Fig. 8From: An elastic-net logistic regression approach to generate classifiers and gene signatures for types of immune cells and T helper cell subsetsBenchmarking ROC performance curves. ROC curves to illustrate relative performance between logistic regression gene set and the manually curated (Panel a), CIBERSORT (Panel b), and single cell gene sets (Panel c). The logistic regression gene set’s performance is shown in red. Shaded regions are 95% confidence intervals about the average ROC curve simulated from 1000 iterationsBack to article page