Mercurial > repos > eschen42 > w4mclassfilter

comparison w4mclassfilter.xml @ 5:2cdf7d5982c8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/HegemanLab/w4mclassfilter_galaxy_wrapper/tree/master commit a2d17eac4a1343a34cf2908d9ab31b3202a21f64
author eschen42
date Thu, 07 Sep 2017 17:41:09 -0400
parents 499c7ecfa834
children 38ccf6722d54
comparison
equal deleted inserted replaced
4:499c7ecfa834 5:2cdf7d5982c8
1 <tool id="w4mclassfilter" name="Sample_Subset" version="0.98.2"> 1 <tool id="w4mclassfilter" name="Sample_Subset" version="0.98.3">
2 <description>Filter W4M data by sample class</description> 2 <description>Filter W4M data by sample class</description>
3 3
4 <requirements> 4 <requirements>
5 <requirement type="package" version="3.3.1">r-base</requirement> 5 <requirement type="package" version="3.3.2">r-base</requirement>
6 <requirement type="package" version="1.1_4">r-batch</requirement> 6 <requirement type="package" version="1.1_4">r-batch</requirement>
7 <requirement type="package" version="0.98.2">w4mclassfilter</requirement> 7 <requirement type="package" version="0.98.3">w4mclassfilter</requirement>
8 </requirements> 8 </requirements>
9 9
10 <stdio> 10 <stdio>
11 <exit_code range="1:" level="fatal" /> 11 <exit_code range="1:" level="fatal" />
12 </stdio> 12 </stdio>
32 <param name="sampleMetadata_in" label="Sample metadata file" type="data" format="tabular" help="sample x metadata columns, separator: tab" /> 32 <param name="sampleMetadata_in" label="Sample metadata file" type="data" format="tabular" help="sample x metadata columns, separator: tab" />
33 <param name="variableMetadata_in" label="Variable metadata file" type="data" format="tabular" help="variable x metadata columns, separator: tab" /> 33 <param name="variableMetadata_in" label="Variable metadata file" type="data" format="tabular" help="variable x metadata columns, separator: tab" />
34 <param name="samplenameColumn" label="Column that names the sample" type="text" value = "sampleMetadata" help="name of the column in the sample metadata file that has the name of the sample - defaults to 'sampleMetadata'" /> 34 <param name="samplenameColumn" label="Column that names the sample" type="text" value = "sampleMetadata" help="name of the column in the sample metadata file that has the name of the sample - defaults to 'sampleMetadata'" />
35 <param name="classnameColumn" label="Column that names the sample-class" type="text" value = "class" help="name of the column in sample metadata that has the values to be tested against the 'classes' input parameter - defaults to 'class'" /> 35 <param name="classnameColumn" label="Column that names the sample-class" type="text" value = "class" help="name of the column in sample metadata that has the values to be tested against the 'classes' input parameter - defaults to 'class'" />
36 <param name="sampleclassNames" label="Names of sample classes" type="text" value = "" help="comma-separated names (or comma-less regular expressions to match names) of sample-classes to filter in or out; defaults to no names"> 36 <param name="sampleclassNames" label="Names of sample classes" type="text" value = "" help="comma-separated names (or comma-less regular expressions to match names) of sample-classes to filter in or out; defaults to no names">
37 <sanitizer sanitize="False"/> 37 <sanitizer>
38 <valid initial="string.letters">
39 <add preset="string.digits"/>
40 <add value="&#36;" /> <!-- dollar, dollar-sign -->
41 <add value="&#40;" /> <!-- left-paren -->
42 <add value="&#41;" /> <!-- right-paren -->
43 <add value="&#42;" /> <!-- splat, asterisk -->
44 <add value="&#43;" /> <!-- plus -->
45 <add value="&#44;" /> <!-- comma -->
46 <add value="&#46;" /> <!-- dot, period -->
47 <add value="&#58;" /> <!-- colon -->
48 <add value="&#59;" /> <!-- semi, semicolon -->
49 <add value="&#63;" /> <!-- what, question mark -->
50 <add value="&#91;" /> <!-- l-squib, left-squre-bracket -->
51 <add value="&#92;" /> <!-- whack, backslash -->
52 <add value="&#93;" /> <!-- r-squib, right-squre-bracket -->
53 <add value="&#94;" /> <!-- hat, caret -->
54 <add value="&#123;" /> <!-- l-cube, left-curly-bracket -->
55 <add value="&#124;" /> <!-- pipe -->
56 <add value="&#125;" /> <!-- r-cube, right-curly-bracket -->
57 </valid>
58 </sanitizer>
59
38 </param> 60 </param>
39 <param name="wildcards" label="Use wild-cards or regular-expressions" type="select" help="wild-cards (the default) - use '*' and '?' to match class names; regular-expressions - use comma-less regular expressions to match class names"> 61 <param name="wildcards" label="Use wild-cards or regular-expressions" type="select" help="wild-cards (the default) - use '*' and '?' to match class names; regular-expressions - use comma-less regular expressions to match class names">
40 <option value="TRUE" selected="true">wild-cards</option> 62 <option value="TRUE" selected="true">wild-cards</option>
41 <option value="FALSE">regular-expressions</option> 63 <option value="FALSE">regular-expressions</option>
42 </param> 64 </param>
104 <test> 126 <test>
105 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/> 127 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
106 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 128 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
107 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 129 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
108 <param name="classnameColumn" value="gender"/> 130 <param name="classnameColumn" value="gender"/>
131 <param name="sampleclassNames" value="*"/>
132 <param name="wildcards" value="TRUE"/>
133 <param name="samplenameColumn" value="sampleMetadata"/>
134 <param name="inclusive" value="filter-in"/>
135 <output name="sampleMetadata_out">
136 <assert_contents>
137 <not_has_text text="HU_204" />
138 <has_text text="HU_028" />
139 <has_text text="HU_051" />
140 <has_text text="HU_060" />
141 <has_text text="HU_110" />
142 <has_text text="HU_149" />
143 <has_text text="HU_152" />
144 <has_text text="HU_175" />
145 <has_text text="HU_178" />
146 <has_text text="HU_185" />
147 <has_text text="HU_208" />
148 <has_text text="HU_017" />
149 <has_text text="HU_034" />
150 <has_text text="HU_078" />
151 <has_text text="HU_091" />
152 <has_text text="HU_093" />
153 <has_text text="HU_099" />
154 <has_text text="HU_130" />
155 <has_text text="HU_134" />
156 <has_text text="HU_138" />
157 </assert_contents>
158 </output>
159 </test>
160 <test>
161 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
162 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
163 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
164 <param name="classnameColumn" value="gender"/>
109 <param name="sampleclassNames" value="M"/> 165 <param name="sampleclassNames" value="M"/>
166 <param name="wildcards" value="FALSE"/>
110 <param name="samplenameColumn" value="sampleMetadata"/> 167 <param name="samplenameColumn" value="sampleMetadata"/>
111 <param name="inclusive" value="filter-in"/> 168 <param name="inclusive" value="filter-in"/>
112 <output name="sampleMetadata_out"> 169 <output name="sampleMetadata_out">
113 <assert_contents> 170 <assert_contents>
114 <not_has_text text="HU_028" /> 171 <not_has_text text="HU_028" />
138 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/> 195 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
139 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 196 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
140 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 197 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
141 <param name="classnameColumn" value="gender"/> 198 <param name="classnameColumn" value="gender"/>
142 <param name="sampleclassNames" value="M"/> 199 <param name="sampleclassNames" value="M"/>
200 <param name="wildcards" value="FALSE"/>
143 <param name="samplenameColumn" value="sampleMetadata"/> 201 <param name="samplenameColumn" value="sampleMetadata"/>
144 <param name="inclusive" value="filter-in"/> 202 <param name="inclusive" value="filter-in"/>
145 <output name="variableMetadata_out"> 203 <output name="variableMetadata_out">
146 <assert_contents> 204 <assert_contents>
147 <has_text text="HMDB03193" /> 205 <has_text text="HMDB03193" />
167 <param name="dataMatrix_in" value="input_nofilter_dataMatrix.tsv"/> 225 <param name="dataMatrix_in" value="input_nofilter_dataMatrix.tsv"/>
168 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 226 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
169 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 227 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
170 <param name="classnameColumn" value="gender"/> 228 <param name="classnameColumn" value="gender"/>
171 <param name="sampleclassNames" value="M"/> 229 <param name="sampleclassNames" value="M"/>
230 <param name="wildcards" value="FALSE"/>
172 <param name="samplenameColumn" value="sampleMetadata"/> 231 <param name="samplenameColumn" value="sampleMetadata"/>
173 <param name="inclusive" value="filter-in"/> 232 <param name="inclusive" value="filter-in"/>
174 <output name="variableMetadata_out"> 233 <output name="variableMetadata_out">
175 <assert_contents> 234 <assert_contents>
176 <has_text text="HMDB03193" /> 235 <has_text text="HMDB03193" />
196 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/> 255 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
197 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 256 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
198 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 257 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
199 <param name="classnameColumn" value="gender"/> 258 <param name="classnameColumn" value="gender"/>
200 <param name="sampleclassNames" value="[Mm],[fF]"/> 259 <param name="sampleclassNames" value="[Mm],[fF]"/>
260 <param name="wildcards" value="FALSE"/>
201 <param name="samplenameColumn" value="sampleMetadata"/> 261 <param name="samplenameColumn" value="sampleMetadata"/>
202 <param name="inclusive" value="filter-in"/> 262 <param name="inclusive" value="filter-in"/>
203 <output name="sampleMetadata_out"> 263 <output name="sampleMetadata_out">
204 <assert_contents> 264 <assert_contents>
205 <has_text text="HU_028" /> 265 <has_text text="HU_028" />
229 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/> 289 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
230 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 290 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
231 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 291 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
232 <param name="classnameColumn" value=""/> 292 <param name="classnameColumn" value=""/>
233 <param name="sampleclassNames" value="M"/> 293 <param name="sampleclassNames" value="M"/>
294 <param name="wildcards" value="FALSE"/>
234 <param name="samplenameColumn" value="sampleMetadata"/> 295 <param name="samplenameColumn" value="sampleMetadata"/>
235 <param name="inclusive" value="filter-in"/> 296 <param name="inclusive" value="filter-in"/>
236 <output name="sampleMetadata_out"> 297 <output name="sampleMetadata_out">
237 <assert_contents> 298 <assert_contents>
238 <has_text text="HU_028" /> 299 <has_text text="HU_028" />
260 </test> 321 </test>
261 </tests> 322 </tests>
262 323
263 324
264 325
265 <help> 326 <help><![CDATA[
266 <![CDATA[ 327
267 328
268 329 **Author** Arthur Eschenlauer (University of Minnesota, esch0041@umn.edu)
269 **Author** Arthur Eschenlauer (University of Minnesota, esch0041@umn.edu)
270 330
271 -------------------------------------------------------------------------- 331 --------------------------------------------------------------------------
272 332
273 333
274 **R package** 334 **R package**
307 367
308 GC-MS1 and LC-MS1 experiments seek to resolve chemicals as features that have distinct chromatographic behavior and (after ionization) mass-to-charge ratio. 368 GC-MS1 and LC-MS1 experiments seek to resolve chemicals as features that have distinct chromatographic behavior and (after ionization) mass-to-charge ratio.
309 Data for a sample are collected as MS intensities, each of which is associated with a position on a 2D plane with dimensions of m/z ratio and chromatographic retention time. 369 Data for a sample are collected as MS intensities, each of which is associated with a position on a 2D plane with dimensions of m/z ratio and chromatographic retention time.
310 Ideally, features would be sufficiently reproducible from sample-run to sample-run to identify features that are commmon among samples and those that differ. 370 Ideally, features would be sufficiently reproducible from sample-run to sample-run to identify features that are commmon among samples and those that differ.
311 However, the chromatographic retention time for a chemical can vary from one run to another. 371 However, the chromatographic retention time for a chemical can vary from one run to another.
312 In the Workflow4Metabolomics (W4M, [Giacomoni *et al.*, 2014]) "flavor" of Galaxy, the XCMS [Smith *et al.*, 2006] preprocessing tools provide for "retention time correction" to align features among samples, but features may be better aligned if pooled samples and blanks are included. 372 In the Workflow4Metabolomics (W4M, [Giacomoni *et al.*, 2014, Guitton *et al.* 2017]) "flavor" of Galaxy, the XCMS [Smith *et al.*, 2006] preprocessing tools provide for "retention time correction" to align features among samples, but features may be better aligned if pooled samples and blanks are included.
313 373
314 Multivariate statistical techniques may be used to discover clusters of similar samples, and sometimes it is desirable to apply clustering iteratively to smaller and smaller subsets of samples until observable separation of clusters is no longer significant. 374 Multivariate statistical techniques may be used to discover clusters of similar samples, and sometimes it is desirable to apply clustering iteratively to smaller and smaller subsets of samples until observable separation of clusters is no longer significant.
315 Once feature-alignment has been achieved among samples in GC-MS and LC-MS datasets, however, the presence of pools and blanks may confound identification and separation of clusters. 375 Once feature-alignment has been achieved among samples in GC-MS and LC-MS datasets, however, the presence of pools and blanks may confound identification and separation of clusters.
