ZebraZoom

An automated program for high-throughput behavioral analysis and categorization

Olivier Mirat, Jenna R. Sternberg, Kristen Severi, Claire Wyart

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

The zebrafish larva stands out as an emergent model organism for translational studies involving gene or drug screening thanks to its size, genetics, and permeability. At the larval stage, locomotion occurs in short episodes punctuated by periods of rest. Although phenotyping behavior is a key component of large-scale screens, it has not yet been automated in this model system. We developed ZebraZoom, a program to automatically track larvae and identify maneuvers for many animals performing discrete movements. Our program detects each episodic movement and extracts large-scale statistics on motor patterns to produce a quantification of the locomotor repertoire. We used ZebraZoom to identify motor defects induced by a glycinergic receptor antagonist. The analysis of the blind mutant atoh7 revealed small locomotor defects associated with the mutation. Using multiclass supervised machine learning, ZebraZoom categorized all episodes of movement for each larva into one of three possible maneuvers: slow forward swim, routine turn, and escape. ZebraZoom reached 91% accuracy for categorization of stereotypical maneuvers that four independent experimenters unanimously identified. For all maneuvers in the data set, ZebraZoom agreed with four experimenters in 73.2-82.5% of cases. We modeled the series of maneuvers performed by larvae as Markov chains and observed that larvae often repeated the same maneuvers within a group. When analyzing subsequent maneuvers performed by different larvae, we found that larva-larva interactions occurred as series of escapes. Overall, ZebraZoom reached the level of precision found in manual analysis but accomplished tasks in a high-throughput format necessary for large screens.

Original languageEnglish (US)
JournalFrontiers in neural circuits
Issue numberJUNE
DOIs
StatePublished - Jun 12 2013

Fingerprint

Larva
Markov Chains
Preclinical Drug Evaluations
Zebrafish
Locomotion
Permeability
Mutation
Genes

All Science Journal Classification (ASJC) codes

  • Sensory Systems
  • Cellular and Molecular Neuroscience
  • Cognitive Neuroscience
  • Neuroscience (miscellaneous)

Keywords

  • Analysis of kinematics
  • Collective behavior
  • Locomotion in intact behaving animals
  • Machine learning
  • Multiclass categorization
  • Support vector machine classifier
  • Tracking

Cite this

@article{f2cdd0d534544b2f9a7da75cf9158f7a,
title = "ZebraZoom: An automated program for high-throughput behavioral analysis and categorization",
abstract = "The zebrafish larva stands out as an emergent model organism for translational studies involving gene or drug screening thanks to its size, genetics, and permeability. At the larval stage, locomotion occurs in short episodes punctuated by periods of rest. Although phenotyping behavior is a key component of large-scale screens, it has not yet been automated in this model system. We developed ZebraZoom, a program to automatically track larvae and identify maneuvers for many animals performing discrete movements. Our program detects each episodic movement and extracts large-scale statistics on motor patterns to produce a quantification of the locomotor repertoire. We used ZebraZoom to identify motor defects induced by a glycinergic receptor antagonist. The analysis of the blind mutant atoh7 revealed small locomotor defects associated with the mutation. Using multiclass supervised machine learning, ZebraZoom categorized all episodes of movement for each larva into one of three possible maneuvers: slow forward swim, routine turn, and escape. ZebraZoom reached 91{\%} accuracy for categorization of stereotypical maneuvers that four independent experimenters unanimously identified. For all maneuvers in the data set, ZebraZoom agreed with four experimenters in 73.2-82.5{\%} of cases. We modeled the series of maneuvers performed by larvae as Markov chains and observed that larvae often repeated the same maneuvers within a group. When analyzing subsequent maneuvers performed by different larvae, we found that larva-larva interactions occurred as series of escapes. Overall, ZebraZoom reached the level of precision found in manual analysis but accomplished tasks in a high-throughput format necessary for large screens.",
keywords = "Analysis of kinematics, Collective behavior, Locomotion in intact behaving animals, Machine learning, Multiclass categorization, Support vector machine classifier, Tracking",
author = "Olivier Mirat and Sternberg, {Jenna R.} and Kristen Severi and Claire Wyart",
year = "2013",
month = "6",
day = "12",
doi = "https://doi.org/10.3389/fncir.2013.00107",
language = "English (US)",
journal = "Frontiers in Neural Circuits",
issn = "1662-5110",
publisher = "Frontiers Research Foundation",
number = "JUNE",

}

ZebraZoom : An automated program for high-throughput behavioral analysis and categorization. / Mirat, Olivier; Sternberg, Jenna R.; Severi, Kristen; Wyart, Claire.

