Mercurial > repos > iuc > circexplorer2
comparison circexplorer2.xml @ 0:465d6578b4d0 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circexplorer2 commit fe03991cd7c43f5266314d1fb9e4108f1ab102e8
author | iuc |
---|---|
date | Fri, 26 Aug 2022 22:43:38 +0000 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:465d6578b4d0 |
---|---|
1 <tool id="circexplorer2" name="CIRCexplorer2" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05"> | |
2 <description>circular RNA analysis</description> | |
3 <macros> | |
4 <import>macros.xml</import> | |
5 </macros> | |
6 <expand macro="requirements" /> | |
7 <expand macro='xrefs'/> | |
8 <command detect_errors="exit_code"><![CDATA[ | |
9 #if $mode.selector == 'align' | |
10 mkdir -p reads && | |
11 #set file_paths = [] | |
12 #for $i,$input_file in enumerate($mode.fastq) | |
13 #set $fname = 'file' + str($i) + "." + $input_file.ext | |
14 #set $file_path = 'reads/' + $fname | |
15 ln -s '$input_file' '$file_path' && | |
16 $file_paths.append($file_path) | |
17 #end for | |
18 CIRCexplorer2 align | |
19 @threads@ | |
20 --gtf '$mode.gtf' | |
21 -g '$mode.genome' | |
22 --fastq #echo ','.join($file_paths)# | |
23 $mode.bw | |
24 $mode.scale | |
25 $mode.skip_tophat | |
26 $mode.skip_tophat_fusion | |
27 && tar -zcvf alignment.tgz './alignment' | |
28 #else if $mode.selector == 'parse' | |
29 CIRCexplorer2 parse | |
30 -t $mode.aligner.selector | |
31 $mode.aligner.fusion_file | |
32 #if $mode.aligner.selector == 'TopHat-Fusion' | |
33 $mode.aligner.pe | |
34 #end if | |
35 $mode.aligner.f | |
36 #else if $mode.selector == 'annotate' | |
37 ln -s $mode.genome reference_genome.fa && | |
38 CIRCexplorer2 annotate | |
39 -r $mode.ref | |
40 -g reference_genome.fa | |
41 -b $mode.bed | |
42 $mode.no_fix | |
43 $mode.low_confidence | |
44 #else if $mode.selector == 'assemble' | |
45 tar -zxf $mode.tophat && | |
46 CIRCexplorer2 assemble | |
47 @threads@ | |
48 -r $mode.ref | |
49 -m ./alignment | |
50 $mode.remove_rRNA | |
51 && tar -zcvf assemble.tgz './assemble' | |
52 #else | |
53 ln -s '$mode.genome' reference_genome.fa && | |
54 #if $mode.assemble_file.ext.endswith(".gz") | |
55 tar -zxf $mode.assemble_file && | |
56 #else | |
57 tar -xf $mode.assemble_file && | |
58 #end if | |
59 #if $mode.as_option.selector == 'enabled' | |
60 tar -zxf $mode.as_option.tophat && | |
61 #end if | |
62 CIRCexplorer2 denovo | |
63 -d ./assemble | |
64 -r $mode.ref | |
65 -b $mode.bed | |
66 -g reference_genome.fa | |
67 #if $mode.abs | |
68 --abs 'abs' | |
69 #end if | |
70 #if $mode.as_option.selector == 'enabled' | |
71 --as 'as' | |
72 $mode.as_option.type_mapping './alignment' | |
73 #end if | |
74 $mode.no_fix | |
75 $mode.rpkm | |
76 #end if | |
77 ]]></command> | |
78 <inputs> | |
79 <conditional name="mode"> | |
80 <param name="selector" type="select" | |
81 label="Tool module" help="CIRCexplorer2 contains 5 modules. Each module | |
82 functions as an independent component owning its distinctive duty. | |
83 Meanwhile, they inteact with each other, and different circular RNA | |
84 analysis pipelines are derived from different combinations of several | |
85 modules."> | |
86 <option value="align">Align: Map circular RNA junction reads with TopHat2/TopHat-Fusion</option> | |
87 <option value="parse">Parse: Parse fusion junction information from other aligners</option> | |
88 <option value="annotate">Annotate: Annotate circular RNA junction reads with gene annotations</option> | |
