Mercurial > repos > lecorguille > xcms_xcmsset

comparison abims_xcms_xcmsSet.xml @ 0:054e4681667c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author lecorguille
date Fri, 07 Aug 2015 10:49:35 -0400
parents
children c5fa73f1703f
comparison
equal deleted inserted replaced
-1:000000000000 0:054e4681667c
1 <tool id="abims_xcms_xcmsSet" name="xcms.xcmsSet" version="2.0.2">
2
3 <description>Filtration and Peak Identification using xcmsSet function from xcms R package to preprocess LC/MS data for relative quantification and statistical analysis </description>
4
5 <requirements>
6 <requirement type="package" version="3.1.2">R</requirement>
7 <requirement type="binary">Rscript</requirement>
8 <requirement type="package" version="1.44.0">xcms</requirement>
9 <requirement type="package" version="2.1">xcms_w4m_script</requirement>
10 </requirements>
11
12 <stdio>
13 <exit_code range="1:" level="fatal" />
14 </stdio>
15
16 <command>
17 xcms.r
18 #if $inputs.input == "lib":
19 library $__app__.config.user_library_import_dir/$__user_email__/$inputs.library
20 #elif $inputs.input == "zip_file":
21 zipfile $inputs.zip_file
22 #end if
23
24 xfunction xcmsSet
25 ## profmethod $profmethod
26 nSlaves \${GALAXY_SLOTS:-1} method $methods.method
27 #if $methods.method == "centWave":
28 ppm $methods.ppm
29 peakwidth "c($methods.peakwidth)"
30 #if $methods.options_scanrange.option == "show":
31 scanrange "c($methods.options_scanrange.scanrange)"
32 #end if
33 #if $methods.options_c.option == "show":
34 mzdiff $methods.options_c.mzdiff
35 snthresh $methods.options_c.snthresh
36 integrate $methods.options_c.integrate
37 noise $methods.options_c.noise
38 prefilter "c($methods.options_c.prefilter)"
39 #end if
40 #elif $methods.method == "matchedFilter":
41 step $methods.step
42 fwhm $methods.fwhm
43 #if $methods.options_m.option == "show":
44 ## sigma "$methods.options_m.sigma"
45 max $methods.options_m.max
46 snthresh $methods.options_m.snthresh
47 ## mzdiff $methods.options_m.mzdiff
48 steps $methods.options_m.steps
49 ## sleep $methods.options_m.sleep
50 #end if
51 #elif $methods.method == "MSW":
52 snthr $methods.snthr
53 nearbyPeak $methods.nearbyPeak
54 winSize.noise $methods.winSize_noise
55 amp.Th $methods.amp_Th
56 scales "c($methods.scales)"
57 SNR.method "$methods.SNR_method"
58 #end if
59 &amp;&amp; (mv xcmsSet.RData $xsetRData;
60 mv sampleMetadata.tsv $sampleMetadata;
61 mv TICs_raw.pdf $ticsRawPdf;
62 mv BPCs_raw.pdf $bpcsRawPdf;
63 mv xset.log $log);
64 cat $log
65 </command>
66
67 <inputs>
68
69 <conditional name="inputs">
70 <param name="input" type="select" label="Choose your inputs method" >
71 <option value="zip_file" selected="true">Zip file from your history containing your chromatograms</option>
72 <option value="lib" >Library directory name</option>
73 </param>
74 <when value="zip_file">
75 <param name="zip_file" type="data" format="no_unzip.zip" label="Zip file" />
76 </when>
77 <when value="lib">
78 <param name="library" type="text" size="40" label="Library directory name" help="The name of your directory containing all your data" >
79 <validator type="empty_field"/>
80 </param>
81 </when>
82
83 </conditional>
84
85
86 <!--
87 <param name="profmethod" type="select" label="Method to use for profile generation (profmethod)" >
88 <option value="bin" selected="true">bin</option>
89 <option value="binlin">binlin</option>
90 <option value="binlinbase">binlinbase</option>
91 <option value="intlin">intlin</option>
92 </param>
93 <param name="nSlaves" type="integer" value="9" label="MPI-slaves CPU" help="number of MPI-slaves to use for parallel peak detection" />
94 -->
95 <conditional name="methods">
96 <param name="method" type="select" label="Extraction method for peaks detection" help="[method] See the help section below">
97 <option value="centWave" >centWave</option>
98 <option value="matchedFilter" selected="true">matchedFilter</option>
99 <option value="MSW">MSW</option>
100 </param>
101
102 <!-- centWave Filter options -->
103 <when value="centWave">
104 <param name="ppm" type="integer" value="25" label="Max tolerated ppm m/z deviation in consecutive scans in ppm" help="[ppm]" />
105 <param name="peakwidth" type="text" value="20,50" label="Min,Max peak width in seconds" help="[peakwidth]" />
106 <conditional name="options_scanrange">
