Mercurial > repos > mmonsoor > probmetab

comparison ProbMetab.xml @ 0:e13ec2c3fabe draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 25fd6a739741295e3f434e0be0286dee61e06825
author mmonsoor
date Mon, 04 Jul 2016 04:29:25 -0400
parents
children c4bd0c40eb3b
comparison
equal deleted inserted replaced
-1:000000000000 0:e13ec2c3fabe
1 <tool id="Probmetab" name="ProbMetab Tool" version="1.0.1">
2
3 <description>Wrapper function for ProbMetab R package.</description>
4
5 <requirements>
6 <requirement type="package" version="0.4_1">r-snow</requirement>
7 <requirement type="package" version="1.0">r-probmetab</requirement>
8 <requirement type="package" version="1.1_4">r-batch</requirement>
9 </requirements>
10
11 <stdio>
12 <exit_code range="1:" level="fatal" />
13 </stdio>
14
15 <command>
16 LANG=C Rscript $__tool_directory__/probmetab.r
17 #if $acquisition_options.mode == "one":
18 mode_acquisition $acquisition_options.mode xa $acquisition_options.xa
19 ##if $acquisition_options.xsetnofill_options.option == "show":
20 ##xsetnofill $acquisition_options.xsetnofill_options.xsetnofill
21 ##end if
22 #else
23 mode_acquisition $acquisition_options.mode inputs_mode $acquisition_options.input_mode.option
24 #if $acquisition_options.input_mode.option== "two":
25
26 image_pos $acquisition_options.input_mode.image_pos image_neg $acquisition_options.input_mode.image_neg
27 ##if $acquisition_options.input_mode.xsetnofill_options.option == "show":
28 ##xsetPnofill $acquisition_options.input_mode.xsetnofill_options.xsetPnofill xsetNnofill $acquisition_options.input_mode.xsetnofill_options.xsetNnofill
29 ##end if
30 ##else
31 ##image_combinexsannos $acquisition_options.input_mode.image_combinexsannos image_pos $acquisition_options.input_mode.image_pos
32 #end if
33
34 #end if
35
36 #if $option_toexclude.option == "show":
37 toexclude $option_toexclude.toexclude
38 #end if
39 allowMiss $allowMiss html $html kegg_db $kegg_db ppm_tol $ppm_tol
40 opt $opt corths $corths corprob $corprob pcorprob $pcorprob prob $prob
41
42 #if $zip_file:
43 zipfile $zip_file
44 #end if
45
46 </command>
47
48 <inputs>
49
50 <conditional name="acquisition_options">
51 <param name="mode" type="select" label="Choose your acquisition mode" >
52 <option value="one" selected="true" >One acquisition charge mode</option>
53 <option value="two" >Two acquisition charge mode (positif and negatif)</option>
54 </param>
55
56 <!-- One acquisition mode-->
57 <when value="one">
58 <param name="xa" type="data" label="Annotate RData" format="rdata.camera.positive,rdata.camera.negative,rdata" help="Output file from annotate step " />
59 <!--
60 <conditional name="xsetnofill_options">
61 <param name="option" type="select" label="RData group step" help="xcmsSet xcms object after missing data replacement, to retrieve SNR to isotopic peaks." >
62 <option value="show">show</option>
63 <option value="hide" selected="true">hide</option>
64 </param>
65 <when value="show">
66 <param name="xsetnofill" type="data" label="Positive or Negative RData from group step before fillpeaks " format="rdata" help=" output from group step" />
67 </when>
68
69 </conditional>
70 -->
71 </when>
72 <!-- Two acquisition modes-->
73 <when value="two">
74
75
76 <conditional name="input_mode">
77 <param name="option" type="select" label="Choose your input type method:" >
78 <!-- Bug combinexsannos TODO <option value="one">Input from combinexsAnnos step</option> -->
79 <option value="two" selected="true">Rdata inputs from annotate</option>
80 </param>
81 <!--
82 <when value="one">
83 <param name="image_combinexsannos" type="data" label="RData output from combinexsAnnos step" format="rdata" help="output file from combinexAnnos step " />
84 <param name="image_pos" type="data" label="Positive RData ion mode from annotatediffreport step" format="rdata" help="output file from annotatediffreport step " />
85 </when>
86 -->
87 <when value="two">
88 <param name="image_pos" type="data" label="Positive annotate RData" format="rdata.camera.positive,rdata" help="output file from annotate step " />
89 <param name="image_neg" type="data" label="Negative annotate RData" format="rdata.camera.negative,rdata" help="output file from annotate step" />
90 <!--
91 <conditional name="xsetnofill_options">
