Mercurial > repos > iuc > edger

comparison edger.xml @ 14:070900306913 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/edger commit 0c79416d9612d0ebdcb7c3c0543d510e11bb0774
author iuc
date Wed, 11 Oct 2023 11:13:07 +0000
parents 0cb907a2a810
children 5bf899c13979
comparison
equal deleted inserted replaced
13:0cb907a2a810 14:070900306913
2 <description> 2 <description>
3 Perform differential expression of count data 3 Perform differential expression of count data
4 </description> 4 </description>
5 <macros> 5 <macros>
6 <token name="@TOOL_VERSION@">3.36.0</token> 6 <token name="@TOOL_VERSION@">3.36.0</token>
7 <token name="@VERSION_SUFFIX@">2</token> 7 <token name="@VERSION_SUFFIX@">3</token>
8 </macros> 8 </macros>
9 <edam_topics> 9 <edam_topics>
10 <edam_topic>topic_3308</edam_topic> 10 <edam_topic>topic_3308</edam_topic>
11 </edam_topics> 11 </edam_topics>
12 <edam_operations> 12 <edam_operations>
66 66
67 #if $anno.annoOpt=='yes': 67 #if $anno.annoOpt=='yes':
68 -a '$anno.geneanno' 68 -a '$anno.geneanno'
69 #end if 69 #end if
70 70
71 -C '${ ','.join( ['%s' % $x.contrast for x in $rep_contrast] ) }' 71 #if $formula:
72 -F '$formula'
73 #end if
74
75 #if $contrasts.contrastOpt == 'file':
76 -C '$contrasts.cinfo'
77 #else:
78 -C '${ ','.join( ['%s' % $x.contrast for x in $contrasts.rep_contrast] ) }'
79 #end if
72 80
73 #if $f.filt.filt_select == 'yes': 81 #if $f.filt.filt_select == 'yes':
74 #if $f.filt.cformat.format_select == 'cpm': 82 #if $f.filt.cformat.format_select == 'cpm':
75 -c '$f.filt.cformat.cpmReq' 83 -c '$f.filt.cformat.cpmReq'
76 -s '$f.filt.cformat.cpmSampleReq' 84 -s '$f.filt.cformat.cpmSampleReq'
174 <when value="yes"> 182 <when value="yes">
175 <param name="geneanno" type="data" format="tabular" label="Gene Annotations"/> 183 <param name="geneanno" type="data" format="tabular" label="Gene Annotations"/>
176 </when> 184 </when>
177 <when value="no"/> 185 <when value="no"/>
178 </conditional> 186 </conditional>
187 <!-- Optional formula -->
188 <param name="formula" type="text" optional="true" label="Formula for linear model" help="An optional formula for the EdgeR linear model, this will override the use of the fields in factors as a simple sum. The formula can only use elements available in the factors file. This needs to be exactly as EdgeR expect the formula, ie. `~ 0 + factor_A + factor_B:factor_C`. See EdgeR documentation for more details.">
189 <sanitizer invalid_char="">
190 <valid initial="string.letters,string.digits">
191 <add value="_"/>
192 <add value="-"/>
193 <add value="+"/>
194 <add value="*"/>
195 <add value="/"/>
196 <add value="^"/>
197 <add value=":"/>
198 <add value="."/>
199 <add value="~"/>
200 <add value=" "/>
201 <add value="("/>
202 <add value=")"/>
203 <add value="@"/>
204 <add value="$"/>
205 </valid>
206 </sanitizer>
207 </param>
179 <!-- Contrasts --> 208 <!-- Contrasts -->
180 <repeat name="rep_contrast" title="Contrast" min="1" default="1"> 209 <conditional name="contrasts">
181 <param name="contrast" type="text" label="Contrast of Interest" help="Names of two groups to compare separated by a hyphen e.g. Mut-WT. If the order is Mut-WT the fold changes in the results will be up/down in Mut relative to WT. If you have more than one contrast enter each separately using the Insert Contrast button below. For differences between contrasts use e.g. (MT.t1-MT.t0)-(WT.t1-WT.t0). For more info, see Chapter 8 in the limma User's guide: https://www.bioconductor.org/packages/release/bioc/vignettes/limma/inst/doc/usersguide.pdf or https://bioconductor.org/packages/release/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf page 36 for nested comparisons."> 210 <param name="contrastOpt" type="select" label="Input contrasts manually or through a file">
182 <validator type="empty_field"/> 211 <option value="manual">manually</option>
183 <validator type="regex" message="Please only use letters, numbers, parentheses or underscores">^[\w\-()]+$</validator> 212 <option value="file">file</option>
184 </param> 213 </param>
185 </repeat> 214 <when value="manual">
215 <repeat name="rep_contrast" title="Contrast" min="1" default="1">
