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 and 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 2,457 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.
Data availability
The all machine learning datasets are available here: https://www.kumarlab.org/2021/03/11/grooming-behavioral-data/ The code is available here: https://github.com/KumarLabJax/MouseGrooming Behavioral data has been deposited into Mouse Phenome Database. The access for this data will be https://mpdpreview.jax.org/projects/Project1051
Article and author information
Author details
Funding
Jackson Laboratory Director's Innovation Fund
- Vivek Kumar
National Institutes of Health (DA041668)
- Vivek Kumar
National Institutes of Health (DA048634)
- Vivek Kumar
National Science Foundation (TG-DBS170004)
- Vivek Kumar
Brain and Behavioral Foundation
- Vivek Kumar
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Reviewing Editor
- Bianca Jones Marlin, Columbia University, United States
Ethics
Animal experimentation: All studies were performed in accordance with approved protocols from The Jackson Laboratory Institutional Animal Care and Use Committee guidelines (Animal Protocol Number 14010).
Version history
- Received: September 17, 2020
- Accepted: March 5, 2021
- Accepted Manuscript published: March 17, 2021 (version 1)
- Version of Record published: April 13, 2021 (version 2)
Copyright
© 2021, Geuther et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 3,996
- views
-
- 483
- downloads
-
- 31
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Further reading
-
- Computational and Systems Biology
- Genetics and Genomics
We propose a new framework for human genetic association studies: at each locus, a deep learning model (in this study, Sei) is used to calculate the functional genomic activity score for two haplotypes per individual. This score, defined as the Haplotype Function Score (HFS), replaces the original genotype in association studies. Applying the HFS framework to 14 complex traits in the UK Biobank, we identified 3619 independent HFS–trait associations with a significance of p < 5 × 10−8. Fine-mapping revealed 2699 causal associations, corresponding to a median increase of 63 causal findings per trait compared with single-nucleotide polymorphism (SNP)-based analysis. HFS-based enrichment analysis uncovered 727 pathway–trait associations and 153 tissue–trait associations with strong biological interpretability, including ‘circadian pathway-chronotype’ and ‘arachidonic acid-intelligence’. Lastly, we applied least absolute shrinkage and selection operator (LASSO) regression to integrate HFS prediction score with SNP-based polygenic risk scores, which showed an improvement of 16.1–39.8% in cross-ancestry polygenic prediction. We concluded that HFS is a promising strategy for understanding the genetic basis of human complex traits.
-
- Computational and Systems Biology
Revealing protein binding sites with other molecules, such as nucleic acids, peptides, or small ligands, sheds light on disease mechanism elucidation and novel drug design. With the explosive growth of proteins in sequence databases, how to accurately and efficiently identify these binding sites from sequences becomes essential. However, current methods mostly rely on expensive multiple sequence alignments or experimental protein structures, limiting their genome-scale applications. Besides, these methods haven’t fully explored the geometry of the protein structures. Here, we propose GPSite, a multi-task network for simultaneously predicting binding residues of DNA, RNA, peptide, protein, ATP, HEM, and metal ions on proteins. GPSite was trained on informative sequence embeddings and predicted structures from protein language models, while comprehensively extracting residual and relational geometric contexts in an end-to-end manner. Experiments demonstrate that GPSite substantially surpasses state-of-the-art sequence-based and structure-based approaches on various benchmark datasets, even when the structures are not well-predicted. The low computational cost of GPSite enables rapid genome-scale binding residue annotations for over 568,000 sequences, providing opportunities to unveil unexplored associations of binding sites with molecular functions, biological processes, and genetic variants. The GPSite webserver and annotation database can be freely accessed at https://bio-web1.nscc-gz.cn/app/GPSite.