Mercurial > repos > eschen42 > w4mclassfilter

comparison w4mclassfilter.xml @ 12:38f509903a0b 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 b9712e554d16ed26f6c6d0c2e8cd74552b49f694"
author eschen42
date Tue, 01 Oct 2019 16:57:58 -0400
parents 9f5c0e23c205
children c18040b6e8b9
comparison
equal deleted inserted replaced
11:9f5c0e23c205 12:38f509903a0b
1 <tool id="w4mclassfilter" name="W4m Data Subset" version="0.98.11"> 1 <tool id="w4mclassfilter" name="W4m Data Subset" version="0.98.13">
2 <description>Filter W4m data by values or metadata</description> 2 <description>Filter W4m data by values or metadata</description>
3 <!-- Here is the hyphenation standard that I *try* to apply consistently in my documentation: http://www.sandranoonan.com/dont-let-hyphenation-drive-crazy/ --> 3 <!-- Here is the hyphenation standard that I *try* to apply consistently in my documentation: http://www.sandranoonan.com/dont-let-hyphenation-drive-crazy/ -->
4 <requirements> 4 <requirements>
5 <!-- <requirement type="package" version="6.2">readline</requirement> --> 5 <requirement type="package" version="3.6.1">r-base</requirement>
6 <requirement type="package" version="3.4.1">r-base</requirement> 6 <requirement type="package" version="1.1_5">r-batch</requirement>
7 <requirement type="package" version="1.1_4">r-batch</requirement> 7 <requirement type="package" version="0.98.13">w4mclassfilter</requirement>
8 <requirement type="package" version="0.98.8">w4mclassfilter</requirement>
9 </requirements> 8 </requirements>
10 <command detect_errors="aggressive"><![CDATA[ 9 <command detect_errors="aggressive"><![CDATA[
10 unset R_HOME;
11 Rscript $__tool_directory__/w4mclassfilter_wrapper.R 11 Rscript $__tool_directory__/w4mclassfilter_wrapper.R
12 dataMatrix_in '$dataMatrix_in' 12 dataMatrix_in '$dataMatrix_in'
13 sampleMetadata_in '$sampleMetadata_in' 13 sampleMetadata_in '$sampleMetadata_in'
14 variableMetadata_in '$variableMetadata_in' 14 variableMetadata_in '$variableMetadata_in'
15 sampleclassNames '$sampleclassNames' 15 sampleclassNames '$sampleclassNames'
16 inclusive '$inclusive' 16 inclusive '$inclusive'
17 wildcards '$wildcards' 17 wildcards '$wildcards'
18 classnameColumn '$classnameColumn' 18 classnameColumn '$classnameColumn'
19 samplenameColumn 'sampleMetadata' 19 samplenameColumn 'sampleMetadata'
20 variable_range_filter '$variableRangeFilter' 20 variable_range_filter '$variableRangeFilter'
21 transformation '$transformation' 21 transformation '$transformation'
22 dataMatrix_out '$dataMatrix_out' 22 imputation '$imputation'
23 sampleMetadata_out '$sampleMetadata_out' 23 dataMatrix_out '$dataMatrix_out'
24 variableMetadata_out '$variableMetadata_out' 24 sampleMetadata_out '$sampleMetadata_out'
25 variableMetadata_out '$variableMetadata_out'
25 ]]></command> 26 ]]></command>
26 <inputs> 27 <inputs>
27 <param name="dataMatrix_in" format="tabular" label="Data matrix file" type="data" 28 <param name="dataMatrix_in" format="tabular" label="Data matrix file" type="data"
28 help="variables &#10006; samples" /> 29 help="variables &#10006; samples" />
29 <param name="sampleMetadata_in" format="tabular" label="Sample metadata file" type="data" 30 <param name="sampleMetadata_in" format="tabular" label="Sample metadata file" type="data"
93 help="'none' (the default) - do not transform data; 'log2' - log base 2 of data; 'log10' - log base 10 of data; in all cases, negative and missing values are imputed to zero"> 94 help="'none' (the default) - do not transform data; 'log2' - log base 2 of data; 'log10' - log base 10 of data; in all cases, negative and missing values are imputed to zero">
94 <option value="none" selected="true">none</option> 95 <option value="none" selected="true">none</option>
95 <option value="log2">log2</option> 96 <option value="log2">log2</option>
96 <option value="log10">log10</option> 97 <option value="log10">log10</option>
97 </param> 98 </param>
99 <param name="imputation" label="Imputation of missing values" type="select"
100 help="'zero' (the default) - replace missing values with zero; 'center' - replace missing values with feature-median; 'none' - perform no imputation">
101 <option value="zero" selected="true">zero</option>
