Mercurial > repos > iuc > rnaquast

comparison rna_quast.xml @ 3:a9edbe21bf47 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://git.ufz.de/lehmanju/rnaquast commit 5ba8cddaafd411e30baa19da0f93959ef5ccaca0"
author iuc
date Fri, 14 Jan 2022 18:42:15 +0000
parents 96f74538896e
children f9f2ad782d8f
comparison
equal deleted inserted replaced
2:96f74538896e 3:a9edbe21bf47
1 <tool id="rna_quast" name="rnaQUAST" version="@TOOL_VERSION@"> 1 <tool id="rna_quast" name="rnaQUAST" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
2 <description>A Quality Assessment Tool for De Novo Transcriptome Assemblies</description> 2 <description>A quality assessment tool for De Novo transcriptome assemblies</description>
3 <xrefs> 3 <xrefs>
4 <xref type="bio.tools">rnaQUAST</xref> 4 <xref type="bio.tools">rnaQUAST</xref>
5 </xrefs> 5 </xrefs>
6 <macros> 6 <macros>
7 <token name="@TOOL_VERSION@">2.2.1</token> 7 <token name="@TOOL_VERSION@">2.2.1</token>
8 <token name="@VERSION_SUFFIX@">1</token>
8 <xml name="element_matching_line" token_name="" token_expression=""> 9 <xml name="element_matching_line" token_name="" token_expression="">
9 <element name="@NAME@"> 10 <element name="@NAME@">
10 <assert_contents> 11 <assert_contents>
11 <has_line_matching expression="@EXPRESSION@" /> 12 <has_line_matching expression="@EXPRESSION@" />
12 </assert_contents> 13 </assert_contents>
90 <stdio> 91 <stdio>
91 <regex match="Traceback " source="both" level="fatal" description="rnaQuast failed" /> 92 <regex match="Traceback " source="both" level="fatal" description="rnaQuast failed" />
92 </stdio> 93 </stdio>
93 <command detect_errors="exit_code"><![CDATA[ 94 <command detect_errors="exit_code"><![CDATA[
94 #import re 95 #import re
95 #for $i in $in_fasta 96 #for $i in $transcripts
96 ln -s '$i' '${re.sub('[^\w\-.]', '_', i.element_identifier)}' && 97 ln -s '$i' '${re.sub('[^\w\-.]', '_', i.element_identifier)}' &&
97 #end for 98 #end for
98 #if $r 99 #if $r
99 #for $rf in $r 100 #for $rf in $r
100 ln -s '$rf' '${re.sub('[^\w\-.]', '_', rf.element_identifier)}' && 101 ln -s '$rf' '${re.sub('[^\w\-.]', '_', rf.element_identifier)}' &&
107 #end if 108 #end if
108 mkdir outputdir && 109 mkdir outputdir &&
109 rnaQUAST.py 110 rnaQUAST.py
110 --threads \${GALAXY_SLOTS:-1} 111 --threads \${GALAXY_SLOTS:-1}
111 --transcripts 112 --transcripts
112 #for $i in $in_fasta 113 #for $i in $transcripts
113 '${re.sub('[^\w\-.]', '_', i.element_identifier)}' 114 '${re.sub('[^\w\-.]', '_', i.element_identifier)}'
114 #end for 115 #end for
115 $strand_specific 116 $strand_specific
116 #if $r 117 #if $r
117 -r 118 -r
131 --min_alignment '$min_alignment' 132 --min_alignment '$min_alignment'
132 #if "pdf" not in $out_sr and "plots" not in $out_add 133 #if "pdf" not in $out_sr and "plots" not in $out_add
133 --no_plots 134 --no_plots
134 #end if 135 #end if
135 $blat 136 $blat
136 $busco_lineage 137 #if $busco_option.busco == 'true'
137 ##GeneMarkS-T is not available in conda $gene_mark 138 --busco $busco_option.lineage
139 #end if
140 ##$gene_mark
138 $meta 141 $meta
139 --lower_threshold $lower_threshold 142 --lower_threshold $lower_threshold
140 --upper_threshold $upper_threshold 143 --upper_threshold $upper_threshold
141 -o outputdir 144 -o outputdir
142 145
143 && mkdir details 146 && mkdir details
144 147
145 ## move per outputs that are generated for each input (outputdir/ASSEMBLER_output) 148 ## move per outputs that are generated for each input (outputdir/ASSEMBLER_output)
