Five talented early-career researchers at the Institute of Science and Technology Austria (ISTA) have secured a total of 9.2 million euros ($10.7 million) in highly selective Starting Grants from the European Research Council (ERC). With projects focused on AI, astrophysics, bacterial immune systems, quantum matter and optics, this major success underscores ISTA’s ability to attract exceptional young researchers and foster ambitious, curiosity-driven science.

A new study has used a type of machine learning called a neural network to reveal how different kinds of training can change how learning happens. As neural networks learn, they adopt patterns of activity that are strikingly similar to real-life neuron firing patterns. What’s more, the type of training affects both the activity pattern, and the ability to solve a task, in similar ways between neural networks and living brains.

Traditional MIC-based antibiotic susceptibility testing often misses sub-resistant bacteria, including persistent, tolerant, and heteroresistant populations, which may contribute to treatment failure and resistance evolution. Researchers at Huazhong University of Science and Technology have developed DP-AST, a deep learning-based microfluidic rapid phenotypic AST platform inspired by the Dujiangyan irrigation system. DP-AST measures MIC, bacterial growth activity, and concentration-effect curves to identify hidden sub-resistant bacteria. The study also identified gadE as a key regulator of amikacin sub-resistance in E. coli, offering new insights for resistance mechanism studies and future clinical diagnostics.Traditional MIC-based antibiotic susceptibility testing often misses sub-resistant bacteria, including persistent, tolerant, and heteroresistant populations, which may contribute to treatment failure and resistance evolution. Researchers at Huazhong University of Science and Technology have developed DP-AST, a deep learning-based microfluidic rapid phenotypic AST platform inspired by the Dujiangyan irrigation system. DP-AST measures MIC, bacterial growth activity, and concentration-effect curves to identify hidden sub-resistant bacteria. The study also identified gadE as a key regulator of amikacin sub-resistance in E. coli, offering new insights for resistance mechanism studies and future clinical diagnostics.Traditional MIC-based antibiotic susceptibility testing often misses sub-resistant bacteria, including persistent, tolerant, and heteroresistant populations, which may contribute to treatment failure and resistance evolution. Researchers at Huazhong University of Science and Technology have developed DP-AST, a deep learning-based microfluidic rapid phenotypic AST platform inspired by the Dujiangyan irrigation system. DP-AST measures MIC, bacterial growth activity, and concentration-effect curves to identify hidden sub-resistant bacteria. The study also identified gadE as a key regulator of amikacin sub-resistance in E. coli, offering new insights for resistance mechanism studies and future clinical diagnostics.

Researchers at Duke University built one of the first large-scale datasets of stablecoin transfers and used it to train machine-learning models that flag suspicious cryptocurrency wallets. Published in the Blockchain Journal, the study detects illicit activity with high accuracy and, importantly, tells apart different types of criminal behavior, helping compliance teams act on real threats while sparing innocent users from frozen assets.