Table 5 Characteristics of the NN269 and DGSplicer data sets containing true and decoy acceptor and donor splice sites derived from the human genome.
From: Accurate splice site prediction using support vector machines
NN269 | DGSplicer | |||
|---|---|---|---|---|
Acceptor | Donor | Acceptor | Donor | |
Sequence length | 90 | 15 | 36 | 18 |
Consensus positions | AG at 69 | GT at 8 | AG at 26 | GT at 10 |
Train total | 5788 | 5256 | 322156 | 228268 |
Fraction positives | 19.3% | 21.2% | 0.6% | 0.8% |
Test total | 1087 | 990 | 80539 | 57067 |
Fraction positives | 19.4% | 21.0% | 0.6% | 0.8% |