Skip to main content

Table 6 Comparison of predictive performance with other methods.

From: Prediction of cis/trans isomerization in proteins using PSI-BLAST profiles and secondary structure information

Methods Prediction accuracy (%) Dataset used Prediction performance evaluation method
  Q 2 MCC   
Statistical patterna 72.7 - 242 Xaa-Pro bonds self-consistency
COPSb 63.6 - 8584 proteins 10-fold cross-validation
SVM single sequencec 69.8 - 2193 proteins independence test
SVM single sequenced 76.6 0.53 2193 proteins Jack-knife
SVM single sequencee 62.8 0.26 2424 proteins 5-fold cross-validation
SVM PSI-BLASTf 69.8 0.40 2424 proteins 5-fold cross-validation
SVM PSIPREDg 63.6 0.27 2424 proteins 5-fold cross-validation
SVM PSI-BLAST and PSIPREDh 71.5 0.43 2424 proteins 5-fold cross-validation
  1. aPrediction accuracy reported by Frömmel and Preissner [16]. The result cannot be determined from the paper.
  2. bPrediction accuracy estimated based on the average statistical results of COPS [18].
  3. cPrediction accuracy using independence test reported by Wang et al [17].
  4. dPrediction accuracy using jack-knife test reported by Wang et al [17].
  5. ePrediction accuracy of SVM based on single sequence encoding scheme using our dataset.
  6. fPrediction accuracy of SVM based on PSI-BLAST encoding scheme using our dataset.
  7. gPrediction accuracy of SVM based on PSIPRED encoding scheme using our dataset.
  8. hPrediction accuracy of SVM based on PSI-BLAST and PSIPRED encoding scheme using our dataset.