89 <option value="assemble">Assemble: Assemble transcriptome for circular RNAs</option> | |
90 <option value="denovo">De novo: Fetch de novo circular RNA isoforms</option> | |
91 </param> | |
92 <when value="align"> | |
93 <param argument="--gtf" type="data" format="gtf" label="Annotation GTF file" /> | |
94 <expand macro="genome_file"/> | |
95 <param argument="--fastq" type="data" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz" multiple="true" label="RNA-seq FASTQ file(s)" | |
96 help="Only single-read RNA-seq is supported. It is recommended to convert paired-end RNA-seq to single-read RNA-seq before alignment"/> | |
97 <param argument="--bw" type="boolean" truevalue="--bw" falsevalue="" checked="false" | |
98 label="Create BigWig file" help=" It will not consider strand information of read alignment"/> | |
99 <param argument="--scale" type="boolean" truevalue="--scale" falsevalue="" checked="false" | |
100 label="Scale BigWig to HPB" help="Expression levels will be scaled to hits per billion-mapped-bases (HPB)" /> | |
101 <param argument="--skip-tophat" type="boolean" truevalue="--skip-tophat" falsevalue="" checked="false" | |
102 label="Skip TopHat mapping" help="CIRexplorer2 aligns reads onto genome and transcriptome using TopHat2 to | |
103 reduce false positive reads aligned in the TopHat-Fusion alignment step" /> | |
104 <param argument="--skip-tophat-fusion" type="boolean" truevalue="--skip-tophat-fusion" falsevalue="" checked="false" | |
105 label="Skip TopHat fusion" help="It is useful for poly(A)+ RNA-seq" /> | |
106 </when> | |
107 <when value="parse"> | |
108 <conditional name="aligner"> | |
109 <param argument="-t" name="selector" type="select" label="Aligner" | |
110 help="CIRCexplorer2 parse could accept results derived from TopHat-Fusion, | |
111 STAR, MapSplice, BWA and segemehl."> | |
112 <option value="TopHat-Fusion">TopHat-Fusion</option> | |
113 <option value="STAR">STAR</option> | |
114 <option value="MapSplice">MapSplice</option> | |
115 <option value="BWA">BWA</option> | |
116 <option value="segemehl">segemehl</option> | |
117 </param> | |
118 <when value="TopHat-Fusion"> | |
119 <expand macro="parse_fusion" format="bam" label="TopHat-Fusion file" | |
120 help="The required input file is accepted_hits.bam"/> | |
121 <expand macro="parse_statistics"/> | |
122 <param argument="--pe" type="boolean" truevalue="--pe" falsevalue="" checked="false" label="Paired-end aligner file" | |
123 help="Parse paired-end alignment file. If this is set, then -f is set automatically." /> | |
124 </when> | |
125 <when value="STAR"> | |
126 <expand macro="parse_fusion" format="interval,tabular" label="STAR fusion file" | |
127 help="The required input file is Chimeric.out.junction"/> | |
128 <expand macro="parse_statistics"/> | |
129 </when> | |
130 <when value="MapSplice"> | |
131 <expand macro="parse_fusion" format="txt" label="MapSplice fusion file" | |
132 help="The required input file is fusions_raw.txt"/> | |
133 <expand macro="parse_statistics"/> | |
134 </when> | |
135 <when value="BWA"> | |
136 <expand macro="parse_fusion" format="sam" label="BWA fusion file" | |
137 help="The required input file is the output sam file"/> | |
138 <expand macro="parse_statistics"/> | |
139 </when> | |
140 <when value="segemehl"> | |
141 <expand macro="parse_fusion" format="bed" label="segemehl fusion file" | |
142 help="The required input file is splicesites.bed"/> | |
143 <expand macro="parse_statistics"/> | |