316 Multivariate statistical algorithms also may be impacted by missing values or dimensions that have zero variance. 376 Multivariate statistical algorithms also may be impacted by missing values or dimensions that have zero variance (Thévenot *et al.*, 2015).
317 377
318 The w4mclassfilter tool provides a way to choose subsets of samples for further analysis. 378 The w4mclassfilter tool provides a way to choose subsets of samples for further analysis.
319 The tool takes as input the data matrix, sample metadata, and variable metadata Galaxy datasets produced by W4M and produces the same trio of datasets with data only for the selected samples. 379 The tool takes as input the data matrix, sample metadata, and variable metadata Galaxy datasets produced by W4M and produces the same trio of datasets with data only for the selected samples.
320 The tool uses a "sample-class" column in the sample metadata as the basis for including or eliminating samples for further analysis. 380 The tool uses a "sample-class" column in the sample metadata as the basis for including or eliminating samples for further analysis.
321 Class-values to be considered are provided by the user as a comma-separated list. 381 Class-values to be considered are provided by the user as a comma-separated list.
398 458
399 --------------------------------------- 459 ---------------------------------------
400 Wild card patterns to match class-names 460 Wild card patterns to match class-names
401 --------------------------------------- 461 ---------------------------------------
402 462
403 Beginning with v0.98.2, w4mclassfilter supports use of R regular expression patterns to select class-names. 463 Beginning with v0.98.2, w4mclassfilter supports use of R "wild card" patterns to select class-names.
404 464
405 - use '``?``' to match a single character 465 - use '``?``' to match a single character
406 - use '``*``' to match zero or more characters 466 - use '``*``' to match zero or more characters
407 - the entire pattern must match the sample name 467 - the entire pattern must match the sample name
408 468
414 474
415 ------------------------------------------------ 475 ------------------------------------------------
416 Regular expression patterns to match class-names 476 Regular expression patterns to match class-names
417 ------------------------------------------------ 477 ------------------------------------------------
418 478
419 Beginning with v0.98.2, w4mclassfilter supports use of R regular expression patterns to select class-names. 479 Beginning with v0.98.2, w4mclassfilter supports use of R "regular expression" patterns to select class-names.
420 480
421 R uses POSIX 1003.2 standard regular expressions, which allow precise pattern-matching and are exhaustively defined at: 481 R uses POSIX 1003.2 standard regular expressions, which allow precise pattern-matching and are exhaustively defined at:
422 http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap09.html 482 http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap09.html
423 483
424 However, only a few basic building blocks of regular expressions need to be mastered for most cases: 484 However, only a few basic building blocks of regular expressions need to be mastered for most cases:
506 566
507 ---- 567 ----
508 NEWS 568 NEWS
509 ---- 569 ----
510 570
571 CHANGES IN VERSION 0.98.3
572 =========================
573
574 INTERNAL MODIFICATIONS
575
576 * Improved input handling.
577 * Now uses w4mclassfilter R package v0.98.3, although that version has no functional implications for this tool.
578 * Improved reference-list.
579
511 CHANGES IN VERSION 0.98.2 580 CHANGES IN VERSION 0.98.2
512 ========================= 581 =========================
513 582
514 NEW FEATURES 583 NEW FEATURES
515 584
534 603
535 INTERNAL MODIFICATIONS 604 INTERNAL MODIFICATIONS
536 605
537 none 606 none
538 607
539 ]]> 608 ]]></help>
540 </help>
541 <citations> 609 <citations>
610 <!-- Giacomoni_2014 W4M 2.5 -->
611 <citation type="doi">10.1093/bioinformatics/btu813</citation>
612 <!-- Guitton_2017 W4M 3.0 -->
613 <citation type="doi">10.1016/j.biocel.2017.07.002</citation>
614 <!-- Smith_2006 XCMS -->
542 <citation type="doi">10.1021/ac051437y</citation> 615 <citation type="doi">10.1021/ac051437y</citation>
543 <citation type="doi">10.1093/bioinformatics/btu813</citation> 616 <!-- Th_venot_2015 Urinary metabolome statistics -->
617 <citation type="doi">10.1021/acs.jproteome.5b00354</citation>
544 </citations> 618 </citations>
545 <!-- 619 <!--
546 vim:noet:sw=4:ts=4 620 vim:noet:sw=4:ts=4
547 --> </tool> 621 --> </tool>