LarvaTagger: Manual and automatic tagging ofDrosophilalarval behaviour

Abstract

MotivationAs more behavioural assays are carried out in large-scale experiments onDrosophilalarvae, the definitions of the archetypal actions of a larva are regularly refined. In addition, video recording and tracking technologies constantly evolve. Consequently, automatic tagging tools forDrosophilalarval behaviour must be retrained to learn new representations from new data. However, existing tools cannot transfer knowledge from large amounts of previously accumulated data. We introduce LarvaTagger, a piece of software that combines a pre-trained deep neural network, providing a continuous latent representation of larva actions for stereotypical behaviour identification, with a graphical user interface to manually tag the behaviour and train new automatic taggers with the updated ground truth.ResultsWe reproduced results from an automatic tagger with high accuracy, and we demonstrated that pre-training on large databases accelerates the training of a new tagger, achieving similar prediction accuracy using less data.AvailabilityAll the code is free and open source. Docker images are also available. Seegit-lab.pasteur.fr/nyx/LarvaTagger.jl.