146 ## to a joint dir (details) to make them discoverable 149 ## to a joint dir (details) to make them discoverable
147 ## also remove "ASSEMBLER." prefixes from files (otherwise the test macros don't work) 150 ## also remove "ASSEMBLER." prefixes from files (otherwise the test macros don't work)
148 #for $i in $in_fasta 151 #for $i in $transcripts
149 #set basename = os.path.splitext(re.sub('[^\w\-.]', '_', $i.element_identifier))[0] 152 #set basename = os.path.splitext(re.sub('[^\w\-.]', '_', $i.element_identifier))[0]
150 && 153 &&
151 (for f in \$(find 'outputdir/'$basename'_output' -type f); 154 (for f in \$(find 'outputdir/'$basename'_output' -type f);
152 do 155 do
153 d=\$(dirname \$f | cut -d"/" -f2 | cut -d'_' -f1) && 156 d=\$(dirname \$f | cut -d"/" -f2 | cut -d'_' -f1) &&
159 ## the final `true` seems needed since otherwise the `;` at the end is swallowed 162 ## the final `true` seems needed since otherwise the `;` at the end is swallowed
160 && find details/ -name "*.list" -exec mv {} {}.txt \; 163 && find details/ -name "*.list" -exec mv {} {}.txt \;
161 && true 164 && true
162 ]]> </command> 165 ]]> </command>
163 <inputs> 166 <inputs>
164 <param name="in_fasta" type="data" format="fasta" multiple="true" label="Chromosomes/scaffolds file" /> 167 <param argument="--transcripts" type="data" format="fasta" multiple="true" label="Transcripts" help="File(s) with transcripts in FASTA format."/>
165 <param name="strand_specific" argument="-ss" type="boolean" truevalue="-ss" falsevalue="" checked="false" label="Strand-specific" /> 168 <param name="strand_specific" argument="-ss" type="boolean" truevalue="-ss" falsevalue="" checked="false" label="Strand-specific"
166 <param name="r" optional="true" argument="-r" type="data" format="fasta" multiple="true" label="Reference genome" /> 169 help="Set if transcripts were assembled using strand-specific RNA-Seq data in order to benefit from knowing whether the transcript originated from the + or - strand"/>
170 <param name="r" optional="true" argument="-r" type="data" format="fasta" multiple="true" label="Reference genome" help="File with reference genome containing all chromosomes/scaffolds in FASTA forma." />
167 <conditional name="gene_coordinates"> 171 <conditional name="gene_coordinates">
168 <param name="use_gtf" type="select" label="Use file with gene coordinates in GTF/GFF format?" help="We recommend to use files downloaded from GENCODE or Ensembl."> 172 <param name="use_gtf" type="select" label="Use file with gene coordinates in GTF/GFF format?" help="We recommend to use files downloaded from GENCODE or Ensembl.">
169 <option value="true" selected="true">Yes</option> 173 <option value="true" selected="true">Yes</option>
170 <option value="false">No</option> 174 <option value="false">No</option>
171 </param> 175 </param>
172 <when value="true"> 176 <when value="true">
173 <param name="gtf" argument="--gtf" type="data" format="gtf,gff,gff3" multiple="true" label="GTF/GFF file" /> 177 <param name="gtf" argument="--gtf" type="data" format="gtf,gff,gff3" multiple="true" label="GTF/GFF file" />
174 <param argument="--disable_infer_genes" type="boolean" truevalue="--disable_infer_genes" falsevalue="" checked="false" label=" GTF file contains genes records?" /> 178 <param argument="--disable_infer_genes" type="boolean" truevalue="--disable_infer_genes" falsevalue="" checked="false" label=" GTF file contains genes records?"
175 <param argument="--disable_infer_transcripts" type="boolean" truevalue="--disable_infer_transcripts" falsevalue="" checked="false" label="GTF file contains transcripts records?" /> 179 help="Use this option if your GTF file already contains genes records, otherwise gffutils will fix it. Note that gffutils may work for quite a long time"/>
180 <param argument="--disable_infer_transcripts" type="boolean" truevalue="--disable_infer_transcripts" falsevalue="" checked="false" label="GTF file contains transcripts records?" help="Is option if your GTF file already contains transcripts records, otherwise gffutils will fix it."/>
176 </when> 181 </when>
177 <when value="false"> 182 <when value="false">
178 </when> 183 </when>
179 </conditional> 184 </conditional>
180 <param argument="--prokaryote" type="boolean" truevalue="--prokaryote" falsevalue="" checked="false" label="Is genome prokararyotic?" /> 185 <param argument="--prokaryote" type="boolean" truevalue="--prokaryote" falsevalue="" checked="false" label="Is genome prokararyotic?" help="Use this option if the genome is prokaryotic."/>
181 <param argument="--min_alignment" type="integer" value="50" label="Minimal alignment length to be used" /> 186 <param argument="--min_alignment" type="integer" value="50" label="Minimal alignment length to be used" help="Default value is 50"/>
182 <param argument="--blat" type="boolean" truevalue="--blat" falsevalue="" checked="false" label="Run with BLAT alignment tool instead of GMAP?" /> 187 <param argument="--blat" type="boolean" truevalue="--blat" falsevalue="" checked="false" label="Run with BLAT alignment tool instead of GMAP?" help="Blat is especially useful for aligning long sequences and gapped mapping, which cannot be performed properly by other fast sequence mappers designed for short reads. " />
183 <param argument="--busco_lineage" type="boolean" truevalue="--busco_lineage" falsevalue="" checked="false" label="Run BUSCO tool?" help="The BUSCO tool detects core genes in the assembly. Use this option to provide path to the BUSCO lineage data (Eukaryota, Metazoa, Arthropoda, Vertebrata or Fungi)." /> 188 <conditional name="busco_option">
184 <!-- GeneMarkS-T is not available in conda <param argument="\-\-gene_mark" type="boolean" truevalue="\-\-gene_mark" falsevalue="" checked="false" label="Run with GeneMarkS-T gene prediction tool?"/>--> 189 <param argument="--busco" type="select" label="Run BUSCO tool?" help="BUSCO allows to detect core genes in the assembled transcripts">
185 <param argument="--meta" type="boolean" truevalue="--meta" falsevalue="" checked="false" label="Meta Transcriptome" help="Run quality asessment for Meta Transcriptome" /> 190 <option value="false">Disabled</option>
186 <param argument="--lower_threshold" type="integer" value="50" label="Lower threshold for x_assembled/covered/matched metrics." /> 191 <option value="true">Enabled</option>
187 <param argument="--upper_threshold" type="integer" value="95" label="Upper threshold for x_assembled/covered/matched metrics." /> 192 </param>
193 <when value="false"/>
194 <when value="true">
195 <param name="lineage" type="select" label="Lineage" help="Select a lineage for using BUSCO">
196 <option value="metazoa">Metazoa</option>
197 <option value="eukaryota">Eukaryota</option>
198 <option value="arthropoda">Arthropoda</option>
199 <option value="vertebrata">Vertebrata</option>
200 <option value="fungi">Fungi</option>
201 <option value="bacteria">Bacteria</option>
202 </param>
203 </when>
204 </conditional>
205 <!--param argument="-\-gene_mark" type="boolean" truevalue="-\-gene_mark" falsevalue="" checked="false" label="Run with GeneMarkS-T gene prediction tool?" help="GeneMarkS-T allows to predict genes in the assembled transcripts without reference genome"/-->
206 <param argument="--meta" type="boolean" truevalue="--meta" falsevalue="" checked="false" label="Meta Transcriptome" help="Run quality asessment for meta-transcriptome assemblies" />
207 <param argument="--lower_threshold" type="integer" value="50" label="Lower threshold for x-assembled/covered/matched metrics." />
208 <param argument="--upper_threshold" type="integer" value="95" label="Upper threshold for x-assembled/covered/matched metrics." />
188 <param name="out_sr" type="select" multiple="true" label="Short report formats"> 209 <param name="out_sr" type="select" multiple="true" label="Short report formats">
189 <option value="tsv" selected="true">tabular</option> 210 <option value="tsv" selected="true">tabular</option>
190 <option value="txt">txt</option> 211 <option value="txt">txt</option>
191 <option value="tex">tex</option> 212 <option value="tex">tex</option>
192 <option value="pdf" selected="true">pdf</option> 213 <option value="pdf" selected="true">pdf</option>
216 <collection name="list_logs" type="list" label="${tool.name} on ${on_string}: logs"> 237 <collection name="list_logs" type="list" label="${tool.name} on ${on_string}: logs">
217 <discover_datasets ext="txt" pattern="(?P&lt;name&gt;.+)\.log" directory="outputdir/logs/" visible="false" /> 238 <discover_datasets ext="txt" pattern="(?P&lt;name&gt;.+)\.log" directory="outputdir/logs/" visible="false" />
218 <filter>"logs" in out_add</filter> 239 <filter>"logs" in out_add</filter>
219 </collection> 240 </collection>
220 <!-- note the output filter of the next two outputs checks if there is 241 <!-- note the output filter of the next two outputs checks if there is
221 more than 1 input for in_fasta (for 1 its a HDA, for more list or HDAs) --> 242 more than 1 input for transcripts (for 1 its a HDA, for more list or HDAs) -->
222 <collection name="comparison_png" type="list" label="${tool.name} on ${on_string}: comparison plots"> 243 <collection name="comparison_png" type="list" label="${tool.name} on ${on_string}: comparison plots">
223 <discover_datasets ext="png" pattern="(?P&lt;name&gt;.+)\.png" directory="outputdir/comparison_output/" visible="false" recurse="true" /> 244 <discover_datasets ext="png" pattern="(?P&lt;name&gt;.+)\.png" directory="outputdir/comparison_output/" visible="false" recurse="true" />
224 <filter> isinstance(in_fasta, list) and "plots" in out_add</filter> 245 <filter> isinstance(transcripts, list) and "plots" in out_add</filter>
225 </collection> 246 </collection>
226 <collection name="comparison" type="list" label="${tool.name} on ${on_string}: comparison"> 247 <collection name="comparison" type="list" label="${tool.name} on ${on_string}: comparison">
227 <discover_datasets ext="txt" pattern="(?P&lt;name&gt;.+)\.txt" directory="outputdir/comparison_output/" visible="false" recurse="true" /> 248 <discover_datasets ext="txt" pattern="(?P&lt;name&gt;.+)\.txt" directory="outputdir/comparison_output/" visible="false" recurse="true" />
228 <filter> isinstance(in_fasta, list) and "comparison" in out_add</filter> 249 <filter> isinstance(transcripts, list) and "comparison" in out_add</filter>
229 </collection> 250 </collection>
230 <collection name="details" type="list:list" label="${tool.name} on ${on_string}: detailed output"> 251 <collection name="details" type="list:list" label="${tool.name} on ${on_string}: detailed output">
231 <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_____(?P&lt;identifier_1&gt;.+)\.(?P&lt;ext&gt;txt)" directory="details/" visible="false" /> 252 <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_____(?P&lt;identifier_1&gt;.+)\.(?P&lt;ext&gt;txt)" directory="details/" visible="false" />
232 <filter>"details" in out_add</filter> 253 <filter>"details" in out_add</filter>
233 </collection> 254 </collection>
236 <filter>"details_plots" in out_add</filter> 257 <filter>"details_plots" in out_add</filter>
237 </collection> 258 </collection>
238 </outputs> 259 </outputs>
