Mercurial > repos > lecorguille > msnbase_readmsdata

comparison msnbase_readmsdata.xml @ 0:728ebc7ae7dd draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/workflow4metabolomics/xcms commit 9f72e947d9c241d11221cad561f3525d27231857
author lecorguille
date Tue, 18 Sep 2018 16:04:51 -0400
parents
children c0a66f15261b
comparison
equal deleted inserted replaced
-1:000000000000 0:728ebc7ae7dd
1 <tool id="msnbase_readmsdata" name="MSnbase readMSData" version="@WRAPPER_VERSION@.0">
2 <description>Imports mass-spectrometry raw data files</description>
3
4 <macros>
5 <import>macros.xml</import>
6 <import>macros_msnbase.xml</import>
7 </macros>
8
9 <expand macro="requirements"/>
10 <expand macro="stdio"/>
11
12 <command><![CDATA[
13 @COMMAND_RSCRIPT@/msnbase_readmsdata.r
14
15 #if $input.is_of_type("mzxml") or $input.is_of_type("mzml") or $input.is_of_type("mzdata") or $input.is_of_type("netcdf"):
16 singlefile_galaxyPath '$input' singlefile_sampleName '$input.name'
17 #else
18 zipfile '$input'
19 #end if
20
21 @COMMAND_LOG_EXIT@
22 ]]></command>
23
24 <inputs>
25
26 <param name="input" type="data" format="mzxml,mzml,mzdata,netcdf,no_unzip.zip,zip" label="File(s) from your history containing your chromatograms" help="Single file mode for the following formats: mzxml, mzml, mzdata and netcdf. Zip file mode for the following formats: no_unzip.zip, zip. See the help section below." />
27
28 </inputs>
29
30 <outputs>
31 <data name="xsetRData" format="rdata.msnbase.raw" label="${input.name.rsplit('.',1)[0]}.raw.RData" from_work_dir="readmsdata.RData" />
32 <data name="sampleMetadata" format="tabular" label="${input.name.rsplit('.',1)[0]}.sampleMetadata.tsv" from_work_dir="sampleMetadata.tsv" >
33 <filter>input.extension not in ["mzxml","mzml","mzdata","netcdf"]</filter>
34 </data>
35 </outputs>
36
37 <tests>
38
39 <test>
40 <param name="input" value="faahKO_reduce.zip" ftype="zip" />
41 <assert_stdout>
42 <has_text text="rowNames: faahKO_reduce/KO/ko15.CDF faahKO_reduce/KO/ko16.CDF" />
43 <has_text text="faahKO_reduce/WT/wt15.CDF faahKO_reduce/WT/wt16.CDF" />
44 <has_text text="featureNames: F1.S0001 F1.S0002 ... F4.S1278 (5112 total)" />
45 <has_text text="fvarLabels: fileIdx spIdx ... spectrum (27 total)" />
46 <has_text text="faahKO_reduce/KO/ko15.CDF ko15 KO" />
47 <has_text text="faahKO_reduce/KO/ko16.CDF ko16 KO" />
48 <has_text text="faahKO_reduce/WT/wt15.CDF wt15 WT" />
49 <has_text text="faahKO_reduce/WT/wt16.CDF wt16 WT" />
50 </assert_stdout>
51 <output name="sampleMetadata" value="sampleMetadata.tsv" />
52 </test>
53 <test>
54 <param name="input" value="ko15.CDF" ftype="netcdf" />
55 <assert_stdout>
56 <has_text text="rowNames: ./ko15.CDF" />
57 <has_text text="ko15.CDF" />
58 <has_text text="featureNames: F1.S0001 F1.S0002 ... F1.S1278 (1278 total)" />
59 <has_text text="fvarLabels: fileIdx spIdx ... spectrum (27 total)" />
60 <has_text text="./ko15.CDF ko15 ." />
61 </assert_stdout>
62 </test>
63 <!-- DISABLE FOR TRAVIS
64 Useful to generate test-data for the further steps-->
65 <test>
66 <param name="input" value="ko16.CDF" ftype="netcdf" />
67 <assert_stdout>
68 <has_text text="rowNames: ./ko16.CDF" />
69 <has_text text="ko16.CDF" />
70 <has_text text="./ko16.CDF ko16 ." />
71 </assert_stdout>
72 </test>
73 <test>
74 <param name="input" value="wt15.CDF" ftype="netcdf" />
75 <assert_stdout>
76 <has_text text="rowNames: ./wt15.CDF" />
77 <has_text text="wt15.CDF" />
78 <has_text text="./wt15.CDF wt15 ." />
79 </assert_stdout>
80 </test>
81 <test>
82 <param name="input" value="wt16.CDF" ftype="netcdf" />
83 <assert_stdout>
84 <has_text text="rowNames: ./wt16.CDF" />
85 <has_text text="wt16.CDF" />
86 <has_text text="./wt16.CDF wt16 ." />
87 </assert_stdout>
88 </test>
89 <!-- -->
90 </tests>
91
92 <help><![CDATA[
93
94 @HELP_AUTHORS@
95
96 ==================
97 MSnbase readMSData
98 ==================
99
100 -----------
101 Description
102 -----------
103
104 Reads as set of XML-based mass-spectrometry data files and
105 generates an MSnExp object. This function uses the functionality
106 provided by the ‘mzR’ package to access data and meta data in
107 ‘mzData’, ‘mzXML’ and ‘mzML’.
