<html>
<!--
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.5)
- * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
+ * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
*
* This file is part of Jalview.
*
* Jalview is free software: you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
- *
+ *
* Jalview is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR
*
* You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
-->
+<head>
+<title>JNet Secondary Structure Prediction</title>
+</head>
+<body>
+<strong>JNet Secondary Structure Prediction</strong>
+<p>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 neural networks and decides on
+the most likely prediction via a jury network. <br>
+<ul>
+ <li>Cole C., Barber J.D. and Barton G.J. (2008) The Jpred 3
+ secondary structure prediction server <em>Nucleic Acids Research</em> <strong>36</strong>
+ W197-W201</li>
+ <li>Cuff J. A and Barton G.J (1999) Application of enhanced
+ multiple 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→Secondary Structure
+Prediction→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 sequence
+ in the alignment, using the current alignment. Otherwise the first
+ sequence will be submitted for prediction.</li>
+ <li>If just one sequence (or a region on one sequence) has been
+ selected, it will be submitted to the automatic JNet prediction server
+ for homolog detection and prediction.</li>
+ <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 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. A prediction
+will only be made on the visible parts of a sequence (see <a
+ href="../features/hiddenRegions.html">hiding columns</a>) as if it were
+a contiguous polypeptide chain. Prediction accuracy at the hidden column
+boundaries may therefore be less than indicated by JNet's own
+reliability score (see below).</p>
+<p>The result of a JNet prediction for a sequence is a new annotated
+alignment window:</p>
+<img src="jnetprediction.gif">
+<p>The sequence for which the prediction was made is the first one
+in the alignment. If a sequence based prediction was made then the
+remaining sequences in the alignment are the aligned parts of homologs
+which were used to construct a sequence profile for the prediction. If
+the prediction was made using a multiple alignment, then the original
+multiple alignment will be returned, annotated with the prediction.</p>
+The annotation bars below the alignment are as follows:
+</p>
+<ul>
+ <li>Lupas_21, Lupas_14, Lupas_28<br>
+ <em>Coiled-coil predictions for the sequence. These are binary
+ predictions for each location.</em></li>
+ <li>JNETSOL25,JNETSOL5,JNETSOL0<br>
+ <em>Solvent accessibility predictions - binary predictions of 25%,
+ 5% or 0% solvent accessibility.</em></li>
+ <li>JNetPRED<br>
+ <em>The consensus prediction - helices are marked as red tubes,
+ and sheets as dark green arrows.</em></li>
+ <li>JNetCONF<br>
+ <em>The confidence estimate for the prediction. High values mean
+ high confidence. prediction - helices are marked as red tubes, and
+ sheets as dark green arrows.</em></li>
+ <li>JNetALIGN<br>
+ <em>Alignment based prediction - helices are marked as red tubes,
+ and sheets as dark green arrows.</em></li>
+ <li>JNetHMM<br>
+ <em>HMM profile based prediction - helices are marked as red
+ tubes, and sheets as dark green arrows.</em></li>
+ <li>jpred<br>
+ <em>Jpred prediction - helices are marked as red tubes, and sheets
+ as dark green arrows.</em></li>
+ <li>JNETPSSM<br>
+ <em>PSSM based prediction - helices are marked as red tubes, and
+ sheets as dark green arrows.</em></li>
+ <li>JNETFREQ<br>
+ <em>Amino Acid frequency based prediction - helices are marked as
+ red tubes, and sheets as dark green arrows.</em></li>
+ <li>JNETJURY<br>
+ <em>A '*' in this annotation indicates that the JNETJURY was
+ invoked to rationalise significantly different primary predictions.</em></li>
+</ul>
+</p>
+<em>As of Jalview 2.6, the Jnet service accessed accessed via the
+'Secondary structure prediction' submenu should be considered a legacy
+Jalview SOAP service, and will be replaced in the near future by a
+JABAWS Jnet service.</em>
+
+</body>
+</html>