Mercurial > repos > pieterlukasse > prims_masscomb

comparison masscomb_dbsearch_xtandem.xml @ 0:d6001e8d7441

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Push to main toolshed
author pieter.lukasse@wur.nl
date Wed, 08 Jan 2014 11:34:51 +0100
parents
children b34fb7461546
comparison
equal deleted inserted replaced
-1:000000000000 0:d6001e8d7441
1 <tool name="X!Tandem" id="masscomb_xtandem200" version="2.0.0">
2 <description>MS/MS DB search</description>
3 <!--
4 For remote debugging start you listener on port 8000 and use the following as command interpreter:
5 java -jar -Xdebug -Xrunjdwp:transport=dt_socket,address=D0100564.wurnet.nl:8000
6 -->
7 <command interpreter="java -jar">
8 MassComb.jar
9 -action XTANDEMSEARCH
10 -outputFile $outputFile
11 -fileGrouping $fileType.type
12 -inputFile $fileType.inputFile
13 -parametersFile $parametersFile
14 -outputTsv $outTsv
15 -outReport $htmlReportFile
16 -outReportPicturesPath $htmlReportFile.files_path
17 </command>
18 <inputs>
19 <conditional name="fileType">
20 <param name="type" type="select" label="select MS/MS input type">
21 <option value="single" selected="true">single-File</option>
22 <option value="fileSet">fileSet</option>
23 </param>
24 <when value="single">
25 <param name="inputFile" type="data" format="mzml" label="MS/MS input file (mzml)"/>
26 </when>
27 <when value="fileSet">
28 <param name="inputFile" type="data" format="prims.fileset.zip" label="input file"/>
29 </when>
30 </conditional>
31
32 <param name="precursor_mass_tolerance_lower" type="text" size="30" label="precursor monoisotopic mass_tolerance_lower" value="100" help=""/>
33 <param name="precursor_mass_tolerance_upper" type="text" size="30" label="precursor monoisotopic mass_tolerance_upper" value="100" help=""/>
34 <param name="precursor_error_units" type="select" label="precursor_error_units" help="">
35 <option value="ppm" selected="true">ppm</option>
36 <option value="Daltons">Daltons</option>
37 </param>
38 <param name="fragment_mass_tolerance" type="text" size="30" label="fragment_mass_tolerance" value="0.4" help=""/>
39 <param name="fragment_error_units" type="select" label="fragment_error_units" help="">
40 <option value="ppm">ppm</option>
41 <option value="Daltons" selected="true">Daltons</option>
42 </param>
43 <param name="database" type="data" format="fasta" label="Protein sequences DB (FASTA)"/>
44 <!--
45 <param name="min_precursor_charge" type="text" size="30" label="min_precursor_charge" value="1" help=""/>
46 <param name="max_precursor_charge" type="text" size="30" label="max_precursor_charge" value="4" help=""/>-->
47 <param name="fixed_modifications" type="select" display="checkboxes" multiple="true" label="Complete modifications" help="">
48 <option value="57.021464@C">Carbamidomethyl (C)</option>
49 <option value="57.021464@C,10.008269@R,8.014199@K">Cam+SILAC (8@K,10@R)</option>
50 <option value="57.021464@C,4.025107@K,6.020129@R">Cam+SILAC (4@K,6@R)</option>
51 <option value="57.021464@C,4.025107@K,6.020129@R,6.020129@L">Cam+SILAC (4@K,6@R,6@L)</option>
52 <option value="58.005479@C">Carboxymethyl (C)</option>
53 <option value="45.987721@C">Methylthio (C)</option>
54 <option value="47.984744@C">Trioxidation (C)</option>
55 <option value="442.224991@C">ICAT-D (C)</option>
56 <option value="450.275205@C">ICAT-D:2H(8) (C)</option>
57 <option value="227.126991@C">ICAT-C (C)</option>
58 <option value="236.157185@C">ICAT-C:13C(9) (C)</option>
59 <option value="58.005479@C">Carboxymethyl (C)</option>
60 <option value="105.057849@C">Pyridylethyl (C)</option>
61 <option value="71.037114@C">Propionamide (C)</option>
62 <option value="125.047679@C">Nethylmaleimide (C)</option>
63 <option value="144.102063@[,144.102063@K">iTRAQ (N-term,K)</option>
64 <option value="57.021464@C,144.102063@[,144.102063@K">Cam + iTRAQ (C,N-term,K)</option>
65 <option value="57.021464@C,224.152478@K,224.152478@[">Cam + TMT (C,K,nt)</option>
66 <option value="57.021464@C,225.155833@K,225.155833@[">Cam + TMT2plex (C,K,nt)</option>
67 <option value="57.021464@C,229.1629328@K,229.1629328@[">Cam + TMT6plex (C,K,nt)</option>
68 <option value="57.021464@C,28.0313@[,28.0313@K">Cam + Dimethyl (C,28@N-term,K)</option>
69 <option value="57.021464@C,32.0564@[,32.0564@K">Cam + Dimethyl (C,32@N-term,K)</option>
70 <option value="57.021464@C,36.0757@[,36.0757@K">Cam + Dimethyl (C,36@N-term,K)</option>
71 <option value="45.987721@C,144.102063@[,144.102063@K">Methylthio + iTRAQ (C,N-term,K)</option>
72 <option value="45.987721@C,224.152478@K,224.152478@[">Methylthio + TMT (C,K,nt)</option>
73 <option value="45.987721@C,225.155833@K,225.155833@[">Methylthio + TMT2plex (C,K,nt)</option>
74 <option value="45.987721@C,229.1629328@K,229.1629328@[">Methylthio + TMT6plex (C,K,nt)</option>
75 <option value="14.0156@],14.0156@D,14.0156@E">Methy +14Da (D,E,C-term)</option>
76 </param>
77 <param name="potential_modifications" type="select" display="checkboxes" multiple="true" label="Potential modifications" help="">
78 <option value="15.994915@M">Oxidation (M)</option>
79 <option value="15.994915@W">Oxidation (W)</option>
80 <option value="0.984016@N">Deamidation (N)</option>
81 <option value="0.984016@Q">Deamidation (Q)</option>
82 <option value="79.966331@S">Phospho (S)</option>
83 <option value="79.966331@T">Phospho (T)</option>
84 <option value="79.966331@Y">Phospho (Y)</option>
85 <option value="79.956815@Y">Sulfo (Y)</option>
86 <option value="42.010565@K">Acetyl (K)</option>
87 <option value="43.005814@[">Carbamyl (nt)</option>
88 <option value="43.005814@K">Carbamyl (K)</option>
89 <option value="72.021129@[">Carboxyethyl (nt)</option>
90 <option value="72.021129@K">Carboxyethyl (K)</option>
91 <option value="57.021464@[">Carbamidomethyl (nt)</option>
92 <option value="57.021464@K">Carbamidomethyl (K)</option>
93 <option value="57.021464@C">Carbamidomethyl (C)</option>
94 <option value="58.005479@C">Carboxymethyl (C)</option>
95 <option value="45.987721@C">Methylthio (C)</option>
96 <option value="125.047679@C">Nethylmaleimide (C)</option>
97 <option value="31.989829@C">Dioxidation (C)</option>
98 <option value="47.984744@C">Trioxidation (C)</option>
99 <option value="27.994915@K">formyl (K)</option>
100 <option value="27.994915@[">formyl (nt)</option>
101 <option value="114.042927@K">GlyGly (K)</option>
102 <option value="8.0502@C">ICAT-D:2H(8) (C)</option>
103 <option value="9.0302@C">ICAT-C:13C(9) (C)</option>
104 <option value="144.102063@[">iTRAQ (N-term)</option>
105 <option value="144.102063@K">iTRAQ (K)</option>
106 <option value="6.020129@L">Label:13C(6) (L)</option>
107 <option value="6.020129@K">Label:13C(6) (K)</option>
108 <option value="8.014199@K">Label:13C(6)15N(2) (K)</option>
109 <option value="6.020129@R">Label:13C(6) (R)</option>
110 <option value="4.025107@K">Label:2H(4) (K)</option>
111 <option value="125.047679@C">Nethylmaleimide (C)</option>
112 <option value="31.005814@C">Sulfinamide (C)</option>
113 <option value="224.152478@K,224.152478@[">TMT (K,nt)</option>
114 <option value="225.155833@K,225.155833@[">TMT2plex (K,nt)</option>
115 <option value="229.1629328@K,229.1629328@[">TMT6plex (K,nt)</option>
116 </param>
117 <!--
118 <param name="missed_cleavages" type="text" size="30" label="missed_cleavages" value="1" help="Nr. of possible cleavage sites missed by the enzyme"/>-->
119 <param name="minimum_fragment_mz" type="text" size="30" label="minimum_fragment_mz" value="150" help=""/>
120 <param name="cleavage_site" type="select" label="cleavage_site" help="">
121 <option selected="true" value="[RK]|{P}">trypsin, [RK]|{P}</option>
122 <option value="[R]|[X]">endo-arg-C, [R]|[X]</option>
