Fig. 4

The contribution of reference methods to PRDIS specific predictors. In (a) we compare the performance of PRDIS specific methods, represented with violin plots with that of the reference methods (SIFT, PolyPhen-2, PON-P2, CADD and MutationTaster2), represented with black boxplots. We see that specific methods are frequently better than reference methods, but there is an increasing overlap between both approaches as the performance of the reference method grows (e.g. in the cases of PON-P2 or PolyPhen-2). b Performance depends on the number of reference predictors combined: the more we use, the more likely we are to obtain higher performances