Table 4.
data set | first (5 species) | second (43 species) | ||||||
---|---|---|---|---|---|---|---|---|
number of sequences k | 20 | 30 | 40 | 50 | 4 | 6 | 8 | 10 |
naïve kernel (%) | 81.3 | 82.2 | 85.0 | 86.1 | 92.9 | 68.4 | 56.6 | 50.0 |
our preprocessing, from remaining (%) | 100 | 100 | 96.2 | 100 | 94.3 | 89.6 | 87.7 | 90.6 |
total excluded instances (%) | 100 | 100 | 99.4 | 100 | 99.6 | 96.7 | 94.7 | 95.3 |