|
Overall measures of accuracy, obtained in the Self-consistency and in the Jacknife testing. |
||||||||
| Type of test |
TP |
FP |
FN |
TOP1 |
TOP2 |
Qβ |
Cβ |
|
|
|
||||||||
| (A) |
Self-consistency |
205 |
3 |
9 |
9 |
11 |
88.1% |
0.824 |
| Jacknife |
203 |
13 |
11 |
8 |
10 |
84.2% |
0.720 |
|
| (B) |
Self-consistency |
206 |
2 |
8 |
10 |
11 |
66.9% |
0.604 |
| Jacknife |
204 |
12 |
10 |
9 |
10 |
65.7% |
0.532 |
|
|
(A): Comparison against the manual annotation of the TM-segments. (B): comparison against the observed strands of PDB [29]. TP: True Positives. FP: False Positives. FN: False Negatives. TOP1: Proteins with correctly predicted topologies (strand localization and orientation of the loops). TOP2: Proteins with correctly predicted topologies, with the inclusion of shifted strand predictions. Qβ: Percentage of correctly predicted residues [36]. Cβ: Matthews Correlation Coefficient [36]. | ||||||||
Bagos et al. BMC Bioinformatics 2004 5:29 doi:10.1186/1471-2105-5-29 |
||||||||