Skip to main content

Table 6 Results reached by the state-of-the-art approaches in comparison with the proposed method when predicting the DNAm databases. Note that S1 refers to the primary set (GSE32393 series) and S2 to the external database (GSE50220 series)

From: A deep embedded refined clustering approach for breast cancer distinction based on DNA methylation

  ACC ER (%) FN FP ARI NMI
S1 S2 S1 S2 S1 S2 S1 S2 S1 S2 S1 S2
i-DivClu-D [27] 0.7600 0.6700 24.00 33.00 33 16 0 0 0.2546 0.1000 0.3113 0.2422
i-DivClu-M [27] 0.8832 0.7917 11.68 20.83 11 10 5 0 0.5149 0.3203 0.3391 0.3618
LSC-aff. hull [5] 0.8248 0.5208 17.52 47.92 24 23 0 0 0.3934 -0.0560 0.3921 0.1545
LSC-conv. hull [5] 0.8248 0.5625 17.52 43.75 24 21 0 0 0.3934 -0.0210 0.3921 0.1700
Proposed 0.9927 0.9375 0.73 6.25 1 3 0 0 0.9643 0.7374 0.9212 0.6554
  1. The bold values point out the method that has obtained the best results