Mercurial > repos > abims-sbr > blastalign

comparison BlastAlign.xml @ 0:d0ae18156aa2 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/abims-sbr/adaptsearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
author abims-sbr
date Fri, 01 Feb 2019 10:25:52 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:d0ae18156aa2
1 <tool name="BlastAlign" id="blastalign" version="2.1">
2
3 <description>
4 Align the nucleic acid sequences using BLASTN
5 </description>
6
7 <macros>
8 <import>macros.xml</import>
9 </macros>
10
11 <requirements>
12 <expand macro="python_required" />
13 <requirement type="package" version="1.4">blastalign</requirement>
14 </requirements>
15
16 <stdio>
17 <exit_code range="1:" level="fatal" />
18 </stdio>
19
20 <command><![CDATA[
21 ln -s '$input' '$input.element_identifier'".fasta" &&
22
23 BlastAlign -i '$input.element_identifier'".fasta"
24 -m $advanced_option.m
25 #if $advanced_option.r != ""
26 -r $advanced_option.r
27 #end if
28 #if $advanced_option.x != ""
29 -x $advanced_option.x
30 #end if
31 -n $advanced_option.n
32 #if $advanced_option.s != 0
33 -s $advanced_option.s
34 #end if
35 &&
36 ln -s '$input.element_identifier'".fasta.phy" out.phy &&
37 ln -s '$input.element_identifier'".fasta.nxs" out.nxs
38 #if $output_format.value == "fasta"
39 && python $__tool_directory__/scripts/S01_phylip2fasta.py out.phy out.fasta
40 #end if
41
42 ]]></command>
43 <inputs>
44 <param name="input" type="data" format="fasta" label="Choose your file" help="A fasta file with nucleotides sequences" />
45
46 <section name="advanced_option" title="Blast advanced options" expanded="True">
47 <param argument="-m" type="integer" value="95" min="0" max="100" label="Proportion of gaps allowed in any one sequence in the final alignement" help="default = 95, i.e. only removing sequences with extremely short matches" />
48 <param argument="-r" type="text" area="True" size="1x20" label="Choose a reference sequence" help="default is to search for best candidate (if entered, the sequence will be extracted, written to a separate file, and blasted against the original input file)"/>
49 <param argument="-x" type="text" area="True" size="5x25" label="Choose the sequences to be excluded from this analysis" help="name of comma-separated sequences " />
50 <param argument="-n" type="boolean" checked="true" truevalue="T" falsevalue="F" label="Retain original names in output files" help="option F is to output the 15 character name abbreviations (stripped of potentially problematic characters) that is used in the program" />
51 <param argument="-s" type="integer" value="0" min="0" label="Number of sequences to be used in initial search for reference sequence" help="default (= 0) is to find the reference sequence by blasting all sequences against all sequences, only randomly subsampling when it thinks the blast output file might be too large" />
52 </section>
53
54 <param name="output_format" type="select" label="Output format" help="phylip, nexus, or fasta." >
55 <option value="fasta">fasta</option>
56 <option value="phylip">phylip</option>
57 <option value="nexus">nexus</option>
58 </param>
59 </inputs>
60
61 <outputs>
62 <data format="phylip" name="phy" from_work_dir="out.phy" label="Blastalign on ${input.name} in phylip">
63 <filter>output_format == "phylip"</filter>
64 </data>
65 <data format="nexus" name="nxs" from_work_dir="out.nxs" label="Blastalign on ${input.name} in nexus">
66 <filter>output_format == "nexus"</filter>
67 </data>
68 <data format="fasta" name="fasta" from_work_dir="out.fasta" label="Blastalign on ${input.name} in fasta">
69 <filter>output_format == "fasta"</filter>
70 </data>
71 </outputs>
72
73 <tests>
74 <test>
75 <param name="input" ftype="fasta" value="inputs/locus1_sp2.fasta" />
76 <section name="advanced_option">
77 <param name="m" value="95" />
78 <param name="r" value="" />
79 <param name="x" value="" />
80 <param name="n" value="False" />
81 <param name="s" value="0" />
82 </section>
83 <param name="output_format" value="fasta" />
84 <output name="fasta" value="outputs/locus1_sp2.fasta" />
85 </test>
86 <test>
87 <param name="input" ftype="fasta" value="inputs/locus1_sp3.fasta" />
88 <section name="advanced_option">
89 <param name="m" value="95" />
90 <param name="r" value="" />
91 <param name="x" value="" />
92 <param name="n" value="False" />
93 <param name="s" value="0" />
94 </section>
95 <param name="output_format" value="phylip" />
96 <output name="phy" value="outputs/locus1_sp3.phy" />
97 </test>
98 <test>
99 <param name="input" ftype="fasta" value="inputs/locus3_sp2.fasta" />
