Skip to main content

Table 3 Comparing mGOASVM with state-of-the-art multi-label predictors based on leave-one-out cross validation (LOOCV) using (a) the virus dataset and (b) the plant dataset

From: mGOASVM: Multi-label protein subcellular localization based on gene ontology and support vector machines

(a) Performance on the viral protein dataset
Label Subcellular location LOOCV locative accuracy
   Virus-mPLoc [[37]] KNN-SVM [[39]] iLoc-Virus [[33]] mGOASVM
1 Viral capsid 8/8 = 100.0% 8/8 = 100.0% 8/8 = 100.0% 8/8 = 100.0%
2 Host cell membrane 19/33 = 57.6% 27/33 = 81.8% 25/33 = 75.8% 32/33 = 97.0%
3 Host ER 13/20 = 65.0% 15/20 = 75.0% 15/20 = 75.0% 17/20 = 85.0%
4 Host cytoplasm 52/87 = 59.8% 86/87 = 98.8% 64/87 = 73.6% 85/87 = 97.7%
5 Host nucleus 51/84 = 60.7% 54/84 = 65.1% 70/84 = 83.3% 82/84 = 97.6%
6 Secreted 9/20 = 45.0% 13/20 = 65.0% 15/20 = 75.0% 20/20 = 100.0%
Overall Locative Accuracy 152/252 = 60.3% 203/252 = 80.7% 197/252 = 78.2% 244/252 = 96.8%
Overall Actual Accuracy – – 155/207 =74.8% 184/207 = 88.9%
(b) Performance on the plant protein dataset
Label Subcellular location LOOCV locative accuracy  
   Plant-mPLoc [[41]] iLoc-Plant [[42]] mGOASVM  
1 Cell membrane 24/56 = 42.9% 39/56 = 69.6% 53/56 = 94.6%  
2 Cell wall 8/32 = 25.0% 19/32 = 59.4% 27/32 = 84.4%  
3 Chloroplast 248/286 = 86.7% 252/286 = 88.1% 272/286 = 95.1%  
4 Cytoplasm 72/182 = 39.6% 114/182 = 62.6% 174/182 = 95.6%  
5 Endoplasmic reticulum 17/42 = 40.5% 21/42 = 50.0% 38/42 = 90.5%  
6 Extracellular 3/22 = 13.6% 2/22 = 9.1% 22/22 = 100.0%  
7 Golgi apparatus 6/21 = 28.6% 16/21 = 76.2% 19/21 = 90.5%  
8 Mitochondrion 114/150 = 76.0% 112/150 = 74.7% 150/150 = 100.0%  
9 Nucleus 136/152 = 89.5% 140/152 = 92.1% 151/152 = 99.3%  
10 Peroxisome 14/21 = 66.7% 6/21 = 28.6% 21/21 = 100.0%  
11 Plastid 4/39 = 10.3% 7/39 = 17.9% 39/39 = 100.0%  
12 Vacuole 26/52 = 50.0% 28/52 = 53.8% 49/52 = 94.2%  
Overall Locative Accuracy 672/1055 = 63.7% 756/1055 = 71.7% 1015/1055 =96.2%  
Overall Actual Accuracy – 666/978 = 68.1% 855/978 = 87.4%  
  1. “–” means the corresponding references do not provide the overall actual accuracy. KNN-SVM: the KNN-SVM ensemble classifier proposed in[39]. Host ER: Host endoplasmic reticulum.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us