This is an open access article under the terms of the Creat ive Commo ns Attri bution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
The actions of animals provide a window into how their minds work. Recent advances in deep learning are providing powerful approaches to recognize patterns of animal movement from video recordings, including markerless pose estimation models. However, tools to efficiently parse coordinates of animal position and pose into meaningful semantic behavioral labels are lacking. Here, we present PoseRecognition (PoseR), a behavioral decoder leveraging state-of-the-art action recognition models using spatio-temporal graph convolutional networks. We show that it can be used to decode animal behavior quickly and accurately from pose estimations, using zebrafish larvae and mice as model organisms. PoseR can be accessed using a Napari plugin, which facilitates efficient behavioral extraction, annotation, model training and deployment. We have simplified the workflow of behavioral analysis after pose estimation, transforming coordinates of animal position and pose into meaningful semantic behavioral labels, using methods designed for fast and accurate behavioral extraction, annotation, model training and deployment. Furthermore, we contribute a novel method for unsupervised clustering of behaviors and provide open-source access to our zebrafish datasets and models. The design of our tool ensures scalability and versatility for use across multiple species and contexts, improving the efficiency of behavioral analysis across fields.
Life-history-oxidative stress theory predicts that elevated energy costs during reproduction reduce allocation to defences and increase cellular stress, with fitness consequences, particularly when resources are limited. As capital breeders, grey seals are a natural system in which to test this theory. We investigated oxidative damage (malondialdehyde (MDA) concentration) and cellular defences (relative mRNA abundance of heat shock proteins (Hsps) and redox enzymes (REs)) in blubber of wild female grey seals during the lactation fast (n = 17) and summer foraging (n = 13). Transcript abundance of Hsc70 increased, and Nox4, a pro-oxidant enzyme, decreased throughout lactation. Foraging females had higher mRNA abundance of some Hsps and lower RE transcript abundance and MDA concentrations, suggesting they experienced lower oxidative stress than lactating mothers, which diverted resources into pup rearing at the expense of blubber tissue damage. Lactation duration and maternal mass loss rate were both positively related to pup weaning mass. Pups whose mothers had higher blubber glutathione-S-transferase (GST) expression at early lactation gained mass more slowly. Higher glutathione peroxidase (GPx) and lower catalase (CAT) were associated with longer lactation but reduced maternal transfer efficiency and lower pup weaning mass. Cellular stress, and the ability to mount effective cellular defences, could proscribe lactation strategy in grey seal mothers and thus affect pup survival probability. These data support the life-history-oxidative stress hypothesis in a capital breeding mammal and suggest lactation is a period of heightened vulnerability to environmental factors that exacerbate cellular stress. Fitness consequences of stress may thus be accentuated during periods of rapid environmental change.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.