216 <param name="contrast" type="text" label="Contrast of Interest" help="Names of two groups to compare separated by a hyphen e.g. Mut-WT. If the order is Mut-WT the fold changes in the results will be up/down in Mut relative to WT. If you have more than one contrast enter each separately using the Insert Contrast button below. For differences between contrasts use e.g. (MT.t1-MT.t0)-(WT.t1-WT.t0). For more info, see Chapter 8 in the limma User's guide: https://www.bioconductor.org/packages/release/bioc/vignettes/limma/inst/doc/usersguide.pdf or https://bioconductor.org/packages/release/bioc/vignettes/edgeR/inst/doc/edgeRUsersGuide.pdf page 36 for nested comparisons.">
217 <validator type="empty_field"/>
218 <validator type="regex" message="Please only use letters, numbers, parentheses or underscores">^[\w\-()]+$</validator>
219 </param>
220 </repeat>
221 </when>
222 <when value="file">
223 <param name="cinfo" optional="true" type="data" format="tabular" label="Contrasts File" help="Setting this file will ignore any manually added contrasts above, make sure to remove any contrast fields above pressing the trash bin icon, or the tool will fail. First line of the file must be a header, below that each separate contrast should be on a line. Contrast formulas need to be based on ther factors data and potentially the formula provided. See EdgeR documentation on contrasts for more details."/>
224 </when>
225 </conditional>
186 <!-- Filter Options --> 226 <!-- Filter Options -->
187 <section name="f" expanded="false" title="Filter Low Counts"> 227 <section name="f" expanded="false" title="Filter Low Counts">
188 <conditional name="filt"> 228 <conditional name="filt">
189 <param name="filt_select" type="select" label="Filter lowly expressed genes?" help="Treat genes with very low expression as unexpressed and filter out. See the Filter Low Counts section below for more information. Default: No"> 229 <param name="filt_select" type="select" label="Filter lowly expressed genes?" help="Treat genes with very low expression as unexpressed and filter out. See the Filter Low Counts section below for more information. Default: No">
190 <option value="no" selected="true">No</option> 230 <option value="no" selected="true">No</option>
262 <param name="counts" value="matrix.txt"/> 302 <param name="counts" value="matrix.txt"/>
263 <repeat name="rep_factor"> 303 <repeat name="rep_factor">
264 <param name="factorName" value="Genotype"/> 304 <param name="factorName" value="Genotype"/>
265 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/> 305 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
266 </repeat> 306 </repeat>
307 <param name="contrastOpt" value="manual"/>
267 <repeat name="rep_contrast"> 308 <repeat name="rep_contrast">
268 <param name="contrast" value="Mut-WT"/> 309 <param name="contrast" value="Mut-WT"/>
269 </repeat> 310 </repeat>
270 <repeat name="rep_contrast"> 311 <repeat name="rep_contrast">
271 <param name="contrast" value="WT-Mut"/> 312 <param name="contrast" value="WT-Mut"/>
300 <param name="counts" value="matrix-complex.txt"/> 341 <param name="counts" value="matrix-complex.txt"/>
301 <repeat name="rep_factor"> 342 <repeat name="rep_factor">
302 <param name="factorName" value="Genotype"/> 343 <param name="factorName" value="Genotype"/>
303 <param name="groupNames" value="MutA,MutA,MutA,MutB,MutB,MutB,WTA,WTA,WTA,WTB,WTB,WTB"/> 344 <param name="groupNames" value="MutA,MutA,MutA,MutB,MutB,MutB,WTA,WTA,WTA,WTB,WTB,WTB"/>
304 </repeat> 345 </repeat>
346 <param name="contrastOpt" value="manual"/>
305 <repeat name="rep_contrast"> 347 <repeat name="rep_contrast">
306 <param name="contrast" value="(MutA-MutB)-(WTA-WTB)"/> 348 <param name="contrast" value="(MutA-MutB)-(WTA-WTB)"/>
307 </repeat> 349 </repeat>
308 <param name="normalisationOption" value="TMM"/> 350 <param name="normalisationOption" value="TMM"/>
309 <output_collection name="outTables" count="1"> 351 <output_collection name="outTables" count="1">
331 <param name="counts" value="matrix.txt"/> 373 <param name="counts" value="matrix.txt"/>
332 <repeat name="rep_factor"> 374 <repeat name="rep_factor">
333 <param name="factorName" value="Genotype"/> 375 <param name="factorName" value="Genotype"/>
334 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/> 376 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
335 </repeat> 377 </repeat>