107 <param name="option" type="select" label="Scan range option " >
108 <option value="show">show</option>
109 <option value="hide" selected="true">hide</option>
110 </param>
111 <when value="show">
112 <param name="scanrange" type="text" value="" label="scanrange" help="scan range to process, for example (16,365)" >
113 <validator type="empty_field"/>
114 </param>
115 </when>
116 </conditional>
117
118 <conditional name="options_c">
119 <param name="option" type="select" label="Advanced options" >
120 <option value="show">show</option>
121 <option value="hide" selected="true">hide</option>
122 </param>
123 <when value="show">
124 <param name="snthresh" type="integer" value="10" label="Signal/Noise threshold" help="[snthresh] Signal to noise ratio cutoff" />
125 <param name="mzdiff" type="float" value="-0.001" label="Min m/z difference" help="[mzdiff] Min m/z difference for peaks with overlapping RT " />
126 <param name="integrate" type="select" label="peak limits method" help="[integrate]" >
127 <option value="1">peak limits based on smoothed 2nd derivative (less precise)</option>
128 <option value="2">peak limits based on real data (more sensitive to noise)</option>
129 </param>
130 <param name="prefilter" type="text" value="3,100" label="Prefilter step for the first phase" help="[prefilter] Separate by coma k,I. Mass traces are only retained if they contain at least ‘k’ peaks with intensity >= ‘I’"/>
131 <param name="noise" type="integer" value="0" label="Noise filter" help="[noise] optional argument which is useful for data that was centroided without any intensity threshold, centroids with intensity smaller than ‘noise’ are omitted from ROI detection"/>
132 </when>
133 </conditional>
134 </when>
135
136 <!-- matched Filter options -->
137 <when value="matchedFilter">
138 <param name="step" type="float" value="0.01" label="Step size to use for profile generation" help="[step] The peak detection algorithm creates extracted ion base peak chromatograms (EIBPC) on a fixed step size" />
139 <param name="fwhm" type="integer" value="30" label="Full width at half maximum of matched filtration gaussian model peak" help="[fwhm] Only used to calculate the actual sigma" />
140 <conditional name="options_m">
141 <param name="option" type="select" label="Advanced options" >
142 <option value="show">show</option>
143 <option value="hide" selected="true">hide</option>
144 </param>
145 <when value="show">
146 <!--
147 <param name="sigma" type="hidden" value="fwhm/2.3548" label="sigma" help="standard deviation (fwhm/2.3548)" />
148 -->
149 <param name="max" type="integer" value="5" label="Maximum number of peaks per extracted ion chromatogram" help="[max]" />
150 <param name="snthresh" type="integer" value="10" label="Signal to noise ratio cutoff" help="[snthresh]" />
151 <param name="steps" type="integer" value="2" label="Number of steps to merge prior to filtration" help="[steps] The peak identification algorithm combines a given number of EIBPCs prior to filtration and peak detection, as defined by the steps argument" />
152 <!--
153 <param name="mzdiff" type="text" size="20" value="0.8-step*steps" label="m/z difference" help="min m/z difference for peaks with overlapping RT " />
154 -->
155 </when>
156 </conditional>
157 </when>
158
159 <!-- MSW Filter options -->
160 <when value="MSW">
161 <param name="nearbyPeak" type="select" label="Determine whether to include the nearby small peaks of major peaks" help="[nearbyPeak]" >
162 <option value="TRUE">TRUE</option>
163 <option value="FALSE">FALSE</option>
164 </param>
165 <param name="winSize_noise" type="integer" value="500" label="The local window size to estimate the noise level" help="[winSize.noise]" />
166 <param name="snthr" type="integer" value="3" label="SNR (Signal to Noise Ratio) threshold" help="[snthr]" />
167 <param name="amp_Th" type="float" value="0.002" label="Minimum required relative amplitude of the peak" help="[amp.Th] Ratio to the maximum of CWT coefficients" />
168 <param name="scales" type="text" value="seq(1,22,3)" label="Scales for the Continuous Wavelet Transform (CWT)" help="[scales] Scales are linked to the width of the peaks that are to be detected. Tape as indicaded seq('n,n,n') or c(n,n) : seq(from, to, by steps), c - linear vector " />
