Skip to main content
Figure 5 | BMC Bioinformatics

Figure 5

From: OHMM: a Hidden Markov Model accurately predicting the occupancy of a transcription factor with a self-overlapping binding motif

Figure 5

ROC analysis shows that OHMM performs better than a weight matrix. The performances of the HMM and the weight matrix (WM) are represented by the green and the blue curves, respectively. Whereas the HMM and the WM perform similarly for strong sites, the HMM is more accurate in identifying weak sites. The positive examples consist of the 36 known human κB sites present in upstream 800 bp regions (in their native promoters), and the negative examples consist of all 10-mers in the upstream 800 bp regions in 100 randomly selected human genes as described in the text. Leave-one-out cross-validation was performed. ROC: Receiver Operating Characteristic curve.

Back to article page