Wolbachia detection in Aedes aegypti using MALDI-TOF MS coupled to artificial intelligence

Area of Science:

• Medical Entomology
• Molecular Biology
• Bioinformatics

Background:

• Aedes aegypti mosquitoes transmit arboviruses like dengue, Zika, and chikungunya.
• Insecticide resistance complicates Ae. aegypti control efforts.
• Releasing Wolbachia-infected mosquitoes is an emerging strategy to control arboviruses.

Purpose of the Study:

• To evaluate the reliability of MALDI-TOF MS coupled with CNN for detecting Wolbachia in field-collected Ae. aegypti.
• To compare the performance of this new method against existing techniques like LAMP and qPCR.

Main Methods:

• Analysis of laboratory-reared and field-collected Ae. aegypti using MALDI-TOF MS.
• Application of Convolutional Neural Network (CNN) machine learning models to spectral data.
• Comparison with Loop-Mediated Isothermal Amplification (LAMP) and quantitative Polymerase Chain Reaction (qPCR).

Main Results:

• CNN successfully recognized spectral patterns of Wolbachia infection in Ae. aegypti.
• MALDI-TOF MS and CNN achieved high accuracy (97%), specificity (99%), and sensitivity (93%) for Wolbachia detection.
• The combined method demonstrated superior efficiency compared to LAMP and comparable efficiency to qPCR.

Conclusions:

• MALDI-TOF MS coupled with CNN is a reliable and efficient method for detecting Wolbachia in Ae. aegypti.
• This approach offers a valuable tool for monitoring the prevalence of Wolbachia in field mosquito populations.
• It supports the effectiveness evaluation of Wolbachia-based arbovirus control programs.