Skip to main content

Table 5 Comparison of predictive accuracy for plant proteins in the TargetP data set with three types of feature vectors

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
20 feature vectors (amino acid composition) 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   
400 feature vectors (all adjacent amino acid composition) cTP 0.8227 0.4128 0.4806 0.6126 0.7372
  mTP 0.8342 0.8797 0.7686   
  SP 0.8253 0.8880 0.8015   
  other 0.2963 0.8000 0.4339   
40 feature vectors cTP 0.8014 0.9040 0.8270 0.8594 0.9064
  mTP 0.9402 0.9081 0.8739   
  SP 0.9628 0.9317 0.9255   
  other 0.8272 0.8590 0.8110   
  1. Note: Parameters of Table 2 are used for all methods.