92 <param name="option" type="select" label="Two RData group step (positive and negative)" help="xcmsSet xcms objects after missing data replacement from your two acquisition modes, to retrieve SNR to isotopic peaks." >
93 <option value="show">show</option>
94 <option value="hide" selected="true">hide</option>
95 </param>
96 <when value="show">
97 <param name="xsetPnofill" type="data" label="Positive RData from group step before fillpeaks " format="rdata.xcms.group,rdata" help="" />
98 <param name="xsetNnofill" type="data" label="Negative RData from group step before fillpeaks" format="rdata.xcms.group,rdata" help="" />
99 </when>
100 </conditional>
101 -->
102 </when>
103 </conditional>
104 </when>
105
106 </conditional>
107
108
109 <param name="allowMiss" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Retrieves peaks with no eviendence of adduct or isotope" help=" [allowMiss] (ionAnnot function) Logical, annotate also the peaks as single charged molecules [M+/-H]." />
110 <conditional name="option_toexclude">
111 <param name="option" type="select" label="Exclude samples" >
112 <option value="show">show</option>
113 <option value="hide" selected="true">hide</option>
114 </param>
115 <when value="show">
116 <param name="toexclude" type="text" value="blank,medium,QC" label="samples to be excluded of peak counting to non-annotated peak selection." help="" />
117 </when>
118 <when value="hide" />
119 </conditional>
120 <!--
121 <conditional name="useIso_options">
122 <param name="option" type="select" label="Calculates the relative isotopic abundance ratio (Carbon 13)" >
123 <option value="show">Yes</option>
124 <option value="hide" selected="true">No</option>
125 </param>
126 <when value="show">
127 <param name="var" type="select" label="var (incorporate.isotopes)" help="1 to use standard mean/sd estimators to carbon number prediction, 2 for median/mad estimators." >
128 <option value="1">1</option>
129 <option value="2" selected="true">2</option>
130 </param>
131 </when>
132 </conditional>
133 -->
134 <param name="html" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Logical, check if you want to generate a HTML ProbMetab report" help=" [html] (export.class.table function).This parameter uses the raw data to plot EICs and may be time consuming." />
135
136 <param name="kegg_db" type="text" size="40" label="Search on KEGG database or multiple organisms " help="Search on all KEGG organisms or multiple organisms (id1,id2,id3,...).By default,the value is KEGG which means searching on all KEGG organism. The list of KEGG IDs are available at http://rest.kegg.jp/list/organism" value="KEGG" >
137 <validator type="empty_field"/>
138 </param>
139 <param name="ppm_tol" type="integer" value="8" label="Parts per million mass tolerance allowed in the mass search" help="[ppm.tol] (create.reactionMfunction) " />
140
141
142 <param name="opt" type="select" label="Correlation option" help="[opt] (reac2cor function) cor for correlation, and pcor for partial correlation." >
143 <option value="cor" selected="true">cor</option>
144 <option value="pcor">pcor</option>
145 </param>
146
147
148 <param name="corprob" type="float" value="0.8" label="Probability that the correlation is considered significant" help="[corprob] (reac2cor function) " />
149
150
151 <param name="pcorprob" type="float" value="0.8" label="Probability that the partial correlation is considered significant." help="[pcorprob](reac2cor function)" />
152 <param name="corths" type="float" value="0.75" label="Correlation intensity threshold" help="[corths] (reac2cor function)" />
153
154 <param name="prob" type="select" label=" Calculation of the probability to attribute a mass to a compound" help="[prob] (export.class.table function). Default is 'count'. See the tool help for more details." >
155 <option value="count" selected="true">Count</option>
156 <option value="mean">Mean</option>
157 </param>
158 <!--
159 <param name="organismId" type="text" size="40" value="NULL" label="organismIdorganismId" help="(create.pathway.node.attributes function) KEGG organism id (http://www.kegg.jp/kegg/catalog/org_list.html) to filter possible pathways for known pathways for that organism. Only works for KEGG database for now. Default is NULL (all KEGG organisms).
