Lectures: Biomechanics, Action segmentation and Behavioral Clustering#
Today we will cover five diverse topics from biomechanics to multimodal behavioral analysis! Overall the lecures are 3h long, so please pick, You can come back later and watch the others.
Part 1: DeepLabCut in Applied Biomechanics (1 h)#
DLC in applied Biomechanics by Johanna Schultz
Key papers mentioned in this talk:
Using a biologically mimicking climbing robot to explore the performance landscape of climbing in lizards by Schultz JT, Beck HK, Haagensen T, Proost T, Clemente CJ. in Proc Biol Sci. 2021
Tail Base Deflection but not Tail Curvature Varies with Speed in Lizards: Results from an Automated Tracking Analysis Pipeline by Schultz JT, Cieri RL, Proost T, Pilai R, Hodgson M, Plum F, Clemente CJ. in Integr Comp Biol. 202
Further reading (goes beyond this course, but recommended):
Biomechanics of Movement: The Science of Sports, Robotics, and Rehabilitation by Thomas K. Uchida and Scott L. Delp
Linking biomechanics via neural networks to modeling proprioception: Task-driven neural network models predict neural dynamics of proprioception
Check out this cool Science paper on squirrel parkour, potentially inspired by this video from Youtuber Mark Rober
Part 2: Behavioral analysis with MoSeq (30 min)#
Talk on unsupervised behavior with keypoint MoSeq
Highly recommended reading 📚 (recommended in the scope of this course):
Weinreb et al. Keypoint-MoSeq: parsing behavior by linking point tracking to pose dynamics, bioRxiv 2023
Wiltschko et al. Mapping Sub-Second Structure in Mouse Behavior, Neuron 2015
Further reading (goes beyond this course, but recommended):
Datta, Anderson, Branson, Perona and Leifer Computational Neuroethology: A Call to Action, Neuron 2019
Markowitz et al. The Striatum Organizes 3D Behavior via Moment-to-Moment Action Selection, Cell 2018
Klibaite et al. Deep phenotyping reveals movement phenotypes in mouse neurodevelopmental models, Molecular Autism 2022
Hsu et al. B-SOiD, an open-source unsupervised algorithm for identification and fast prediction of behaviors, Nature Communications 2021
Luxem et al. Identifying behavioral structure from deep variational embeddings of animal motion, Communications Biology 2022
Part 3: Action segmentation (23 min)#
[Tutorial on DLC2Action and Action Segmentation by Elizaveta Kozlova (EPFL)https://www.youtube.com/watch?v=_bB3WjI8hyE)
Further reading 📚 (recommended in the scope of this course):
Anderson and Perona Toward a science of computational ethology, Neuron, 2014
Datta, Anderson, Branson, Perona and Leifer Computational Neuroethology: A Call to Action, Neuron 2019
Sturman et al Deep learning-based behavioral analysis reaches human accuracy and is capable of outperforming commercial solutions, Neuropsychopharmacology 2020
Further reading (goes beyond this course, but recommended):
Bohnslav, et al. DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels., eLife 2021
Nilsson et al. Simple Behavioral Analysis (SimBA)–an open source toolkit for computer classification of complex social behaviors in experimental animals, BioRxiv 2020
Segalin et al. The Mouse Action Recognition System (MARS) software pipeline for automated analysis of social behaviors in mice, eLife 2021
Kabra et al. JAABA: interactive machine learning for automatic annotation of animal behavior, Nature methods 2013
Branson et al. High-throughput ethomics in large groups of Drosophila Nature methods 2009
Part 4: Joint behavioral and neural modeling (45 min + Q & A)#
Cosyne keynote talk by Dr. Mackenzie Mathis (EPFL)
Further reading 📚 (recommended in the scope of this course):
Schneider*, Lee*, Mathis Learnable latent embeddings for joint behavioural and neural analysis, Nature, 20223
Website: https://cebra.ai
Part 5: Behavior, or what the brain does (33 min)#
Talk by Dr. Nacho Sanguinetti (Harvard University)