108
109 .. _xcms: https://bioconductor.org/packages/release/bioc/html/xcms.html
110 .. _here: http://web11.sb-roscoff.fr/download/w4m/howto/w4m_HowToPerformXcmsPreprocessing_v02.pdf
111
112
113 -----------------
114 Workflow position
115 -----------------
116
117 **Upstream tools**
118
119 ========================= ==========================================
120 Name Format
121 ========================= ==========================================
122 Upload File mzxml,mzml,mzdata,netcdf,no_unzip.zip,zip
123 ========================= ==========================================
124
125 The easier way to process is to create a Dataset Collection of the type List
126
127 **Downstream tools**
128
129 =========================== ==================== ====================
130 Name Output file Format
131 =========================== ==================== ====================
132 xcms.findChromPeaks ``*``.raw.RData rdata.msnbase.raw
133 =========================== ==================== ====================
134
135
136
137 **Example of a metabolomic workflow**
138
139 .. image:: msnbase_readmsdata_workflow.png
140
141 ---------------------------------------------------
142
143
144
145 -----------
146 Input files
147 -----------
148
149 =========================== ==================================
150 Parameter : num + label Format
151 =========================== ==================================
152 OR : Zip file zip
153 --------------------------- ----------------------------------
154 OR : Single file mzXML, mzML, mzData, netCDF
155 =========================== ==================================
156
157 **Choose your inputs**
158
159 You have two methods for your inputs:
160
161 | Single file (recommended): You can put a single file as input. That way, you will be able to launch several readMSData and findChromPeaks in parallel and use "findChromPeaks Merger" before groupChromPeaks.
162 | Zip file: You can put a zip file containing your inputs: myinputs.zip (containing all your conditions as sub-directories).
163
164 Zip file: Steps for creating the zip file
165 -----------------------------------------
166
167 **Step1: Creating your directory and hierarchize the subdirectories**
168
169
170 VERY IMPORTANT: If you zip your files under Windows, you must use the 7Zip_ software, otherwise your zip will not be well unzipped on the W4M platform (corrupted zip bug).
171
172 .. _7Zip: http://www.7-zip.org/
173
174 Your zip should contain all your conditions as sub-directories. For example, two conditions (mutant and wild):
175 arabidopsis/wild/01.raw
176 arabidopsis/mutant/01.raw
177
178 **Step2: Creating a zip file**
179
180 Create your zip file (*e.g.* arabidopsis.zip).
181
182 **Step 3 : Uploading it to our Galaxy server**
183
184 If your zip file is less than 2Gb, you can use the Get Data tool to upload it.
185
186 Otherwise if your zip file is larger than 2Gb, please refer to the HOWTO_ on workflow4metabolomics.org.
187
188 .. _HOWTO: http://application.sb-roscoff.fr/download/w4m/howto/galaxy_upload_up_2Go.pdf
189
190 For more information, do not hesitate to send us an email at supportATworkflow4metabolomics.org.
191
192 Advices for converting your files into mzXML format (XCMS input)
193 ----------------------------------------------------------------
194
195 We recommend you to convert your raw files into **mzXML** in centroid mode (smaller files); this way the files will be compatible with the xmcs centWave algorithm.
196
197 **We recommend you the following parameters:**
198
199 Use Filtering: **True**
200
201 Use Peak Picking: **True**
202
203 Peak Peaking -Apply to MS Levels: **All Levels (1-)** : Centroid Mode
204
205 Use zlib: **64**
206
207 Binary Encoding: **64**
208
209 m/z Encoding: **64**
210
211 Intensity Encoding: **64**
212
213
214 ------------
215 Output files
216 ------------
217
218 xset.RData: rdata.msnbase.raw format
219
220 | Rdata file that is necessary in the second step of the workflow "xcms.findChromPeaks".
221
222 sampleMetadata.tsv (only when a zip is used)
223
224 | Tabular file that contains for each sample its associated class and polarity (positive,negative and mixed).
225 | This file is necessary in further steps of the workflow, as the Anova and PCA steps for example.
226 | You get a sampleMetadata.tsv only if you use a zip. Otherwise, you have to provide one for the findChromPeaks Merger step.
227
228 ---------------------------------------------------
229
230 Changelog/News
231 --------------
232
233
234 **Version 2.4.0.0 - 29/03/2018**
235
236 - NEW: a new dedicated tool to read the raw data. This function was previously included in xcms.findChromPeaks. This way, you will now be able to display TICs and BPCs before xcms.findChromPeaks.
237
238 ]]></help>
239
240 <expand macro="citation" />
241 </tool>