144 </when> | |
145 </conditional> | |
146 </when> | |
147 <when value="annotate"> | |
148 <expand macro="annotation_file"/> | |
149 <expand macro="genome_file"/> | |
150 <expand macro="junction_file"/> | |
151 <param argument="--no-fix" type="boolean" truevalue="--no-fix" falsevalue="" checked="false" label="No fix mode" | |
152 help="When enabled, realignment step of fusion junction reads will be skipped. It is useful for species with | |
153 poor gene annotations, but the accuracy of circular RNA prediction would decrease." /> | |
154 <param argument="--low-confidence" type="boolean" truevalue="--low-confidence" falsevalue="" checked="false" label="Low confidence" | |
155 help="By default, it extracts fusion junction reads exactly matching the boundaries of exons of the same isoform by default. | |
156 If you set the --low-confidence, it will also extract fusion junction reads matching the boundaries of exons of the different | |
157 isofoms of the same gene" /> | |
158 </when> | |
159 <when value="assemble"> | |
160 <expand macro="annotation_file"/> | |
161 <expand macro="tophat_file"/> | |
162 <param argument="--remove-rRNA" type="boolean" truevalue="--remove-rRNA" falsevalue="" checked="false" | |
163 label="Remove rRNA" help="Ignore rRNA during assembling (only for human hg19)" /> | |
164 </when> | |
165 <when value="denovo"> | |
166 <expand macro="annotation_file"/> | |
167 <expand macro="junction_file"/> | |
168 <expand macro="genome_file"/> | |
169 <param name="assemble_file" type="data" format="tgz,tar" label="Assemble file" | |
170 help="Generated by the module CIRCexplorer2 assemble" /> | |
171 <param argument="--abs" type="boolean" truevalue="--abs" falsevalue="" checked="false" | |
172 label="Detect alternative back-splicing" help="When set, it will characterize the | |
173 alternative back-splicing of circular RNAs" /> | |
174 <conditional name="as_option"> | |
175 <param name="selector" type="select" label="Characterize alternative splicing of cirRNAs" | |
176 help="If enabled, it will characterize the alternative splicing of circular RNAs, including | |
177 cassette exons, retained introns, A5SS and A3SS"> | |
178 <option value="disabled">Disabled</option> | |
179 <option value="enabled">Enabled</option> | |
180 </param> | |
181 <when value="disabled"/> | |
182 <when value="enabled"> | |
183 <expand macro="tophat_file"/> | |
184 <param name="type_mapping" type="select" label="Type of mapping" | |
185 help="In this mode, you should also offer the path of TopHat mapping directory for | |
186 p(A)-/p(A)+ RNA-seq via -m/-n option"> | |
187 <option value="-m">p(A)-</option> | |
188 <option value="-n">p(A)+ RNA-seq</option> | |
189 </param> | |
190 </when> | |
191 </conditional> | |
192 <param argument="--no-fix" type="boolean" truevalue="--no-fix" falsevalue="" checked="false" label="No-fix mode" | |
193 help="If enabled, realignment step of fusion junction reads will be skipped. It is useful for species with | |
194 poor gene annotations, but the accuracy of circular RNA prediction would decrease." /> | |
195 <param argument="--rpkm" type="boolean" truevalue="--rpkm" falsevalue="" checked="false" label="Calculate RPKM for cassete exons" | |
196 help="If enabled, RPKM of cassette exons would be calculated" /> | |
197 </when> | |
198 </conditional> | |
199 </inputs> | |
200 <outputs> | |
201 <data name="alignment" format="tgz" from_work_dir="alignment.tgz" label="${tool.name} on ${on_string}: alignment file "> | |
