Table 13 MD-SFS forward selection approach on TG-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 | 20.5% | HPZXV | 23.5% | HPZXV | 28.8% |
1-10 | FXBPC,ZVH | 29.8% | BVFXP,CH | 30.7% | BPXVF,SKCHZ | 37.6% |
1-15 | FXTBV,ACPZE,fH | 33.4% | BTEPX,AfFVS | 33.4% | BPEXf,RAKFS,HCV | 41.5% |
All | LDA-Atr* | 38.0% | SVM-Atr* | 35.9% | NB-Atr* | 45.3% |