Skip to main content
Figure 2 | BMC Bioinformatics

Figure 2

From: A novel ensemble learning method for de novo computational identification of DNA binding sites

Figure 2

Correlation between accuracy and Sig scores. Non-degenerate 6-mers from S. cerevisiae were scored according to Sig scores based on (a) Overrepresentation, (b) Overrepresentation-KS, (c) Coverage and (d) KS metrics of statistical significance. The 6-mers were randomly sampled from both the upstream regions and the known binding sites to ensure coverage or a wide range of accuracy. The x-axis plots the Bonferroni-corrected and log2 transformed Sig score for each metric. The red lines indicate the 95th Sig percentile.

Back to article page