202 <filter>mode['selector'] == 'align'</filter> | |
203 </data> | |
204 <data name="fusion_junction_bw" format="bigwig" from_work_dir="./alignment/tophat/accepted_hits.bw" label="${tool.name} on ${on_string}: BigWig"> | |
205 <filter>mode['selector'] == 'align'</filter> | |
206 <filter>mode['bw']</filter> | |
207 </data> | |
208 <data name="parse" format="bed" from_work_dir="back_spliced_junction.bed" label="${tool.name} on ${on_string}: back spliced junction (BED)"> | |
209 <filter>mode['selector'] == 'parse'</filter> | |
210 </data> | |
211 <data name="annotate" format="tabular" from_work_dir="circularRNA_known.txt" label="${tool.name} on ${on_string}: circRNA known"> | |
212 <filter>mode['selector'] == 'annotate'</filter> | |
213 </data> | |
214 <data name="annotate_low" format="tabular" from_work_dir="low_conf_circularRNA_known.txt" label="${tool.name} on ${on_string}: Low confidence circRNA"> | |
215 <filter>mode['selector'] == 'annotate'</filter> | |
216 <filter>mode['low_confidence']</filter> | |
217 </data> | |
218 <data name="assemble" format="tgz" from_work_dir="assemble.tgz" label="${tool.name} on ${on_string}: assemble file"> | |
219 <filter>mode['selector'] == 'assemble'</filter> | |
220 </data> | |
221 <data name="denovo_combined" format="tabular" from_work_dir="./denovo/combined_ref.txt" label="${tool.name} on ${on_string}: combined ref"> | |
222 <filter>mode['selector'] == 'denovo'</filter> | |
223 </data> | |
224 <data name="denovo_circularRNA" format="tabular" from_work_dir="./denovo/circularRNA_full.txt" label="${tool.name} on ${on_string}: circRNA full"> | |
225 <filter>mode['selector'] == 'denovo'</filter> | |
226 </data> | |
227 <data name="denovo_annotated" format="tabular" from_work_dir="./denovo/annotated_circ.txt" label="${tool.name} on ${on_string}: annotated circRNA"> | |
228 <filter>mode['selector'] == 'denovo'</filter> | |
229 </data> | |
230 <data name="denovo_novel" format="tabular" from_work_dir="./denovo/novel_circ.txt" label="${tool.name} on ${on_string}: novel circRNA"> | |
231 <filter>mode['selector'] == 'denovo'</filter> | |
232 </data> | |
233 <data name="denovo_abs5" format="tabular" from_work_dir="./abs/a5bs.txt" label="${tool.name} on ${on_string}: a5bs"> | |
234 <filter>mode['selector'] == 'denovo'</filter> | |
235 <filter>mode['abs']</filter> | |
236 </data> | |
237 <data name="denovo_abs3" format="tabular" from_work_dir="./abs/a3bs.txt" label="${tool.name} on ${on_string}: a3bs"> | |
238 <filter>mode['selector'] == 'denovo'</filter> | |
239 <filter>mode['abs']</filter> | |
240 </data> | |
241 <data name="denovo_all_exon" format="tabular" from_work_dir="./as/all_exon_info.txt" label="${tool.name} on ${on_string}: all exon info"> | |
242 <filter>mode['selector'] == 'denovo'</filter> | |
243 <filter>mode['as_option'] == 'enabled'</filter> | |
244 </data> | |
245 <data name="denovo_all_intron" format="tabular" from_work_dir="./as/all_intron_info.txt" label="${tool.name} on ${on_string}: all intron info"> | |
246 <filter>mode['selector'] == 'denovo'</filter> | |
247 <filter>mode['as_option'] == 'enabled'</filter> | |
248 </data> | |
249 <data name="denovo_a5ss" format="tabular" from_work_dir="./as/all_A5SS_info.txt" label="${tool.name} on ${on_string}: all A5SS info"> | |
250 <filter>mode['selector'] == 'denovo'</filter> | |
251 <filter>mode['as_option'] == 'enabled'</filter> | |
252 </data> | |
253 <data name="denovo_a3ss" format="tabular" from_work_dir="./as/all_A3SS_info.txt" label="${tool.name} on ${on_string}: all A3SS info"> | |
254 <filter>mode['selector'] == 'denovo'</filter> | |
255 <filter>mode['as_option'] == 'enabled'</filter> | |
256 </data> | |
257 </outputs> | |
258 <tests> | |
259 <test expect_num_outputs="1"> | |
260 <!--Test 01: Module align default options--> | |
261 <conditional name="mode"> | |
262 <param name="selector" value="align"/> | |
263 <param name="gtf" value="annotation_01.gtf"/> | |
264 <param name="genome" value="reference_01.fa"/> | |
265 <param name="fastq" value="reads_01.fastq,reads_02.fastq,reads_03.fastq"/> | |
266 <param name="skip_tophat_fusion" value="true"/> | |
267 </conditional> | |
268 <output name="alignment"> | |
269 <assert_contents> | |
270 <has_size value="3426053" delta="5000"/> | |
271 </assert_contents> | |
272 </output> | |
273 </test> | |
274 <test expect_num_outputs="2"> | |
275 <!--Test 02: Module align compressed files--> | |
276 <conditional name="mode"> | |
277 <param name="selector" value="align"/> | |
278 <param name="gtf" value="annotation_01.gtf"/> | |
279 <param name="genome" value="reference_01.fa"/> | |
280 <param name="fastq" value="reads_01.fastq.gz,reads_02.fastq.gz,reads_03.fastq.gz"/> | |
281 <param name="skip_tophat_fusion" value="true"/> | |
282 <param name="bw" value="true"/> | |
283 <param name="scale" value="true"/> | |
284 </conditional> | |
285 <output name="alignment"> | |
286 <assert_contents> | |
287 <has_size value="3435977" delta="5000"/> | |
288 </assert_contents> | |
289 </output> | |
290 <output name="fusion_junction_bw" value="test_02.bigwig" ftype="bigwig"/> | |
291 </test> | |
292 <test expect_num_outputs="1"> | |
293 <!--Test 03: Module parse--> | |
294 <conditional name="mode"> | |
295 <param name="selector" value="parse"/> | |
296 <conditional name="aligner"> | |
297 <param name="selector" value="MapSplice"/> | |
298 <param name="fusion_file" value="mapsplice_chimeric.junction"/> | |
299 </conditional> | |
300 </conditional> | |
301 <output name="parse" value="test_03.bed" ftype="bed"/> | |
302 </test> | |
303 <test expect_num_outputs="1"> | |
304 <!--Test 04: Module parse STAR--> | |
305 <conditional name="mode"> | |
306 <param name="selector" value="parse"/> | |
307 <conditional name="aligner"> | |
308 <param name="selector" value="STAR"/> | |
309 <param name="fusion_file" value="STAR_chimeric.junction"/> | |
310 <param name="f" value="true"/> | |
311 </conditional> | |
312 </conditional> | |
313 <output name="parse" value="test_04.bed" ftype="bed"/> | |
314 </test> | |
315 <test expect_num_outputs="1"> | |
316 <!--Test 05: Module annotate--> | |
317 <conditional name="mode"> | |
318 <param name="selector" value="annotate"/> | |
319 <param name="ref" value="annotation_02.txt"/> | |
320 <param name="genome" value="reference_02.fa"/> | |
321 <param name="bed" value="test_04.bed"/> | |
322 </conditional> | |
323 <output name="annotate" value="test_05.tabular" ftype="tabular"/> | |
324 </test> | |
325 <test expect_num_outputs="2"> | |
326 <!--Test 06: Module annotate--> | |
327 <conditional name="mode"> | |
328 <param name="selector" value="annotate"/> | |
329 <param name="ref" value="annotation_02.txt"/> | |
330 <param name="genome" value="reference_02.fa"/> | |
331 <param name="bed" value="test_04.bed"/> | |
332 <param name="no_fix" value="true"/> | |
333 <param name="low_confidence" value="true"/> | |
334 </conditional> | |
335 <output name="annotate" value="test_06.tabular" ftype="tabular"/> | |