123 <option value="[K]|[X]">endo-lys-C, [K]|[X]</option>
124 <option value="[E]|[X]">endo-glu-C, [E]|[X]</option>
125 <option value="[X]|[D]">endo-asp-N, [X]|[D]</option>
126 <option value="[ED]|[X]">V8, [ED]|[X]</option>
127 <option value="[FYWL]|{P}">chymotrypsin, [FYWL]|{P}</option>
128 </param>
129 <param name="maximum_missed_cleavage_sites" type="integer" size="10" value="1"
130 label="maximum missed cleavage sites"
131 help="maximum number of missed cleavage sites allowed within a peptide. For a specific,
132 aggressive enzyme such as trypsin, the number of missed sites will be low: a value of 1 or 2 is appropriate.
133 For a non-specific enzyme, such as pepsin, then a value of 50 is more appropriate."/>
134 <param name="max_valid_expect" type="text" size="30" label="maximum valid expectation value" value="0.1"
135 help="Max E-Value of a hit to be reported. All results with expectation values less than this value
136 are considered to be statisitically significant and are recorded. "/>
137 <conditional name="refinementOpt">
138 <param name="refinement" type="select" label="Refine search" help="Select this to enable a second round of more
139 detailed searching, using only the set of proteins found by the contraints above. E.g.
140 Rather than entering the 'potential modifications' in the options above, try entering them here only. This is
141 faster and limits this more thorough searching to a set of proteins for which there is already some evidence.">
142 <option value="yes">Yes</option>
143 <option value="no" selected="true">No</option>
144 </param>
145 <when value="yes">
146 <param name="refine_point_mutation" type="select" label="Allow for point mutations (substitutions)"
147 help="Test the selected sequences for the possibility of a point mutation in each one of the
148 peptides generated with the initial cleavage chemistry.">
149 <option value="yes" selected="true">Yes</option>
150 <option value="no">No</option>
151 </param>
152 <param name="refine_potential_modifications" type="select" display="checkboxes" multiple="true" label="Potential modifications to look for in refined search" help="">
153 <option value="15.994915@M">Oxidation (M)</option>
154 <option value="15.994915@W">Oxidation (W)</option>
155 <option value="0.984016@N">Deamidation (N)</option>
156 <option value="0.984016@Q">Deamidation (Q)</option>
157 <option value="79.966331@S">Phospho (S)</option>
158 <option value="79.966331@T">Phospho (T)</option>
159 <option value="79.966331@Y">Phospho (Y)</option>
160 <option value="79.956815@Y">Sulfo (Y)</option>
161 <option value="42.010565@K">Acetyl (K)</option>
162 <option value="43.005814@[">Carbamyl (nt)</option>
163 <option value="43.005814@K">Carbamyl (K)</option>
164 <option value="72.021129@[">Carboxyethyl (nt)</option>
165 <option value="72.021129@K">Carboxyethyl (K)</option>
166 <option value="57.021464@[">Carbamidomethyl (nt)</option>
167 <option value="57.021464@K">Carbamidomethyl (K)</option>
168 <option value="57.021464@C">Carbamidomethyl (C)</option>
169 <option value="58.005479@C">Carboxymethyl (C)</option>
170 <option value="45.987721@C">Methylthio (C)</option>
171 <option value="125.047679@C">Nethylmaleimide (C)</option>
172 <option value="31.989829@C">Dioxidation (C)</option>
173 <option value="47.984744@C">Trioxidation (C)</option>
174 <option value="27.994915@K">formyl (K)</option>
175 <option value="27.994915@[">formyl (nt)</option>
176 <option value="114.042927@K">GlyGly (K)</option>
177 <option value="8.0502@C">ICAT-D:2H(8) (C)</option>
178 <option value="9.0302@C">ICAT-C:13C(9) (C)</option>
179 <option value="144.102063@[">iTRAQ (N-term)</option>
180 <option value="144.102063@K">iTRAQ (K)</option>
181 <option value="6.020129@L">Label:13C(6) (L)</option>
182 <option value="6.020129@K">Label:13C(6) (K)</option>