378 <param name="contrastOpt" value="manual"/>
336 <repeat name="rep_contrast"> 379 <repeat name="rep_contrast">
337 <param name="contrast" value="Mut-WT"/> 380 <param name="contrast" value="Mut-WT"/>
338 </repeat> 381 </repeat>
339 <param name="normalisationOption" value="TMM"/> 382 <param name="normalisationOption" value="TMM"/>
340 <output_collection name="outTables" count="1"> 383 <output_collection name="outTables" count="1">
354 <param name="counts" value="matrix.txt"/> 397 <param name="counts" value="matrix.txt"/>
355 <repeat name="rep_factor"> 398 <repeat name="rep_factor">
356 <param name="factorName" value="Genotype"/> 399 <param name="factorName" value="Genotype"/>
357 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/> 400 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
358 </repeat> 401 </repeat>
402 <param name="contrastOpt" value="manual"/>
359 <repeat name="rep_contrast"> 403 <repeat name="rep_contrast">
360 <param name="contrast" value="Mut-WT"/> 404 <param name="contrast" value="Mut-WT"/>
361 </repeat> 405 </repeat>
362 <param name="normalisationOption" value="TMM"/> 406 <param name="normalisationOption" value="TMM"/>
363 <output name="outReport"> 407 <output name="outReport">
381 </repeat> 425 </repeat>
382 <repeat name="rep_factor"> 426 <repeat name="rep_factor">
383 <param name="factorName" value="Batch"/> 427 <param name="factorName" value="Batch"/>
384 <param name="groupNames" value="b1,b2,b3,b1,b2,b3"/> 428 <param name="groupNames" value="b1,b2,b3,b1,b2,b3"/>
385 </repeat> 429 </repeat>
430 <param name="contrastOpt" value="manual"/>
386 <repeat name="rep_contrast"> 431 <repeat name="rep_contrast">
387 <param name="contrast" value="Mut-WT"/> 432 <param name="contrast" value="Mut-WT"/>
388 </repeat> 433 </repeat>
389 <param name="normalisationOption" value="TMM"/> 434 <param name="normalisationOption" value="TMM"/>
390 <output_collection name="outTables" count="1"> 435 <output_collection name="outTables" count="1">
400 <test expect_num_outputs="2"> 445 <test expect_num_outputs="2">
401 <param name="format" value="matrix"/> 446 <param name="format" value="matrix"/>
402 <param name="ffile" value="yes"/> 447 <param name="ffile" value="yes"/>
403 <param name="finfo" value="factorinfo.txt"/> 448 <param name="finfo" value="factorinfo.txt"/>
404 <param name="counts" value="matrix.txt"/> 449 <param name="counts" value="matrix.txt"/>
450 <param name="contrastOpt" value="manual"/>
405 <repeat name="rep_contrast"> 451 <repeat name="rep_contrast">
406 <param name="contrast" value="Mut-WT"/> 452 <param name="contrast" value="Mut-WT"/>
407 </repeat> 453 </repeat>
408 <param name="normalisationOption" value="TMM"/> 454 <param name="normalisationOption" value="TMM"/>
409 <output_collection name="outTables" count="1"> 455 <output_collection name="outTables" count="1">
422 <param name="counts" value="matrix.txt"/> 468 <param name="counts" value="matrix.txt"/>
423 <repeat name="rep_factor"> 469 <repeat name="rep_factor">
424 <param name="factorName" value="Genotype"/> 470 <param name="factorName" value="Genotype"/>
425 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/> 471 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
426 </repeat> 472 </repeat>
473 <param name="contrastOpt" value="manual"/>
427 <repeat name="rep_contrast"> 474 <repeat name="rep_contrast">
428 <param name="contrast" value="Mut-WT"/> 475 <param name="contrast" value="Mut-WT"/>
429 </repeat> 476 </repeat>
430 <param name="normalisationOption" value="TMM"/> 477 <param name="normalisationOption" value="TMM"/>
431 <output_collection name="outTables" count="2"> 478 <output_collection name="outTables" count="2">
449 <param name="counts" value="matrix.txt"/> 496 <param name="counts" value="matrix.txt"/>
450 <repeat name="rep_factor"> 497 <repeat name="rep_factor">
451 <param name="factorName" value="Genotype"/> 498 <param name="factorName" value="Genotype"/>
452 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/> 499 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
453 </repeat> 500 </repeat>
501 <param name="contrastOpt" value="manual"/>
454 <repeat name="rep_contrast"> 502 <repeat name="rep_contrast">
455 <param name="contrast" value="Mut-WT"/> 503 <param name="contrast" value="Mut-WT"/>
