Machine learning methods have emerged as promising tools to predict antimicrobial resistance (AMR) and uncover resistance determinants from genomic data. This study shows that sampling biases driven by population structure severely undermine the accuracy of AMR prediction models even with large datasets, providing recommendations for evaluating the accuracy of future methods.

Some biodegradable tableware is made with wheat straw or bran, ingredients that may contain gluten. Researchers tested commercially available biodegradable items, reporting the initial results in ACS’ Journal of Agricultural and Food Chemistry. One plate contained gluten and transferred the allergen into some foods and drinks at levels above gluten-free thresholds. The researchers say that because these products don’t require allergen labels, they could pose a health risk for people who need to avoid gluten.