Machine Learning in Modeling of Mouse Behavior
Mouse behavior is a primary outcome in evaluations of therapeutic efficacy. Exhaustive, continuous, multiparametric behavioral phenotyping is a valuable tool for understanding the pathophysiological status of mouse brain diseases. Automated home cage behavior analysis produces highly granulated data...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-09-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2021.700253/full |
| _version_ | 1819129479042170880 |
|---|---|
| author | Marjan Gharagozloo Abdelaziz Amrani Kevin Wittingstall Andrew Hamilton-Wright Denis Gris |
| author_facet | Marjan Gharagozloo Abdelaziz Amrani Kevin Wittingstall Andrew Hamilton-Wright Denis Gris |
| author_sort | Marjan Gharagozloo |
| collection | DOAJ |
| description | Mouse behavior is a primary outcome in evaluations of therapeutic efficacy. Exhaustive, continuous, multiparametric behavioral phenotyping is a valuable tool for understanding the pathophysiological status of mouse brain diseases. Automated home cage behavior analysis produces highly granulated data both in terms of number of features and sampling frequency. Previously, we demonstrated several ways to reduce feature dimensionality. In this study, we propose novel approaches for analyzing 33-Hz data generated by CleverSys software. We hypothesized that behavioral patterns within short time windows are reflective of physiological state, and that computer modeling of mouse behavioral routines can serve as a predictive tool in classification tasks. To remove bias due to researcher decisions, our data flow is indifferent to the quality, value, and importance of any given feature in isolation. To classify day and night behavior, as an example application, we developed a data preprocessing flow and utilized logistic regression (LG), support vector machines (SVM), random forest (RF), and one-dimensional convolutional neural networks paired with long short-term memory deep neural networks (1DConvBiLSTM). We determined that a 5-min video clip is sufficient to classify mouse behavior with high accuracy. LG, SVM, and RF performed similarly, predicting mouse behavior with 85% accuracy, and combining the three algorithms in an ensemble procedure increased accuracy to 90%. The best performance was achieved by combining the 1DConv and BiLSTM algorithms yielding 96% accuracy. Our findings demonstrate that computer modeling of the home-cage ethome can clearly define mouse physiological state. Furthermore, we showed that continuous behavioral data can be analyzed using approaches similar to natural language processing. These data provide proof of concept for future research in diagnostics of complex pathophysiological changes that are accompanied by changes in behavioral profile. |
| first_indexed | 2024-12-22T08:44:22Z |
| format | Article |
| id | doaj.art-e608316189d840fb982b044e8331f4a1 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-22T08:44:22Z |
| publishDate | 2021-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-e608316189d840fb982b044e8331f4a12022-12-21T18:32:09ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2021-09-011510.3389/fnins.2021.700253700253Machine Learning in Modeling of Mouse BehaviorMarjan Gharagozloo0Abdelaziz Amrani1Kevin Wittingstall2Andrew Hamilton-Wright3Denis Gris4Department of Neurology, Johns Hopkins University, Baltimore, MD, United StatesDepartment of Pediatrics, Faculty of Medicine, Université de Sherbrooke, Sherbrooke, QC, CanadaDepartment of Radiology, Sherbrooke Molecular Imaging Center, Université de Sherbrooke, Sherbrooke, QC, CanadaSchool of Computer Science, University of Guelph, Guelph, ON, CanadaDepartment of Pharmacology and Physiology, Faculty of Medicine, Université de Sherbrooke, Sherbrooke, QC, CanadaMouse behavior is a primary outcome in evaluations of therapeutic efficacy. Exhaustive, continuous, multiparametric behavioral phenotyping is a valuable tool for understanding the pathophysiological status of mouse brain diseases. Automated home cage behavior analysis produces highly granulated data both in terms of number of features and sampling frequency. Previously, we demonstrated several ways to reduce feature dimensionality. In this study, we propose novel approaches for analyzing 33-Hz data generated by CleverSys software. We hypothesized that behavioral patterns within short time windows are reflective of physiological state, and that computer modeling of mouse behavioral routines can serve as a predictive tool in classification tasks. To remove bias due to researcher decisions, our data flow is indifferent to the quality, value, and importance of any given feature in isolation. To classify day and night behavior, as an example application, we developed a data preprocessing flow and utilized logistic regression (LG), support vector machines (SVM), random forest (RF), and one-dimensional convolutional neural networks paired with long short-term memory deep neural networks (1DConvBiLSTM). We determined that a 5-min video clip is sufficient to classify mouse behavior with high accuracy. LG, SVM, and RF performed similarly, predicting mouse behavior with 85% accuracy, and combining the three algorithms in an ensemble procedure increased accuracy to 90%. The best performance was achieved by combining the 1DConv and BiLSTM algorithms yielding 96% accuracy. Our findings demonstrate that computer modeling of the home-cage ethome can clearly define mouse physiological state. Furthermore, we showed that continuous behavioral data can be analyzed using approaches similar to natural language processing. These data provide proof of concept for future research in diagnostics of complex pathophysiological changes that are accompanied by changes in behavioral profile.https://www.frontiersin.org/articles/10.3389/fnins.2021.700253/fullmachine learningbehaviorhome-cage ethomecomputer modelingcircadian rythm |
| spellingShingle | Marjan Gharagozloo Abdelaziz Amrani Kevin Wittingstall Andrew Hamilton-Wright Denis Gris Machine Learning in Modeling of Mouse Behavior Frontiers in Neuroscience machine learning behavior home-cage ethome computer modeling circadian rythm |
| title | Machine Learning in Modeling of Mouse Behavior |
| title_full | Machine Learning in Modeling of Mouse Behavior |
| title_fullStr | Machine Learning in Modeling of Mouse Behavior |
| title_full_unstemmed | Machine Learning in Modeling of Mouse Behavior |
| title_short | Machine Learning in Modeling of Mouse Behavior |
| title_sort | machine learning in modeling of mouse behavior |
| topic | machine learning behavior home-cage ethome computer modeling circadian rythm |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2021.700253/full |
| work_keys_str_mv | AT marjangharagozloo machinelearninginmodelingofmousebehavior AT abdelazizamrani machinelearninginmodelingofmousebehavior AT kevinwittingstall machinelearninginmodelingofmousebehavior AT andrewhamiltonwright machinelearninginmodelingofmousebehavior AT denisgris machinelearninginmodelingofmousebehavior |