Fig. 2
From: On the evaluation of the fidelity of supervised classifiers in the prediction of chimeric RNAs
Overall performance of several chRNA classifiers at the read level. Progressive sampling using five genomes along chRNA mutation profiles, from “r1” to “r5”. Training were performed with a 10-fold cross validation scheme along with a tuning grid to each ML technique. Additionally, we repeated each run three times (e.g., rX1, rX2, and rX3) to check models stability. Thus, having a total of 15 performance points. Models’ performance were average to each run (r1 to r5). The chRNA’s classes distribution along reads (a). Performance metrics of ACC (b), Kappa (c), and AUC (d) highlight the robustness of ensemble models. Classification performance using another independent genome (e)