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

Obesity is a growing health concern, mainly caused by poor dietary habits. Yet, accurately tracking the diet and food intake of individuals with obesity is challenging. Although 3D motion capture technology is becoming increasingly important in healthcare, its potential for detecting early signs of obesity has not been fully explored. In this research, we used a deep LSTM network trained with individual identity (identity-trained deep LSTM network) to analyze 3D time-series skeleton data from mouse models with diet-induced obesity. First, we analyzed the data from two different viewpoints: allocentric and egocentric. Second, we trained various deep recurrent networks (e.g., RNN, GRU, LSTM) to predict the identity. Lastly, we tested whether these models effectively encode obese-like motion representations by training a support vector classifier with the latent features from the last layer. Our experimental results indicate that the optimal performance is achieved when utilizing an identity-trained deep LSTM network in conjunction with an egocentric viewpoint. This approach suggests a new way to use deep learning to spot health risks in mouse models of obesity and should be useful for detecting early signs of obesity in humans.

Hypothalamic GABRA5-positive neurons control obesity via astrocytic GABA.

The lateral hypothalamic area (LHA) regulates food intake and energy balance. Although LHA neurons innervate adipose tissues, the identity of neurons that regulate fat is undefined. Here we show that GABRA5-positive neurons in LHA (GABRA5LHA) polysynaptically project to brown and white adipose tissues in the periphery. GABRA5LHA are a distinct subpopulation of GABAergic neurons and show decreased pacemaker firing in diet-induced obesity mouse models in males. Chemogenetic inhibition of GABRA5LHA suppresses fat thermogenesis and increases weight gain, whereas gene silencing of GABRA5 in LHA decreases weight gain. In the diet-induced obesity mouse model, GABRA5LHA are tonically inhibited by nearby reactive astrocytes releasing GABA, which is synthesized by monoamine oxidase B (Maob). Gene silencing of astrocytic Maob in LHA facilitates fat thermogenesis and reduces weight gain significantly without affecting food intake, which is recapitulated by administration of a Maob inhibitor, KDS2010. We propose that firing of GABRA5LHA suppresses fat accumulation and selective inhibition of astrocytic GABA is a molecular target for treating obesity.