In a paper published in National Science Review, a team of Chinese scientists developed an attention-based deep learning model, CGMformer, pretrained on a well-controlled and diverse corpus of continuous glucose monitoring (CGM) data to represent individual’s intrinsic metabolic state and enable clinical applications. It can accurately characterize individual dynamic glycemic behaviors such as maintenance of fasting blood glucose homeostasis and adaptation to postprandial hyperglycemia., It can assist in the diagnosis, disease duration assessment, and complication prediction of type 2 diabetes, subtype classification of non-diabetic populations, predict postprandial glucose responses accurately and provide personalized dietary recommendations for diabetes patients, thereby enabling lifestyle intervention recommendations.

A study documented the comprehensive responses of microbial community characteristics to degradation processes using field-based sampling, and soil microcosm experiments were conducted to simulate effects of global change on microorganisms and explore their relationships to ecosystem functioning across stages of alpine pioneer community degradation.

Recently, a research team led by Professor Zhi-Guo Zhang from Beijing University of Chemical Technology, in collaboration with Professor Ye Long from Tianjin University has published a breakthrough work in the field of flexible polymer solar cells on National Science Review. Their research has revealed the inherent trade-off of efficiency, stability and stretchability via acceptors materials structural regulation, providing critical insights for the bright future of flexible organic photovoltaics.

　Led by Assistant Prof. Kou Li, a research group in Chuo University, Japan, has developed an all-printable device fabrication strategy to resolve the existing technical limitations of multi-functional image sensor sheets for non-destructive inspections, with a recent paper publication in Small Science.