|
0
|
1 <tool name="NapQ" id="napq" version="0.0.1">
|
|
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
|
|
|
23 <repeat name="identificationFileList" title="Peptide identification files" help="Full set of MS/MS peptide identification files, including peptides that could not be quantified.">
|
|
|
24 <param name="identificationsFile" type="data" format="apml,mzidentml,prims.fileset.zip" label="Identifications file (APML or MZIDENTML or MZIDENTML fileSet)" />
|
|
|
25 <param name="spectraFile" type="data" format="mzidentml,prims.fileset.zip" optional="true" label="(Optional) Spectra fileSet (mzml file or fileSet)"
|
|
|
26 help="Select this in case your Identifications file is MZIDENTML or MZIDENTML fileSet" />
|
|
|
27 </repeat>
|
|
|
28
|
|
|
29 <param name="namingConventionCodesForSamples" type="text" size="100" value=""
|
|
|
30 label="Part of run/file name that identifies the sample"
|
|
|
31 help="Add the CSV list of codes that occur in the file names
|
|
|
32 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 -->
|
|
|
33
|
|
|
34
|
|
|
35 <conditional name="is2D_LC_MS">
|
|
|
36 <param name="fractions" type="boolean" truevalue="Yes" falsevalue="No" checked="false"
|
|
|
37 label="Data is from 2D LC-MS"
|
|
|
38 help="Data acquisition was done in multiple fractions."/>
|
|
|
39 <when value="Yes">
|
|
|
40 <param name="namingConventionCodesForFractions" type="text" size="100" value=""
|
|
|
41 label="Part of run/file name that identifies the 2D LC-MS fraction"
|
|
|
42 help="Add the CSV list of codes that occur in the file names
|
|
|
43 and that stand for a fraction code. E.g. '_F1,_F2,_F3,etc.' Use this to avoid
|
|
|
44 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 -->
|
|
|
45 </when>
|
|
6
|
46 <when value="No">
|
|
|
47 </when>
|
|
0
|
48 </conditional>
|
|
|
49
|
|
|
50 </inputs>
|
|
|
51 <configfiles>
|
|
|
52 <configfile name="identificationsConfigFile">## start comment
|
|
|
53 ## iterate over the selected files and store their names in the config file
|
|
|
54 #for $i, $s in enumerate( $identificationFileList )
|
|
|
55 ${s.identificationsFile}|${s.spectraFile}
|
|
|
56 ## also print out the datatype in the next line, based on previously configured datatype
|
|
|
57 #if isinstance( $s.identificationsFile.datatype, $__app__.datatypes_registry.get_datatype_by_extension('apml').__class__):
|
|
|
58 apml
|
|
|
59 #else:
|
|
|
60 mzid
|
|
|
61 #end if
|
|
|
62 #end for
|
|
|
63 ## end comment</configfile>
|
|
|
64 </configfiles>
|
|
|
65 <outputs>
|
|
|
66 <data name="outputApml" format="apml" label="${tool.name} on ${on_string}: peptide quantifications (APML)"/>
|
|
|
67 <data name="outputTsv" format="tabular" label="${tool.name} on ${on_string}: peptide quantifications (TSV)"/>
|
|
|
68 <!-- in tsv we can have cols like: pep, avg_m/z, avg rt, m/z window, rt window, i_s1, i_s2, ...-->
|
|
|
69 <data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - HTML report"/>
|
|
|
70 <!-- here we show the samples extracted and the files used to 'build up' each sample -->
|
|
|
71 </outputs>
|
|
|
72 <tests>
|
|
|
73 </tests>
|
|
|
74 <help>
|
|
|
75
|
|
|
76 .. class:: infomark
|
|
|
77
|
|
|
78 This tool takes in multiple peptide identification result files that have peptide identifications
|
|
|
79 coupled to some quantification (e.g. precursor intensity information or for example data coming
|
|
|
80 from MS^E acquisition where peptide identification and quantification are done in the same run and reported together).
|
|
|
81 Then, based on the given experiment design parameters (i.e. how the result files related back to
|
|
|
82 replicate runs and samples), it produces a new file in which the peptides are reported with
|
|
|
83 their calculated quantifications at the sample level.
|
|
|
84
|
|
|
85 The figure below explains this:
|
|
|
86
|
|
|
87 .. image:: $PATH_TO_IMAGES/napq_overview.png
|
|
|
88
|
|
4
|
89 .
|
|
0
|
90
|
|
|
91
|
|
|
92
|
|
|
93
|
|
|
94 </help>
|
|
|
95 </tool>
|
