Skip to main content

Table 6 Distribution of the number of labels predicted by mGOASVM for proteins in the virus and plant datasets

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

Dataset

Condition

Case

n k o , n k e or n k u

(No, Ne or Nu)/Nact

   

k =0

k =1

k =2

k >2

 

Virus

| ℳ ( p i ) | > | ℒ ( p i ) |

Over-prediction

0

18

0

0

18/207 = 8.7%

 

| ℳ ( p i ) | = | ℒ ( p i ) |

Equal-prediction

187

0

0

0

187/207 = 90.3%

 

| ℳ ( p i ) | < | ℒ ( p i ) |

Under-prediction

0

2

0

0

2/207 = 1.0%

Plant

| ℳ ( p i ) | > | ℒ ( p i ) |

Over-prediction

0

83

2

0

85/978 = 8.7%

 

| ℳ ( p i ) | = | ℒ ( p i ) |

Equal-prediction

879

0

0

0

879/978 = 89.9%

 

| ℳ ( p i ) | < | ℒ ( p i ) |

Under-prediction

0

14

0

0

14/978 = 1.4%

  1. ℳ ( p i ) : Number of predicted labels for the i-th (i=1,…, Nact) protein; ℒ ( p i ) : Number of the true labels for the i-th protein; Over-prediction: the number of predicted labels is larger than that of the true labels; Equal-prediction: the number of predicted labels is equal to that of the true labels; Under-prediction: the number of predicted labels is smaller than that of the true labels; n k o , n k e or n k u : the number of proteins that are over-, equal-, or under-predicted by k (k=0,…,5 for the virus dataset and k= 0,…,11 for the plant dataset) labels, respectively; No, Ne or Nu: the total number of proteins that are over-, equal-, or under-predicted, respectively.