Skip to main content

Table 6 Support estimation method performance on long-gap-length model conditions

From: Non-parametric and semi-parametric support estimation using SEquential RESampling random walks on biomolecular sequences

Model conditionPR-AUC (%)
GUIDANCE2SERES + GUIDANCE2Pairwise t-test corrected q-value
10.long.A92.3292.94\(9.7 \times 10^{-4}\)
10.long.B90.6291.64\(3.3 \times 10^{-6}\)
10.long.C85.1087.93\(9.7 \times 10^{-4}\)
10.long.D79.2286.18\(9.7 \times 10^{-4}\)
10.long.E67.6378.48\(9.7 \times 10^{-4}\)
Model conditionROC-AUC (%)
GUIDANCE2SERES + GUIDANCE2DeLong et al. test corrected q-value
10.long.A89.9990.99\(<10^{-10}\)
10.long.B91.8493.02\(<10^{-10}\)
10.long.C93.1494.59\(<10^{-10}\)
10.long.D93.8996.13\(<10^{-10}\)
10.long.E92.6294.38\(<10^{-10}\)
  1. The performance of GUIDANCE2 and SERES + GUIDANCE2 is compared across model conditions 10.long.A through 10.long.E (named in order of generally increasing sequence divergence). Aggregate PR-AUC and ROC-AUC are reported across all replicate datasets in a model condition (\(n=20\)), and the best AUC for each pairwise method comparison on a model condition is shown in italics. Statistical significance of PR-AUC or ROC-AUC differences was assessed using a one-tailed pairwise t-test or DeLong et al. [5] test, respectively, and multiple test correction was performed using the method of Benjamini and Hochberg [1]. Corrected q-values are reported (\(n=20\)) and all were significant (\(\alpha =0.05\))