Skip to main content

Table 4 The overall prediction accuracy achieved using Rotation Forest to each feature groups investigated in this study (in percentage).

From: Gram-positive and gram-negative subcellular localization using rotation forest and physicochemical-based features

Features Gram-positive Gram-negative
PSSM_AAC 75.7 71.2
PSSM_AC 79.5 72.2
OSD 63.9 63.9
OSA 67.7 68.9
PSSM_AAC + PSSM_AC 80.5 74.9
PSSM_AAC + PSSM_AC + OSD 81.3 75.6
PSSM_AAC + PSSM_AC + OSD + OSA 83.6 76.6
  1. It also shows the results achieved using Rotation Forest to the combination of feature groups to build the Combination of all for feature groups together. We use attribute number 9 (Hydrophobicity scale (contact energy derived from 3D data) attribute) for this experiment as using this attribute we attain our best results.