录
查看更多内容
影响因子：
3
作者：
Bass, Chris;Williamson, Martin S.;Wilding, Craig S.;Donnelly, Martin J.;Field, Linda M.
通讯作者：
Field, Linda M.
DOI：
10.1016/s0140-6736(15)00417-1
发表时间：
2016-04-23
期刊：
Lancet (London, England)
影响因子：
--
作者：
Hemingway J;Ranson H;Magill A;Kolaczinski J;Fornadel C;Gimnig J;Coetzee M;Simard F;Roch DK;Hinzoumbe CK;Pickett J;Schellenberg D;Gething P;Hoppé M;Hamon N
通讯作者：
Hamon N
影响因子：
1.9
作者：
HOC, TQ;CHARLWOOD, JD
通讯作者：
CHARLWOOD, JD
影响因子：
3.8
作者：
Sikulu-Lord MT;Milali MP;Henry M;Wirtz RA;Hugo LE;Dowell FE;Devine GJ
通讯作者：
Devine GJ
影响因子：
3.2
作者：
Anagonou R;Agossa F;Azondékon R;Agbogan M;Oké-Agbo F;Gnanguenon V;Badirou K;Agbanrin-Youssouf R;Attolou R;Padonou GG;Sovi A;Ossè R;Akogbéto M
通讯作者：
Akogbéto M