Fig. 4

Strong correspondence in relative performance of VEPs on the DMS vs clinical benchmarks. Average pairwise win rates in the DMS vs clinical benchmarks are plotted. Population-free and population-tuned VEPs show extremely strong correlations. In contrast, the clinical-trained VEPs show a much weaker correlation overall. The tendency for some clinical-trained VEPs to show large rightward shifts, reflecting relatively increased performance on the clinical benchmark, is likely to be due to circularity due to training on variants and genes present in the pathogenic and putatively benign datasets