Using mid-infrared spectroscopy and supervised machine-learning to identify vertebrate blood meals in the malaria vector, Anopheles arabiensis

Autor: Klaas Wynne, Doreen J. Siria, Simon A. Babayan, Halfan S. Ngowo, Emmanuel P. Mwanga, Heather M. Ferguson, Fredros O. Okumu, Mario González Jiménez, Joseph P. Mgando, Salum A. Mapua, Francesco Baldini, Francis Nangacha, Prashanth Selvaraj
Rok vydání: 2019
Předmět:
Spectrophotometry
Infrared
computer.software_genre
Mid infrared spectroscopy
0302 clinical medicine
030212 general & internal medicine
Malaria vector
Goats
Anopheles
Mosquito blood meals
3. Good health
Anopheles arabiensis
Blood
Infectious Diseases
Vector surveillance
Vertebrates
Female
Supervised Machine Learning
lcsh:Arctic medicine. Tropical medicine
lcsh:RC955-962
030231 tropical medicine
Mosquito Vectors
Biology
Machine learning
Host Specificity
lcsh:Infectious and parasitic diseases
03 medical and health sciences
medicine
Animals
Humans
lcsh:RC109-216
Spectral data
Mid-infrared spectroscopy
business.industry
Research
Feeding Behavior
medicine.disease
Blood meal
biology.organism_classification
Malaria
Ifakara
Logistic Models
Parasitology
Artificial intelligence
business
Chickens
computer
Zdroj: Malaria Journal
Malaria Journal, Vol 18, Iss 1, Pp 1-9 (2019)
ISSN: 1475-2875
DOI: 10.1186/s12936-019-2822-y
Popis: Background: The propensity of diferent Anopheles mosquitoes to bite humans instead of other vertebrates infuences their capacity to transmit pathogens to humans. Unfortunately, determining proportions of mosquitoes that\ud have fed on humans, i.e. Human Blood Index (HBI), currently requires expensive and time-consuming laboratory procedures involving enzyme-linked immunosorbent assays (ELISA) or polymerase chain reactions (PCR). Here, midinfrared (MIR) spectroscopy and supervised machine learning are used to accurately distinguish between vertebrate blood meals in guts of malaria mosquitoes, without any molecular techniques.\ud Methods: Laboratory-reared Anopheles arabiensis females were fed on humans, chickens, goats or bovines, then held for 6 to 8 h, after which they were killed and preserved in silica. The sample size was 2000 mosquitoes (500 per host species). Five individuals of each host species were enrolled to ensure genotype variability, and 100 mosquitoes\ud fed on each. Dried mosquito abdomens were individually scanned using attenuated total refection-Fourier transform infrared (ATR-FTIR) spectrometer to obtain high-resolution MIR spectra (4000 cm−1\ud to 400 cm−1\ud ). The spectral\ud data were cleaned to compensate atmospheric water and CO2 interference bands using Bruker-OPUS software, then\ud transferred to Python™ for supervised machine-learning to predict host species. Seven classifcation algorithms were trained using 90% of the spectra through several combinations of 75–25% data splits. The best performing model was used to predict identities of the remaining 10% validation spectra, which had not been used for model training or testing.\ud Results: The logistic regression (LR) model achieved the highest accuracy, correctly predicting true vertebrate blood meal sources with overall accuracy of 98.4%. The model correctly identifed 96% goat blood meals, 97% of bovine blood meals, 100% of chicken blood meals and 100% of human blood meals. Three percent of bovine blood meals\ud were misclassifed as goat, and 2% of goat blood meals misclassifed as human.\ud Conclusion: Mid-infrared spectroscopy coupled with supervised machine learning can accurately identify multiple vertebrate blood meals in malaria vectors, thus potentially enabling rapid assessment of mosquito blood-feeding histories and vectorial capacities. The technique is cost-efective, fast, simple, and requires no reagents other than\ud desiccants. However, scaling it up will require field validation of the findings and boosting relevant technical capacity in affected countries.
Databáze: OpenAIRE
Externí odkaz: