documentation

[jalview.git] / help / html / webServices / jnet.html

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