Table 9 MD-SFS backward elimination approach on EDD-dataset using MA-based criterion
From: A strategy to select suitable physicochemical attributes of amino acids for protein fold recognition
No. of attributes used | LDA | SVM | NB | |||
|---|---|---|---|---|---|---|
| Â | Attribute | PFR | Attribute | PFR | Attribute | PFR |
| Â | HPZXV | 27.5% | HPZXV | 31.7% | HPZXV | 38.4% |
1-10 | FXPHC,BVSKZ | 38.8% | BPCZX,FHKV | 39.4% | BXPVF,SKHC | 47.7% |
1-15 | BTXVZ,fFAEP,HCRSK | 45.5% | BTPVC,fKXFA,HS | 43.3% | BXPAf,KFSZH,CT | 51.3% |
All | LDA-Atr* | 51.8% | SVM-Atr* | 47.4% | NB-Atr* | 53.9% |