Shiga University

Understanding the latent disease patterns embedded in electronic health records (EHRs) is crucial for making precise and proactive healthcare decisions. Federated graph learning-based methods are commonly employed to extract complex disease patterns from the distributed EHRs without sharing the client-side raw data. However, the intrinsic characteristics of the distributed EHRs are typically non-independent and identically distributed (Non-IID), significantly bringing challenges related to data imbalance and leading to a notable decrease in the effectiveness of making healthcare decisions derived from the global model. To address these challenges, we introduce a novel personalized federated learning framework named PEARL, which is designed for disease prediction on Non-IID EHRs. Specifically, PEARL incorporates disease diagnostic code attention and admission record attention to extract patient embeddings from all EHRs. Then, PEARL integrates self-supervised learning into a federated learning framework to train a global model for hierarchical disease prediction. To improve the performance of the client model, we further introduce a fine-tuning scheme to personalize the global model using local EHRs. During the global model updating process, a differential privacy (DP) scheme is implemented, providing a high-level privacy guarantee. Extensive experiments conducted on the real-world MIMIC-III dataset validate the effectiveness of PEARL, demonstrating competitive results when compared with baselines.

Plants sense and respond to environmental cues during 24 h fluctuations in their environment. This requires the integration of internal cues such as circadian timing with environmental cues such as light and temperature to elicit cellular responses through signal transduction. However, the integration and transduction of circadian and environmental signals by plants growing in natural environments remains poorly understood. To gain insights into 24 h dynamics of environmental signaling in nature, we performed a field study of signal transduction from the nucleus to chloroplasts in a natural population of Arabidopsis halleri. Using several modeling approaches to interpret the data, we identified that the circadian clock and temperature are key regulators of this pathway under natural conditions. We identified potential time-delay steps between pathway components, and diel fluctuations in the response of the pathway to temperature cues that are reminiscent of the process of circadian gating. We found that our modeling framework can be extended to other signaling pathways that undergo diel oscillations and respond to environmental cues. This approach of combining studies of gene expression in the field with modeling allowed us to identify the dynamic integration and transduction of environmental cues, in plant cells, under naturally fluctuating diel cycles.

Chloroplasts accumulate in regions of plant cells exposed to irradiation to maximize light reception for efficient photosynthesis. This response is mediated by the blue‐light receptor phototropin. Upon the perception of blue light, phototropin is photoactivated, an unknown signal is transmitted from the photoactivated phototropin to distant chloroplasts, and the chloroplasts begin their directional movement. How activated phototropin initiates this signal transmission is unknown. Here, using the liverwort Marchantia polymorpha, we analysed whether increased photoactive phototropin levels mediate signal transmission and chloroplast behaviour during the accumulation response. The signal transmission rate was higher in transgenic cells overexpressing phototropin than in wild‐type cells. However, the chloroplast directional movement was similar between wild‐type and transgenic cells. Consistent with the observation, increasing the amount of photoactivated phototropin through higher blue‐light intensity also accelerated signal transmission but did not affect chloroplast behaviour in wild‐type cells. Photoactivation of phototropin under weak blue‐light led to the greater protein level of phosphorylated phototropin in cells overexpressing phototropin than in wild‐type cells, whereas the autophosphorylation level within each phototropin molecule was similar. These results indicate that the abundance of photoactivated phototropin modulates the signal transmission rate to distant chloroplasts but does not affect chloroplast behaviour during the accumulation response.