TABLE 1.
Predicted by Neural nets: Mitochondrial with score: 1.08. Predicted by Pentamers: Mitochondrial with score: 1.2. Integral Prediction of protein location: Mitochondrial with score: 5.6. | |||||
Location weights: | LocDB | PotLocDB | Neural nets | Pentamers | Integral |
Nuclear | 0.0 | 0.0 | 0.40 | 0.0 | 0.31 |
Plasma membrane | 0.0 | 0.0 | 0.34 | 0.21 | 1.97 |
Extracellular | 0.0 | 0.0 | 0.26 | 0.35 | 1.16 |
Cytoplasmic | 0.0 | 0.0 | 0.24 | 0.06 | 0.29 |
Mitochondrial | 0.0 | 0.0 | 1.08 | 1.2 | 5.60 |
Endoplasm. retic. | 0.0 | 0.0 | 0.28 | 0.02 | 0.17 |
Peroxisomal | 0.0 | 0.0 | 0.02 | 0.09 | 0.00 |
Lysosomal | 0.0 | 0.0 | 0.09 | 0.02 | 0.00 |
Golgi | 0.0 | 0.0 | 0.00 | 1.08 | 0.36 |
Vacuolar | 0.0 | 0.0 | 0.29 | 0.05 | 0.13 |
LocDB: scores based on query protein’s homologies with proteins of known localization.
PotLocDB: scores based on homologies with proteins which locations are not experimentally known but are assumed from strong theoretical evidence.
NNets: scores assigned by neural networks.
Pentamers: scores based on comparisons of pentamer distributions calculated for QUERY and DB sequences.
Integral are final scores that combine all above previous scores using a final neural net.
http://www.softberry.com/berry.phtml?topic=protcompan&group=help&subgroup=proloc