BehaviorDEPOT is a simple, flexible tool for automated behavioral detection based on markerless pose tracking
Quantitative descriptions of animal behavior are essential to study the neural substrates of cognitive and emotional processes. Analyses of naturalistic behaviors are often performed by hand or with expensive, inflexible commercial software. Recently, machine learning methods for markerless pose est...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2022-08-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/74314 |
| _version_ | 1811181275278475264 |
|---|---|
| author | Christopher J Gabriel Zachary Zeidler Benita Jin Changliang Guo Caitlin M Goodpaster Adrienne Q Kashay Anna Wu Molly Delaney Jovian Cheung Lauren E DiFazio Melissa J Sharpe Daniel Aharoni Scott A Wilke Laura A DeNardo |
| author_facet | Christopher J Gabriel Zachary Zeidler Benita Jin Changliang Guo Caitlin M Goodpaster Adrienne Q Kashay Anna Wu Molly Delaney Jovian Cheung Lauren E DiFazio Melissa J Sharpe Daniel Aharoni Scott A Wilke Laura A DeNardo |
| author_sort | Christopher J Gabriel |
| collection | DOAJ |
| description | Quantitative descriptions of animal behavior are essential to study the neural substrates of cognitive and emotional processes. Analyses of naturalistic behaviors are often performed by hand or with expensive, inflexible commercial software. Recently, machine learning methods for markerless pose estimation enabled automated tracking of freely moving animals, including in labs with limited coding expertise. However, classifying specific behaviors based on pose data requires additional computational analyses and remains a significant challenge for many groups. We developed BehaviorDEPOT (DEcoding behavior based on POsitional Tracking), a simple, flexible software program that can detect behavior from video timeseries and can analyze the results of experimental assays. BehaviorDEPOT calculates kinematic and postural statistics from keypoint tracking data and creates heuristics that reliably detect behaviors. It requires no programming experience and is applicable to a wide range of behaviors and experimental designs. We provide several hard-coded heuristics. Our freezing detection heuristic achieves above 90% accuracy in videos of mice and rats, including those wearing tethered head-mounts. BehaviorDEPOT also helps researchers develop their own heuristics and incorporate them into the software’s graphical interface. Behavioral data is stored framewise for easy alignment with neural data. We demonstrate the immediate utility and flexibility of BehaviorDEPOT using popular assays including fear conditioning, decision-making in a T-maze, open field, elevated plus maze, and novel object exploration. |
| first_indexed | 2024-04-11T09:14:42Z |
| format | Article |
| id | doaj.art-32813bdabc4e4f1b9dc0d73326bb57b4 |
| institution | Directory Open Access Journal |
| issn | 2050-084X |
| language | English |
| last_indexed | 2024-04-11T09:14:42Z |
| publishDate | 2022-08-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj.art-32813bdabc4e4f1b9dc0d73326bb57b42022-12-22T04:32:23ZengeLife Sciences Publications LtdeLife2050-084X2022-08-011110.7554/eLife.74314BehaviorDEPOT is a simple, flexible tool for automated behavioral detection based on markerless pose trackingChristopher J Gabriel0https://orcid.org/0000-0003-3193-2807Zachary Zeidler1https://orcid.org/0000-0001-6539-4360Benita Jin2https://orcid.org/0000-0002-2580-8618Changliang Guo3Caitlin M Goodpaster4https://orcid.org/0000-0002-2456-9010Adrienne Q Kashay5Anna Wu6Molly Delaney7https://orcid.org/0000-0002-4464-7282Jovian Cheung8Lauren E DiFazio9Melissa J Sharpe10https://orcid.org/0000-0002-5375-2076Daniel Aharoni11https://orcid.org/0000-0003-4931-8514Scott A Wilke12Laura A DeNardo13https://orcid.org/0000-0002-7607-4773Department of Physiology, University of California, Los Angeles, Los Angeles, United States; UCLA Neuroscience Interdepartmental Program, University of California, Los Angeles, Los Angeles, United StatesDepartment of Physiology, University of California, Los Angeles, Los Angeles, United StatesDepartment of Physiology, University of California, Los Angeles, Los Angeles, United States; UCLA Molecular, Cellular, and Integrative Physiology Program, University of California, Los Angeles, Los Angeles, United StatesDepartment of Neurology, University of California, Los Angeles, Los Angeles, United StatesUCLA Neuroscience Interdepartmental Program, University of California, Los Angeles, Los Angeles, United StatesDepartment of Psychiatry, University of California, Los Angeles, Los Angeles, United StatesDepartment of Physiology, University of California, Los Angeles, Los Angeles, United StatesDepartment of Psychiatry, University of California, Los