annotate tools/protein_analysis/signalp3.xml @ 23:1f7678c1f4ad draft

Uploaded v0.2.5 take 7, using RST for README file; development moved to GitHub
author peterjc
date Tue, 17 Sep 2013 12:05:12 -0400
parents 90e3d02f8013
children 41a42022f815
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
17
af3174637834 Uploaded v0.2.5 preview 1, adding links to Tool Shed entry
peterjc
parents: 8
diff changeset
1 <tool id="signalp3" name="SignalP 3.0" version="0.0.12">
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
2 <description>Find signal peptides in protein sequences</description>
7
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
3 <!-- If job splitting is enabled, break up the query file into parts -->
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
4 <!-- Using 2000 chunks meaning 4 threads doing 500 each is ideal -->
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
5 <parallelism method="basic" split_inputs="fasta_file" split_mode="to_size" split_size="2000" merge_outputs="tabular_file"></parallelism>
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
6 <command interpreter="python">
7
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
7 signalp3.py $organism $truncate "\$NSLOTS" $fasta_file $tabular_file
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
8 ##Set the number of threads in the runner entry in universe_wsgi.ini
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
9 ##which (on SGE at least) will set the $NSLOTS environment variable.
19
4cd848c5590b Uploaded v0.2.5 preview 3, use $NSLOTS in the PSORT wrappers.
peterjc
parents: 17
diff changeset
10 ##If the environment variable isn't set, get "", and the python wrapper
4cd848c5590b Uploaded v0.2.5 preview 3, use $NSLOTS in the PSORT wrappers.
peterjc
parents: 17
diff changeset
11 ##defaults to four threads.
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
12 </command>
7
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
13 <stdio>
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
14 <!-- Anything other than zero is an error -->
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
15 <exit_code range="1:" />
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
16 <exit_code range=":-1" />
5e62aefb2918 Uploaded v0.1.2 to Test Tool Shed
peterjc
parents: 6
diff changeset
17 </stdio>
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
18 <inputs>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
19 <param name="fasta_file" type="data" format="fasta" label="FASTA file of protein sequences"/>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
20 <param name="organism" type="select" display="radio" label="Organism">
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
21 <option value="euk">Eukaryote</option>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
22 <option value="gram+">Gram positive</option>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
23 <option value="gram-">Gram negative</option>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
24 </param>
4
1426b2bae76d Migrated tool version 0.0.7 from old tool shed archive to new tool shed repository
peterjc
parents: 3
diff changeset
25 <param name="truncate" type="integer" label="Truncate sequences to this many amino acids" value="70" help="Use zero for no truncation, maximum value 6000">
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
26 <validator type="in_range" min="0" max="6000" message="Truncation value should be at most 6000. Use zero for no truncation."/>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
27 </param>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
28 </inputs>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
29 <outputs>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
30 <data name="tabular_file" format="tabular" label="SignalP $organism results" />
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
31 </outputs>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
32 <requirements>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
33 <requirement type="binary">signalp</requirement>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
34 </requirements>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
35 <tests>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
36 <test>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
37 <param name="fasta_file" value="four_human_proteins.fasta" ftype="fasta"/>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
38 <param name="organism" value="euk"/>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
39 <param name="truncate" value="0"/>
1
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
40 <output name="tabular_file" file="four_human_proteins.signalp3.tabular" ftype="tabular"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
41 </test>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
42 <test>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
43 <param name="fasta_file" value="empty.fasta" ftype="fasta"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
44 <param name="organism" value="euk"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
45 <param name="truncate" value="60"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
46 <output name="tabular_file" file="empty_signalp3.tabular" ftype="tabular"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
47 </test>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
48 <test>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
49 <param name="fasta_file" value="empty.fasta" ftype="fasta"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
50 <param name="organism" value="gram+"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
51 <param name="truncate" value="80"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
52 <output name="tabular_file" file="empty_signalp3.tabular" ftype="tabular"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
53 </test>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
54 <test>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
55 <param name="fasta_file" value="empty.fasta" ftype="fasta"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
56 <param name="organism" value="gram-"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
57 <param name="truncate" value="0"/>
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
58 <output name="tabular_file" file="empty_signalp3.tabular" ftype="tabular"/>
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
59 </test>
4
1426b2bae76d Migrated tool version 0.0.7 from old tool shed archive to new tool shed repository
peterjc
parents: 3
diff changeset
60 <test>
1426b2bae76d Migrated tool version 0.0.7 from old tool shed archive to new tool shed repository
peterjc
parents: 3
diff changeset
61 <param name="fasta_file" value="rxlr_win_et_al_2007.fasta" ftype="fasta"/>
1426b2bae76d Migrated tool version 0.0.7 from old tool shed archive to new tool shed repository
peterjc
parents: 3
diff changeset
62 <param name="organism" value="euk"/>
1426b2bae76d Migrated tool version 0.0.7 from old tool shed archive to new tool shed repository
peterjc
parents: 3
diff changeset
63 <param name="truncate" value="70"/>
1426b2bae76d Migrated tool version 0.0.7 from old tool shed archive to new tool shed repository
peterjc
parents: 3
diff changeset
64 <output name="tabular_file" file="rxlr_win_et_al_2007_sp3.tabular" ftype="tabular"/>
1426b2bae76d Migrated tool version 0.0.7 from old tool shed archive to new tool shed repository
peterjc
parents: 3
diff changeset
65 </test>
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
66 </tests>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
67 <help>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
68
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
69 **What it does**
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
70
1
9a8a7f680dd6 Migrated tool version 0.0.3 from old tool shed archive to new tool shed repository
peterjc
parents: 0
diff changeset
71 This calls the SignalP v3.0 tool for prediction of signal peptides, which uses both a Neural Network (NN) and Hidden Markov Model (HMM) to produce two sets of scores.
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
72
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
73 The input is a FASTA file of protein sequences, and the output is tabular with twenty columns (one row per protein):
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
74
8
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
75 ====== =================================================
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
76 Column Description
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
77 ------ -------------------------------------------------
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
78 1 Sequence identifier
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
79 2-14 Neural Network (NN) predictions (13 columns)
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
80 15-20 Hidden Markov Model (HMM) predictions (6 columns)
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
81 ====== =================================================
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
82
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
83 Internally the input FASTA file is divided into parts (to allow multiple processors to be used), and the proteins truncated as specified (see below). The raw output from SignalP is then reformatted into a tabular layout suitable for Galaxy (see below).
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
84
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
85 **Neural Network Scores**
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
86
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
87 For each organism class (Eukaryote, Gram-negative and Gram-positive), two different neural networks are used, one for predicting the actual signal peptide and one for predicting the position of the signal peptidase I (SPase I) cleavage site.
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
88
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
89 The NN output comprises three different scores (C-max, S-max and Y-max) and two scores derived from them (S-mean and D-score).
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
90
8
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
91 ====== ======= ===============================================================
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
92 Column Name Description
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
93 ------ ------- ---------------------------------------------------------------
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
94 2-4 C-score The C-score is the 'cleavage site' score. For each position in
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
95 the submitted sequence, a C-score is reported, which should
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
96 only be significantly high at the cleavage site. Confusion is
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
97 often seen with the position numbering of the cleavage site.
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
98 When a cleavage site position is referred to by a single number,
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
99 the number indicates the first residue in the mature protein,
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
100 meaning, that a predicted cleavage site between amino acid 26-27
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
101 is reported as 27, corresponding to the mature protein starting
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
102 at (and including) position 27.
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
103 ------ ------- ---------------------------------------------------------------
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
104 5-7 S-score The S-score for the signal peptide prediction is calculated for
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
105 every single amino acid position in the submitted sequence (not
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
106 shown in the output via Galaxy), with high scores indicating
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
107 that the corresponding amino acid is part of a signal peptide,
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
108 and low scores indicating that the amino acid is part of a
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
109 mature protein.
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
110 ------ ------- ---------------------------------------------------------------
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
111 8-10 Y-max Y-max is a derivative of the C-score combined with the S-score
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
112 resulting in a better cleavage site prediction than the raw
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
113 C-score alone. This is due to the fact that multiple high-peaking
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
114 C-scores can be found in one sequence, where only one is the
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
115 true cleavage site. The cleavage site is assigned from the
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
116 Y-score where the slope of the S-score is steep and a
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
117 significant C-score is found.
