New AI tool can help track and identify complex fruit fly behavior

image

How do you recognize a fruit fly’s hunger? Consult a computer.

It’s true at University of Tulane, where researchers have created a new A. I. tool that can tell you when fruit flies are hungry, sleepy, or singing( yes, they do sing ), despite the fact that it may sound like the bad dad joke.

The system, known as MAFDA( for Novel Machine-learning-based Automatic Fly – behavioral Detection and Annotation ), uses cameras and recently created software to track and identify intricate interactive behaviors of individual flies within a larger group. This enables scientists to contrast and compare the behaviors of fruit flies from various genetic backgrounds.

With studies of Drosophila melanogaster winning six Nobel Prizes, scientists have used fruit flies’ simple genome and short lifespan to unravel mysteries of inheritance and immunity in humans for more than a century. Humans and fruit flies have 60 % of the same DNA.

The MAFDA system makes it simpler to study the tiny, winged insects than earlier algorithms, which were less accurate at tracking individual flies within a group.

From the chromosome theory of inheritance to innate immunity, fruit flies are like trailblazers in the discovery of novel concepts. It is a significant advancement in behavior studies to be able to quantify the behavior of flies.

Wu-Min Deng, PhD, corresponding author, biochemistry and molecular biology professor, and Gerald & amp, Flora Jo Mansfield Piltz Endowed Professor in Cancer Research at Tulane School of Medicine

The significance of the platform is” undeniable ,” according to Wenkan Liu, a graduate student in medicine who created the MAFDA system.

It expedites research, reduces human error, and offers complex insights into behavior genetics, according to Liu. This tool has the potential to be crucial because it improves reproducibility and opens the door for new research in large-scale behavioral analysis.

A recent study that found the gene that causes flies to perceive pheromones is also the one that regulates the production of phenomens led to the development of MAFDA. These results, which were published in Science Advances, refute the conventional wisdom that distinct genes regulate the production and perception of pheromones and have broad implications for human behavioral evolution, metabolism, and sex dimorphism.

The researchers anticipate seeing MAFDA used in a range of applications in the future. MAFDA could eventually be used to study other insects in addition to mice and fish, according to Jie Sun, lead author and postdoctoral fellow at Tulane School of Medicine, and the system might be helpful in researching drug effects.

According to Sun,” The more information we provide the machine, the better it is at correctly identifying various behaviors, from courtship to feeding, and so on.” This tool is very significant and important.

Researchers at Tulane are working to package the system so that it can be used by more scientists both there and around the world. MAFDA is already being used on other research projects there.

That’s the objective, Deng declared. The initial thought was to be able to determine a fly’s health status. Although it may be too much to ask at this time, we’re hoping that the community will use this more widely and that we can move in that direction in the future.

Journal mention:
J. Sun and colleagues Integrating lipid metabolism, pheromone production, and perception using hepatocyte nuclear factor 4 and fruitless. Science develops. Do. org / 10.1126 / sciadv. adf6254.

Leave a Reply