Extended Data Fig. 3: Machine learning models to classify Enterobacteriaceae colonization status.
From: Ecological dynamics of Enterobacteriaceae in the human gut microbiome across global populations
a, Area Under the ROC Curve (AUROC) performance results of different machine learning methods, datasets and outcome variables (taxa) relating the gut microbiome composition with Enterobacteriaceae colonization status (n = 10 independent seeds per analysis). Box lengths represent the IQR of the data, the central line represents the median value, and the whiskers depict the lowest and highest values within 1.5 times the IQR of the first and third quartiles, respectively. b, ROC curve of the machine learning results linking the gut microbiome composition with Enterobacteriaceae status. AUROC values represent the median of gradient boosting models across 10 independent seeds, stratified by continent and only considering samples from healthy adults c, All-against-all performance results comparing models trained and tested using microbiome samples across different continents. All models were generated with the gradient boosting algorithm using samples from healthy adults only to classify Enterobacteriaceae colonization status.