183 <option value="8.014199@K">Label:13C(6)15N(2) (K)</option>
184 <option value="6.020129@R">Label:13C(6) (R)</option>
185 <option value="4.025107@K">Label:2H(4) (K)</option>
186 <option value="125.047679@C">Nethylmaleimide (C)</option>
187 <option value="31.005814@C">Sulfinamide (C)</option>
188 <option value="224.152478@K,224.152478@[">TMT (K,nt)</option>
189 <option value="225.155833@K,225.155833@[">TMT2plex (K,nt)</option>
190 <option value="229.1629328@K,229.1629328@[">TMT6plex (K,nt)</option>
191 </param>
192 <param name="refine_max_valid_expect" type="text" size="30" label="maximum valid expectation value for identifications coming from refine step" value="0.01"
193 help="Max E-Value of a 'refine based' hit to be reported. Notice that the default value here is stricter than
194 the same parameter for 'non-refine based' identifications above. "/>
195 </when>
196 </conditional>
197 <param name="reverse_scoring" type="select" label="Scoring, include reverse" help=" Use the X! Tandem protein sequence reverse method (sequences are reversed in memory and searched again, the tag ':reversed' is added to the protein description).">
198 <option value="yes">Yes</option>
199 <option value="no" selected="true">No</option>
200 <option value="only">Only</option>
201 </param>
202
203 </inputs>
204 <configfiles>
205 <configfile name="parametersFile">&lt;?xml version="1.0" encoding="UTF-8"?&gt;
206 &lt;tns:Program xmlns:tns="http://masscomb.pri.com/toolparameters/" name="XTandemWrapper" program="XTandemWrapper"&gt;
207 &lt;Files/&gt;
208 &lt;Parameters&gt;
209 &lt;Attribute attributeName="xtandemLocation" value="/home/lukas007/galaxy-dist/tool-data/prims/tandem-linux-12-10-01-1/bin/" type="Unknown" description=""/&gt;
210 &lt;Attribute attributeName="database" value="${database}" type="Unknown" description=""/&gt;
211 &lt;Attribute attributeName="precursor_mass_tolerance_lower" toolSpecificName="spectrum, parent monoisotopic mass error minus" value="${precursor_mass_tolerance_lower}" type="Unknown" description=""/&gt;
212 &lt;Attribute attributeName="precursor_mass_tolerance_upper" toolSpecificName="spectrum, parent monoisotopic mass error plus" value="${precursor_mass_tolerance_upper}" type="Unknown" description=""/&gt;
213 &lt;Attribute attributeName="precursor_error_units" toolSpecificName="spectrum, parent monoisotopic mass error units" value="${precursor_error_units}" type="Unknown" description=""/&gt;
214 &lt;Attribute attributeName="fragment_mass_tolerance" toolSpecificName="spectrum, fragment monoisotopic mass error" value="${fragment_mass_tolerance}" type="Unknown" description=""/&gt;
215 &lt;Attribute attributeName="fragment_error_units" toolSpecificName="spectrum, fragment monoisotopic mass error units" value="${fragment_error_units}" type="Unknown" description=""/&gt;
216 &lt;Attribute attributeName="fixed_modifications" toolSpecificName="residue, modification mass" value="${fixed_modifications}" type="Unknown" description=""/&gt;
217 &lt;Attribute attributeName="potential_modifications" toolSpecificName="residue, potential modification mass" value="${potential_modifications}" type="Unknown" description=""/&gt;
218 &lt;Attribute attributeName="minimum_fragment_mz" toolSpecificName="spectrum, minimum fragment mz" value="${minimum_fragment_mz}" type="Unknown" description=""/&gt;
219 &lt;Attribute attributeName="cleavage_site" toolSpecificName="protein, cleavage site" value="${cleavage_site}" type="Unknown" description=""/&gt;
220 &lt;Attribute attributeName="maximum_missed_cleavage_sites" toolSpecificName="scoring, maximum missed cleavage sites" value="${maximum_missed_cleavage_sites}" type="Unknown" description=""/&gt;
221 &lt;Attribute attributeName="max_valid_expect" toolSpecificName="output, maximum valid expectation value" value="${max_valid_expect}" type="Unknown" description=""/&gt;