102 <option value="center">center</option>
103 <option value="none">none</option>
104 </param>
98 </inputs> 105 </inputs>
99 <outputs> 106 <outputs>
100 <data name="dataMatrix_out" format="tabular" label="${dataMatrix_in.name}.subset" ></data> 107 <data name="dataMatrix_out" format="tabular" label="${dataMatrix_in.name}.subset" ></data>
101 <data name="sampleMetadata_out" format="tabular" label="${sampleMetadata_in.name}.subset" ></data> 108 <data name="sampleMetadata_out" format="tabular" label="${sampleMetadata_in.name}.subset" ></data>
102 <data name="variableMetadata_out" format="tabular" label="${variableMetadata_in.name}.subset" ></data> 109 <data name="variableMetadata_out" format="tabular" label="${variableMetadata_in.name}.subset" ></data>
108 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 115 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
109 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 116 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
110 <param name="classnameColumn" value="gender"/> 117 <param name="classnameColumn" value="gender"/>
111 <param name="sampleclassNames" value="M"/> 118 <param name="sampleclassNames" value="M"/>
112 <param name="wildcards" value="FALSE"/> 119 <param name="wildcards" value="FALSE"/>
113 <param name="inclusive" value="filter-in"/> 120 <param name="inclusive" value="TRUE"/>
114 <param name="variableRangeFilter" value="FEATMAX:6.30103:,mz:200:,rt::800"/> 121 <param name="variableRangeFilter" value="FEATMAX:2e6:,mz:200:,rt::800"/>
115 <param name="transformation" value="log10"/> 122 <param name="transformation" value="none"/>
116 <output name="dataMatrix_out"> 123 <output name="dataMatrix_out">
117 <assert_contents> 124 <assert_contents>
118 <has_text text="5.87336711011293" /> 125 <has_text text="747080" />
126 <not_has_text text="13420742" />
127 <not_has_text text="47259" />
119 </assert_contents> 128 </assert_contents>
120 </output> 129 </output>
121 <output name="sampleMetadata_out"> 130 <output name="sampleMetadata_out">
122 <assert_contents> 131 <assert_contents>
132 <has_text text="HU_017" />
133 <has_text text="HU_034" />
134 <has_text text="HU_078" />
135 <has_text text="HU_091" />
136 <has_text text="HU_093" />
137 <has_text text="HU_099" />
138 <has_text text="HU_130" />
139 <has_text text="HU_134" />
140 <has_text text="HU_138" />
123 <not_has_text text="HU_028" /> 141 <not_has_text text="HU_028" />
124 <not_has_text text="HU_051" /> 142 <not_has_text text="HU_051" />
125 <not_has_text text="HU_060" /> 143 <not_has_text text="HU_060" />
126 <not_has_text text="HU_110" /> 144 <not_has_text text="HU_110" />
127 <not_has_text text="HU_149" /> 145 <not_has_text text="HU_149" />
129 <not_has_text text="HU_175" /> 147 <not_has_text text="HU_175" />
130 <not_has_text text="HU_178" /> 148 <not_has_text text="HU_178" />
131 <not_has_text text="HU_185" /> 149 <not_has_text text="HU_185" />
132 <not_has_text text="HU_204" /> 150 <not_has_text text="HU_204" />
133 <not_has_text text="HU_208" /> 151 <not_has_text text="HU_208" />
134 <has_text text="HU_017" />
135 <has_text text="HU_034" />
136 <has_text text="HU_078" />
137 <has_text text="HU_091" />
138 <has_text text="HU_093" />
139 <has_text text="HU_099" />
140 <has_text text="HU_130" />
141 <has_text text="HU_134" />
142 <has_text text="HU_138" />
143 </assert_contents> 152 </assert_contents>
144 </output> 153 </output>
145 <output name="variableMetadata_out"> 154 <output name="variableMetadata_out">
146 <assert_contents> 155 <assert_contents>
156 <has_text text="HMDB00208" />
157 <has_text text="HMDB01032" />
158 <has_text text="HMDB01101.1" />
159 <has_text text="HMDB13189" />
147 <not_has_text text="HMDB00191" /> 160 <not_has_text text="HMDB00191" />
148 <has_text text="HMDB00208" />
149 <not_has_text text="HMDB00251" /> 161 <not_has_text text="HMDB00251" />
150 <not_has_text text="HMDB00299" /> 162 <not_has_text text="HMDB00299" />
151 <not_has_text text="HMDB00512" /> 163 <not_has_text text="HMDB00512" />
152 <not_has_text text="HMDB00518" /> 164 <not_has_text text="HMDB00518" />
153 <not_has_text text="HMDB00715" /> 165 <not_has_text text="HMDB00715" />
154 <not_has_text text="HMDB00822" /> 166 <not_has_text text="HMDB00822" />