160 " />
161
162 -->
163
164 <!-- To pass planemo test -->
165 <param name="zip_file" type="data" format="no_unzip.zip,zip" label="Zip file" help="Use only if you get a message which say that your original zip file have been deleted on the server." />
166
167 </inputs>
168
169 <outputs>
170 <!-- <data name="output_image" format="rdata" from_work_dir="probmetab.RData" label="Probmetab.RData" /> -->
171 <data name="html_output" format="html" from_work_dir="AnalysisExample.html" label="Probmetab.Analysis_Report_html" >
172 <filter>(html)</filter>
173 </data>
174 <data name="tsv_output" format="tabular" from_work_dir="Analysis_Report.tsv" label="Probmetab.CytoScape_output_Attribute_List.tsv" />
175 <data name="eics" format="zip" from_work_dir="Analysis_Report.zip" label="Probmetab.Analysis_Report_EICs_plots.zip" >
176 <filter>(html)</filter>
177 </data>
178 <data name="sif_output" format="tabular" from_work_dir="sif.tsv" label="Probmetab.CytoScape_output.sif" />
179 <data name="log" format="txt" from_work_dir="probmetab.log" label="Probmetab.log" />
180 <data name="variableMetadata" format="tabular" from_work_dir="variableMetadata.tsv" label="variableMetadata.tsv" >
181 <filter>(acquisition_options['mode'] == 'one')</filter>
182 </data>
183
184 <data name="CombineMolIon" format="tabular" from_work_dir="CombineMolIon.tsv" label="CombineMolIon.tsv" >
185 <filter>(acquisition_options['mode'] == 'two')</filter>
186 </data>
187 <data name="variableMetadata_Positive" format="tabular" from_work_dir="variableMetadata_Positive.tsv" label="variableMetadata_Positive.tsv" >
188 <filter>(acquisition_options['mode'] == 'two')</filter>
189 </data>
190 <data name="variableMetadata_Negative" format="tabular" from_work_dir="variableMetadata_Negative.tsv" label="variableMetadata_Negative.tsv" >
191 <filter>(acquisition_options['mode'] == 'two')</filter>
192 </data>
193
194 </outputs>
195
196 <tests>
197 <test>
198 <param name="acquisition_options|mode" value="one" />
199 <param name="acquisition_options|xa" value="faahOK.xset.group.retcor.group.fillPeaks.annotate.negative.Rdata" />
200 <param name="zip_file" value="faahKO_reduce.zip" ftype="zip" />
201 <output name="log">
202 <assert_contents>
203 <has_text text="ko15 ko16 wt15 wt16" />
204 <has_text text="Step 1... determine cutoff point" />
205 <has_text text="Step 2... estimate parameters of null distribution and eta0" />
206 <has_text text="Step 3... compute p-values and estimate empirical PDF/CDF" />
207 <has_text text="Step 4... compute q-values and local fdr" />
208 </assert_contents>
209 </output>
210 </test>
211 </tests>
212
213
214 <help>
215
216 .. class:: infomark
217
218 **Authors** Ricardo R. Silva et al. (2013) rsilvabioinfo@usp.br
219
220 | If you use this tool, please cite: Silva RR and al.(2010). ProbMetab: an R package for Bayesian probabilistic annotation of LC-MS-based metabolomics..
221 | For details about this tool, please go to http://labpib.fmrp.usp.br/methods/probmetab/
222
223 .. class:: infomark
224
225 **Galaxy integration** Misharl Monsoor misharl.monsoor@sb-roscoff.fr ABIMS TEAM, Station biologique de Roscoff.
226
227 | Contact support@workflow4metabolomics.org for any questions or concerns about the Galaxy implementation of this tool.
228
229 .. class:: infomark
230
231 **Contributors** Ricardo R. Silva rsilvabioinfo@usp.br, Yann Guitton yann.guitton@univ-nantes.fr and Jean-François Martin jean-francois.martin@toulouse.inra.fr
232
233 ---------------------------------------------------
234
235
236 =========
237 ProbMetab
238 =========
239
240 -----------
241 Description
242 -----------
243
244 **What it does?**
245
246 ProbMetab, an R package that promotes substantial improvement in automatic probabilistic liquid chromatography-mass spectrometry-based metabolome annotation. The inference engine core is based on a Bayesian model implemented to (i) allow diverse source of experimental data and metadata to be systematically incorporated into the model with alternative ways to calculate the likelihood function and (ii) allow sensitive selection of biologically meaningful biochemical reaction databases as Dirichlet-categorical prior distribution. Additionally, to ensure result interpretation by system biologists, we display the annotation in a network where observed mass peaks are connected if their candidate metabolites are substrate/product of known biochemical reactions. This graph can be overlaid with other graph-based analysis, such as partial correlation networks, in a visualization scheme exported to Cytoscape, with web and stand-alone versions.
247
248
249 **Details**
250
251 ProbMetab assumes peak detection, retention time correction and peak grouping [4, 5] in order to
252 perform mass peak to compound assignment.
253
254 Once the initial annotation for different forms of the same ion (adducts and isotopes), is defined,
255 one can seek for a non-redundant set of putative molecules (after charge and possible adduct
256 correction) for further inference of compound identity.
257
258 Experience shows that standard mass rules for adduct search may lose peaks, and specific rule tables must be setup for a given
259 experimental condition. In order to address this issue, a flexible workflow, which allows users to
260 integrate different methods, would improve true molecular ions recovery.
261
262 The ion annotation table has the following core information: exact mass of putative molecule with experimental error; isotopic pattern associated; adduct form associated, and the original reference to raw data.
