Skip to main content

Table 1 Overview of prioritization results.

From: Candidate gene prioritization by network analysis of differential expression using machine learning approaches

    STRING v. 7.1 STRING v. 8.2
    top 10 top 20 AUC top 10 top 20 AUC
  Standard genetic procedure: Simple Expression Ranking 20 25 0.801 20 25 0.801
  Direct Neighborhood Ranking log2 ratio 27 31 0.859 12 23 0.747
  ε >0.15, a = 0.5 sign. log2 ratio 28 31 0.880 12 24 0.760
   test statistic 29 30 0.856 13 22 0.738
  Kernel Ridge Regression Ranking log2 ratio 23 29 0.809 14 26 0.759
  λ = 1, nn = 50, K LED , α = 0.5 sign. log2 ratio 27 32 0.868 17 25 0.817
RRMA   test statistic 20 26 0.771 15 20 0.691
  Heat Kernel Diffusion Ranking log2 ratio 32 34 0.900 32 33 0.913
  all expression values for p0 , m = 2, α = 0.5 sign. log2 ratio 31 34 0.910 31 35 0.923
   test statistic 32 34 0.901 32 34 0.911
  Arnoldi Diffusion Ranking log2 ratio 27 31 0.857 27 29 0.851
  m = 2, α = 0.5 sign. log2 ratio 28 31 0.885 28 31 0.873
   test statistic 28 30 0.855 28 29 0.844
  Standard genetic procedure: Simple Expression Ranking 18 24 0.777 18 24 0.777
  Direct Neighborhood Ranking log2 ratio 27 31 0.874 12 23 0.761
  ε >0.15, a = 0.5 sign. log2 ratio 25 28 0.855 11 22 0.736
   test statistic 27 31 0.863 12 24 0.750
  Kernel Ridge Regression Ranking log2 ratio 21 28 0.769 17 24 0.756
  λ = 1, nn = 50, K LED , α = 0.5 sign. log2 ratio 27 31 0.835 20 26 0.796
GCRMA   test statistic 19 22 0.745 16 23 0.744
  Heat Kernel Diffusion Ranking log2 ratio 31 33 0.905 32 34 0.914
  all expression values for p0 , m = 2, α = 0.5 sign. log2 ratio 28 33 0.889 29 34 0.907
   test statistic 32 33 0.895 32 35 0.913
  Arnoldi Diffusion Ranking log2 ratio 27 32 0.875 26 31 0.874
  m = 2, α = 0.5 sign. log2 ratio 25 29 0.860 25 28 0.852
   test statistic 27 31 0.865 28 31 0.862
  Standard genetic procedure: Simple Expression Ranking 24 28 0.837 24 28 0.837
  Direct Neighborhood Ranking log2 ratio 23 27 0.846 9 20 0.743
  ε > 0.15, a = 0.5 sign. log2 ratio 25 28 0.844 11 22 0.729
   test statistic 27 30 0.855 12 24 0.745
  Kernel Ridge Regression Ranking log2 ratio 18 24 0.736 17 24 0.766
  λ = 1, nn = 50, K LED , α = 0.5 sign. log2 ratio 23 29 0.834 17 22 0.755
MAS5   test statistic 13 18 0.790 16 24 0.790
  Heat Kernel Diffusion Ranking log2 ratio 26 32 0.877 28 34 0.890
  all expression values for p0 , m = 2, α = 0.5 sign. log2 ratio 26 31 0.877 26 34 0.899
   test statistic 32 32 0.890 31 34 0.904
  Arnoldi Diffusion Ranking log2 ratio 25 27 0.849 24 27 0.851
  m = 2, α = 0.5 sign. log2 ratio 25 29 0.853 25 27 0.847
   test statistic 26 30 0.858 27 29 0.850
  1. The results are based on optimized parameter settings for all presented strategies using different STRING networks. Note that the results of the Simple Expression Ranking do not depend on the network because they are only using differential expression levels to rank the candidate genes.