Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: Promoter prediction and annotation of microbial genomes based on DNA sequence and structural responses to superhelical stress

Figure 4

(A) The sensitivity (true positive rate) and specificity (1 – false positive rate) achieved in classifying 1000 E. coli K12 sequences into promoters and non-promoters, based on their sum of G(x) parameters. The graph shows how the sensitivity and specificity depend on the threshold for regarding a sequence as a promoter. Of the 1000 sequences analyzed here, half are promoters and half are not. (B) ROC curves comparing the performance of SIDD vs NNPP at identifying promoters in E. coli K12. (C) The performance of our SIDD-based promoter discriminator is comparable for sequences in E. coli K12 and in Bacillus subtilis.

Back to article page