Fig. 2

Signature classification performance. A Box-plots were generated for each signature’s AUCs as measured across the validation datasets for bacterial vs. non-bacterial and viral vs. non-viral classification. B Signature AUC distributions were compared against each other with the Wilcoxon rank-sum test, and p-values were plotted in a heatmap for bacterial classification (top) and viral classification (bottom). P-values were corrected for multiple comparisons with the Benjamini/Hochberg method. * indicates p-value ≤ 0.05. C Linear regression was applied to the relationship between the number of genes in a signature (log-transformed) and the signature’s median AUC across the validation datasets for bacterial classification (left) and viral classification (right)