<H2>Changes in v/1.1</H2>
<HR>
<p>
  <LI>The training dataset has been slightly enlarged to include more
      'negative' (non-glycosylated) sites.</LI>
  <LI>Surface-derived threshold has been modified to perform a running
      average.</LI>
  <LI>Glycosylation potentials have been sigmoidally scaled to magnify the
      distinction between positive and negative sites.</LI>
<p>
We expect the server to predict sites more 'specifically', that is to pick
up<B>O-GlcNAc</B> sites from<B>secreted and membrane proteins</B> of
<I>D.discoideum</I>. Predictions with the new server may vary from those made
with DictyOGlyc v/1.0. On a general basis, the server picks fewer glycosylation
sites presumably excluding more false positives.
<p>
Feedback, Comments and suggestions are most welcome.
<br>