3 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
4 * Copyright (C) $$Year-Rel$$ The Jalview Authors
6 * This file is part of Jalview.
8 * Jalview is free software: you can redistribute it and/or
9 * modify it under the terms of the GNU General Public License
10 * as published by the Free Software Foundation, either version 3
11 * of the License, or (at your option) any later version.
13 * Jalview is distributed in the hope that it will be useful, but
14 * WITHOUT ANY WARRANTY; without even the implied warranty
15 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
16 * PURPOSE. See the GNU General Public License for more details.
18 * You should have received a copy of the GNU General Public License
19 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
20 * The Jalview Authors are detailed in the 'AUTHORS' file.
23 <title>JNet Secondary Structure Prediction</title>
26 <strong>JNet Secondary Structure Prediction</strong>
28 Secondary structure prediction methods attempts to infer the likely
29 secondary structure for a protein based on its amino acid
30 composition and similarity to sequences with known secondary
31 structure. The most recent version of the method, JPred4, employs a
32 series of neural networks trained to predict different secondary
33 structure types from a sequence profile, and when necessary, employs
34 a jury network to identify the most likely secondary structure
35 prediction.<br><ul><li>Drozdetskiy A, Cole C, Procter J & Barton GJ. (2015)<br/>
36 JPred4: a protein secondary structure prediction server<br/>
37 <em>Nucleic Acids Research</em>, <strong>Web Server issue</strong> (first published 15th April 2015)<br/>
38 <a href="http://dx.doi.org/10.1093/nar/gkv332">http://dx.doi.org/10.1093/nar/gkv332</a>
40 <li>Cole C., Barber J.D. and Barton G.J. (2008) The Jpred 3
41 secondary structure prediction server <em>Nucleic Acids Research</em> <strong>36</strong>
43 <li>Cuff J. A and Barton G.J (1999) Application of enhanced
44 multiple sequence alignment profiles to improve protein secondary
45 structure prediction <em>Proteins</em> <strong>40</strong> 502-511</li>
48 The function available from the
49 <strong>Web Service→Secondary Structure
50 Prediction→JNet Secondary Structure Prediction</strong>
51 menu does two different kinds of prediction, dependent upon the
52 currently selected region:
55 <li>If nothing is selected, and the displayed sequences appear to
56 be aligned, then a JNet prediction will be run for the first sequence
57 in the alignment, using the current alignment. Otherwise the first
58 sequence will be submitted for prediction.</li>
59 <li>If just one sequence (or a region on one sequence) has been
60 selected, it will be submitted to the automatic JNet prediction server
61 for homolog detection and prediction.</li>
62 <li>If a set of sequences are selected, and they appear to be
63 aligned, then the alignment will be used for a Jnet prediction on the <strong>first</strong>
64 sequence selected in the set (that is, the one nearest the top of the
65 alignment window).</li>
67 <p><strong>Note</strong>: JNet secondary structure prediction is a
68 'non-column-separable' service - predictions are based on the sequence
69 profile of contiguous stretches of amino-acid sequence. A prediction
70 will only be made on the visible parts of a sequence (see <a
71 href="../features/hiddenRegions.html">hiding columns</a>) as if it were
72 a contiguous polypeptide chain. Prediction accuracy at the hidden column
73 boundaries may therefore be less than indicated by JNet's own
74 reliability score (see below).</p>
75 <p>The result of a JNet prediction for a sequence is a new annotated
77 <img src="jnetprediction.gif">
78 <p>The sequence for which the prediction was made is the first one
79 in the alignment. If a sequence based prediction was made then the
80 remaining sequences in the alignment are the aligned parts of homologs
81 which were used to construct a sequence profile for the prediction. If
82 the prediction was made using a multiple alignment, then the original
83 multiple alignment will be returned, annotated with the prediction.</p>
84 The annotation bars below the alignment are as follows:
87 <li>Lupas_21, Lupas_14, Lupas_28<br>
88 <em>Coiled-coil predictions for the sequence. These are binary
89 predictions for each location.</em></li>
90 <li>JNETSOL25,JNETSOL5,JNETSOL0<br>
91 <em>Solvent accessibility predictions - binary predictions of 25%,
92 5% or 0% solvent accessibility.</em></li>
94 <em>The consensus prediction - helices are marked as red tubes,
95 and sheets as dark green arrows.</em></li>
97 <em>The confidence estimate for the prediction. High values mean
98 high confidence. prediction - helices are marked as red tubes, and
99 sheets as dark green arrows.</em></li>
101 <em>Alignment based prediction - helices are marked as red tubes,
102 and sheets as dark green arrows.</em></li>
104 <em>HMM profile based prediction - helices are marked as red
105 tubes, and sheets as dark green arrows.</em></li>
107 <em>Jpred prediction - helices are marked as red tubes, and sheets
108 as dark green arrows.</em></li>
110 <em>PSSM based prediction - helices are marked as red tubes, and
111 sheets as dark green arrows.</em></li>
113 <em>Amino Acid frequency based prediction - helices are marked as
114 red tubes, and sheets as dark green arrows.</em></li>
116 <em>A '*' in this annotation indicates that the JNETJURY was
117 invoked to rationalise significantly different primary predictions.</em></li>
120 <em>JNet annotation created in Jalview 2.8.2 and later versions
121 can be displayed on other alignments via the <a
122 href="../features/annotation.html#seqannots">Add reference
123 annotation</a> Sequence ID popup menu option.
125 <em>As of Jalview 2.6, the Jnet service accessed accessed via the
126 'Secondary structure prediction' submenu should be considered a legacy
127 Jalview SOAP service, and will be replaced in the near future by a
128 JPred4 Rest service.</em>