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
118 ------ ------- ---------------------------------------------------------------
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
119 11-12 S-mean The S-mean is the average of the S-score, ranging from the
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
120 N-terminal amino acid to the amino acid assigned with the
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
121 highest Y-max score, thus the S-mean score is calculated for
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
122 the length of the predicted signal peptide. The S-mean score
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
123 was in SignalP version 2.0 used as the criteria for
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
124 discrimination of secretory and non-secretory proteins.
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
125 ------ ------- ---------------------------------------------------------------
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
126 13-14 D-score The D-score was introduced in SignalP version 3.0 and is a
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
127 simple average of the S-mean and Y-max score. The score shows
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
128 superior discrimination performance of secretory and
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
129 non-secretory proteins to that of the S-mean score which was
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
130 used in SignalP version 1 and 2.
391a142c1e60 Uploaded
peterjc
parents: 7
diff changeset
131 ====== ======= ===============================================================
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
132
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
133 For non-secretory proteins all the scores represented in the SignalP3-NN output should ideally be very low.
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
134
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
135 **Hidden Markov Model Scores**
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
136
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
137 The hidden Markov model calculates the probability of whether the submitted sequence contains a signal peptide or not. The eukaryotic HMM model also reports the probability of a signal anchor, previously named uncleaved signal peptides. Furthermore, the cleavage site is assigned by a probability score together with scores for the n-region, h-region, and c-region of the signal peptide, if such one is found.
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
138
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
139 The 'type' column uses 'S' for a signal peptide (i.e. secretory protein) and 'Q' for non-secretory protein.
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
140
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
141 **Notes**
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
142
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
143 The raw output 'short' output from TMHMM v2.0 looks something like this (21 columns space separated - shown here formatted nicely). Notice that the identifiers are given twice, the first time truncated (as part of the NN predictions) and the second time in full (in the HMM predictions).
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
144
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
145 ==================== ===== === = ===== === = ===== === = ===== = ===== = =================================== = ===== === = ===== =
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
146 # SignalP-NN euk predictions # SignalP-HMM euk predictions
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
147 ----------------------------------------------------------------------------- ------------------------------------------------------------
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
148 # name Cmax pos ? Ymax pos ? Smax pos ? Smean ? D ? # name ! Cmax pos ? Sprob ?
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
149 gi|2781234|pdb|1JLY| 0.061 17 N 0.043 17 N 0.199 1 N 0.067 N 0.055 N gi|2781234|pdb|1JLY|B Q 0.000 17 N 0.000 N
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
150 gi|4959044|gb|AAD342 0.099 191 N 0.012 38 N 0.023 12 N 0.014 N 0.013 N gi|4959044|gb|AAD34209.1|AF069992_1 Q 0.000 0 N 0.000 N
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
151 gi|671626|emb|CAA856 0.139 381 N 0.020 8 N 0.121 4 N 0.067 N 0.044 N gi|671626|emb|CAA85685.1| Q 0.000 0 N 0.000 N
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
152 gi|3298468|dbj|BAA31 0.208 24 N 0.184 38 N 0.980 32 Y 0.613 Y 0.398 N gi|3298468|dbj|BAA31520.1| Q 0.066 24 N 0.139 N
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
153 ==================== ===== === = ===== === = ===== === = ===== = ===== = =================================== = ===== === = ===== =
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
154
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
155 In order to make this easier to use in Galaxy, the wrapper script simplifies this to remove the redundant column and use tabs for separation. It also includes a header line with unique column names.
