Your browser does not support the video tag.
Fish fingers: A new machine learning approach defines an 80-dimensional “fingerprint” of zebrafish social behavior.
Researchers are looking to develop better techniques to assess zebrafish social behavior, reveal unpublished studies presented at Neuroscience 2022 in San Diego, California. And with good reason. Fish can model aspects of autism genetics that are hard to access in other species, other work has found.
The clear impression is that despite their evolutionary distance from humans, zebrafish can tell something meaningful about social behavior – and how genes linked to autism can alter it.
“I think people have become more and more open to the idea in recent years,” says Yijie Geng, a postdoctoral researcher in Randall Peterson’s lab at the University of Utah in Salt Lake City.
Zebrafish are very social, say Geng and other researchers who study them. In the wild, they are rarely alone, preferring to form loose aggregations of fish called shoals and sometimes exhibiting tighter, more coordinated schooling behavior.
One of the challenges is that manually scoring this behavior is a tedious and time-consuming task, and most tests only capture a few aspects of the behavior at most. Fish behavior analysis software exists but also has limitations. “It classifies by parameters that are important to us, but we don’t know if they are important to zebrafish,” says Geng.
Ebetween artificial intelligence. In a poster presentation on Tuesday, Geng detailed a machine learning program called ZeChat that can analyze the behavior of up to 80 fish at a time.
Geng and Peterson placed pairs of zebrafish larvae in 2-by-4-centimeter enclosures and separated them with a piece of transparent plexiglass that runs down the middle of each enclosure (see video above). Cameras record fish as they interact through the barrier, and the algorithm automatically detects and classifies behavior.
Other researchers are developing approaches using this principle, known as unsupervised deep learning, to assess the behavior of other species of model organisms.
“The computer is also not a zebrafish, but the advantage it has over a human is that it doesn’t distinguish between details,” says Geng.
The result is a map of 80 different zebrafish behaviors, including some – like number 8, eye movement; number 36, adjustment of the position during the sleep phase; and the number 40, changing from dormant to active at the window – humans can interpret, while the meaning of others remains a mystery.
The algorithm describes an 80-dimensional behavioral “fingerprint” for each fish based on how often it performs each of the behaviors.
Geng and Peterson used ZeChat to assess the effects of 237 different drugs on the behavior of wild-type zebrafish. Different classes of drugs have produced distinct behavioral fingerprints, and compounds that have similar functions produce similar ones.
Drugs that stimulate a type of dopamine receptor increase sociability in fish, the researchers found. The drugs made the fish more likely to stay close to the barrier, flap their tails and swim quickly, and turn around faster and more frequently than the control zebrafish.
Three different drugs in this class – pramipexole, piribedil and 7-hydroxy-DPAT-HBr – rescue social deficits in zebrafish exposed to the antiepileptic valproic acid, which is linked to autism.
The research also appears in a paper published on bioRxiv in October 2021. Geng aims to develop a version of the algorithm that could analyze the behavior of two zebrafish swimming together without being separated by a barrier.
AAs interest in zebrafish social behavior grows, researchers are also looking for ways to limit the number of animals needed for studies.
But zebrafish aren’t easily fooled by researchers’ schemes, according to an unpublished study featured in a poster Wednesday. In a version of a procedure called the open-choice free-swimming test, a zebrafish in one tank spends more time at the end closest to a fish in an adjacent tank than at the other end, which has a mirror.
“Overwhelmingly, our fish preferred the living congener to the mirror,” says Drew Velkey, director of the neuroscience program at Christopher Newport University in Newport News, Va., who presented the work. “They prefer the high-fidelity stimulus.”
Velkey’s team has previously shown that zebrafish prefer swimming near a live shoal of other zebrafish than near video of a shoal or an animatronic model. The female zebrafish can even tell the difference between an established school of fish that has been swimming together for seven days and a newly formed school – and prefers to swim close to the former.
The new findings reinforce the idea that “these animals are able to make very fine social distinctions,” says Velkey. He thinks this ability could make zebrafish useful for assessing autism-related genetic alterations associated with subtle behavioral differences.
A a similar free-swimming test shows that fish lacking the autism-linked gene GRIN2B have social deficits, according to a poster presented Monday.
When three-week-old fish are placed in a long enclosure with a chamber containing another fish at one end and an empty chamber at the other, GRIN2B fish show no preference for one end or the other. At this age, wild-type fish will choose to spend most of their time at the end closest to other fish.
“We hadn’t done social behavior analyzes before we had these fish,” says Josiah Zoodsma, a graduate student mentored by Lonnie Wollmuth and Howard Sirotkin at Stony Brook University in New York, who presented the work. .
The researchers first performed standard tests of locomotion, learning, and sensory responses with the GRIN2B fish “and saw nothing. They were completely wild-type,” says Zoodsma.
Mice lacking GRIN2B die shortly after birth, so the team was puzzled to find no obvious abnormalities in the zebrafish model. But in the meantime, studies on the social behavior of zebrafish were beginning to be better known.
“All of this led us to start looking at social behavior,” says Zoodsma.
GRIN2B codes for part of the NMDA receptor, involved in the transmission of excitatory nerve signals. Other NMDA receptor subunits appear to be upregulated in GRIN2B fish, possibly protecting the fish from displaying other abnormalities. “But even with this adaptation, it does not solve this problem [social behavior]says Zoodsma.
Additionally, fish lacking other NMDA receptor subunits do not have social deficits. “It really highlights the uniqueness of what 2B does in development,” he says.
The results were also published in Molecular autism in September.
Lily more reports from Neuroscience 2022.
Cite this article: https://doi.org/10.53053/UZEN7612
#Zebrafish #social #behavior #swimming #mainstream #Spectrum #Autism #Research #News