Skip to main content

Table 1 Results on benchmark dataset of different features through jackknife validation.

From: Identifying DNA-binding proteins by combining support vector machine and PSSM distance transformation

Methods Acc(%) MCC SN(%) SP(%)
PSSM-DDTa 79.72 0.607 81.33 78.18
PSSM-SDTb 74.79 0.512 77.147 74.93
PSSM-DTc 79.96 0.622 81.91 78.00
  1. PSSM-DT can extract two kinds protein features, called PSSM-DDT and PSSM-SDT respectively. And PSSM-DT represents the combination of PSSM-DDT and PSSM-SDT. The results were got by testing the models on benchmark dataset through jackknife validation.
  2. athe predictor using PSSM-DDT as protein representation
  3. bthe predictor using PSSM-SDT as protein representation
  4. cthe predictor using PSSM-DT as protein representation