Table 5 Performance of different GO-vector construction methods based on leave-one-out cross validation (LOOCV) for (a) the virus dataset and (b) the plant dataset
(a) Performance on the viral protein dataset | ||
|---|---|---|
GO Vector construction | Locative accuracy | Actual accuracy |
methods | Â | Â |
1-0 value | 244/252 = 96.8% | 179/207 = 86.5% |
Term-frequency (TF) | 244/252 = 96.8% | 184/207 = 88.9% |
(b) Performance on the plant protein dataset | ||
GO Vector construction | Locative accuracy | Actual accuracy |
methods | Â | Â |
1-0 value | 1014/1055 = 96.1% | 788/978 = 80.6% |
Term-frequency (TF) | 1015/1055 = 96.2% | 855/978 = 87.4% |