Dataset Information

Action detection using a neural network elucidates the genetics of mouse grooming behavior.

ABSTRACT: 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.

SUBMITTER: Geuther BQ

PROVIDER: S-EPMC8043749 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Action detection using a neural network elucidates the genetics of mouse grooming behavior.

Geuther Brian Q BQ Peer Asaf A He Hao H Sabnis Gautam G Philip Vivek M VM Kumar Vivek V

eLife 20210317

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 ...[more]

PMID: 33729153

Similar Datasets

Project description:BackgroundDealing with the high dimension of both neuroimaging data and genetic data is a difficult problem in the association of genetic data to neuroimaging. In this article, we tackle the latter problem with an eye toward developing solutions that are relevant for disease prediction. Supported by a vast literature on the predictive power of neural networks, our proposed solution uses neural networks to extract from neuroimaging data features that are relevant for predicting Alzheimer's Disease (AD) for subsequent relation to genetics. The neuroimaging-genetic pipeline we propose is comprised of image processing, neuroimaging feature extraction and genetic association steps. We present a neural network classifier for extracting neuroimaging features that are related with the disease. The proposed method is data-driven and requires no expert advice or a priori selection of regions of interest. We further propose a multivariate regression with priors specified in the Bayesian framework that allows for group sparsity at multiple levels including SNPs and genes.ResultsWe find the features extracted with our proposed method are better predictors of AD than features used previously in the literature suggesting that single nucleotide polymorphisms (SNPs) related to the features extracted by our proposed method are also more relevant for AD. Our neuroimaging-genetic pipeline lead to the identification of some overlapping and more importantly some different SNPs when compared to those identified with previously used features.ConclusionsThe pipeline we propose combines machine learning and statistical methods to benefit from the strong predictive performance of blackbox models to extract relevant features while preserving the interpretation provided by Bayesian models for genetic association. Finally, we argue in favour of using automatic feature extraction, such as the method we propose, in addition to ROI or voxelwise analysis to find potentially novel disease-relevant SNPs that may not be detected when using ROIs or voxels alone.

Project description:Stereotypic and/or repetitive behavior is one of the major symptoms of autism spectrum disorder (ASD). Increase of self-grooming behavior is a behavioral phenotype commonly observed in the mouse models for ASD. Previously, we have shown that knockout of acid-sensing ion channel 3 (ASIC3) led to the increased self-grooming behavior in resident-intruder test. Given the facts that ASIC3 is mainly expressed in the peripheral dorsal root ganglion (DRG) and conditional knockout of ASIC3 in the proprioceptors induced proprioception deficits. We speculate a hypothesis that stereotypic phenotype related to ASD, pararalled with striatal dysfunction, might be caused by proprioception defect in the peripheral sensory neuron origin. Herein, we investigate in depth whether and how ASIC3 is involved in the regulation of self-grooming behavior. First, we observed that Asic3 null mutant mice exhibited increased self-grooming in social interaction during juvenile stage. Similarly, they displayed increased self-grooming behavior in a novel cage in the absence of cagemate. To further understand the mechanism by which ASIC3 affects grooming behavior, we analyzed neurochemical, neuropathological and electrophysiological features in the dorsal striatum of Asic3 null mutant mice. Knockout of Asic3 increased dopamine (DA) activity and phospho-ERK immunoreactivities in the dorsal striatum. Furthermore, we detected a lower paired-pulse ratio (PPR) and impaired long-term potentiation (LTP) in corticostriatal circuits in Asic3 null mutant mice as compared with wild-type (WT) littermates. Moreover, knockout of Asic3 altered the medial spiny neurons in the striatum with defects in presynaptic function and decrease of dendritic spines. Lastly, genetic ablation of Asic3 specifically in parvalbumin-positive (PV+) cells resulted in the increase of self-grooming behavior in mice. These findings suggest knockout of Asic3 in the PV+ neurons alters grooming behavior by co-opting corticostriatal circuits.

Dataset Information

Action detection using a neural network elucidates the genetics of mouse grooming behavior.

Publications

Action detection using a neural network elucidates the genetics of mouse grooming behavior.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets