|
1
|
1 <tool id="clustalw" name="ClustalW" version="0.1">
|
|
|
2 <description>multiple sequence alignment program for DNA or proteins</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="2.1">clustalw</requirement>
|
|
|
5 </requirements>
|
|
|
6 <command>
|
|
|
7 #if ($range.mode=="part")
|
|
|
8 clustalw2 -infile=$input -outfile=$output -OUTORDER=$out_order -RANGE=$range.seq_range_start,$range.seq_range_end
|
|
|
9 #elif ($range.mode=="complete")
|
|
|
10 clustalw2 -infile=$input -outfile=$output -OUTORDER=$out_order
|
|
|
11 #end if
|
|
|
12 #if ($outcontrol.outform=="clustal")
|
|
|
13 -SEQNOS=$outcontrol.out_seqnos
|
|
|
14 #end if
|
|
|
15 #if ($outcontrol.outform=="phylip")
|
|
|
16 -OUTPUT=PHYLIP
|
|
|
17 #end if
|
|
|
18 #if ($outcontrol.outform=="fasta")
|
|
|
19 -OUTPUT=FASTA
|
|
|
20 #end if
|
|
|
21 -TYPE=$dnarna 1>$outlog 2>&1
|
|
|
22 </command>
|
|
|
23 <inputs>
|
|
|
24 <page>
|
|
|
25 <param format="fasta" name="input" type="data" label="Fasta File" />
|
|
|
26 <param name="outname" label="Name for output files to make it easy to remember what you did" type="text" size="50" value="Clustal_run" />
|
|
|
27 <param name="dnarna" type="select" label="Data Type">
|
|
|
28 <option value="DNA" selected="True">DNA nucleotide sequences</option>
|
|
|
29 <option value="PROTEIN">Protein sequences</option>
|
|
|
30 </param>
|
|
|
31 <conditional name="outcontrol">
|
|
|
32 <param name="outform" type="select" label="Output alignment format">
|
|
|
33 <option value="clustal" selected="True">Native Clustal output format</option>
|
|
|
34 <option value="phylip">Phylip format</option>
|
|
|
35 <option value="fasta">Fasta format</option>
|
|
|
36 </param>
|
|
|
37 <when value="fasta" />
|
|
|
38 <when value="phylip" />
|
|
|
39 <when value="clustal">
|
|
|
40 <param name="out_seqnos" type="select" label="Show residue numbers in clustal format output">
|
|
|
41 <option value="ON">yes</option>
|
|
|
42 <option value="OFF" selected="true">no</option>
|
|
|
43 </param>
|
|
|
44 </when>
|
|
|
45 </conditional>
|
|
|
46 <param name="out_order" type="select" label="Output Order">
|
|
|
47 <option value="ALIGNED">aligned</option>
|
|
|
48 <option value="INPUT">same order as input file</option>
|
|
|
49 </param>
|
|
|
50
|
|
|
51 <conditional name="range">
|
|
|
52 <param name="mode" type="select" label="Output complete alignment (or specify part to output)">
|
|
|
53 <option value="complete">complete alignment</option>
|
|
|
54 <option value="part">only part of the alignment</option>
|
|
|
55 </param>
|
|
|
56 <when value="complete">
|
|
|
57 </when>
|
|
|
58 <when value="part">
|
|
|
59 <param name="seq_range_start" size="5" type="integer" value="1" label="start point" help="sequence range to write">
|
|
|
60 </param>
|
|
|
61 <param name="seq_range_end" size="5" type="integer" value="99999" label="end point" >
|
|
|
62 </param>
|
|
|
63 </when>
|
|
|
64 </conditional>
|
|
|
65 </page>
|
|
|
66 </inputs>
|
|
|
67 <outputs>
|
|
|
68 <data format="clustal" name="output" label="${outname}_output.${outcontrol.outform}">
|
|
|
69 <change_format>
|
|
|
70 <when input="outcontrol.outform" value="phylip" format="phylip" />
|
|
|
71 <when input="outcontrol.outform" value="fasta" format="fasta" />
|
|
|
72 </change_format>
|
|
|
73 </data>
|
|
|
74 <data format="txt" name="outlog" label="${outname}_clustal_log.txt"/>
|
|
|
75 </outputs>
|
|
|
76 <tests>
|
|
|
77 <test>
|
|
|
78 <param name="input" value="rgClustal_testin.fasta" />
|
|
|
79 <param name = "outname" value="" />
|
|
|
80 <param name = "outform" value="fasta" />
|
|
|
81 <param name = "dnarna" value="DNA" />
|
|
|
82 <param name = "mode" value="complete" />
|
|
|
83 <param name = "out_order" value="ALIGNED" />
|
|
|
84 <output name="output" file="rgClustal_testout.fasta" ftype="fasta" />
|
|
|
85 <output name="output" file="rgClustal_testout.log" ftype="txt" lines_diff="5" />
|
|
|
86 </test>
|
|
|
87 </tests>
|
|
|
88 <help>
|
|
|
89
|
|
|
90 **Note**
|
|
|
91
|
|
|
92 This tool allows you to run a multiple sequence alignment with ClustalW2 (see Clustsrc_) using the default options.
|
|
|
93
|
|
|
94 For a tutorial introduction, see ClustalW2_
|
|
|
95
|
|
|
96 You can align DNA or protein sequences in the input file which should be multiple sequences to be aligned in a fasta file
|
|
|
97
|
|
|
98 A log will be output to your history showing the output Clustal would normally write to standard output.
|
|
|
99
|
|
|
100 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
|
|
|
101 the output format, you can create a 'Logo' image using the Sequence Logo tool.
|
|
|
102
|
|
|
103 If Clustal format is chosen, you have the option of adding basepair counts to the output
|
|
|
104
|
|
|
105 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
|
|
|
106
|
|
|
107 ----
|
|
|
108
|
|
|
109 **Attribution**
|
|
|
110
|
|
|
111 Clustal attribution and associated documentation are available at Clustsrc_
|
|
|
112
|
|
|
113 The first iteration of this Galaxy wrapper was written by Hans-Rudolf Hotz - see Clustfirst_
|
|
|
114
|
|
|
115 It was modified by Ross Lazarus for the rgenetics project
|
|
|
116
|
|
|
117 This wrapper is now LGPL
|
|
|
118
|
|
|
119 .. _ClustalW2: http://www.ebi.ac.uk/2can/tutorials/protein/clustalw.html
|
|
|
120
|
|
|
121 .. _Clustsrc: http://www.clustal.org
|
|
|
122
|
|
|
123 .. _Clustfirst: http://lists.bx.psu.edu/pipermail/galaxy-dev/2010-November/003732.html
|
|
|
124
|
|
|
125 </help>
|
|
|
126
|
|
|
127 </tool>
|
|
|
128
|
