Mercurial > repos > pieterlukasse > prims_proteomics
annotate sedmat.xml @ 17:40ec8770780d
* Added support for pepxml (and more specifically for
ProteomeDiscoverer 1.4). Tested with ProteomeDiscoverer 1.4 pepxml.
* Improved HTML report of NapQ tool.
* Fixed issue that was preventing SEDMAT matching from running
in parallel/multi-threaded.
| author | pieter.lukasse@wur.nl |
|---|---|
| date | Mon, 14 Apr 2014 17:11:33 +0200 |
| parents | 08e93cd411b9 |
| children |
| rev | line source |
|---|---|
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
1 <tool name="SedMat" id="sedmat1" version="1.0.3"> |
| 0 | 2 <description>Matches MS and MS/MS results</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 SedMat_cli.jar | |
| 9 -pl $inputMS | |
| 10 -plInputFormat apml | |
| 11 -ppids $fileType.inputFormatType.ppidsFile | |
| 12 -ppidsFileGrouping $fileType.type | |
| 13 -ppidsInputFormat $fileType.inputFormatType.ppidsInputFormat | |
| 13 | 14 -ppidsFileDescription "$fileType.inputFormatType.ppidsFile.name" |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
15 #if $fileType.inputFormatType.ppidsInputFormat == "MZML_MZIDENTML_COMBI" |
| 0 | 16 -spectraDataFile $fileType.inputFormatType.spectraDataFile |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
17 #end if |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
18 #if $fileType.inputFormatType.ppidsInputFormat == "pepxml" |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
19 -pepxmlDataType $fileType.inputFormatType.pepxmlDataType |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
20 -pepxmlGeneratedBy $fileType.inputFormatType.pepxmlGeneratedBy |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
21 #end if |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
22 -out $outputData |
| 0 | 23 -outUnmatchedMS2 $outUnmatchedMS2 |
| 24 -mtol $mtol | |
| 25 -rttol $rttol | |
| 26 -rtShiftDetectionWindow $rtShiftDetectionWindow | |
| 27 -matchOnSameSourceOnly $matchOnSameSourceOnly | |
| 28 -chargeStatesToGenerate $chargeStatesToGenerate | |
| 29 -outReport $htmlReportFile | |
| 30 -outReportPicturesPath $htmlReportFile.files_path | |
| 31 #if $troubleshoot1.troubleshootPeakLocations == True | |
| 32 -troubleshootPeakLocations YES | |
| 33 -mStart $troubleshoot1.mStart | |
| 34 -mEnd $troubleshoot1.mEnd | |
| 35 -rtStart $troubleshoot1.rtStart | |
| 36 -rtEnd $troubleshoot1.rtEnd | |
| 37 -filterSourceName $troubleshoot1.filterSourceName | |
| 38 #end if | |
| 39 #if $matchOnNamingConvention.match == True | |
| 40 -matchOnNamingConvention YES | |
| 41 -namingConventionCodesForMatching $matchOnNamingConvention.namingConventionCodesForMatching | |
| 42 #end if | |
| 43 | |
| 44 </command> | |
| 45 | |
| 46 <inputs> | |
| 47 | |
| 48 <param name="inputMS" type="data" format="apml" label="MS data (APML format)" /> | |
| 49 <!-- possible option <validator type="metadata" check="base_name" message="Metadata missing, click the pencil icon in the history item and set base_name."/> --> | |
| 50 | |
| 51 <conditional name="fileType"> | |
| 52 <param name="type" type="select" label="Peptide identification file grouping type"> | |
| 53 <option value="single" selected="true">single-File</option> | |
| 54 <option value="fileSet">fileSet</option> | |
| 55 </param> | |
| 56 <when value="single"> | |
| 57 <conditional name="inputFormatType"> | |
| 58 <param name="ppidsInputFormat" type="select" label="MS/MS input format"> | |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
59 <option value="MZML_MZIDENTML_COMBI" selected="true">mzIdentML on mzML</option> |
| 0 | 60 <option value="apml">APML</option> |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
61 <option value="pepxml">pepxml (beta support)</option> |
| 0 | 62 </param> |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
63 <when value="MZML_MZIDENTML_COMBI"> |
| 0 | 64 <param name="spectraDataFile" type="data" format="mzml" label="MS/MS spectra file (mzml)"/> |
| 65 <param name="ppidsFile" type="data" format="mzid" label="MS/MS peptide identifications file (mzidentml)"/> | |