155 <has_text text="HMDB01032" />
156 <has_text text="HMDB01101.1" />
157 <not_has_text text="HMDB03193" /> 167 <not_has_text text="HMDB03193" />
158 <not_has_text text="HMDB04824" /> 168 <not_has_text text="HMDB04824" />
159 <not_has_text text="HMDB10348" /> 169 <not_has_text text="HMDB10348" />
160 <has_text text="HMDB13189" />
161 <not_has_text text="HMDB59717" /> 170 <not_has_text text="HMDB59717" />
162 </assert_contents> 171 </assert_contents>
163 </output> 172 </output>
164 </test> 173 </test>
165 <!-- test 2 --> 174 <!-- test 2 -->
166 <test> 175 <test>
167 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/> 176 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
168 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 177 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
169 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 178 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
170 <param name="classnameColumn" value="sampleMetadata"/>
171 <!-- test that hyphens in regular expressions work --> 179 <!-- test that hyphens in regular expressions work -->
172 <param name="sampleclassNames" value="HU_[0-9][0-9][0-9]"/> 180 <param name="sampleclassNames" value="HU_[0-9][0-9][0-9]"/>
181 <param name="inclusive" value="TRUE"/>
173 <param name="wildcards" value="FALSE"/> 182 <param name="wildcards" value="FALSE"/>
174 <param name="inclusive" value="filter-in"/> 183 <param name="classnameColumn" value="sampleMetadata"/>
175 <param name="variableRangeFilter" value="FEATMAX:20.93157:,mz:200:,rt::800"/> 184 <!-- test that variableRangeFilter works with tranformation -->
176 <param name="transformation" value="log2"/> 185 <param name="variableRangeFilter" value="FEATMAX:6.30103:,mz:200:,rt::800"/>
177 <output name="dataMatrix_out"> 186 <param name="transformation" value="log10"/>
178 <assert_contents> 187 <param name="imputation" value="zero"/>
179 <has_text text="19.5109032146715" /> 188 <output name="dataMatrix_out" md5="5644d2ea01d072ee1d0c40e29e9d0089">
189 <assert_contents>
190 <has_text text="5.8733671" />
180 </assert_contents> 191 </assert_contents>
181 </output> 192 </output>
182 <output name="sampleMetadata_out"> 193 <output name="sampleMetadata_out">
183 <assert_contents> 194 <assert_contents>
195 <has_text text="HU_017" />
184 <has_text text="HU_028" /> 196 <has_text text="HU_028" />
197 <has_text text="HU_034" />
185 <has_text text="HU_051" /> 198 <has_text text="HU_051" />
186 <has_text text="HU_060" /> 199 <has_text text="HU_060" />
200 <has_text text="HU_078" />
201 <has_text text="HU_091" />
202 <has_text text="HU_093" />
203 <has_text text="HU_099" />
187 <has_text text="HU_110" /> 204 <has_text text="HU_110" />
205 <has_text text="HU_130" />
206 <has_text text="HU_134" />
207 <has_text text="HU_138" />
188 <has_text text="HU_149" /> 208 <has_text text="HU_149" />
189 <has_text text="HU_152" /> 209 <has_text text="HU_152" />
190 <has_text text="HU_175" /> 210 <has_text text="HU_175" />
191 <has_text text="HU_178" /> 211 <has_text text="HU_178" />
192 <has_text text="HU_185" /> 212 <has_text text="HU_185" />
193 <not_has_text text="HU_204" />
194 <has_text text="HU_208" /> 213 <has_text text="HU_208" />
195 <has_text text="HU_017" /> 214 <not_has_text text="HU_204" />
196 <has_text text="HU_034" />
197 <has_text text="HU_078" />
198 <has_text text="HU_091" />
199 <has_text text="HU_093" />
200 <has_text text="HU_099" />
201 <has_text text="HU_130" />
202 <has_text text="HU_134" />
203 <has_text text="HU_138" />
204 </assert_contents> 215 </assert_contents>
205 </output> 216 </output>
206 <output name="variableMetadata_out"> 217 <output name="variableMetadata_out">
207 <assert_contents> 218 <assert_contents>
208 <has_text text="HMDB00191" /> 219 <has_text text="HMDB00191" />
209 <has_text text="HMDB00208" /> 220 <has_text text="HMDB00208" />
221 <has_text text="HMDB01032" />
222 <has_text text="HMDB01101.1" />
223 <has_text text="HMDB13189" />
210 <not_has_text text="HMDB00251" /> 224 <not_has_text text="HMDB00251" />
211 <not_has_text text="HMDB00299" /> 225 <not_has_text text="HMDB00299" />
212 <not_has_text text="HMDB00512" /> 226 <not_has_text text="HMDB00512" />
213 <not_has_text text="HMDB00518" /> 227 <not_has_text text="HMDB00518" />
214 <not_has_text text="HMDB00715" /> 228 <not_has_text text="HMDB00715" />
215 <not_has_text text="HMDB00822" /> 229 <not_has_text text="HMDB00822" />
216 <has_text text="HMDB01032" />
217 <has_text text="HMDB01101.1" />
218 <not_has_text text="HMDB03193" /> 230 <not_has_text text="HMDB03193" />
219 <not_has_text text="HMDB04824" /> 231 <not_has_text text="HMDB04824" />
220 <not_has_text text="HMDB10348" /> 232 <not_has_text text="HMDB10348" />
221 <has_text text="HMDB13189" />
222 <not_has_text text="HMDB59717" /> 233 <not_has_text text="HMDB59717" />
223 </assert_contents> 234 </assert_contents>
224 </output> 235 </output>
225 </test> 236 </test>
226 <!-- test 3 --> 237 <!-- test 3 -->
228 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/> 239 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
229 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 240 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
230 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 241 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
231 <param name="classnameColumn" value="gender"/> 242 <param name="classnameColumn" value="gender"/>
232 <param name="sampleclassNames" value="M"/> 243 <param name="sampleclassNames" value="M"/>
233 <param name="inclusive" value="filter-in"/> 244 <param name="inclusive" value="TRUE"/>
234 <param name="transformation" value="none"/> 245 <param name="transformation" value="none"/>
235 <output name="dataMatrix_out"> 246 <output name="dataMatrix_out">
236 <assert_contents> 247 <assert_contents>
237 <not_has_text text="HU_028" /> 248 <not_has_text text="HU_028" />
238 <not_has_text text="HU_051" /> 249 <not_has_text text="HU_051" />
279 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 290 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
280 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 291 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
281 <param name="classnameColumn" value="gender"/> 292 <param name="classnameColumn" value="gender"/>
282 <param name="sampleclassNames" value="*"/> 293 <param name="sampleclassNames" value="*"/>
283 <param name="wildcards" value="TRUE"/> 294 <param name="wildcards" value="TRUE"/>
284 <param name="inclusive" value="filter-in"/> 295 <param name="inclusive" value="TRUE"/>
296 <param name="imputation" value="zero"/>
297 <output name="dataMatrix_out" md5="b2eac4946d3803a07606286b50451af4">
298 <assert_contents>
299 <not_has_text text="NA" />
300 </assert_contents>
301 </output>
285 <output name="sampleMetadata_out"> 302 <output name="sampleMetadata_out">
286 <assert_contents> 303 <assert_contents>
287 <not_has_text text="HU_204" /> 304 <not_has_text text="HU_204" />
288 <has_text text="HU_028" /> 305 <has_text text="HU_028" />
289 <has_text text="HU_051" /> 306 <has_text text="HU_051" />
313 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 330 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
314 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 331 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
315 <param name="classnameColumn" value="gender"/> 332 <param name="classnameColumn" value="gender"/>
316 <param name="sampleclassNames" value="M"/> 333 <param name="sampleclassNames" value="M"/>
317 <param name="wildcards" value="FALSE"/> 334 <param name="wildcards" value="FALSE"/>
318 <param name="inclusive" value="filter-in"/> 335 <param name="inclusive" value="TRUE"/>
319 <output name="sampleMetadata_out"> 336 <output name="sampleMetadata_out">
320 <assert_contents> 337 <assert_contents>
321 <not_has_text text="HU_028" /> 338 <not_has_text text="HU_028" />
322 <not_has_text text="HU_051" /> 339 <not_has_text text="HU_051" />
323 <not_has_text text="HU_060" /> 340 <not_has_text text="HU_060" />
347 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 364 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
348 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 365 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
349 <param name="classnameColumn" value="gender"/> 366 <param name="classnameColumn" value="gender"/>
350 <param name="sampleclassNames" value="M"/> 367 <param name="sampleclassNames" value="M"/>
