Leg-tracking and automated behavioral classification in Drosophila

TL;DR

This paper introduces a novel real-time leg-tracking method for Drosophila using infrared fluorescence and machine learning to classify behaviors, enabling high-resolution ethological profiling.

Contribution

It presents the first real-time, multi-leg tracking system combined with machine learning for behavioral classification in fruit flies.

Findings

Achieved real-time tracking of all legs in Drosophila.

Developed classifiers for multiple behavioral features.

Provided high-resolution ethological profiles.

Abstract

Here we present the first method for tracking each leg of a fruit fly behaving spontaneously upon a trackball, in real time. Legs were tracked with infrared-fluorescent dye invisible to the fly, and compatible with two-photon microscopy and controlled visual stimuli. We developed machine learning classifiers to identify instances of numerous behavioral features (e.g. walking, turning, grooming) thus producing the highest resolution ethological profiles for individual flies.