169 <param name="SNR_method" type="text" value="data.mean" label="SNR (Signal to Noise Ratio) method" help="[SNR.method] Method to estimate noise level. Currently, only 95 percentage quantile is supported." />
170 </when>
171 </conditional>
172 </inputs>
173
174 <outputs>
175 <data name="xsetRData" format="rdata.xcms.raw" label="xset.RData" />
176 <data name="sampleMetadata" format="tabular" label="sampleMetadata.tsv" />
177 <data name="ticsRawPdf" format="pdf" label="xset.TICs_raw.pdf" />
178 <data name="bpcsRawPdf" format="pdf" label="xset.BPCs_raw.pdf" />
179 <data name="log" format="txt" label="xset.log.txt" />
180 </outputs>
181
182 <tests>
183 <test>
184 <param name="inputs.input" value="zip_file" />
185 <param name="inputs.zip_file" value="sacuri.zip" />
186 <param name="methods.method" value="matchedFilter" />
187 <param name="methods.step" value="0.01" />
188 <param name="methods.fwhm" value="4" />
189 <param name="methods.options_m.option" value="show" />
190 <param name="methods.options_m.max" value="50" />
191 <param name="methods.options_m.snthresh" value="1" />
192 <param name="methods.options_m.steps" value="2" />
193 <output name="xsetRData" file="xset.RData" />
194 <output name="sampleMetadata" file="sampleMetadata.tsv" />
195 <output name="ticsRawPdf" file="xset.TICs_raw.pdf" />
196 <output name="bpcsRawPdf" file="xset.BPCs_raw.pdf" />
197 <output name="log" file="xset.log.txt" />
198 </test>
199 </tests>
200
201 <help>
202
203 .. class:: infomark
204
205 **Authors** Colin A. Smith csmith@scripps.edu, Ralf Tautenhahn rtautenh@gmail.com, Steffen Neumann sneumann@ipb-halle.de, Paul Benton hpaul.benton08@imperial.ac.uk and Christopher Conley cjconley@ucdavis.edu
206
207 .. class:: infomark
208
209 **Galaxy integration** ABiMS TEAM - UPMC/CNRS - Station biologique de Roscoff and Yann Guitton yann.guitton@univ-nantes.fr - part of Workflow4Metabolomics.org [W4M]
210
211 | Contact support@workflow4metabolomics.org for any questions or concerns about the Galaxy implementation of this tool.
212
213 ---------------------------------------------------
214
215 ============
216 Xcms.xcmsSet
217 ============
218
219 -----------
220 Description
221 -----------
222
223 This tool is used for preprocessing analyte data from multiple LC/MS files (formats NetCDF, mzXML and mzData). It extracts ion from each sample independently and using a statistic model, peaks are filtered and integrated.
224 You can read a tutorial on how to perform xcms preprocessing which is available here_.
225
226 .. _here: http://web11.sb-roscoff.fr/download/w4m/howto/w4m_HowToPerformXcmsPreprocessing_v02.pdf
227
228
229 -----------------
230 Workflow position
231 -----------------
232
233 **Upstream tools**
234
235 ========================= ================= ======= =========
236 Name output file format parameter
237 ========================= ================= ======= =========
238 NA NA zip NA
239 ========================= ================= ======= =========
240
241
242 **Downstream tools**
243
244 +---------------------------+--------------------+-----------------+
245 | Name | Output file | Format |
246 +===========================+====================+=================+
247 |xcms.group | xset.RData | rdata.xcms.raw |
248 +---------------------------+--------------------+-----------------+
249 |PCA ellipsoid by factors | sampleMetadata.tsv | Tabular |
250 +---------------------------+--------------------+-----------------+
251 |Anova | sampleMetadata.tsv | Tabular |
252 +---------------------------+--------------------+-----------------+
253
254
255 **Example of a metabolomic workflow**
256
257 .. image:: XCMS_Galaxy_workflow.png
258
259
260 ------
261
262 .. class:: infomark
263
264 The output file is an xset.RData file. You can continue your analysis using it in **xcms.group** tool.
265
266 ---------------------------------------------------
267
268
269
270 -----------
271 Input files
272 -----------
273
274 +---------------------------+------------+
275 | Parameter : num + label | Format |
276 +===========================+============+
277 | 1 : Choose your inputs | zip |
278 +---------------------------+------------+
279
280 **Choose your inputs**
281
282 You have two methods for your inputs:
283
284 | Zip file (recommended): You can put a zip file containing your inputs: myinputs.zip (containing all your conditions as sub-directories).