351 <param name="wildcards" value="FALSE"/> 368 <param name="wildcards" value="FALSE"/>
352 <param name="inclusive" value="filter-in"/> 369 <param name="inclusive" value="TRUE"/>
353 <output name="variableMetadata_out"> 370 <output name="variableMetadata_out">
354 <assert_contents> 371 <assert_contents>
355 <has_text text="HMDB03193" /> 372 <has_text text="HMDB03193" />
356 <not_has_text text="HMDB00822" /> 373 <not_has_text text="HMDB00822" />
357 <has_text text="HMDB01101" /> 374 <has_text text="HMDB01101" />
377 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 394 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
378 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 395 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
379 <param name="classnameColumn" value="gender"/> 396 <param name="classnameColumn" value="gender"/>
380 <param name="sampleclassNames" value="M"/> 397 <param name="sampleclassNames" value="M"/>
381 <param name="wildcards" value="FALSE"/> 398 <param name="wildcards" value="FALSE"/>
382 <param name="inclusive" value="filter-in"/> 399 <param name="inclusive" value="TRUE"/>
383 <output name="variableMetadata_out"> 400 <output name="variableMetadata_out">
384 <assert_contents> 401 <assert_contents>
385 <has_text text="HMDB03193" /> 402 <has_text text="HMDB03193" />
386 <not_has_text text="HMDB00822" /> 403 <not_has_text text="HMDB00822" />
387 <has_text text="HMDB01101" /> 404 <has_text text="HMDB01101" />
407 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 424 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
408 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 425 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
409 <param name="classnameColumn" value="gender"/> 426 <param name="classnameColumn" value="gender"/>
410 <param name="sampleclassNames" value="[Mm],[fF]"/> 427 <param name="sampleclassNames" value="[Mm],[fF]"/>
411 <param name="wildcards" value="FALSE"/> 428 <param name="wildcards" value="FALSE"/>
412 <param name="inclusive" value="filter-in"/> 429 <param name="inclusive" value="TRUE"/>
413 <output name="sampleMetadata_out"> 430 <output name="sampleMetadata_out">
414 <assert_contents> 431 <assert_contents>
415 <has_text text="HU_028" /> 432 <has_text text="HU_028" />
416 <has_text text="HU_051" /> 433 <has_text text="HU_051" />
417 <has_text text="HU_060" /> 434 <has_text text="HU_060" />
441 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/> 458 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
442 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/> 459 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
443 <param name="classnameColumn" value=""/> 460 <param name="classnameColumn" value=""/>
444 <param name="sampleclassNames" value="M"/> 461 <param name="sampleclassNames" value="M"/>
445 <param name="wildcards" value="FALSE"/> 462 <param name="wildcards" value="FALSE"/>
446 <param name="inclusive" value="filter-in"/> 463 <param name="inclusive" value="TRUE"/>
447 <output name="sampleMetadata_out"> 464 <output name="sampleMetadata_out">
448 <assert_contents> 465 <assert_contents>
449 <has_text text="HU_028" /> 466 <has_text text="HU_028" />
450 <has_text text="HU_051" /> 467 <has_text text="HU_051" />
451 <has_text text="HU_060" /> 468 <has_text text="HU_060" />
467 <has_text text="HU_134" /> 484 <has_text text="HU_134" />
468 <has_text text="HU_138" /> 485 <has_text text="HU_138" />
469 </assert_contents> 486 </assert_contents>
470 </output> 487 </output>
471 </test> 488 </test>
489 <!-- test 10 - extends test4 with no imputation rather than zero imputation -->
490 <test>
491 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
492 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
493 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
494 <param name="classnameColumn" value="gender"/>
495 <param name="sampleclassNames" value="*"/>
496 <param name="wildcards" value="TRUE"/>
497 <param name="inclusive" value="TRUE"/>
498 <param name="imputation" value="none"/>
499 <output name="dataMatrix_out" md5="cc9ab8bdb70b68b43b19b7327d285166">
500 <assert_contents>
501 <not_has_text text="HU_204" />
502 <has_text text="NA" />
503 <has_text text="HU_028" />
504 </assert_contents>
505 </output>
