Parametrization | Method | TP | FP | FN | Sn | Sp |
---|
 | 1st-ATG | 0 | 1,150 | 0 | 0.0000 | 0.0000 |
 | TISHunter | 69 | 1,081 | 0 | 0.0600 | 0.0600 |
 | ATGpr | 97 | 1,053 | 0 | 0.0843 | 0.0843 |
 | TIS Miner | 216 | 832 | 102 | 0.1878 | 0.2061 |
 | NetStart | 216 | 930 | 4 | 0.1878 | 0.1885 |
homogeneous | LLKR | 437 | 671 | 42 | 0.3800 | 0.3944 |
 | WLLKR | 531 | 467 | 152 | 0.4617 | 0.5321 |
 | MFCWLLKR | 525 | 625 | 0 | 0.4565 | 0.4565 |
 | PFCWLLKR | 542 | 551 | 57 | 0.4713 | 0.4959 |
 | BAYES | 442 | 511 | 197 | 0.3843 | 0.4638 |
cluster-specific | LLKR | 552 | 550 | 48 | 0.4800 | 0.5009 |
 | WLLKR | 663 | 380 | 107 | 0.5765 | 0.6357 |
 | MFCWLLKR | 683 | 467 | 0 | 0.5939 | 0.5939 |
 | PFCWLLKR | 679 | 419 | 52 | 0.5904 | 0.6184 |
 | BAYES | 567 | 406 | 177 | 0.4930 | 0.5827 |
random split | LLKR | 434 | 672 | 44 | 0.3774 | 0.3924 |
 | WLLKR | 522 | 468 | 160 | 0.4539 | 0.5273 |
 | MFCWLLKR | 530 | 620 | 0 | 0.4609 | 0.4609 |
 | PFCWLLKR | 541 | 551 | 58 | 0.4704 | 0.4954 |
 | BAYES | 439 | 512 | 199 | 0.3817 | 0.4616 |
- TIS identification statistics are reported exclusively for the 1,150 maximal reading frames containing in-frame ATG sites upstream from the true TIS, under three distinct parameter utilization approaches: homogeneous, a priori-known cluster-specific with k = 3, and three-fold random split. TP represents the number of instances for which the method correctly identified a TIS; FP for which a prediction was made, though incorrect; and FN for which no prediction was made, but should have been (see Figure 2). , and .