Fig. 4
From: Extracting DNA words based on the sequence features: non-uniform distribution and integrity
![Fig. 4](http://media.springernature.com/full/springer-static/image/art%3A10.1186%2Fs12976-016-0028-3/MediaObjects/12976_2016_28_Fig4_HTML.gif)
Evaluation of function prediction based on DNA words. “se”, “sp”, “share” indicated sensitivity, specificity, and the predicted accuracy rate in the share group, respectively. The black bar indicated the predicted effect without the interaction, and the white bar indicated the predicted effect with the first-order interaction