506 <output name="sampleMetadata_out">
507 <assert_contents>
508 <not_has_text text="HU_204" />
509 <has_text text="HU_028" />
510 </assert_contents>
511 </output>
512 </test>
513 <!-- test 11 - extends test4 with center imputation rather than zero imputation -->
514 <test>
515 <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
516 <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
517 <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
518 <param name="classnameColumn" value="gender"/>
519 <param name="sampleclassNames" value="*"/>
520 <param name="wildcards" value="TRUE"/>
521 <param name="inclusive" value="TRUE"/>
522 <param name="imputation" value="center"/>
523 <output name="dataMatrix_out" md5="75a4802bb8887709e4d4dec8c2c3d3cf">
524 <assert_contents>
525 <not_has_text text="HU_204" />
526 <not_has_text text="NA" />
527 <has_text text="HU_028" />
528 </assert_contents>
529 </output>
530 <output name="sampleMetadata_out">
531 <assert_contents>
532 <not_has_text text="HU_204" />
533 <has_text text="HU_028" />
534 </assert_contents>
535 </output>
536 </test>
472 </tests> 537 </tests>
473 <help><![CDATA[ 538 <help><![CDATA[
474 539
475 540
476 **Author** Arthur Eschenlauer (University of Minnesota, esch0041@umn.edu) 541 **Author** Arthur Eschenlauer (University of Minnesota, esch0041@umn.edu)
529 - Features may be eliminated by specifying minimum or maximum value (or both) allowable in columns of variableMetadata. 594 - Features may be eliminated by specifying minimum or maximum value (or both) allowable in columns of variableMetadata.
530 - Features may be eliminated by “range of row-maximum for each feature”, i.e., by specifying minimum or maximum intensity (or both) allowable in each row of the dataMatrix (i.e., for the feature across all samples). 595 - Features may be eliminated by “range of row-maximum for each feature”, i.e., by specifying minimum or maximum intensity (or both) allowable in each row of the dataMatrix (i.e., for the feature across all samples).
531 596
532 This tool also performs several operations to address several data issues that may impede downstream statistical analysis: 597 This tool also performs several operations to address several data issues that may impede downstream statistical analysis:
533 598
534 - Missing values in dataMatrix are imputed to zero.
535 - The values in the dataMatrix may be log-transformed if desired.
536 - Samples that are missing from either sampleMetadata or dataMatrix are eliminated. 599 - Samples that are missing from either sampleMetadata or dataMatrix are eliminated.
537 - Features that are missing from either variableMetadata or dataMatrix are eliminated. 600 - Features that are missing from either variableMetadata or dataMatrix are eliminated.
538 - Features and samples that have zero variance are eliminated. 601 - Features and samples that have zero variance are eliminated.
539 - Samples and features are sorted alphabetically in rows and columns of dataMatrix and in rows of variableMetadata and sampleMetadata. 602 - Samples and features are sorted alphabetically in rows and columns of dataMatrix and in rows of variableMetadata and sampleMetadata.
540 - The names of the first columns of variableMetadata and sampleMetadata are set respectively to "variableMetadata" and "sampleMetadata". 603 - The names of the first columns of variableMetadata and sampleMetadata are set respectively to "variableMetadata" and "sampleMetadata".
604 - If desired, the values in the dataMatrix may be log-transformed.
605 - If desired, each missing value in dataMatrix is replaced with zero or the median value observed for the corresponding feature.
541 606
542 This tool may be applied several times sequentially, which may be useful for: 607 This tool may be applied several times sequentially, which may be useful for:
543 608
544 - analyzing subsets of samples for progressively smaller sets of treatment-levels, or 609 - analyzing subsets of samples for progressively smaller sets of treatment-levels, or
545 - choosing subsets of samples based on criteria in several columns of the sampleMetadata table. 610 - choosing subsets of samples based on criteria in several columns of the sampleMetadata table.
