Fig. 1
![Fig. 1](http://media.springernature.com/full/springer-static/image/art%3A10.1186%2Fs12859-016-1436-4/MediaObjects/12859_2016_1436_Fig1_HTML.gif)
Tolerance profile of HOXA5 shows regions of similarity between sequence-based prediction algorithms: SIFT and PROVEAN. However, subtle differences in tolerance can be observed when comparing these sequence-based algorithms with a structure-based algorithm, PolyPhen-2. Insight into potential regions of interest can be also obtained from genome-wide prediction algorithms such as FATHMM-MKL and CADD