EUVIMEDEUVIMED entdecken
Open Access

FlyVISTA, an integrated machine learning platform for deep phenotyping of sleep in Drosophila

Mehmet F Keleş iD, Ali Osman Berk Sapci iD, Casey Brody, Isabelle Palmer iD, Anuradha Mehta, Shahin Ahmadi, Christin Le iD, Öznur Taştan, Sündüz Keleş, Mark N Wu iD

Science Advances · 14.03.2025 · 11 (11)

DOI: 10.1126/sciadv.adq8131 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 14.03.2025. Verfasst von Mehmet F Keleş und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Johns Hopkins University, Baltimore, MD 21205, USA. Hauptthemen laut MEDLINE: Sleep, Machine Learning, Drosophila, Deep Learning. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 98 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NINDS NIH HHS, NHGRI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

There is great interest in using genetically tractable organisms such as Drosophila to gain insights into the regulation and function of sleep. However, sleep phenotyping in Drosophila has largely relied on simple measures of locomotor inactivity. Here, we present FlyVISTA, a machine learning platform to perform deep phenotyping of sleep in flies. This platform comprises a high-resolution closed-loop video imaging system, coupled with a deep learning network to annotate 35 body parts, and a computational pipeline to extract behaviors from high-dimensional data. FlyVISTA reveals the distinct spatiotemporal dynamics of sleep and wake-associated microbehaviors at baseline, following administration of the sleep-inducing drug gaboxadol, and with dorsal fan-shaped body drivers. We identify a microbehavior (“haltere switch”) exclusively seen during quiescence that indicates a deeper sleep stage. These results enable the rigorous analysis of sleep in Drosophila and set the stage for computational analyses of microbehaviors in quiescent animals.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SleepMachine LearningDrosophilaDeep LearningDrosophila melanogasterAnimalsPhenotypeBehavior, Animal

Autor:innen und Institutionen

  • Department of Neurology, Johns Hopkins University, Baltimore, MD 21205, USA.
  • Department of Computer Science, Sabanci University, Tuzla, Istanbul 34956, Turkey.
  • Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI 53706, USA.
  • Department of Neuroscience, Johns Hopkins University, Baltimore, MD 21287, USA.

ORCID-Profile: Mehmet F Keleş, Ali Osman Berk Sapci, Isabelle Palmer, Christin Le, Mark N Wu

Förderung

  • NINDS NIH HHS
  • NHGRI NIH HHS

Zitieren

APA

Keleş, M. F., Sapci, A. O. B., Brody, C., Palmer, I., Mehta, A., Ahmadi, S., Le, C., Taştan, Ö., Keleş, S., & Wu, M. N. (2025). FlyVISTA, an integrated machine learning platform for deep phenotyping of sleep in Drosophila. Science Advances, 11(11). https://doi.org/10.1126/sciadv.adq8131

Vancouver

Keleş MF, Sapci AOB, Brody C, Palmer I, Mehta A, Ahmadi S, et al. FlyVISTA, an integrated machine learning platform for deep phenotyping of sleep in Drosophila. Science Advances. 2025;11(11). doi:10.1126/sciadv.adq8131

BibTeX
@article{Kele2025,
  author = {Keleş, Mehmet F and Sapci, Ali Osman Berk and Brody, Casey and Palmer, Isabelle and Mehta, Anuradha and Ahmadi, Shahin and Le, Christin and Taştan, Öznur and Keleş, Sündüz and Wu, Mark N},
  title = {FlyVISTA, an integrated machine learning platform for deep phenotyping of sleep in Drosophila},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {11},
  doi = {10.1126/sciadv.adq8131}
}
Kostenlos starten →