Action detection using a neural network elucidates the genetics of mouse grooming behavior
Automated detection of complex animal behaviors remains a challenging problem in neuroscience, particularly for behaviors that consist of disparate sequential motions. Grooming is a prototypical stereotyped behavior that is often used as an endophenotype in psychiatric genetics. Here, we used mouse...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2021-03-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/63207 |
| _version_ | 1818028330922803200 |
|---|---|
| author | Brian Q Geuther Asaf Peer Hao He Gautam Sabnis Vivek M Philip Vivek Kumar |
| author_facet | Brian Q Geuther Asaf Peer Hao He Gautam Sabnis Vivek M Philip Vivek Kumar |
| author_sort | Brian Q Geuther |
| collection | DOAJ |
| description | Automated detection of complex animal behaviors remains a challenging problem in neuroscience, particularly for behaviors that consist of disparate sequential motions. Grooming is a prototypical stereotyped behavior that is often used as an endophenotype in psychiatric genetics. Here, we used mouse grooming behavior as an example and developed a general purpose neural network architecture capable of dynamic action detection at human observer-level performance and operating across dozens of mouse strains with high visual diversity. We provide insights into the amount of human annotated training data that are needed to achieve such performance. We surveyed grooming behavior in the open field in 2457 mice across 62 strains, determined its heritable components, conducted GWAS to outline its genetic architecture, and performed PheWAS to link human psychiatric traits through shared underlying genetics. Our general machine learning solution that automatically classifies complex behaviors in large datasets will facilitate systematic studies of behavioral mechanisms. |
| first_indexed | 2024-12-10T05:02:05Z |
| format | Article |
| id | doaj.art-9cc87ec9b00c4f6ebd127333425c0a8c |
| institution | Directory Open Access Journal |
| issn | 2050-084X |
| language | English |
| last_indexed | 2024-12-10T05:02:05Z |
| publishDate | 2021-03-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj.art-9cc87ec9b00c4f6ebd127333425c0a8c2022-12-22T02:01:21ZengeLife Sciences Publications LtdeLife2050-084X2021-03-011010.7554/eLife.63207Action detection using a neural network elucidates the genetics of mouse grooming behaviorBrian Q Geuther0https://orcid.org/0000-0002-7822-486XAsaf Peer1https://orcid.org/0000-0002-7577-353XHao He2Gautam Sabnis3Vivek M Philip4Vivek Kumar5https://orcid.org/0000-0001-6643-7465The Jackson Laboratory, Bar Harbor, United StatesThe Jackson Laboratory, Bar Harbor, United StatesThe Jackson Laboratory, Bar Harbor, United StatesThe Jackson Laboratory, Bar Harbor, United StatesThe Jackson Laboratory, Bar Harbor, United StatesThe Jackson Laboratory, Bar Harbor, United StatesAutomated detection of complex animal behaviors remains a challenging problem in neuroscience, particularly for behaviors that consist of disparate sequential motions. Grooming is a prototypical stereotyped behavior that is often used as an endophenotype in psychiatric genetics. Here, we used mouse grooming behavior as an example and developed a general purpose neural network architecture capable of dynamic action detection at human observer-level performance and operating across dozens of mouse strains with high visual diversity. We provide insights into the amount of human annotated training data that are needed to achieve such performance. We surveyed grooming behavior in the open field in 2457 mice across 62 strains, determined its heritable components, conducted GWAS to outline its genetic architecture, and performed PheWAS to link human psychiatric traits through shared underlying genetics. Our general machine learning solution that automatically classifies complex behaviors in large datasets will facilitate systematic studies of behavioral mechanisms.https://elifesciences.org/articles/63207action detectionmachine learninggroomingneural networkGWAS |
| spellingShingle | Brian Q Geuther Asaf Peer Hao He Gautam Sabnis Vivek M Philip Vivek Kumar Action detection using a neural network elucidates the genetics of mouse grooming behavior eLife action detection machine learning grooming neural network GWAS |
| title | Action detection using a neural network elucidates the genetics of mouse grooming behavior |
| title_full | Action detection using a neural network elucidates the genetics of mouse grooming behavior |
| title_fullStr | Action detection using a neural network elucidates the genetics of mouse grooming behavior |
| title_full_unstemmed | Action detection using a neural network elucidates the genetics of mouse grooming behavior |
| title_short | Action detection using a neural network elucidates the genetics of mouse grooming behavior |
| title_sort | action detection using a neural network elucidates the genetics of mouse grooming behavior |
| topic | action detection machine learning grooming neural network GWAS |
| url | https://elifesciences.org/articles/63207 |
| work_keys_str_mv | AT brianqgeuther actiondetectionusinganeuralnetworkelucidatesthegeneticsofmousegroomingbehavior AT asafpeer actiondetectionusinganeuralnetworkelucidatesthegeneticsofmousegroomingbehavior AT haohe actiondetectionusinganeuralnetworkelucidatesthegeneticsofmousegroomingbehavior AT gautamsabnis actiondetectionusinganeuralnetworkelucidatesthegeneticsofmousegroomingbehavior AT vivekmphilip actiondetectionusinganeuralnetworkelucidatesthegeneticsofmousegroomingbehavior AT vivekkumar actiondetectionusinganeuralnetworkelucidatesthegeneticsofmousegroomingbehavior |