Table 2 The area under the curve (AUC) for the GWAS Catalogue comparisons, holding data and classifier constant, while varying algorithm and annotations.

From: Smoking Gun or Circumstantial Evidence? Comparison of Statistical Learning Methods using Functional Annotations for Prioritizing Risk Variants

Annotations →

Gagliano et al.

Ritchie et al.

Kircher et al.

Elastic Net

0.67 [0.65–0.68] (0.67)

0.65 [0.63–0.66] (0.67)

0.71 [0.69–0.73] (0.74)

Random Forest (altered minimum node size)

0.67 [0.65–0.68] (0.69)

0.68 [0.66–0.69] (0.72)

0.70 [0.68–0.72] (0.79)

Support Vector Machine (with prior feature selection)

0.66 [0.65–0.68] (0.66)

0.64 [0.63–0.66] (0.66)

0.64 [0.61–0.66] (0.68)

  1. The 95% confidence interval based on 2000 bootstrap replicates (generated using the R package pROC) is shown in square brackets. The AUC in the training set is in parentheses.
Back to article page