Skip to main content

Table 8 The effect of noise level on GRN reconstruction in case of non-linearity between the genes. Results are the average of accuracy of the Link criteria for GRN reconstruction of 10 different randomly generated synthetic networks

From: Identifying time-delayed gene regulatory networks via an evolvable hierarchical recurrent neural network

Methods σ 2 TP FP FN Precision Recall F-score Nominal p-value Adjusted p-value
HRNN 0.1 20.2 28.3 19.0 0.41 0.51 0.46   
  0.25 19.9 26.7 20.6 0.42 0.49 0.45   
  0.5 17.9 28.4 21.3 0.38 0.45 0.41   
  1 11.2 30.5 28.4 0.26 0.28 0.27   
  1.5 5.9 32.2 33.6 0.15 0.14 0.15   
TD-ARACNE 0.1 13.5 102.5 25.7 0.12 0.34 0.17 1.9×10−10 9.5×10−10
  0.25 14.7 107.3 25.8 0.11 0.36 0.16 1.4×10−8 7.0×10−8
  0.5 12.0 102.0 27.2 0.09 0.30 0.13 1.3×10−7 6.5×10−7
  1 14.5 129.5 25.1 0.10 0.37 0.15 3.0×10−4 1.5×10−3
  1.5 12.2 115.8 27.3 0.11 0.31 0.14 0.86 1
HCC-CLINDE 0.1 19.0 9.5 20.2 0.66 0.48 0.56 0.04 0.2
  0.25 18.0 10.3 22.5 0.63 0.44 0.52 0.08 0.4
  0.5 12.8 8.4 26.4 0.61 0.33 0.42 0.78 1
  1 4.1 9.4 35.5 0.29 0.10 0.15 0.01 0.05
  1.5 0.5 7.3 39.0 0.06 0.01 0.02 1.2×10−6 6.0×10−6
TSNI 0.1 14.1 139.9 25.1 0.09 0.36 0.14 6.2×10−11 3.1×10−10
  0.25 13.6 128.4 26.9 0.09 0.33 0.14 7.2×10−10 3.6×10−9
  0.5 15.3 138.7 23.9 0.09 0.38 0.15 4.2×10−8 2.1×10−7
  1 17.6 160.4 22.0 0.09 0.44 0.16 4.8×10−4 2.4×10−3
  1.5 15.1 150.9 24.4 0.08 0.37 0.14 0.63 1
ebdbNet 0.1 7.8 56.2 31.4 0.12 0.20 0.14 1.5×10−9 7.5×10−9
  0.25 7.7 58.3 32.8 0.11 0.18 0.13 8.9×10−10 4.4×10−9
  0.5 5.2 48.8 34.0 0.09 0.13 0.10 4.4×10−9 2.2×10−8
  1 6.2 55.8 33.4 0.10 0.15 0.12 5.0×10−5 2.5×10−4
  1.5 5.2 54.8 34.3 0.07 0.13 0.09 0.02 0.1
  1. The p-values are for how the Link F-scores of other methods compare with HRNN. σ 2 is variance of the noise. Networks include 20 genes