In: Frontiers in neural circuits, No. JUNE, 12.06.2013.

Research output: Contribution to journalArticle

TY - JOUR

T1 - ZebraZoom

T2 - An automated program for high-throughput behavioral analysis and categorization

AU - Mirat, Olivier

AU - Sternberg, Jenna R.

AU - Severi, Kristen

AU - Wyart, Claire

PY - 2013/6/12

Y1 - 2013/6/12

N2 - The zebrafish larva stands out as an emergent model organism for translational studies involving gene or drug screening thanks to its size, genetics, and permeability. At the larval stage, locomotion occurs in short episodes punctuated by periods of rest. Although phenotyping behavior is a key component of large-scale screens, it has not yet been automated in this model system. We developed ZebraZoom, a program to automatically track larvae and identify maneuvers for many animals performing discrete movements. Our program detects each episodic movement and extracts large-scale statistics on motor patterns to produce a quantification of the locomotor repertoire. We used ZebraZoom to identify motor defects induced by a glycinergic receptor antagonist. The analysis of the blind mutant atoh7 revealed small locomotor defects associated with the mutation. Using multiclass supervised machine learning, ZebraZoom categorized all episodes of movement for each larva into one of three possible maneuvers: slow forward swim, routine turn, and escape. ZebraZoom reached 91% accuracy for categorization of stereotypical maneuvers that four independent experimenters unanimously identified. For all maneuvers in the data set, ZebraZoom agreed with four experimenters in 73.2-82.5% of cases. We modeled the series of maneuvers performed by larvae as Markov chains and observed that larvae often repeated the same maneuvers within a group. When analyzing subsequent maneuvers performed by different larvae, we found that larva-larva interactions occurred as series of escapes. Overall, ZebraZoom reached the level of precision found in manual analysis but accomplished tasks in a high-throughput format necessary for large screens.

AB - The zebrafish larva stands out as an emergent model organism for translational studies involving gene or drug screening thanks to its size, genetics, and permeability. At the larval stage, locomotion occurs in short episodes punctuated by periods of rest. Although phenotyping behavior is a key component of large-scale screens, it has not yet been automated in this model system. We developed ZebraZoom, a program to automatically track larvae and identify maneuvers for many animals performing discrete movements. Our program detects each episodic movement and extracts large-scale statistics on motor patterns to produce a quantification of the locomotor repertoire. We used ZebraZoom to identify motor defects induced by a glycinergic receptor antagonist. The analysis of the blind mutant atoh7 revealed small locomotor defects associated with the mutation. Using multiclass supervised machine learning, ZebraZoom categorized all episodes of movement for each larva into one of three possible maneuvers: slow forward swim, routine turn, and escape. ZebraZoom reached 91% accuracy for categorization of stereotypical maneuvers that four independent experimenters unanimously identified. For all maneuvers in the data set, ZebraZoom agreed with four experimenters in 73.2-82.5% of cases. We modeled the series of maneuvers performed by larvae as Markov chains and observed that larvae often repeated the same maneuvers within a group. When analyzing subsequent maneuvers performed by different larvae, we found that larva-larva interactions occurred as series of escapes. Overall, ZebraZoom reached the level of precision found in manual analysis but accomplished tasks in a high-throughput format necessary for large screens.

KW - Analysis of kinematics

KW - Collective behavior

KW - Locomotion in intact behaving animals

KW - Machine learning

KW - Multiclass categorization

KW - Support vector machine classifier

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=84879045548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879045548&partnerID=8YFLogxK

U2 - https://doi.org/10.3389/fncir.2013.00107

DO - https://doi.org/10.3389/fncir.2013.00107

M3 - Article

JO - Frontiers in Neural Circuits

JF - Frontiers in Neural Circuits

SN - 1662-5110

IS - JUNE

ER -