456 </repeat> 504 </repeat>
457 <param name="normalisationOption" value="TMM"/> 505 <param name="normalisationOption" value="TMM"/>
458 <param name="lrtOption" value="true"/> 506 <param name="lrtOption" value="true"/>
492 <param name="countsFile" value="WT3.counts,Mut3.counts"/> 540 <param name="countsFile" value="WT3.counts,Mut3.counts"/>
493 </repeat> 541 </repeat>
494 </repeat> 542 </repeat>
495 <param name="annoOpt" value="yes"/> 543 <param name="annoOpt" value="yes"/>
496 <param name="geneanno" value="anno.txt"/> 544 <param name="geneanno" value="anno.txt"/>
545 <param name="contrastOpt" value="manual"/>
497 <repeat name="rep_contrast"> 546 <repeat name="rep_contrast">
498 <param name="contrast" value="Mut-WT"/> 547 <param name="contrast" value="Mut-WT"/>
499 </repeat> 548 </repeat>
500 <repeat name="rep_contrast"> 549 <repeat name="rep_contrast">
501 <param name="contrast" value="WT-Mut"/> 550 <param name="contrast" value="WT-Mut"/>
528 <param name="counts" value="matrix.txt"/> 577 <param name="counts" value="matrix.txt"/>
529 <repeat name="rep_factor"> 578 <repeat name="rep_factor">
530 <param name="factorName" value="Genotype"/> 579 <param name="factorName" value="Genotype"/>
531 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/> 580 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
532 </repeat> 581 </repeat>
582 <param name="contrastOpt" value="manual"/>
533 <repeat name="rep_contrast"> 583 <repeat name="rep_contrast">
534 <param name="contrast" value="Mut-WT"/> 584 <param name="contrast" value="Mut-WT"/>
535 </repeat> 585 </repeat>
536 <param name="normalisationOption" value="TMM"/> 586 <param name="normalisationOption" value="TMM"/>
537 <param name="filt_select" value="yes"/> 587 <param name="filt_select" value="yes"/>
563 <param name="counts" value="matrix.txt"/> 613 <param name="counts" value="matrix.txt"/>
564 <repeat name="rep_factor"> 614 <repeat name="rep_factor">
565 <param name="factorName" value="Genotype"/> 615 <param name="factorName" value="Genotype"/>
566 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/> 616 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
567 </repeat> 617 </repeat>
618 <param name="contrastOpt" value="manual"/>
568 <repeat name="rep_contrast"> 619 <repeat name="rep_contrast">
569 <param name="contrast" value="Mut-WT"/> 620 <param name="contrast" value="Mut-WT"/>
570 </repeat> 621 </repeat>
571 <param name="normalisationOption" value="TMM"/> 622 <param name="normalisationOption" value="TMM"/>
572 <param name="filt_select" value="yes"/> 623 <param name="filt_select" value="yes"/>
597 <param name="counts" value="matrix.txt"/> 648 <param name="counts" value="matrix.txt"/>
598 <repeat name="rep_factor"> 649 <repeat name="rep_factor">
599 <param name="factorName" value="Genotype"/> 650 <param name="factorName" value="Genotype"/>
600 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/> 651 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
601 </repeat> 652 </repeat>
653 <param name="contrastOpt" value="manual"/>
602 <repeat name="rep_contrast"> 654 <repeat name="rep_contrast">
603 <param name="contrast" value="Mut-WT"/> 655 <param name="contrast" value="Mut-WT"/>
604 </repeat> 656 </repeat>
605 <param name="normalisationOption" value="TMM"/> 657 <param name="normalisationOption" value="TMM"/>
606 <param name="filt_select" value="yes"/> 658 <param name="filt_select" value="yes"/>
624 <not_has_text text="-0.0682"/> 676 <not_has_text text="-0.0682"/>
625 </assert_contents> 677 </assert_contents>
626 </element> 678 </element>
627 </output_collection> 679 </output_collection>
628 </test> 680 </test>
681 <!-- Ensure formula and contrast file work -->
682 <test expect_num_outputs="2">
683 <param name="format" value="matrix"/>
684 <param name="counts" value="matrix.txt"/>
685 <repeat name="rep_factor">
686 <param name="factorName" value="Genotype"/>
687 <param name="groupNames" value="Mut,Mut,Mut,WT,WT,WT"/>
688 </repeat>
689 <repeat name="rep_factor">
690 <param name="factorName" value="Batch"/>
691 <param name="groupNames" value="b1,b2,b3,b1,b2,b3"/>
692 </repeat>
693 <param name="contrastOpt" value="file"/>
694 <param name="cinfo" value="contrasts_file.txt"/>
695 <param name="formula" value="~ 0 + Genotype + Batch"/>