239 <tests> 260 <tests>
240 <test expect_num_outputs="7"> 261 <test expect_num_outputs="7">
241 <param name="in_fasta" value="idba.fasta,Trinity.fasta" ftype="fasta" /> 262 <param name="transcripts" value="idba.fasta,Trinity.fasta" ftype="fasta" />
242 <param name="r" value="Saccharomyces_cerevisiae.R64-1-1.75.dna.toplevel.fa" ftype="fasta" /> 263 <param name="r" value="Saccharomyces_cerevisiae.R64-1-1.75.dna.toplevel.fa" ftype="fasta" />
243 <conditional name="gene_coordinates"> 264 <conditional name="gene_coordinates">
244 <param name="use_gtf" value="true" /> 265 <param name="use_gtf" value="true" />
245 <param name="gtf" value="Saccharomyces_cerevisiae.R64-1-1.75.gtf" ftype="gtf" /> 266 <param name="gtf" value="Saccharomyces_cerevisiae.R64-1-1.75.gtf" ftype="gtf" />
246 <param name="disable_infer_genes" value="true" /> 267 <param name="disable_infer_genes" value="true" />
258 <expand macro="details_output_test" assembler="Trinity" /> 279 <expand macro="details_output_test" assembler="Trinity" />
259 <expand macro="details_output_test" assembler="idba" /> 280 <expand macro="details_output_test" assembler="idba" />
260 </output_collection> 281 </output_collection>
261 </test> 282 </test>
262 <test expect_num_outputs="6"> 283 <test expect_num_outputs="6">
263 <param name="in_fasta" value="Trinity.fasta" ftype="fasta" /> 284 <param name="transcripts" value="Trinity.fasta" ftype="fasta" />
264 <conditional name="gene_coordinates"> 285 <conditional name="gene_coordinates">
265 <param name="use_gtf" value="false" /> 286 <param name="use_gtf" value="false" />
266 </conditional> 287 </conditional>
267 <param name="min_alignment" value="30" /> 288 <param name="min_alignment" value="30" />
268 <param name="lower_threshold" value="45" /> 289 <param name="lower_threshold" value="45" />
282 <element name="Trinity"> 303 <element name="Trinity">
283 <expand macro="element_has_text" name="Nx" text="PNG" /> 304 <expand macro="element_has_text" name="Nx" text="PNG" />
284 <expand macro="element_has_text" name="transcript_length" text="PNG" /> 305 <expand macro="element_has_text" name="transcript_length" text="PNG" />
285 </element> 306 </element>
286 </output_collection> 307 </output_collection>
308 </test>
309 <test expect_num_outputs="6">
310 <param name="transcripts" value="Trinity.fasta" ftype="fasta" />
311 <conditional name="gene_coordinates">
312 <param name="use_gtf" value="false" />
313 </conditional>
314 <param name="min_alignment" value="30" />
315 <param name="lower_threshold" value="45" />
316 <param name="upper_threshold" value="95" />
317 <param name="out_sr" value="txt,tex,tsv,pdf" />
318 <param name="out_add" value="logs,details_plots" />
319 <conditional name="busco_option">
320 <param name="busco" value="true"/>
321 <param name="lineage" value="metazoa"/>
322 </conditional>
323 <expand macro="pdf_output_test" />
324 <expand macro="tex_output_test" />
325 <expand macro="tsv_output_test" />
326 <expand macro="txt_output_test" />
327 <output_collection name="list_logs" type="list">
328 <expand macro="element_has_text" name="Trinity.GeneMarkS_T.err" text="" />
329 <expand macro="element_matching_line" name="rnaQUAST" expression="Thank you for using rnaQUAST!" />
330 </output_collection>
331 <output_collection name="details_png" type="list:list" count="1">
332 <element name="Trinity">
333 <expand macro="element_has_text" name="Nx" text="PNG" />
334 <expand macro="element_has_text" name="transcript_length" text="PNG" />
335 </element>
336 </output_collection>
337 <assert_command>
338 <has_text text="--busco metazoa"/>
339 </assert_command>
287 </test> 340 </test>
288 </tests> 341 </tests>
289 <help><![CDATA[ 342 <help><![CDATA[
290 **What is rnaQUAST** 343 **What is rnaQUAST**
291 - a quality assessment tool for de novo transcriptome assemblies 344 - a quality assessment tool for de novo transcriptome assemblies