263
264
265
266
267 -----------------
268 Workflow position
269 -----------------
270
271
272 **Upstream tools**
273
274 ========================= ========================================== ======= ==========
275 Name Output file Format Parameter
276 ========================= ========================================== ======= ==========
277 xcms.annotate xset.annotate_POS (or NEG).RData RData RData file
278 ========================= ========================================== ======= ==========
279
280
281 **General schema of the metabolomic workflow**
282
283 .. image:: probmetab_workflow.png
284
285
286 -----------
287 Input files
288 -----------
289
290 +---------------------------+------------+
291 | Parameter : label | Format |
292 +===========================+============+
293 |RData Input | RData |
294 +---------------------------+------------+
295 |RData group step | RData |
296 +---------------------------+------------+
297
298
299 ----------
300 Parameters
301 ----------
302
303 **Allow Miss**
304
305
306 Optionally retrieves peaks with no evidence of adduct or isotope and annotate them as single charged molecules [M+/-H].
307
308
309 **polarity**
310
311
312 Acquisition mode of mass spectrometer.
313
314
315 **Exclude samples**
316
317
318 Samples to be excluded of peak counting to non-annotated peak selection.
319
320 **Calculate**
321
322 **intervals**
323 A vector of SNR numerical intervals, to which different carbon offset should be added to predicted C-number.
324
325 **offset**
326
327 A vector of empirically estimated carbon offset to be added to predicted C-number.
328
329 **massWeigth**
330 Is the contribution parameter of the probabilistic model.
331
332 **likelihood**
333
334 Which noise model to use, "erfc" to complementary error function, or "gaussian" to standard gaussian with two sd corresponding to the given p.p.m precision.
335
336 **precision**
337
338 Equipment mass accuracy, usually the same used in exact mass search.
339
340 **KEGG database**
341
342
343 Select if you want to search on all KEGG organisms or multiple organisms (id1,id2,id3,...).By default,the value is KEGG which means searching on all KEGG organism. The list of KEGG IDs are available at "http://rest.kegg.jp/list/organism".
344
345 **ppm.tol**
346
347
348 Parts per million mass tolerance allowed in the mass search (create.reactionMfunction).
349
350 **HTML**
351
352
353 Logical, check if you want to generate a HTML ProbMetab report.This parameter uses the raw data to plot EICs and may be time consuming.
354
355 **opt**
356
357
358 (reac2cor function) Correlation option, cor for correlation, and pcor for partial correlation.
359
360 **corprob**
361
362 (reac2cor function) Probability that the correlation is considered significant.
363
364
365 **pcorprob**
366
367
368 (reac2cor function) Probability that the partial correlation is considered significant.
369
370 **corths**
371
372
373 (reac2cor function) Correlation intensity threshold.
374
375 **prob**
376
377 (export.class.table). How to calculate the probability to attribute a mass to a compound. Default is "count", which divide the number of times each identity was was attributed by the number of samples. Optionally the user could choose to use the mean of the probabilities of the identity, "mean".
378
379
380 **organismIdorganismId**
381
382 (create.pathway.node.attributes function) KEGG organism id (http://www.kegg.jp/kegg/catalog/org_list.html) to filter possibibly pathwyas for known pathways for that organism. Only works for KEGG database for now. Default isNULL (all KEGG organisms).
383
384
385
386 ------------
387 Output files
388 ------------
389
390 Probmetab.RData
391 | Rdata file, that be used outside Galaxy in R.
392
393 Probmetab.Analysis_Report_htmlSelect if you want to search on all KEGG organisms or multiple organisms (id1,id2,id3,...).By default,the value is KEGG which means searching on all KEGG organism. The list of KEGG IDs are available at http://rest.kegg.jp/list/organism
394 | A list with a matrix "classTable" with attributions and probabilities and indexes of selected masses from xcms peak table (HTML format).
395
396 Probmetab.CytoScape_output_Attribute_List.tsv
397 | A list with a matrix "classTable" with attributions and probabilities and indexes of selected masses from xcms peak table, that can be used as Attribute table list in CytoScape (tsv format).
398
399 Probmetab.Analysis_Report_EICs_plots
400 | Zip file containing the EIC plots (PNG format) of the metabolites that are listed in the HTML or tsv report.
401
402 Probmetab.CytoScape_output.sif
403 | Sif format file that can be used in CytoScape to visualize the network.
404
405
406 ---------------------------------------------------
407
408 Changelog/News
409 --------------
410
411 **Version 1.0.1 - 16/05/2016**
412
413 - TEST: refactoring to pass planemo test using conda dependencies
414
415
416 **Version 1.0.0 - 10/06/2015**
417
418 - NEW: ProbMetab first version
419
420
421 </help>
422 <citations>
423 <citation type="doi">10.1093/bioinformatics/btu019</citation>
424 <citation type="doi">10.1093/bioinformatics/btu813</citation>
425 </citations>
426 </tool>
427
428