comparison cactus_cactus.xml @ 3:9422c5a87ee2 draft

"planemo upload for repository https://github.com/usegalaxy-au/tools-au commit a2c67f11b7e96be2babfdf8a60cb2e2eb181ffe9"
author galaxy-australia
date Tue, 20 Sep 2022 05:38:05 +0000
parents 8b67dd48fec1
children 3c8227556fdc
comparison
equal deleted inserted replaced
2:8b67dd48fec1 3:9422c5a87ee2
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="xrefs"/> 6 <expand macro="xrefs"/>
7 <expand macro="requirements"/> 7 <expand macro="requirements"/>
8 <command detect_errors="exit_code"><![CDATA[ 8 <command detect_errors="exit_code"><![CDATA[
9 ## Check the FASTA headers
10 ## This is only necessary in pangenome mode
11 #if $aln_mode.aln_mode_select == 'intraspecies':
12 #for $seq in $in_seqs:
13 if
14 #if $seq.fasta.is_of_type('fasta.gz'):
15 zgrep
16 #else
17 grep
18 #end if
19 "^>" $seq.fasta | grep -q "[[:space:]]" ; then
20 echo "Error parsing input FASTA." ;
21 echo "Pangenome mode fails if there are spaces in the header." ;
22 echo "Please remove them with the NormalizeFasta tool." ;
23 exit 1
24 ; fi &&
25 #end for
26 #end if
27
28 ## Set up seqfile 9 ## Set up seqfile
29 10
30 #if $aln_mode.aln_mode_select == 'interspecies': 11 #if $aln_mode.aln_mode_select == 'interspecies':
31 cat $aln_mode.in_tree >> seqfile.txt && 12 cat $aln_mode.in_tree >> seqfile.txt &&
32 #end if 13 #end if
188 <assert_contents> 169 <assert_contents>
189 <has_size value="7420424" delta="200000" /> 170 <has_size value="7420424" delta="200000" />
190 </assert_contents> 171 </assert_contents>
191 </output> 172 </output>
192 </test> 173 </test>
193 <!-- FASTA header --> 174 <!-- FASTA header with spaces (used to fail) -->
194 <test expect_exit_code="1" expect_failure="true"> 175 <test expect_num_outputs="1">
195 <conditional name="aln_mode"> 176 <conditional name="aln_mode">
196 <param name="aln_mode_select" value="intraspecies"/> 177 <param name="aln_mode_select" value="intraspecies"/>
197 </conditional> 178 </conditional>
198 <repeat name="in_seqs"> 179 <repeat name="in_seqs">
199 <param name="label" value="badheader1"/> 180 <param name="label" value="badheader1"/>
201 </repeat> 182 </repeat>
202 <repeat name="in_seqs"> 183 <repeat name="in_seqs">
203 <param name="label" value="badheader2"/> 184 <param name="label" value="badheader2"/>
204 <param name="fasta" value="bh2.fasta.gz"/> 185 <param name="fasta" value="bh2.fasta.gz"/>
205 </repeat> 186 </repeat>
187 <output name="out_hal">
188 <assert_contents>
189 <has_size value="3382274" delta="200000" />
190 </assert_contents>
191 </output>
206 </test> 192 </test>
207 </tests> 193 </tests>
208 <help><![CDATA[ 194 <help><![CDATA[
209 **What it does** 195 **What it does**
210 196
239 `minigraph <https://github.com/lh3/minigraph>`__ to generate a graph of 225 `minigraph <https://github.com/lh3/minigraph>`__ to generate a graph of
240 the input genomes and then use the graph to order the alignments. To use 226 the input genomes and then use the graph to order the alignments. To use
241 pangenome mode, select ‘Within-species’ in the ‘Alignment mode’ 227 pangenome mode, select ‘Within-species’ in the ‘Alignment mode’
242 dropdown. 228 dropdown.
243 229
244 ⚠️ To use pangenome mode, you will have to remove spaces from the headers in your FASTA file.
245 You can do this with the NormalizeFasta tool.
246
247 **Input** 230 **Input**
248 231
249 The developers recommend soft-masking your genomes with RepeatMasker 232 The developers recommend soft-masking your genomes with RepeatMasker
250 before running Cactus. RepeatMasker is available on Galaxy. 233 before running Cactus. RepeatMasker is available on Galaxy.
251 234