Mercurial > repos > pieterlukasse > prims_proteomics
annotate napq.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 | d56c18ed0f77 |
| children | d31c6978d9d0 |
| rev | line source |
|---|---|
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
16
diff
changeset
|
1 <tool name="NapQ" id="napq" version="0.0.3"> |
| 5 | 2 <description>'no alignment' (alignment-free) peptide quantification</description> |
| 0 | 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 --> | |
| 8 <command interpreter="java -jar "> | |
| 9 NapQ.jar | |
| 10 -identificationsConfigFile $identificationsConfigFile | |
| 6 | 11 -namingConventionCodesForSamples "$namingConventionCodesForSamples" |
| 0 | 12 #if $is2D_LC_MS.fractions == True |
| 6 | 13 -namingConventionCodesForFractions "$is2D_LC_MS.namingConventionCodesForFractions" |
| 0 | 14 #end if |
| 15 -outputApml $outputApml | |
| 16 -outputTsv $outputTsv | |
| 17 -outReport $htmlReportFile | |
| 18 -outReportPicturesPath $htmlReportFile.files_path | |
| 19 </command> | |
| 20 | |
| 21 <inputs> | |
| 22 | |
| 16 | 23 <repeat name="identificationFileList" title="Peptide identification files" help="Set of MS/MS peptide identification files that have some form of quantification data coupled to it (e.g. MSE identifications&intensity)."> |
| 0 | 24 <param name="identificationsFile" type="data" format="apml,mzidentml,prims.fileset.zip" label="Identifications file (APML or MZIDENTML or MZIDENTML fileSet)" /> |
| 25 </repeat> | |
| 26 | |
| 27 <param name="namingConventionCodesForSamples" type="text" size="100" value="" | |
| 28 label="Part of run/file name that identifies the sample" | |
| 29 help="Add the CSV list of codes that occur in the file names | |
| 30 and that stand for a sample code. E.g. '_S1,_S2,_S3,etc.' "/> <!-- could do regular expressions as well but this would be hard for biologists, e.g. _F\d\b --> | |
| 31 | |
| 32 | |
| 33 <conditional name="is2D_LC_MS"> | |
| 34 <param name="fractions" type="boolean" truevalue="Yes" falsevalue="No" checked="false" | |
| 35 label="Data is from 2D LC-MS" | |
| 36 help="Data acquisition was done in multiple fractions."/> | |
| 37 <when value="Yes"> | |
| 38 <param name="namingConventionCodesForFractions" type="text" size="100" value="" | |
| 39 label="Part of run/file name that identifies the 2D LC-MS fraction" | |
| 40 help="Add the CSV list of codes that occur in the file names | |
| 41 and that stand for a fraction code. E.g. '_F1,_F2,_F3,etc.' Use this to avoid | |
| 42 that each (fraction) file is seen as a separate run."/> <!-- could do regular expressions as well but this would be hard for biologists, e.g. _F\d\b --> | |
| 43 </when> | |
| 6 | 44 <when value="No"> |
| 45 </when> | |
| 0 | 46 </conditional> |
| 47 | |
| 48 </inputs> | |
| 49 <configfiles> | |
| 50 <configfile name="identificationsConfigFile">## start comment | |
| 51 ## iterate over the selected files and store their names in the config file | |
| 52 #for $i, $s in enumerate( $identificationFileList ) | |
| 16 | 53 ${s.identificationsFile} |
| 0 | 54 ## also print out the datatype in the next line, based on previously configured datatype |
| 55 #if isinstance( $s.identificationsFile.datatype, $__app__.datatypes_registry.get_datatype_by_extension('apml').__class__): | |
| 56 apml | |
| 57 #else: | |
| 58 mzid | |
| 59 #end if | |
| 60 #end for | |
| 61 ## end comment</configfile> | |
| 62 </configfiles> | |
| 63 <outputs> | |
| 64 <data name="outputApml" format="apml" label="${tool.name} on ${on_string}: peptide quantifications (APML)"/> | |
| 65 <data name="outputTsv" format="tabular" label="${tool.name} on ${on_string}: peptide quantifications (TSV)"/> | |
| 66 <!-- in tsv we can have cols like: pep, avg_m/z, avg rt, m/z window, rt window, i_s1, i_s2, ...--> | |
| 67 <data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - HTML report"/> | |
| 68 <!-- here we show the samples extracted and the files used to 'build up' each sample --> | |
| 69 </outputs> | |
| 70 <tests> | |
| 71 </tests> | |
| 72 <help> | |
| 73 | |
| 74 .. class:: infomark | |
| 75 | |
| 76 This tool takes in multiple peptide identification result files that have peptide identifications | |
| 77 coupled to some quantification (e.g. precursor intensity information or for example data coming | |
| 78 from MS^E acquisition where peptide identification and quantification are done in the same run and reported together). | |
| 79 Then, based on the given experiment design parameters (i.e. how the result files related back to | |
| 80 replicate runs and samples), it produces a new file in which the peptides are reported with | |
| 81 their calculated quantifications at the sample level. | |
| 82 | |
| 83 The figure below explains this: | |
| 84 | |
| 85 .. image:: $PATH_TO_IMAGES/napq_overview.png | |
| 86 | |
| 4 | 87 . |
| 0 | 88 |
| 89 | |
| 90 | |
| 91 | |
| 92 </help> | |
| 93 </tool> |