The authors collected a total of 2,430 inbred lines derived from elite commercial hybrids and 503 inbred lines from natural populations. Such a panel holds a broadly sourced and genetically diverse inbred population. Combining resequencing technology, population genetics analysis, and deep learning algorithms, they conducted a genetic diversity analysis and predicted key breeding traits for 2,933 maize inbred lines. This work offers novel insights into maize genetic improvement and lays a foundation for intelligent breeding design.

An investigation published in National Science Review firstly presents comprehensive analysis for the spatiotemporal patterns and underlying drivers of compound low-solar-low-wind extremes over time across China. This research underscores the importance for nations engaging in progressive decarbonization to consider compound low-solar-low-wind extremes in renewable energy development and power sector planning, and proposes interregional renewable electricity transmission as a potential solution.

Researchers have developed a biomimetic artificial muscle that replicates the structure and mechanical properties of natural muscle tissue, offering a promising solution for volumetric muscle loss treatment. Published in National Science Review, the study highlights the material's superior biocompatibility, mechanical adaptability, and multifunctionality. The artificial muscle promotes myogenic differentiation, enhances angiogenesis, and demonstrates exceptional actuation performance, making it a viable candidate for applications in prosthetics and regenerative medicine. This innovation sets the stage for new directions in clinical treatments and advanced biomedical materials.

Artificial intelligence has the potential to improve the analysis of medical image data. For example, algorithms based on deep learning can determine the location and size of tumors. This is the result of AutoPET, an international competition in medical image analysis, where researchers of Karlsruhe Institute of Technology (KIT) were ranked fifth. The seven best autoPET teams report in the journal Nature Machine Intelligence on how algorithms can detect tumor lesions in positron emission tomography (PET) and computed tomography (CT). (DOI: 10.1038/s42256-024-00912-9)

Piezoelectric and triboelectric tactile sensors, crucial for applications in robotics and wearable devices, face challenges in flexibility and environmental resilience. In a new study, researchers have developed innovative manufacturing strategies to enhance sensor performance by optimizing material properties and fabrication techniques. These advancements are set to drive the creation of highly sensitive, self-powered sensors for next-generation technologies, enabling breakthroughs in healthcare, robotics, and human-machine interfaces.