World Wide Web Prediction Server
Center for Biological Sequence Analysis
|high||at position +1 (immediately after the cleavage site)|
|low||at all other positions.|
|high||at all positions before the cleavage site|
|low||at 30 positions
after the cleavage site and |
in the N-terminals of non-secretory proteins.
Specifically, the Y-score is a geometric average between the C-score and a smoothed derivative of the S-score (i.e., the difference between the mean S-score over d positions before and d positions after the current position, where d varies with the chosen network ensemble).
All three scores are averages of five networks trained on different partitions of the data.
For each sequence, SignalP will report the maximal C-, S-, and Y-scores, and the mean S-score between the N-terminal and the predicted cleavage site. These values are used to distinguish between signal peptides and non-signal peptides. If the your sequence is predicted to have a signal peptide, the cleavage site is predicted to be immediately before the position with the maximal Y-score.
For a typical signal peptide, the C- and Y-scores will be high at position +1, while the S-score will be high before the cleavage site and low thereafter:
In the following example, the true cleavage site would be incorrectly predicted when relying on the maximal value of the C-score alone, but SignalP is able to predict it correctly by using the combined Y-score (the true cleavage site is marked with an arrow):
For a typical non-secretory protein, all three scores are very low throughout the sequence:
In the following example, there are C-score and S-score peaks above the cutoff values, but SignalP is still able to classify it correctly as a non-secretory protein by using the Y-score or the mean value of the S-score (the C-score peak occurs far away from the S-score decline, and the region of high S-score is too short):