222 &lt;Attribute attributeName="refinement" toolSpecificName="refine" value="${refinementOpt.refinement}" type="Unknown" description=""/&gt;
223 #if $refinementOpt.refinement == "yes"
224 &lt;Attribute attributeName="refine_point_mutation" toolSpecificName="refine, point mutations" value="${refinementOpt.refine_point_mutation}" type="Unknown" description=""/&gt;
225 &lt;Attribute attributeName="refine_potential_modifications" toolSpecificName="refine, potential modification mass" value="${refinementOpt.refine_potential_modifications}" type="Unknown" description=""/&gt;
226 &lt;Attribute attributeName="refine_max_valid_expect" toolSpecificName="refine, maximum valid expectation value" value="${refinementOpt.refine_max_valid_expect}" type="Unknown" description=""/&gt;
227 #end if
228 &lt;Attribute attributeName="reverse_scoring" toolSpecificName="scoring, include reverse" value="${reverse_scoring}" type="Unknown" description=""/&gt;
229 &lt;/Parameters&gt;
230 &lt;/tns:Program&gt;
231 </configfile>
232 </configfiles>
233 <outputs>
234 <data name="outputFile" format="bioml" label="${tool.name} on ${on_string} - Results XML">
235 <change_format>
236 <when input="fileType.type" value="fileSet" format="prims.fileset.zip" />
237 </change_format>
238 </data>
239 <data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - HTML report"> </data>
240 <data name="outTsv" format="tabular" label="${tool.name} on ${on_string} - TSV report"> </data>
241 </outputs>
242 <tests>
243 <test>
244 </test>
245 </tests>
246 <help>
247
248 .. class:: infomark
249
250 This tool searches MS/MS spectra against a database using X!Tandem.
251
252 For a complete set of parameters and their default values see `the X!Tandem parameters documentation page`_ .
253 Parameters that are not
254 made available in the UI above but are listed in the given link are submitted with their
255 default values.
256
257 For more information on the refine step see: `Why should I use "refinement" to find modifications?`_ .
258
259 For more information on the expectation value calculation see:
260 `A Method for Assessing the Statistical Significance of Mass Spectrometry-Based Protein Identifications Using General Scoring Schemes`_
261 , David Fenyö and Ronald C. Beavis, Anal. Chem., 2003, 75, 768-774.
262 This reference describes how peptides are scored by X!Tandem.
263 The expectation values on the individual peptides are calculated using this method.
264 <!-- Add this from Ron's email ? :
265 They are an estimate of the spectrum-to-peptide match E-value associated with the
266 null-hypothesis "all spectrum-to-peptide matches are stochasitic".
267 -->
268
269 .. _the X!Tandem parameters documentation page: http://www.thegpm.org/tandem/api/index.html
270
271 .. _Why should I use "refinement" to find modifications?: http://www.thegpm.org/GPM/refine.html
272
273 .. _A Method for Assessing the Statistical Significance of Mass Spectrometry-Based Protein Identifications Using General Scoring Schemes: http://www.ncbi.nlm.nih.gov/pubmed/12622365
274
275 -----
276
277 **Output**
278
279 This tools returns the X!Tandem XML output which can be converted to MzIdentML using the DBSearch converter tool.
280
281 It also returns an HTML file with the list of peptides and the option to visualize the peptide to spectrum match
282 using an embedded spectrum viewer.
283
284 .. image:: $PATH_TO_IMAGES/xtandem_results_viewer.png
285
286 Last but not least, it returns the list of identifications in TSV (tab separated values) format for users that are satisfied with this
287 and do not need further processing steps like protein inference.
288
289 For the GPM web UI of X!Tandem see:
290 http://ppp.thegpm.org/tandem/thegpm_ppp.html
291
292 </help>
293 </tool>