Skip to main content

Table 6 Comparison of predictive accuracy of our methods for plant proteins in the TargetP data set. "cTP", "mTP", "SP", and "other" indicate proteins destined for chloroplast, mitochondria, secretory pathway, and other locations (nucleus and cytosol), respectively.

From: Subcellular location prediction of proteins using support vector machines with alignment of block sequences utilizing amino acid composition

Predictor Location Sensitivity Specificity MCC Average MCC Overall Accuracy
Our method (SVM with specifying posconstraint and negconstraint) cTP 0.8440 0.9015 0.8507 0.8655 0.9096
  mTP 0.9348 0.9125 0.8735   
  SP 0.9665 0.9319 0.9282   
  other 0.8148 0.8684 0.8095   
Our method (SVM without specifying posconstraint and negconstraint) cTP 0.7518 0.9550 0.8249 0.8525 0.8989
  mTP 0.9592 0.8506 0.8363   
  SP 0.9554 0.9554 0.9375   
  other 0.7963 0.8897 0.8111   
Nearest Neighbor Classifier (with our similarity measure) cTP 0.7447 0.7664 0.7131 0.7255 0.8128
  mTP 0.8750 0.7854 0.7098   
  SP 0.8848 0.9015 0.8508   
  other 0.6111 0.7674 0.6284   
  1. Note: In the first method, all parameters of Table 2 are given. In the second and third methods, gap penalty = 0.4, γ = 2.5, c = 10, w = 20 are given although posconstraint and negconstraint are not specified.