Skip to main content
. 2021 Oct 18;11:20607. doi: 10.1038/s41598-021-99747-2

Figure 2.

Figure 2

Comparison of in silico strategies to prioritize 249 variants of uncertain significance with functional investigations performed. (a) Receiver operating characteristic area under the curve (AUC) comparisons for nine in silico prioritization strategies demonstrating that SpliceAI (AUC = 0.95, 95%CI 0.92–0.97) and a consensus approach (AUC = 0.94, 95% CI 0.91–0.97) outperform other strategies for prioritization; (b) AUC comparisons between SpliceAI, a consensus approach and a novel metric, demonstrates that a weighted approach slightly increases accuracy of prioritization over single approaches alone (AUC = 0.96, 95% CI 0.94–0.98); (c, d) Accuracy comparisons of each in silico prioritization approach across 2000 bootstraps utilizing region-specific pre-defined thresholds: (c) Violin plot demonstrating the calculated accuracy of each in silico prioritization approach; (d) frequency that each strategy is the best or joint-best performing.