From: Protein sequences classification by means of feature extraction with substitution matrices
Dataset (source) | Identity percentage (%) | Family/class | Size | Total |
---|---|---|---|---|
DS1 (Swiss-prot) | 48 | High-potential Iron-Sulfur Protein | 19 | 60 |
 |  | Hydrogenase Nickel Incorporation Protein HypA | 20 |  |
 |  | Hlycine Dehydrogenase | 21 |  |
DS2 (Swiss-prot) | 48 | Chemokine | 255 | 510 |
 |  | Melanocortin | 255 |  |
DS3 (Swiss-prot) | 25 | Monomer | 208 | 717 |
 |  | Homodimer | 335 |  |
 |  | Homotrimer | 40 |  |
 |  | Homotetramer | 95 |  |
 |  | Homopentamer | 11 |  |
 |  | Homohexamer | 23 |  |
 |  | Homooctamer | 5 |  |
DS4 (Swiss-prot) | 28 | human TLR | 14 | 40 |
 |  | Non-human TLR | 26 |  |
DS5 (SCOP) | 84 | All-α domain | 70 | 277 |
 |  | All-β domain | 61 |  |
 |  | α/β domain | 81 |  |
 |  | α + β domain | 65 |  |