For each input sequence the server predicts the possibility of
For eukaryotic sequences, an example of the output is shown below, but it is different in the version for bacteria.
For that version, four scores are generated by the SecretomeP server for each input sequence. The determining score is the 'SecP score', for which a value above 0.5 indicates possible secretion.
This score is the score mentioned in the
paper, while the others are provided merely to give an idea about the degree of consent among the three different models used for the prediciton.
Even though SecretomeP is trained to predict
non-classical secretion, it usually gives high score
to proteins entering the classical secretory pathway (having signal peptides). The user is advised to check for conventional signal peptides if in doubt (See SignalP for more information).
# Name NN-score Odds Weighted Warning
# by prior
FGF1_HUMAN 0.847 4.267 0.009 -
FGF4_HUMAN 0.945 6.804 0.014 signal peptide predicted by SignalP
ATRX_HUMAN 0.093 0.205 0.000 -
In the example above the first protein, known to enter the non-classical
is correctly predicted as secretory. The second classical secreted protein,
is correctly predicted as secretory, but a warning that a signal peptide
is predicted is reported. The third protein,
a known nuclear protein, receives a low score, thus is correctly classified.