Skip to main content

Table 8 Empirical study results

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

DatasetPR-AUC (%)ROC-AUC (%)
GUIDANCE1SERES + GUIDANCE1GUIDANCE1SERES + GUIDANCE1
IGIA62.6769.2889.5091.62
IGIB73.6087.4794.4997.39
IGIC272.6775.3682.2583.87
IGID63.7476.3095.1096.73
IGIE93.5695.4290.0893.30
IGIIA73.0383.0686.4996.45
PA2398.5499.4182.5993.63
PE2398.4499.2794.7597.41
PM2397.5398.4894.2096.44
SA1699.7299.8691.0795.57
SA2398.3599.2481.7692.18
DatasetPR-AUC (%)ROC-AUC (%)
GUIDANCE2SERES + GUIDANCE2GUIDANCE2SERES + GUIDANCE2
IGIA67.468.4991.3891.94
IGIB80.6686.7296.4797.38
IGIC274.4473.2784.6382.51
IGID75.1578.3896.4497.09
IGIE94.695.4491.8493.49
IGIIA78.1685.0994.5096.82
PA2399.2499.5391.4894.88
PE2399.0799.3496.7297.63
PM2398.6898.8596.9397.28
SA1699.8899.9196.2297.22
SA2399.0499.3389.9393.18
  1. The empirical study made use of benchmark RNA datasets and curated reference alignments from the CRW database [3]. Results are shown for intronic (“IG” prefix) and non-intronic datasets (“P” prefix and “S” prefix, following “primary” and “seed” nomenclature from the CRW database). For each dataset, we report each method’s PR-AUC and ROC-AUC. For each dataset and pairwise method comparison, the best AUC is shown in italics. Methods, performance measures, table layout, and table description are otherwise identical to Table 5