| 66 </when> | |
| 67 <when value="apml"> | |
| 68 <param name="ppidsFile" type="data" format="apml" label="MS/MS peptide identifications file (apml)"> | |
| 69 <!-- TODO - find out how to use | |
| 70 <validator type="expression" message="You already selected this file as the MS data file.">value.id == inputMS,{"inputMS":$inputMS},{}</validator>--> | |
| 71 </param> | |
| 72 </when> | |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
73 <when value="pepxml"> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
74 <param name="ppidsFile" type="data" format="pepxml" label="MS/MS peptide identifications file (pepxml)"/> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
75 <param name="pepxmlDataType" type="select" label=">> Type of data stored in the pepxml" |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
76 help="Options marked with (*) are ProteomeDiscoverer specific scenarios"> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
77 <option value="" selected="true">--Please select--</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
78 <option value="single_2d" >2D LC-MS runs, one per msms_run_summary</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
79 <option value="multi_2d">(*) 2D LC-MS runs, multiple runs (e.g. rx.F1 to rx.FN) merged as a 'single' msms_run_summary</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
80 <option value="single_1d">1D LC-MS runs, one per msms_run_summary</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
81 </param> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
82 <param name="pepxmlGeneratedBy" type="select" label=">> pepxml generated by" |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
83 help="Some tools, like ProteomeDiscoverer 1.4, have specific issues in their pepxml generation logic. Correctly indicating the tool used here will ensure known issues are taken |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
84 into consideration when the file is parsed." > |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
85 <option value="" selected="true">--Please select--</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
86 <option value="proteome_discoverer_v1.4">ProteomeDiscoverer 1.4</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
87 <option value="other">Other</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
88 </param> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
89 |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
90 </when> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
91 |
| 0 | 92 </conditional> |
| 93 </when> | |
| 94 <when value="fileSet"> | |
| 95 <conditional name="inputFormatType"> | |
| 96 <param name="ppidsInputFormat" type="select" label="inputFormat"> | |
| 97 <option value="mzid" selected="true">mzIdentML on mzML</option> | |
| 98 </param> | |
| 99 <when value="mzid"> | |
| 100 <param name="spectraDataFile" type="data" format="prims.fileset.zip" label="MS/MS spectra fileSet (N mzml files)"/> | |
| 101 <param name="ppidsFile" type="data" format="prims.fileset.zip" label="MS/MS peptide identifications fileSet (N mzidentml files)"/> | |
| 102 </when> | |
| 103 </conditional> | |
| 104 </when> | |
| 105 </conditional> | |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
106 <param name="mtol" type="float" size="10" value="50.0" label="m/z tolerance (ppm) " /> |
| 0 | 107 <param name="rttol" type="integer" size="10" value="150" label="Rention time tolerance (seconds) " /> |
| 108 <param name="rtShiftDetectionWindow" type="integer" size="10" value="20" label="Rention time shift detection window (seconds) " help="Size of the window to use for average rt shift calculations"/> | |
| 109 | |
| 110 <param name="matchOnSameSourceOnly" type="boolean" checked="false" label="Match peaks from same source only" help="If you want this, you might have to inform how to match the source files"/> | |
| 111 <conditional name="matchOnNamingConvention"> | |