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
156
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
157 =================================== ============= =========== ============ ============= =========== ============ ============= =========== ============ ============== ============= ========== ========= ======== ============== ============ ============= =============== ==============
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
158 #ID NN_Cmax_score NN_Cmax_pos NN_Cmax_pred NN_Ymax_score NN_Ymax_pos NN_Ymax_pred NN_Smax_score NN_Smax_pos NN_Smax_pred NN_Smean_score NN_Smean_pred NN_D_score NN_D_pred HMM_type HMM_Cmax_score HMM_Cmax_pos HMM_Cmax_pred HMM_Sprob_score HMM_Sprob_pred
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
159 gi|2781234|pdb|1JLY|B 0.061 17 N 0.043 17 N 0.199 1 N 0.067 N 0.055 N Q 0.000 17 N 0.000 N
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
160 gi|4959044|gb|AAD34209.1|AF069992_1 0.099 191 N 0.012 38 N 0.023 12 N 0.014 N 0.013 N Q 0.000 0 N 0.000 N
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
161 gi|671626|emb|CAA85685.1| 0.139 381 N 0.020 8 N 0.121 4 N 0.067 N 0.044 N Q 0.000 0 N 0.000 N
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
162 gi|3298468|dbj|BAA31520.1| 0.208 24 N 0.184 38 N 0.980 32 Y 0.613 Y 0.398 N Q 0.066 24 N 0.139 N
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
163 =================================== ============= =========== ============ ============= =========== ============ ============= =========== ============ ============== ============= ========== ========= ======== ============== ============ ============= =============== ==============
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
164
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
165 **Truncation**
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
166
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
167 Signal peptides are found at the start of a protein, so there is limited value in providing the full length sequence, and providing the full sequence slows down the analysis. Furthermore, SignalP has an upper bound on the sequence length it will accept (6000bp). Thus for practical reasons it is useful to truncate the proteins before passing them to SignalP. However, the precise point they are truncated does have a small influence on some score values, and thus to the results.
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
168
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
169 **References**
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
170
20
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
171 If you use this Galaxy tool in work leading to a scientific publication please
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
172 cite the following papers:
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
173
22
90e3d02f8013 Uploaded v0.2.5 preview 6, can use accents in <help> RST
peterjc
parents: 20
diff changeset
174 Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
20
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
175 Galaxy tools and workflows for sequence analysis with applications
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
176 in molecular plant pathology. PeerJ 1:e167
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
177 http://dx.doi.org/10.7717/peerj.167
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
178
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
179 Bendtsen, Nielsen, von Heijne, and Brunak (2004).
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
180 Improved prediction of signal peptides: SignalP 3.0.
20
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
181 J. Mol. Biol., 340:783-795.
6
39a6e46cdda3 Migrated tool version 0.0.9 from old tool shed archive to new tool shed repository
peterjc
parents: 4
diff changeset
182 http://dx.doi.org/10.1016/j.jmb.2004.05.028
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
183
20
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
184 Nielsen, Engelbrecht, Brunak and von Heijne (1997).
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
185 Identification of prokaryotic and eukaryotic signal peptides and prediction of their cleavage sites.
20
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
186 Protein Engineering, 10:1-6.
6
39a6e46cdda3 Migrated tool version 0.0.9 from old tool shed archive to new tool shed repository
peterjc
parents: 4
diff changeset
187 http://dx.doi.org/10.1093/protein/10.1.1
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
188
20
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
189 Nielsen and Krogh (1998).
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
190 Prediction of signal peptides and signal anchors by a hidden Markov model.
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
191 Proceedings of the Sixth International Conference on Intelligent Systems for Molecular Biology (ISMB 6),
20
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
192 AAAI Press, Menlo Park, California, pp. 122-130.
6
39a6e46cdda3 Migrated tool version 0.0.9 from old tool shed archive to new tool shed repository
peterjc
parents: 4
diff changeset
193 http://www.ncbi.nlm.nih.gov/pubmed/9783217
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
194
20
a538e182fab3 Uploaded v0.2.5 preview 4, adding Cock et al. 2003 citation information.
peterjc
parents: 19
diff changeset
195 See also http://www.cbs.dtu.dk/services/SignalP-3.0/output.php
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
196
17
af3174637834 Uploaded v0.2.5 preview 1, adding links to Tool Shed entry
peterjc
parents: 8
diff changeset
197 This wrapper is available to install into other Galaxy Instances via the Galaxy
af3174637834 Uploaded v0.2.5 preview 1, adding links to Tool Shed entry
peterjc
parents: 8
diff changeset
198 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/tmhmm_and_signalp
0
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
199 </help>
a2eeeaa6f75e Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
peterjc
parents:
diff changeset
200 </tool>