A University of Missouri entomologist, Robert Sites, discovered two previously unknown saucer bug species, Ctenipocoris sagittatus from Guyana and Venezuela and Ctenipocoris reticulatus from India, expanding scientific knowledge of global biodiversity. The findings highlight both the complexity of identifying these tiny aquatic insects and the vast amount of life that remains undiscovered in freshwater ecosystems around the world.

Researchers at Oak Ridge National Laboratory have developed SimuScan, an AI system that helps an atomic force microscope — a tool that maps surfaces at the scale of molecules — recognize meaningful features and decide where to look next. Trained on realistic, simulated images, it can reduce the need for expert manual control and make nanoscale imaging faster, more consistent, and better suited for automated, high-throughput research.

University of Missouri researchers have published a major review of flow matching, an emerging AI approach that helps scientists model how biological systems change over time, offering new opportunities in drug discovery, precision medicine and disease research. The work highlights how flow matching could ultimately help create AI-powered “virtual cells” that accelerate biomedical breakthroughs and improve understanding of living systems.

The Korea Research Institute of Standards and Science (KRISS, President Dr. Lee Ho Seong) has developed a deep learning technology that predicts, in real time, the vibrations at multiple locations inside a nuclear power plant using the signal from just a single seismometer, and that quantifies the risk at each location to enable the prioritization of inspections. In particular, because the AI model can be flexibly designed to match the vibration characteristics of a structure, it is expected to be widely applicable to major industrial facilities such as semiconductor plants and data centers in the future.

Venous thromboembolism (VTE), including deep vein thrombosis and pulmonary embolism, is a life-threatening complication in patients with cervical cancer that can significantly worsen survival and treatment outcomes. Although several clinical risk assessment tools are available, they primarily rely on laboratory measurements obtained at a single time point, limiting their ability to capture the evolving biological processes that precede thrombosis. While deep learning models have demonstrated strong predictive performance, their limited interpretability and high computational demands remain barriers to routine clinical implementation.