| 112 <param name="match" type="boolean" truevalue="Yes" falsevalue="No" checked="false" label="Match using naming convention" help="Use a list of codes that occur in the file names and that link them together."/> | |
| 113 <when value="Yes"> | |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
114 <param name="namingConventionCodesForMatching" type="text" size="100" value="" label=">> List of codes in naming convention" help="Add the CSV list of codes that occur in the file names and that link them together. E.g. '_F1,_F2,_F3,_F4,_F5,_F6,_F7,etc.'"/> |
| 0 | 115 </when> |
| 6 | 116 <when value="No"> |
| 117 </when> | |
| 0 | 118 </conditional> |
| 119 | |
| 120 <param name="chargeStatesToGenerate" type="select" display="checkboxes" multiple="true" label="Generate extra charge states" help="The selected charge states will be generated for each MS2 feature "> | |
| 121 <option value="1" selected="true">1</option> | |
| 122 <option value="2" selected="true">2</option> | |
| 123 <option value="3" selected="true">3</option> | |
| 124 <option value="4" selected="true">4</option> | |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
125 <option value="5" selected="true">5</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
126 <option value="6" >6</option> |
|
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
13
diff
changeset
|
127 <option value="7" >7</option> |
| 0 | 128 </param> |
| 129 | |
| 130 <param name="summaryReport" type="boolean" checked="true" label="Generate summary report" help="NB: this will increase the processing time"/> | |
| 131 | |
| 132 <conditional name="troubleshoot1"> | |
| 133 <param name="troubleshootPeakLocations" type="boolean" truevalue="Yes" falsevalue="No" checked="false" label="Troubleshoot ms1/ms2 peak locations" help="Small trial run to check if the MS and MS/MS peak lists in their current states can easily be matched "/> | |
| 134 <when value="Yes"> | |
| 135 <param name="mStart" optional="false" type="integer" size="10" value="100" label="Set m/z start " /> | |
| 136 <param name="mEnd" optional="false" type="integer" size="10" value="1000" label="Set m/z end " /> | |
| 137 <param name="rtStart" optional="false" type="integer" size="10" value="10" label="Set rention time start (minutes) " /> | |
| 138 <param name="rtEnd" optional="false" type="integer" size="10" value="20" label="Set rention time end (minutes) " /> | |
| 139 <param name="filterSourceName" type="text" size="100" value="" label="Restrict matching to a specific subset of the files " help="Part of a file name that occurs in both a ms1 and ms2 file (e.g. 'RibO_1_msE1')"/> | |
| 140 </when> | |
| 6 | 141 <when value="No"> |
| 142 </when> | |
| 0 | 143 </conditional> |
| 144 | |
| 145 </inputs> | |
| 146 <outputs> | |
| 147 <data name="outputData" format="apml" label="${inputMS.metadata.base_name} - ${tool.name} on ${on_string}: APML" metadata_source="inputMS"></data> | |
| 148 <data name="outUnmatchedMS2" format="csv" label="${inputMS.metadata.base_name} - ${tool.name} on ${on_string}: unmatched MS2 features CSV" metadata_source="inputMS"></data> | |
| 149 <data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - HTML report"> | |
| 150 <!-- If the expression is false, the file is not created --> | |
| 151 <filter>( summaryReport == True )</filter> | |
| 152 </data> | |
| 153 </outputs> | |
| 154 <tests> | |
| 155 <!-- find out how to use --> | |
| 156 <test> | |
| 157 </test> | |
| 158 </tests> | |
| 159 <help> | |
| 160 | |
| 161 .. class:: infomark | |
| 162 | |
| 163 This tool matches MS and MS/MS results. SEDMAT stands for "Single Experiment Data Matching Tool". | |
| 164 It can match peaks found in the MS spectra with the peptides found using the MS/MS spectra. | |
| 165 The result is the list of MS peaks annotated with peptides and proteins. | |
| 166 | |
| 167 ----- | |
| 168 | |
| 169 **Output example** | |
| 170 | |
| 171 This tools returns APML output, a Cytoscape network (.xgmml) of the matches and Retention Time plots (.pdf). | |
| 172 | |
| 173 </help> | |
| 174 </tool> |