Angeles, Los Angeles, United StatesDepartment of Psychiatry, University of California, Los Angeles, Los Angeles, United StatesDepartment of Psychology, University of California, Los Angeles, Los Angeles, United StatesDepartment of Psychology, University of California, Los Angeles, Los Angeles, United StatesDepartment of Neurology, University of California, Los Angeles, Los Angeles, United StatesDepartment of Psychiatry, University of California, Los Angeles, Los Angeles, United StatesDepartment of Physiology, University of California, Los Angeles, Los Angeles, United StatesQuantitative descriptions of animal behavior are essential to study the neural substrates of cognitive and emotional processes. Analyses of naturalistic behaviors are often performed by hand or with expensive, inflexible commercial software. Recently, machine learning methods for markerless pose estimation enabled automated tracking of freely moving animals, including in labs with limited coding expertise. However, classifying specific behaviors based on pose data requires additional computational analyses and remains a significant challenge for many groups. We developed BehaviorDEPOT (DEcoding behavior based on POsitional Tracking), a simple, flexible software program that can detect behavior from video timeseries and can analyze the results of experimental assays. BehaviorDEPOT calculates kinematic and postural statistics from keypoint tracking data and creates heuristics that reliably detect behaviors. It requires no programming experience and is applicable to a wide range of behaviors and experimental designs. We provide several hard-coded heuristics. Our freezing detection heuristic achieves above 90% accuracy in videos of mice and rats, including those wearing tethered head-mounts. BehaviorDEPOT also helps researchers develop their own heuristics and incorporate them into the software’s graphical interface. Behavioral data is stored framewise for easy alignment with neural data. We demonstrate the immediate utility and flexibility of BehaviorDEPOT using popular assays including fear conditioning, decision-making in a T-maze, open field, elevated plus maze, and novel object exploration.https://elifesciences.org/articles/74314automated behavioral analysisdeeplabcutopen-sourceminicamdecision-makingconditioned fear |
| spellingShingle | Christopher J Gabriel Zachary Zeidler Benita Jin Changliang Guo Caitlin M Goodpaster Adrienne Q Kashay Anna Wu Molly Delaney Jovian Cheung Lauren E DiFazio Melissa J Sharpe Daniel Aharoni Scott A Wilke Laura A DeNardo BehaviorDEPOT is a simple, flexible tool for automated behavioral detection based on markerless pose tracking eLife automated behavioral analysis deeplabcut open-source minicam decision-making conditioned fear |
| title | BehaviorDEPOT is a simple, flexible tool for automated behavioral detection based on markerless pose tracking |
| title_full | BehaviorDEPOT is a simple, flexible tool for automated behavioral detection based on markerless pose tracking |
| title_fullStr | BehaviorDEPOT is a simple, flexible tool for automated behavioral detection based on markerless pose tracking |
| title_full_unstemmed | BehaviorDEPOT is a simple, flexible tool for automated behavioral detection based on markerless pose tracking |
| title_short | BehaviorDEPOT is a simple, flexible tool for automated behavioral detection based on markerless pose tracking |
| title_sort | behaviordepot is a simple flexible tool for automated behavioral detection based on markerless pose tracking |
| topic | automated behavioral analysis deeplabcut open-source minicam decision-making conditioned fear |
| url | https://elifesciences.org/articles/74314 |
| work_keys_str_mv | AT christopherjgabriel behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT zacharyzeidler behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT benitajin behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT changliangguo behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT caitlinmgoodpaster behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT adrienneqkashay behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT annawu behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT mollydelaney behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT joviancheung behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT laurenedifazio behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT melissajsharpe behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT danielaharoni behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT scottawilke behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking AT lauraadenardo behaviordepotisasimpleflexibletoolforautomatedbehavioraldetectionbasedonmarkerlessposetracking |