X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;ds=sidebyside;f=help%2Fhtml%2FwebServices%2Fjnet.html;h=7a6015ac42278b5957462b8fda3c1eda45c009c6;hb=83b541e967d19e6aeb5b02f476a77399f5f79d22;hp=feefe77f28b5d4dc5245417d363f6f45621723af;hpb=c29c0a190d8095d8a0c646a59447cadaa2a5af55;p=jalview.git

diff --git a/help/html/webServices/jnet.html b/help/html/webServices/jnet.html
index feefe77..7a6015a 100755
--- a/help/html/webServices/jnet.html
+++ b/help/html/webServices/jnet.html
@@ -8,7 +8,7 @@
 Secondary structure prediction methods attempts to infer the likely secondary
 structure for a protein based on its amino acid composition and
 similarity to sequences with known secondary structure. The JNet
-method uses several different prediction methods and decides on the
+method uses several different neural networks and decides on the
 most likely prediction via a jury network. <br>
 <ul>
 <li>Cuff J. A and Barton G.J (1999) Application of enhanced multiple
@@ -16,9 +16,9 @@ sequence alignment profiles to improve protein secondary
 structure prediction <em>Proteins</em> <strong>40</strong> 502-511</li></ul>
 </p>
 The function available from the <strong>Web Service&#8594;Secondary
-Structure Prediction&#8594;JNet Secondary Structure 
-Prediction</strong> menu does two different kinds of prediction, 
-dependent upon the currently selected region:</p> 
+Structure Prediction&#8594;JNet Secondary Structure
+Prediction</strong> menu does two different kinds of prediction,
+dependent upon the currently selected region:</p>
 <ul>
 <li>If nothing is selected, and the displayed sequences appear to
 be aligned, then a JNet prediction will be run for the first
@@ -33,9 +33,15 @@ for homolog detection and prediction.
 <li>If a set of sequences are selected, and they appear to be aligned,
 then the alignment will be used for a Jnet prediction on the
 <strong>first</strong> sequence selected in the set (that is, the one
-that was first clicked on).
-</li>      
+nearest the top of the alignment window).
+</li>
 </ul>
+<p><strong>Note</strong>: JNet secondary structure prediction is a
+ 'non-column-separable' service - predictions are based on the
+ sequence profile of contiguous stretches of amino-acid sequence. This
+ means that all columns of the alignment, or selection will be submitted
+ for prediction, not just the visible ones (see <a
+ href="../features/hiddenRegions.html">hiding columns</a>).
 <p>The result of a JNet prediction for a sequence is a new annotated
  alignment window:</p>
 <img src="jnetprediction.gif">