|
Rank of correct class single-localized and multi-localized sequences using a 7-gram model |
||||
| Rank of correct class |
||||
|
|
||||
| 1 |
2 |
3 |
4 |
|
|
|
||||
| Single-localized only |
88.8a |
92.2 |
94.5 |
96.3 |
| CYT-NUC: 1 correct |
88.2a |
96.1 |
99.5 |
100.0 |
| CYT-NUC: both correct |
66.5a |
82.9 |
96.3 |
|
| All multi-localized: 1 correct |
81.9a |
92.0 |
96.1 |
97.4 |
| All multi-localized: both correct |
59.7a |
73.8 |
83.2 |
|
|
This table shows the percent of the data that had the correct localization predicted within the top r most probable classes, where r is the rank of the correct class. aItems representing the overall accuracy of ngLOC on those sequences specified. CYT, cytoplasm; NUC, nuclear. | ||||
King and Guda Genome Biology 2007 8:R68 doi:10.1186/gb-2007-8-5-r68 |
||||