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.

GolpHCat (TMEM87A), a unique voltage-dependent cation channel in Golgi apparatus, contributes to Golgi-pH maintenance and hippocampus-dependent memory.

Impaired ion channels regulating Golgi pH lead to structural alterations in the Golgi apparatus, such as fragmentation, which is found, along with cognitive impairment, in Alzheimer's disease. However, the causal relationship between altered Golgi structure and cognitive impairment remains elusive due to the lack of understanding of ion channels in the Golgi apparatus of brain cells. Here, we identify that a transmembrane protein TMEM87A, renamed Golgi-pH-regulating cation channel (GolpHCat), expressed in astrocytes and neurons that contributes to hippocampus-dependent memory. We find that GolpHCat displays unique voltage-dependent currents, which is potently inhibited by gluconate. Additionally, we gain structural insights into the ion conduction through GolpHCat at the molecular level by determining three high-resolution cryogenic-electron microscopy structures of human GolpHCat. GolpHCat-knockout mice show fragmented Golgi morphology and altered protein glycosylation and functions in the hippocampus, leading to impaired spatial memory. These findings suggest a molecular target for Golgi-related diseases and cognitive impairment.