SUBTLE: An unsupervised platform with temporal link embedding that maps animal behavior

Kwon, Jea; Kim, Sunpil; Kim, Dong-Kyum; Joo, Jinhyeong; Kim, SoHyung; Cha, Meeyoung; Lee, C. Justin

doi:10.1101/2023.04.12.536531

Cited by 3 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Key body points (marker positions) of mice were extracted by the AVATAR system as previously described 33, 52 . Briefly, mouse movement in an open-field chamber (transparent cuboid, 20 cm (w) × 20 cm (l) x 30 cm (h)) was recorded over a period of 10 minutes using five cameras positioned on four sides and one at the bottom, operating at a frequency of 20 Hz.…”

Section: Methodsmentioning

confidence: 99%

Cerebellar tonic inhibition orchestrates the maturation of information processing and motor coordination

Kwon,

Kim,

Woo

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Tonic inhibition in cerebellar granule cells (GC) is crucial in information coding fidelity for motor coordination. It emerges in activity-dependent and -independent manners, and their interplay evolves with age. However, specific molecular and cellular mechanisms and how their change affects network-level computation and motor behavior remain unclear. Here we show that, while net tonic inhibitory current remains unchanged, the main source of tonic GABA switches from synaptic spillover (neuronal activity-dependent) to astrocytic Best1 (activity-independent) throughout adolescence (4-8 weeks) in mice. Computational modeling based on experimental data demonstrated that this switch down-regulates the internally generated network activity mediating mutual inhibition between GC clusters receiving different inputs, thereby enhancing their independence. Consistent with simulations, 3D-posture analysis revealed an age-dependent increase in independent limb movements during spontaneous motion, which was impaired in Best1 knockout mice. Our findings highlight the late-stage development of complex motor coordination driven by the emergence of astrocyte-mediated tonic inhibition.

show abstract

Section: Methodsmentioning

confidence: 99%

Cerebellar tonic inhibition orchestrates the maturation of information processing and motor coordination

Kwon,

Kim,

Woo

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Predicting the risk of diet-induced obesity (DIO) through early behavioral pattern observation presents a promising avenue for healthcare systems. While 3D skeleton data provide detailed spatiotemporal information on dynamic movements, the complexity of data structure makes it challenging to extract meaningful insights, such as disease traits [ 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Egocentric 3D Skeleton Learning in a Deep Neural Network Encodes Obese-like Motion Representations

Kwon,

Sa,

Kim

et al. 2024

Exp Neurobiol

Self Cite

View full text Add to dashboard Cite

OpenLabCluster: Active Learning Based Clustering and Classification of Animal Behaviors in Videos Based on Automatically Extracted Kinematic Body Keypoints

Keselman

Shlizerman

2022

Preprint

View full text Add to dashboard Cite

Quantifying natural behavior from video recordings is a key component in ethological studies. Markerless pose estimation methods have provided an important step toward that goal by automatically inferring kinematic body keypoints. The next step in behavior quantification is utilization of these features toward organizing and interpreting behavioral segments into states. In this work, we introduce a novel deep learning toolset to address this aim. In particular, we introduce OpenLabCluster which clusters segments into groups according to the similarity of kinematic body keypoints and then employs active learning approach which refines the clusters and classifies them into behavioral states. The active learning approach is an iterative semi-supervised deep learning methodology selecting representative examples of segments to be annotated such that the annotation informs clustering and classification of all segments. With these methodologies, OpenLabCluster contributes to faster and more accurate organization of behavioral segments with only a sparse number of them being annotated. We demonstrate OpenLabCluster performance on four different datasets, which include different animal species exhibiting natural behaviors, and show that it boosts clustering and classification compared to existing methods, even when all segments have been annotated. OpenLabCluster has been developed as an open-source interactive graphic interface which includes all necessary functions to perform clustering and classification, informs the scientist of the outcomes in each step, and incorporates the choices made by the scientist in further steps.

show abstract

SUBTLE: An unsupervised platform with temporal link embedding that maps animal behavior

Cited by 3 publications

References 45 publications

Cerebellar tonic inhibition orchestrates the maturation of information processing and motor coordination

Cerebellar tonic inhibition orchestrates the maturation of information processing and motor coordination

Egocentric 3D Skeleton Learning in a Deep Neural Network Encodes Obese-like Motion Representations

OpenLabCluster: Active Learning Based Clustering and Classification of Animal Behaviors in Videos Based on Automatically Extracted Kinematic Body Keypoints

Contact Info

Product

Resources

About