Mercurial > repos > pieterlukasse > prims_proteomics
annotate napq.xml @ 19:d31c6978d9d0
fixes for NapQ
author | pieter.lukasse@wur.nl |
---|---|
date | Mon, 26 Jan 2015 06:24:15 +0100 |
parents | 40ec8770780d |
children | 46f568202d46 |
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 $htmlReportFile.files_path | |
19 </command> | |
20 | |
21 <inputs> | |
22 | |
16 | 23 <repeat name="identificationFileList" title="Peptide identification files" help="Set of MS/MS peptide identification files that have some form of quantification data coupled to it (e.g. MSE identifications&intensity)."> |
0 | 24 <param name="identificationsFile" type="data" format="apml,mzidentml,prims.fileset.zip" label="Identifications file (APML or MZIDENTML or MZIDENTML fileSet)" /> |
25 </repeat> | |
26 | |
27 <param name="namingConventionCodesForSamples" type="text" size="100" value="" | |
28 label="Part of run/file name that identifies the sample" | |
29 help="Add the CSV list of codes that occur in the file names | |
19 | 30 and that stand for a sample code. E.g. '_S1,_S2,_S3,etc.' "> <!-- could do regular expressions as well but this would be hard for biologists, e.g. _F\d\b --> |
31 <sanitizer> | |
32 <!-- adding more characters to the set of "valid" ones: --> | |
33 <valid> | |
34 <add preset="string.printable"/> | |
35 <add value="#"/> | |
36 <add value="@"/> | |
37 <add value="$"/> | |
38 <add value="%"/> | |
39 <add value="&"/> | |
40 <add value="*"/> | |
41 <add value="["/> | |
42 <add value="]"/> | |
43 <add value="|"/> | |
44 <add value="{"/> | |
45 <add value="}"/> | |
46 </valid> | |
47 </sanitizer> | |
48 </param> | |
0 | 49 |
50 <conditional name="is2D_LC_MS"> | |
51 <param name="fractions" type="boolean" truevalue="Yes" falsevalue="No" checked="false" | |
52 label="Data is from 2D LC-MS" | |
53 help="Data acquisition was done in multiple fractions."/> | |
54 <when value="Yes"> | |
55 <param name="namingConventionCodesForFractions" type="text" size="100" value="" | |
56 label="Part of run/file name that identifies the 2D LC-MS fraction" | |
57 help="Add the CSV list of codes that occur in the file names | |
58 and that stand for a fraction code. E.g. '_F1,_F2,_F3,etc.' Use this to avoid | |
19 | 59 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 --> |
60 <sanitizer> | |
61 <!-- adding more characters to the set of "valid" ones: --> | |
62 <valid> | |
63 <add preset="string.printable"/> | |
64 <add value="#"/> | |
65 <add value="@"/> | |
66 <add value="$"/> | |
67 <add value="%"/> | |
68 <add value="&"/> | |
69 <add value="*"/> | |
70 <add value="["/> | |
71 <add value="]"/> | |
72 <add value="|"/> | |
73 <add value="{"/> | |
74 <add value="}"/> | |
75 </valid> | |
76 </sanitizer> | |
77 </param> | |
78 | |
0 | 79 </when> |
6 | 80 <when value="No"> |
81 </when> | |
0 | 82 </conditional> |
83 | |
84 </inputs> | |
85 <configfiles> | |
86 <configfile name="identificationsConfigFile">## start comment | |
87 ## iterate over the selected files and store their names in the config file | |
88 #for $i, $s in enumerate( $identificationFileList ) | |
16 | 89 ${s.identificationsFile} |
0 | 90 ## also print out the datatype in the next line, based on previously configured datatype |
91 #if isinstance( $s.identificationsFile.datatype, $__app__.datatypes_registry.get_datatype_by_extension('apml').__class__): | |
92 apml | |
93 #else: | |
94 mzid | |
95 #end if | |
96 #end for | |
97 ## end comment</configfile> | |
98 </configfiles> | |
99 <outputs> | |
100 <data name="outputApml" format="apml" label="${tool.name} on ${on_string}: peptide quantifications (APML)"/> | |
101 <data name="outputTsv" format="tabular" label="${tool.name} on ${on_string}: peptide quantifications (TSV)"/> | |
102 <!-- in tsv we can have cols like: pep, avg_m/z, avg rt, m/z window, rt window, i_s1, i_s2, ...--> | |
103 <data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - HTML report"/> | |
104 <!-- here we show the samples extracted and the files used to 'build up' each sample --> | |
105 </outputs> | |
106 <tests> | |
107 </tests> | |
108 <help> | |
109 | |
110 .. class:: infomark | |
111 | |
112 This tool takes in multiple peptide identification result files that have peptide identifications | |
113 coupled to some quantification (e.g. precursor intensity information or for example data coming | |
114 from MS^E acquisition where peptide identification and quantification are done in the same run and reported together). | |
115 Then, based on the given experiment design parameters (i.e. how the result files related back to | |
116 replicate runs and samples), it produces a new file in which the peptides are reported with | |
117 their calculated quantifications at the sample level. | |
118 | |
119 The figure below explains this: | |
120 | |
121 .. image:: $PATH_TO_IMAGES/napq_overview.png | |
122 | |
4 | 123 . |
0 | 124 |
125 | |
126 | |
127 | |
128 </help> | |
129 </tool> |