Fig. 3
From: On the evaluation of the fidelity of supervised classifiers in the prediction of chimeric RNAs
Box-plots of the selected features to discriminate chRNAs (TRUE and FALSE) at the read level. From left to right (score_break_length, score_break_variance, coefficient_variation, score_is_duplicate, mean_amplitude, score_nb_merge, coefficient_dispersion_interquartile). Best discrimination results are obtaining with the features score_is_duplicate, coefficient_variation, and score_break_length