Table 1. Performance of individual feature-based models for the bound sequence dataset, evaluated by LOOCV.
Window | #1 | #2 | #3 | #4 | #5 | #6 | #7 | #8 | #9 | Average |
5 | 0.604 | 0.580 | 0.601 | 0.601 | 0.673 | 0.599 | 0.583 | 0.617 | 0.637 | 0.611 |
7 | 0.617 | 0.575 | 0.607 | 0.609 | 0.678 | 0.600 | 0.578 | 0.613 | 0.640 | 0.613 |
9 | 0.632 | 0.576 | 0.598 | 0.609 | 0.678 | 0.613 | 0.589 | 0.607 | 0.650 | 0.617 |
11 | 0.622 | 0.565 | 0.593 | 0.597 | 0.673 | 0.593 | 0.564 | 0.606 | 0.648 | 0.607 |
13 | 0.633 | 0.576 | 0.603 | 0.599 | 0.672 | 0.602 | 0.5687 | 0.613 | 0.657 | 0.614 |
15 | 0.623 | 0.543 | 0.603 | 0.598 | 0.674 | 0.600 | 0.539 | 0.607 | 0.662 | 0.605 |
Physicochemical propensities (#1), amino acid composition (#2), amino acid function group (#3), amino acid functional composition (#4), evolutionary profile (#5), sparse profile (#6), amino acid pair profile (#7), secondary structure (#8), relative accessible surface area (#9).