285 | library folder: You must specify the name of your "library" (folder) created within your space project (for example: /projet/externe/institut/login/galaxylibrary/yourlibrary). Your library must contain all your conditions as sub-directories.
286
287 ----------
288 Parameters
289 ----------
290
291 Extraction method for peaks detection
292 -------------------------------------
293
294 **Matched Filter**
295
296 | One parameter to consider is the Gaussian model peak width used for matched filtration,an integral part of the peak detection algorithm.
297 | For a discussion of how model peak width affects the signal to noise ratio, see Danielsson et al. (2002).
298
299
300 **cent Wave**
301
302 | This algorithm is most suitable for high resolution LC/{TOF,OrbiTrap,FTICR}-MS data in centroid mode.
303 | Due to the fact that peak centroids are used, a binning step is not necessary.
304 | The method is capable of detecting close-by-peaks and also overlapping peaks. Some efforts are made to detect the exact peak boundaries to get precise peak integrals.
305
306 **MSW**
307
308 | Wavelet based, used for direct infusion data. Continuous wavelet transform (CWT) can be used to locate chromatographic peaks on different scales.
309 | If you wish to have more details about the other parameters, you can read the following documents:
310 | -Example of preprocessing data with XCMS : http://www.bioconductor.org/packages/2.12/bioc/vignettes/xcms/inst/doc/xcmsPreprocess.pdf
311 | -Details and explanations for all the parameters of XCMS package: http://www.bioconductor.org/packages/release/bioc/manuals/xcms/man/xcms.pdf
312
313
314 ------------
315 Output files
316 ------------
317
318 xset.TICs_raw.pdf
319
320 | "Total Ion Chromatograms" graph in pdf format.
321
322 xset.BPCs_raw.pdf
323
324 | "Base Peak Chromatograms" graph in pdf format with each class samples opposed.
325
326 sampleMetadata.tsv
327
328 | Tabular file that contains for each sample, it's associated class and polarity (positive,negative and mixed).
329 | This file is necessary in the Anova and PCA step of the workflow.
330
331 xset.RData: rdata.xcms.raw format
332
333 | Rdata file that is necessary in the second step of the workflow "xcms.group".
334
335 ------
336
337 .. class:: infomark
338
339 The output file is an xset.RData file. You can continue your analysis using it in **xcms.group** tool.
340
341 ---------------------------------------------------
342
343 ---------------
344 Working example
345 ---------------
346
347 Input files
348 -----------
349
350 | zip_file -> **sacuri.zip**
351
352 Parameters
353 ----------
354
355 | Method -> **matchedFilter**
356 | step -> **0.01**
357 | fwhm -> **4**
358 | Advanced option -> **show**
359 | max: -> **50**
360 | snthresh -> **1**
361 | steps -> **2**
362
363
364 Output files
365 ------------
366
367 | **1) xset.RData: RData file**
368
369 | **2) Example of a sampleMetadata.tsv :**
370
371
372 +---------------------------+------------+---------+
373 | sampleMetadata | class | polarity|
374 +===========================+============+=========+
375 |HU_neg_017 | bio |negative |
376 +---------------------------+------------+---------+
377 |HU_neg_028 | bio |negative |
378 +---------------------------+------------+---------+
379 |HU_neg_034 | bio |negative |
380 +---------------------------+------------+---------+
381 |Blanc04 | blank |negative |
382 +---------------------------+------------+---------+
383 |Blanc06 | blank |negative |
384 +---------------------------+------------+---------+
385 |Blanc09 | blank |negative |
386 +---------------------------+------------+---------+
387
388
389
390 | **3) Example of xset.TICs_raw.pdf (Total Ion Chromatograms) :**
391
392 .. image:: xcms_tics.png
393
394
395 </help>
396
397
398 <citations>
399 <citation type="doi">10.1021/ac051437y</citation>
400 <citation type="doi">10.1093/bioinformatics/btu813</citation>
401 </citations>
402
403 </tool>