100 <section name="advanced_option">
101 <param name="m" value="95" />
102 <param name="r" value="" />
103 <param name="x" value="" />
104 <param name="n" value="False" />
105 <param name="s" value="0" />
106 </section>
107 <param name="output_format" value="nexus" />
108 <output name="nxs" value="outputs/locus3_sp2.nxs" />
109 </test>
110 <!--
111 <test>
112 <param name="input" ftype="fasta" value="inputs/locus8_sp2.fasta" />
113 <section name="advanced_option">
114 <param name="m" value="95" />
115 <param name="r" value="" />
116 <param name="x" value="" />
117 <param name="n" value="False" />
118 <param name="s" value="0" />
119 </section>
120 <param name="output_format" value="phylip" />
121 <output name="phy" value="outputs/locus8_sp2.phy" />
122 </test>
123 -->
124 <test>
125 <param name="input" ftype="fasta" value="inputs/locus8_sp2.fasta" />
126 <section name="advanced_option">
127 <param name="m" value="95" />
128 <param name="r" value="" />
129 <param name="x" value="" />
130 <param name="n" value="False" />
131 <param name="s" value="0" />
132 </section>
133 <param name="output_format" value="fasta" />
134 <output name="phy" value="outputs/locus8_sp2.fasta" />
135 </test>
136
137 <!--locus10_sp2.fasta locus1_sp3.fasta locus2_sp2.fasta locus3_sp2.fasta locus4_sp2.fasta locus5_sp2.fasta locus6_sp2.fasta locus7_sp2.fasta locus8_sp2.fasta locus9_sp2.fasta-->
138 </tests>
139
140 <help>
141 <![CDATA[
142
143 .. class:: infomark
144
145 **Authors** BlastAlign has been written by Robert Belshaw and Aris Katzourakis.
146
147 .. class:: infomark
148
149 **Galaxy integration** Julie Baffard and ABiMS TEAM, Roscoff Marine Station
150
151 | Contact support.abims@sb-roscoff.fr for any questions or concerns about the Galaxy implementation of this tool.
152 | Credits : Gildas le Corguillé, Misharl Monsoor, Victor Mataigne
153
154 --------
155
156 **Description**
157
158 BlastAlign takes a set of nucleic sequences in a file in fasta format and returns a multiple alignment (in Nexus and Phylip formats) using BLAST+. This Galaxy implementation works with dataset collections, which allows multiple parallels runs of BlastAlign at once on many files.
159
160 --------
161
162 **Parameters**
163
164 The choice of several parameters for the blast is possible.
165
166 **-m : Proportion of gaps allowed in any one sequence in the final alignement**
167 integer (between 0 and 100).
168 By default : 95%, i.e. only removes sequences with extremely short matches.
169 We find 50 the most useful.
170
171 **-r : Name of reference sequence**
172 text.
173 Default is searching for best candidate.
174 If entered, the sequence will be extracted, written to a separate file, and blasted against the original input file.
175
176 **-x : Name of sequences to be excluded from the analysis**
177 text.
178 names must be comma-separated.
179
180 **-n**
181 If checked : retain original names in output files.
182 If not checked : output the 15 character name abbreviations (stripped of potentially problematic characters) that is used in the tool.
183 Default : checked.
184
185 **-s : Number of sequences to be used in initial search for reference sequence**
186 integer (between 0 and total number of sequences).
187 Default : 0
188 Default is finding the reference sequence by blasting all sequences against all sequences, only randomly subsampling when it thinks the blast output file might be too large.
189
190 ** Output format :**
191 The user have the choice between three format (only one is returned per run) : fasta, phylip, and nexus.
192
193 --------
194
195 **Outputs**
196
197 The output format is
198
199 - 'Blastalign_on_{input.name}_phylip' :
200 the aligned sequences in Phylip format.
201
202 - 'Blastalign_on_{input.name}_nexus' :
203 the aligned sequences in Nexus format.
204
205 - 'Blastalign_on_{input_file}_fasta' :
206 the aligned sequences in Fasta format if the option "fasta format" is checked.
207
208 ---------
209
210 Changelog
211 ---------
212
213 **Version 2.1 - 17/01/2018**
214
215 - New parameter "output format"
216 - Applied some bugfixes and minor improvments
217
218 **Version 2.0 - 21/04/2017**
219
220 - NEW: BlastAlign will now be launched on one file at once. Although, it will manage a Dataset Collection to deal with numerous files.
221
222 **Version 1.0 - 13/04/2017**
223
224 - TEST: Add funtional test with planemo
225 - IMPROVEMENT: Use conda dependencies for blastalign, blast-legacy, perl, python
226
227 ]]>
228
229 </help>
230
231 <citations>
232 <citation type="doi">10.1093/bioinformatics/bth459</citation>
233 </citations>
234
235 </tool>
236