605 Variable-range filters (default = no filters) 670 Variable-range filters (default = no filters)
606 | comma-separated names of variable-range filters (see the 'Variable-range filters' section below) 671 | comma-separated names of variable-range filters (see the 'Variable-range filters' section below)
607 | 672 |
608 673
609 Data-transformation (default = '``none``') 674 Data-transformation (default = '``none``')
610 | '``none``' - do not transform data matrix values 675 | '``none``' - Do not transform data matrix values.
611 | '``log2``' - take the log base 2 of the values in the data matrix 676 | '``log2``' - Take the log base 2 of the values in the data matrix.
612 | '``log10``' - take the log base 10 of the values in the data matrix 677 | '``log10``' - Take the log base 10 of the values in the data matrix.
613 | In both cases, negative and missing values are imputed to zero. 678 |
679
680 Data-imputation (default = '``zero``')
681 | '``none``' - Do not impute data matrix values.
682 | '``zero``' - Negative and missing values are imputed to zero.
683 | '``center``' - For each feature, negative and missing values are imputed to the median of other values.
614 | 684 |
615 685
616 686
617 ------------ 687 ------------
618 Output files 688 Output files
706 - **If the "maximum" is less than the "minimum", then the range is exclusive** (e.g., "mz:800:200" means retain only features whose mz is NOT in the range 200-800) 776 - **If the "maximum" is less than the "minimum", then the range is exclusive** (e.g., "mz:800:200" means retain only features whose mz is NOT in the range 200-800)
707 - **If the name supplied in the first field is 'FEATMAX',** then the string is defining the minimum (and possibly, though less useful, maximum) intensity for each feature in the dataMatrix. For example, "FEATMAX:1e6:" would specify that any feature would be excluded if no sample had an intensity for that feature greater than 1000000. 777 - **If the name supplied in the first field is 'FEATMAX',** then the string is defining the minimum (and possibly, though less useful, maximum) intensity for each feature in the dataMatrix. For example, "FEATMAX:1e6:" would specify that any feature would be excluded if no sample had an intensity for that feature greater than 1000000.
708 778
709 - Note, however, that when the "maximum" is greater than the "minimum" for the FEATMAX range specification, then the specification is ignored. 779 - Note, however, that when the "maximum" is greater than the "minimum" for the FEATMAX range specification, then the specification is ignored.
710 780
781 ----------------------------------
782 Data transformation and imputation
783 ----------------------------------
784
785 Data may optionally be log2- or log10-transformed.
786
787 Negative intensity values are always substituted with zeros.
788
789 Missing intensity data values may optionally be imputed. Missing values may be substituted with zeros (as may be appropriate for univariate analysis) or with the median for the feature (as may be appropriate for multivariate analysis). (Note that the median feature-intensity is computed for the samples *before* variable-range filters are applied.)
790
711 ----------------------------------------------------------------------------- 791 -----------------------------------------------------------------------------
712 792
713 ---------------- 793 ----------------
714 WORKING EXAMPLES 794 WORKING EXAMPLES
715 ---------------- 795 ----------------
716
717 .. class:: infomark
718 796
719 ----------- 797 -----------
720 Input Files 798 Input Files
721 ----------- 799 -----------
722 800
728 | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/tools/w4mclassfilter/test-data/input_sampleMetadata.tsv | 806 | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/tools/w4mclassfilter/test-data/input_sampleMetadata.tsv |
729 +------------------------------------------------------------------------------------------------------------------------------------------------------+ 807 +------------------------------------------------------------------------------------------------------------------------------------------------------+
730 | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/tools/w4mclassfilter/test-data/input_variableMetadata.tsv | 808 | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/tools/w4mclassfilter/test-data/input_variableMetadata.tsv |
731 +------------------------------------------------------------------------------------------------------------------------------------------------------+ 809 +------------------------------------------------------------------------------------------------------------------------------------------------------+
732 810
733 .. class:: infomark
734
735 ------------------------------- 811 -------------------------------
736 Running Without Range-Filtering 812 Running Without Range-Filtering
737 ------------------------------- 813 -------------------------------
738 814
739 This example retains only samples whose 'gender' attribute is 'M'. 815 This example retains only samples whose 'gender' attribute is 'M'.