336 </test> | |
337 <test expect_num_outputs="4"> | |
338 <!--Test 07: Module de novo--> | |
339 <conditional name="mode"> | |
340 <param name="selector" value="denovo"/> | |
341 <param name="ref" value="annotation_02.txt"/> | |
342 <param name="bed" value="test_04.bed"/> | |
343 <param name="genome" value="reference_02.fa"/> | |
344 <param name="assemble_file" value="assemble.tgz"/> | |
345 </conditional> | |
346 <output name="denovo_combined" value="test_07_combined.txt" ftype="tabular"/> | |
347 <output name="denovo_circularRNA" value="test_07_full.txt" ftype="tabular"/> | |
348 <output name="denovo_annotated" value="test_07_annotated.txt" ftype="tabular"/> | |
349 <output name="denovo_novel" value="test_07_novel.txt" ftype="tabular"/> | |
350 </test> | |
351 <test expect_num_outputs="6"> | |
352 <!--Test 08: Module de novo additional options--> | |
353 <conditional name="mode"> | |
354 <param name="selector" value="denovo"/> | |
355 <param name="ref" value="annotation_02.txt"/> | |
356 <param name="bed" value="test_04.bed"/> | |
357 <param name="genome" value="reference_02.fa"/> | |
358 <param name="assemble_file" value="assemble.tgz"/> | |
359 <param name="abs" value="true"/> | |
360 <param name="no_fix" value="true"/> | |
361 <param name="rpkm" value="true"/> | |
362 </conditional> | |
363 <output name="denovo_combined" value="test_08_combined.txt" ftype="tabular"/> | |
364 <output name="denovo_circularRNA" value="test_08_full.txt" ftype="tabular"/> | |
365 <output name="denovo_annotated" value="test_08_annotated.txt" ftype="tabular"/> | |
366 <output name="denovo_novel" value="test_08_novel.txt" ftype="tabular"/> | |
367 <output name="denovo_abs5" value="test_08_a5bs.txt" ftype="tabular"/> | |
368 <output name="denovo_abs3" value="test_08_a3bs.txt" ftype="tabular"/> | |
369 </test> | |
370 </tests> | |
371 <help><![CDATA[ | |
372 | |
373 .. class:: infomark | |
374 | |
375 **Purpose** | |
376 | |
377 CIRCexplorer2 is a comprehensive and integrative circular RNA analysis toolset. It is the successor | |
378 of CIRCexplorer with plenty of new features to facilitate circular RNA identification and characterization. | |
379 | |
380 ------------------- | |
381 | |
382 .. class:: infomark | |
383 | |
384 **Features** | |
385 | |
386 * Precisely annotate circular RNAs (Annotate) | |
387 * Support multiple circular RNA aligners (TopHat2/TopHat-Fusion, STAR, MapSplice, BWA and segemehl) (Align and Parse) | |
388 * De novo assemble novel circular RNA transcripts (Assemble) | |
389 * Characterize various of alternative (back-)splicing events of circular RNAs (Denovo) | |
390 * Fast identify circuar RNAs with STAR or BWA (Parse) | |
391 * Support both single-read and paired-end sequencing. | |
392 | |
393 ------------------- | |
394 | |
395 .. class:: infomark | |
396 | |
397 **Modules** | |
398 | |
399 CIRCexplorer2 contains 5 modules. Each module functions as an independent component owning its distinctive duty. | |
400 Meanwhile, they inteact with each other, and different circular RNA analysis pipelines are derived from different | |
401 combinations of several modules. Understanding the detailed mechanism of each module could facilitate your circular | |
402 RNA research. | |
403 | |
404 CIRCexplorer2 documentation is available from `here <http://circexplorer2.readthedocs.org/>`_, including installation instructions and tutorial. | |
405 | |
406 ]]></help> | |
407 <expand macro="citations" /> | |
408 </tool> |