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
37 <li>Drozdetskiy A, Cole C, Procter J & Barton GJ. (2015)<br />
38 JPred4: a protein secondary structure prediction server<br /> <em>Nucleic
39 Acids Research</em>, <strong>Web Server issue</strong> (first
40 published 15th April 2015)<br /> <a
41 href="http://dx.doi.org/10.1093/nar/gkv332"
42 >http://dx.doi.org/10.1093/nar/gkv332</a>
44 <li>Cole C., Barber J.D. and Barton G.J. (2008) The Jpred 3
45 secondary structure prediction server <em>Nucleic Acids
46 Research</em> <strong>36</strong> W197-W201
48 <li>Cuff J. A and Barton G.J (1999) Application of enhanced
49 multiple sequence alignment profiles to improve protein secondary
50 structure prediction <em>Proteins</em> <strong>40</strong> 502-511
54 The function available from the
55 <strong>Web Service→Secondary Structure
56 Prediction→JNet Secondary Structure Prediction</strong> menu does two
57 different kinds of prediction, dependent upon the currently selected
61 <li>If nothing is selected, and the displayed sequences appear
62 to be aligned, then a JNet prediction will be run for the first
63 sequence in the alignment, using the current alignment. Otherwise
64 the first sequence will be submitted for prediction.</li>
65 <li>If just one sequence (or a region on one sequence) has been
66 selected, it will be submitted to the automatic JNet prediction
67 server for homolog detection and prediction.</li>
68 <li>If a set of sequences are selected, and they appear to be
69 aligned, then the alignment will be used for a Jnet prediction on
70 the <strong>first</strong> sequence selected in the set (that is,
71 the one nearest the top of the alignment window).
75 <strong>Note</strong>: JNet secondary structure prediction is a
76 'non-column-separable' service - predictions are based on the
77 sequence profile of contiguous stretches of amino-acid sequence. A
78 prediction will only be made on the visible parts of a sequence (see
79 <a href="../features/hiddenRegions.html">hiding columns</a>) as if
80 it were a contiguous polypeptide chain. Prediction accuracy at the
81 hidden column boundaries may therefore be less than indicated by
82 JNet's own reliability score (see below).
84 <p>The result of a JNet prediction for a sequence is a new
85 annotated alignment window:</p>
86 <img src="jnetprediction.gif">
87 <p>The sequence for which the prediction was made is the first one
88 in the alignment. If a sequence based prediction was made then the
89 remaining sequences in the alignment are the aligned parts of
90 homologs which were used to construct a sequence profile for the
91 prediction. If the prediction was made using a multiple alignment,
92 then the original multiple alignment will be returned, annotated
93 with the prediction.</p>
94 The annotation bars below the alignment are as follows:
97 <li>Lupas_21, Lupas_14, Lupas_28<br> <em>Coiled-coil
98 predictions for the sequence. These are binary predictions for
99 each location.</em></li>
100 <li>JNETSOL25,JNETSOL5,JNETSOL0<br> <em>Solvent
101 accessibility predictions - binary predictions of 25%, 5% or 0%
102 solvent accessibility.</em></li>
103 <li>JNetPRED<br> <em>The consensus prediction -
104 helices are marked as red tubes, and sheets as dark green
106 <li>JNetCONF<br> <em>The confidence estimate for the
107 prediction. High values mean high confidence. prediction -
108 helices are marked as red tubes, and sheets as dark green
110 <li>JNetALIGN<br> <em>Alignment based prediction -
111 helices are marked as red tubes, and sheets as dark green
113 <li>JNetHMM<br> <em>HMM profile based prediction -
114 helices are marked as red tubes, and sheets as dark green
116 <li>jpred<br> <em>Jpred prediction - helices are
117 marked as red tubes, and sheets as dark green arrows.</em></li>
118 <li>JNETPSSM<br> <em>PSSM based prediction - helices
119 are marked as red tubes, and sheets as dark green arrows.</em></li>
120 <li>JNETFREQ<br> <em>Amino Acid frequency based
121 prediction - helices are marked as red tubes, and sheets as dark
122 green arrows.</em></li>
123 <li>JNETJURY<br> <em>A '*' in this annotation
124 indicates that the JNETJURY was invoked to rationalise
125 significantly different primary predictions.</em></li>
128 <em>JNet annotation created in Jalview 2.8.2 and later versions
129 can be displayed on other alignments via the <a
130 href="../features/annotation.html#seqannots"
131 >Add reference annotation</a> Sequence ID popup menu option.
133 <em>As of Jalview 2.6, the Jnet service accessed accessed via the
134 'Secondary structure prediction' submenu should be considered a
135 legacy Jalview SOAP service, and will be replaced in the near future
136 by a JPred4 Rest service.</em>