740 816
741 **Input parameters** 817 **Input parameters**
742 818
743 +------------------------------------+-------------------------------+ 819 +---------------------------------------------+-------------------------------+
744 | Input Parameter | Value | 820 | Input Parameter | Value |
745 +====================================+===============================+ 821 +=============================================+===============================+
746 | Names of sample-classes | M | 822 | Column that names the sample-class | gender |
747 +------------------------------------+-------------------------------+ 823 +---------------------------------------------+-------------------------------+
748 | Include named classes | filter-in | 824 | Names of sample-classes | M |
749 +------------------------------------+-------------------------------+ 825 +---------------------------------------------+-------------------------------+
750 | Column that names the sample-class | gender | 826 | Use 'wild-cards' or 'regular expressions' | wild-cards |
751 +------------------------------------+-------------------------------+ 827 +---------------------------------------------+-------------------------------+
752 | Variable range-filters | (Leave this field empty.) | 828 | Exclude/include named classes | filter-in |
753 +------------------------------------+-------------------------------+ 829 +---------------------------------------------+-------------------------------+
754 | Data transforamtion | none | 830 | Variable range-filters | (Leave this field empty.) |
755 +------------------------------------+-------------------------------+ 831 +---------------------------------------------+-------------------------------+
832 | Data transforamtion | none |
833 +---------------------------------------------+-------------------------------+
834 | Missing-value imputation | center |
835 +---------------------------------------------+-------------------------------+
756 836
757 **Expected outputs** 837 **Expected outputs**
758 838
759 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------+ 839 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------+
760 | Expected Output | Download from URL | 840 | Expected Output | Download from URL |
764 | Sample metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/tools/w4mclassfilter/test-data/expected_sampleMetadata.tsv | 844 | Sample metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/tools/w4mclassfilter/test-data/expected_sampleMetadata.tsv |
765 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------+ 845 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------+
766 | Variable metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/tools/w4mclassfilter/test-data/expected_variableMetadata.tsv | 846 | Variable metadata | https://raw.githubusercontent.com/HegemanLab/w4mclassfilter_galaxy_wrapper/master/tools/w4mclassfilter/test-data/expected_variableMetadata.tsv |
767 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------+ 847 +-------------------+-------------------------------------------------------------------------------------------------------------------------------------------------+
768 848
769 .. class:: infomark
770
771 ---------------------------- 849 ----------------------------
772 Running With Range-Filtering 850 Running With Range-Filtering
773 ---------------------------- 851 ----------------------------
774 852
775 This example retains only features whose mz is greater than 200, whose rt is less than 800, and whose maximum intensity across all samples is 2,000,000. 853 This example retains only features whose mz is greater than 200, whose rt is less than 800, and whose maximum intensity across all samples is 2,000,000.
776 This example retains all samples (except those having zero variance for all feature), although it would be possible to filter on samples as well. 854 This example retains all samples (except those having zero variance for all feature), although it would be possible to filter on samples as well.
777 855
778 **Input parameters** 856 **Input parameters**
779 857
780 +------------------------------------+------------------------------------+ 858 +---------------------------------------------+-----------------------------------+
781 | Input Parameter | Value | 859 | Input Parameter | Value |
782 +====================================+====================================+ 860 +=============================================+===================================+
783 | Names of sample-classes | (Leave this field empty.) | 861 | Column that names the sample-class | sampleMetadata |
784 +------------------------------------+------------------------------------+ 862 +---------------------------------------------+-----------------------------------+
785 | Include named classes | filter-out | 863 | Names of sample-classes | HU_13[48] |
786 +------------------------------------+------------------------------------+ 864 +---------------------------------------------+-----------------------------------+
787 | Column that names the sample-class | gender | 865 | Use 'wild-cards' or 'regular expressions' | regular-expressions |
788 +------------------------------------+------------------------------------+ 866 +---------------------------------------------+-----------------------------------+
789 | Variable range-filters | FEATMAX:20.93157:,mz:200:,rt::800 | 867 | Exclude/include named classes | filter-out |
790 +------------------------------------+------------------------------------+ 868 +---------------------------------------------+-----------------------------------+
791 | Data transforamtion | log2 | 869 | Variable range-filters | FEATMAX:20.93157:,mz:200:,rt::800 |
792 +------------------------------------+------------------------------------+ 870 +---------------------------------------------+-----------------------------------+
871 | Data transforamtion | log2 |
872 +---------------------------------------------+-----------------------------------+
873 | Missing-value imputation | zero |
874 +---------------------------------------------+-----------------------------------+
793 875
794 **Expected outputs** 876 **Expected outputs**
795 877
796 +-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------+ 878 +-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------+
797 | Expected Output | Download from URL | 879 | Expected Output | Download from URL |