Learning algorithms estimate pose and detect motor anomalies in flies exposed to minimal doses of a toxicant

Gianluca Manduca; Valeria Zeni; Sara Moccia; Beatrice A Milano; Angelo Canale; Giovanni Benelli; Cesare Stefanini; Donato Romano

doi:10.1016/j.isci.2023.108349

Learning algorithms estimate pose and detect motor anomalies in flies exposed to minimal doses of a toxicant

iScience. 2023 Oct 27;26(12):108349. doi: 10.1016/j.isci.2023.108349. eCollection 2023 Dec 15.

Authors

Gianluca Manduca^{1

2}, Valeria Zeni³, Sara Moccia^{1

2}, Beatrice A Milano^{4

5}, Angelo Canale³, Giovanni Benelli³, Cesare Stefanini^{1

2}, Donato Romano^{1

2}

Affiliations

¹ The BioRobotics Institute, Sant'Anna School of Advanced Studies, Viale Rinaldo Piaggio 34, 56025, Pontedera, Pisa, Italy.
² Department of Excellence in Robotics and AI, Sant'Anna School of Advanced Studies, Piazza Martiri della Libertà 33, 56127, Pisa, Italy.
³ Department of Agriculture, Food and Environment, University of Pisa, Via del Borghetto 80, 56124, Pisa, Italy.
⁴ Institute of Life Sciences, Sant'Anna School of Advanced Studies, Piazza Martiri della Libertà 33, 56127, Pisa, Italy.
⁵ Faculty of Medicine and Surgery, University of Pisa, Via Roma 55/Building 57, 56126, Pisa, Italy.

Abstract

Pesticide exposure, even at low doses, can have detrimental effects on ecosystems. This study aimed at validating the use of machine learning for recognizing motor anomalies, produced by minimal insecticide exposure on a model insect species. The Mediterranean fruit fly, Ceratitis capitata (Diptera: Tephritidae), was exposed to food contaminated with low concentrations of Carlina acaulis essential oil (EO). A deep learning approach enabled fly pose estimation on video recordings in a custom-built arena. Five machine learning algorithms were trained on handcrafted features, extracted from the predicted pose, to distinguish treated individuals. Random Forest and K-Nearest Neighbor algorithms best performed, with an area under the receiver operating characteristic (ROC) curve of 0.75 and 0.73, respectively. Both algorithms achieved an accuracy of 0.71. Results show the machine learning potential for detecting sublethal effects arising from insecticide exposure on fly motor behavior, which could also affect other organisms and environmental health.

Keywords: Biological sciences; Toxicology.