Skip to main content
. 2010 Sep 4;26(18):i482–i488. doi: 10.1093/bioinformatics/btq375

Fig. 1.

Fig. 1.

A scheme of the prediction procedure. A protein sequence is transformed into a vector of 545 features. The vector is independently sent to 10 boosted stump classifiers, each of which produces a numerical result. The mean and the standard deviation of the 10 results are reported.