Figure 5From: A machine learning strategy to identify candidate binding sites in human protein-coding sequenceSensitivity-specificity curves for Eponine-Exons model on independent sets of sequences. Specificity vs. sensitivity for the Eponine-Exons model on independent sets of intergenic, intron, and UTR exon sequences compared with random sequences of matching mono- and di-nucleotide composition. All curves are based on sets of 1000 sequences. In the case of intergenic sequences, standard-deviation error bars were calculated based on results from four independent sets of sequences.Back to article page