0
|
1 <tool id="clustalw" name="ClustalW" version="0.1">
|
|
2 <requirements>
|
|
3 <requirement type="package" version="2.1">clustalw2</requirement>
|
|
4 </requirements>
|
|
5 <description>multiple sequence alignment program for DNA or proteins</description>
|
|
6 <command interpreter="python">
|
|
7 rgClustalw.py -i "$input" -o "$output" -s "$out_order" -l "$outlog" -t "$outname" -d "$dnarna"
|
|
8 #if ($range.mode=="part")
|
|
9 -b "$range.seq_range_start" -e "$range.seq_range_end"
|
|
10 #end if
|
|
11 #if ($outcontrol.outform=="clustal")
|
|
12 -f "CLUSTAL"
|
|
13 #if ($outcontrol.out_seqnos=="ON")
|
|
14 -q "ON"
|
|
15 #end if
|
|
16 #end if
|
|
17 #if ($outcontrol.outform=="phylip")
|
|
18 -f "PHYLIP"
|
|
19 #end if
|
|
20 #if ($outcontrol.outform=="fasta")
|
|
21 -f "FASTA"
|
|
22 #end if
|
|
23 </command>
|
|
24 <inputs>
|
|
25 <page>
|
|
26 <param format="fasta" name="input" type="data" label="Fasta File" />
|
|
27 <param name="outname" label="Name for output files to make it easy to remember what you did" type="text" size="50" value="Clustal_run" />
|
|
28 <param name="dnarna" type="select" label="Data Type">
|
|
29 <option value="DNA" selected="True">DNA nucleotide sequences</option>
|
|
30 <option value="PROTEIN">Protein sequences</option>
|
|
31 </param>
|
|
32 <conditional name="outcontrol">
|
|
33 <param name="outform" type="select" label="Output alignment format">
|
|
34 <option value="clustal" selected="True">Native Clustal output format</option>
|
|
35 <option value="phylip">Phylip format</option>
|
|
36 <option value="fasta">Fasta format</option>
|
|
37 </param>
|
|
38 <when value="fasta" />
|
|
39 <when value="phylip" />
|
|
40 <when value="clustal">
|
|
41 <param name="out_seqnos" type="select" label="Show residue numbers in clustal format output">
|
|
42 <option value="ON">yes</option>
|
|
43 <option value="OFF" selected="true">no</option>
|
|
44 </param>
|
|
45 </when>
|
|
46 </conditional>
|
|
47 <param name="out_order" type="select" label="Output Order">
|
|
48 <option value="ALIGNED">aligned</option>
|
|
49 <option value="INPUT">same order as input file</option>
|
|
50 </param>
|
|
51
|
|
52 <conditional name="range">
|
|
53 <param name="mode" type="select" label="Output complete alignment (or specify part to output)">
|
|
54 <option value="complete">complete alignment</option>
|
|
55 <option value="part">only part of the alignment</option>
|
|
56 </param>
|
|
57 <when value="complete">
|
|
58 </when>
|
|
59 <when value="part">
|
|
60 <param name="seq_range_start" size="5" type="integer" value="1" label="start point" help="sequence range to write">
|
|
61 </param>
|
|
62 <param name="seq_range_end" size="5" type="integer" value="99999" label="end point" >
|
|
63 </param>
|
|
64 </when>
|
|
65 </conditional>
|
|
66 </page>
|
|
67 </inputs>
|
|
68 <outputs>
|
|
69 <data format="clustal" name="output" label="${outname}_output.${outcontrol.outform}">
|
|
70 <change_format>
|
|
71 <when input="outcontrol.outform" value="phylip" format="phylip" />
|
|
72 <when input="outcontrol.outform" value="fasta" format="fasta" />
|
|
73 </change_format>
|
|
74 </data>
|
|
75 <data format="txt" name="outlog" label="${outname}_clustal_log.txt"/>
|
|
76 </outputs>
|
|
77 <tests>
|
|
78 <test>
|
|
79 <param name="input" value="rgClustal_testin.fasta" />
|
|
80 <param name="outname" value="" />
|
|
81 <param name="outform" value="fasta" />
|
|
82 <param name="dnarna" value="DNA" />
|
|
83 <param name="mode" value="complete" />
|
|
84 <param name="out_order" value="ALIGNED" />
|
|
85 <output name="output" file="rgClustal_testout.fasta" ftype="fasta" />
|
|
86 <output name="outlog" file="rgClustal_testout.log" ftype="txt" lines_diff="5" />
|
|
87 </test>
|
|
88 </tests>
|
|
89 <help>
|
|
90
|
|
91 **Note**
|
|
92
|
|
93 This tool allows you to run a multiple sequence alignment with ClustalW2 (see Clustsrc_) using the default options.
|
|
94
|
|
95 For a tutorial introduction, see ClustalW2_
|
|
96
|
|
97 You can align DNA or protein sequences in the input file which should be multiple sequences to be aligned in a fasta file
|
|
98
|
|
99 A log will be output to your history showing the output Clustal would normally write to standard output.
|
|
100
|
|
101 The alignments will appear as a clustal format file or optionally, as phylip or fasta format files in your history. If you choose fasta as
|
|
102 the output format, you can create a 'Logo' image using the Sequence Logo tool.
|
|
103
|
|
104 If Clustal format is chosen, you have the option of adding basepair counts to the output
|
|
105
|
|
106 A subsequence of the alignment can be output by setting the Output complete parameter to "Partial" and defining the offset and end of the subsequence to be output
|
|
107
|
|
108 ----
|
|
109
|
|
110 **Attribution**
|
|
111
|
|
112 Clustal attribution and associated documentation are available at Clustsrc_
|
|
113
|
|
114 The first iteration of this Galaxy wrapper was written by Hans-Rudolf Hotz - see Clustfirst_
|
|
115
|
|
116 It was modified by Ross Lazarus for the rgenetics project - tests and some additional parameters were added
|
|
117
|
|
118 This wrapper is released licensed under the LGPL_
|
|
119
|
|
120 .. _ClustalW2: http://www.ebi.ac.uk/2can/tutorials/protein/clustalw.html
|
|
121
|
|
122 .. _Clustsrc: http://www.clustal.org
|
|
123
|
|
124 .. _Clustfirst: http://lists.bx.psu.edu/pipermail/galaxy-dev/2010-November/003732.html
|
|
125
|
|
126 .. _LGPL: http://www.gnu.org/copyleft/lesser.html
|
|
127
|
|
128 </help>
|
|
129
|
|
130 </tool>
|
|
131
|