Skip to main content

Table 4 The comparison of different methods for the best evaluation values in all cells

From: LightCpG: a multi-view CpG sites detection on single-cell whole genome sequence data

Dataset Methods Acc(%) AUC Fscore(%) MCC(%) SP(%) SE(%)
HCCs LightCpG 94.07 0.9709 85.82 82.10 95.74 87.59
  DeepCpG 93.20 0.9732 85.94 81.67 93.94 90.71
  RF Zhang 90.29 0.9388 80.10 73.95 91.78 85.29
HepG2 LightCpG 83.51 0.9246 82.40 68.04 90.33 78.43
  DeepCpG 84.08 0.9239 82.82 68.14 82.85 85.60
  RF Zhang 81.25 0.8954 80.05 63.48 87.77 76.35
  1. 1LightCpG employs three types of features (sequence feature, structural feature and positional feature) and LightGBM [36] to identify the CpG sites
  2. 2DeepCpG [35] embodies the connection between various cells by using the deep learning model Gated Recurrent Network (GRU) and also extracts features from the DNA sequence by the convolutional neural network (CNN) and one additional fully connected hidden layer. Then DeepCpG uses Fully Connected Neural Network to identify CpG sites
  3. 3RF Zhang [1] extracts the genomic positional features, neighbor features, sequence properties and sic-regulatory elements to identify the CpG sites
  4. 4The boldface is the best value in the column