696 <param name="normalisationOption" value="TMM"/>
697 <output_collection name="outTables" count="2">
698 <element name="edgeR_Mut-WT" ftype="tabular">
699 <assert_contents>
700 <has_text_matching expression="GeneID.*logFC.*logCPM.*F.*PValue.*FDR"/>
701 <has_text_matching expression="11304.*0.4584"/>
702 </assert_contents>
703 </element>
704 <element name="edgeR_WT-Mut" ftype="tabular">
705 <assert_contents>
706 <has_text_matching expression="GeneID.*logFC.*logCPM.*F.*PValue.*FDR"/>
707 </assert_contents>
708 </element>
709 </output_collection>
710 </test>
629 </tests> 711 </tests>
630 <help><![CDATA[ 712 <help><![CDATA[
631 .. class:: infomark 713 .. class:: infomark
632 714
633 **What it does** 715 **What it does**
711 793
712 *Factor Name:* The name of the experimental factor being investigated e.g. Genotype, Treatment. One factor must be entered, the name should start with a letter and spaces must not be used. Optionally, additional factors can be included, these are variables that might influence your experiment e.g. Batch, Gender, Subject. If additional factors are entered, an additive linear model will be used. 794 *Factor Name:* The name of the experimental factor being investigated e.g. Genotype, Treatment. One factor must be entered, the name should start with a letter and spaces must not be used. Optionally, additional factors can be included, these are variables that might influence your experiment e.g. Batch, Gender, Subject. If additional factors are entered, an additive linear model will be used.
713 795
714 *Groups:* The names of the groups for the factor. The names should start with a letter, and only contain letters, numbers and underscores, other characters such as spaces and hyphens must not be used. If entered into the tool form above, the order must be the same as the samples (to which the groups correspond) are listed in the columns of the counts matrix, with the values separated by commas. 796 *Groups:* The names of the groups for the factor. The names should start with a letter, and only contain letters, numbers and underscores, other characters such as spaces and hyphens must not be used. If entered into the tool form above, the order must be the same as the samples (to which the groups correspond) are listed in the columns of the counts matrix, with the values separated by commas.
715 797
798 **Formula:**
799 By default the tool will construct a formula for modelling counts based on the contents of the factors files or the factors given.
800 This can be overriden by directly providing the EdgeR formula in section named Formula.
801
716 **Contrasts of Interest:** 802 **Contrasts of Interest:**
717 The contrasts you wish to make between levels. 803 The contrasts you wish to make between levels.
718 A common contrast would be a simple difference between two levels: "Mut-WT" 804 A common contrast would be a simple difference between two levels: "Mut-WT"
719 represents the difference between the mutant and wild type genotypes. 805 represents the difference between the mutant and wild type genotypes.
720 Multiple contrasts must be entered separately using the Insert Contrast button, spaces must not be used. 806 Multiple contrasts must be entered separately using the Insert Contrast button, spaces must not be used.
807
808 Alternatively, you can specify a file with contrasts. The file must contain a header (it's value is irrelevant)
809 and one contrast per line on the first column (other columns are ignored). If using this option, make sure to
810 remove any contrast section from the manual part, or the tool will fail.
721 811
722 **Filter Low Counts:** 812 **Filter Low Counts:**
723 Genes with very low counts across all libraries provide little evidence for differential expression. 813 Genes with very low counts across all libraries provide little evidence for differential expression.
724 In the biological point of view, a gene must be expressed at some minimal level before 814 In the biological point of view, a gene must be expressed at some minimal level before
725 it is likely to be translated into a protein or to be biologically important. In addition, the 815 it is likely to be translated into a protein or to be biologically important. In addition, the