annotate csv2apml.xml @ 5:5d99c9d0615d

performance improvements for MsFilt
author pieter.lukasse@wur.nl
date Mon, 27 Jan 2014 12:11:29 +0100
parents d50f079096ee
children 40ec8770780d
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
1 <tool name="Csv2Apml" id="csv2apml" version="1.0.2">
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
2 <description>Converts MS/MS data in CSV format to APML format</description>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
3 <!--
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
4 For remote debugging start you listener on port 8000 and use the following as command interpreter:
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
5 java -jar -Xdebug -Xrunjdwp:transport=dt_socket,address=D0100564.wurnet.nl:8000
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
6 //////////////////////////
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
7 -->
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
8 <command interpreter="java -jar ">
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
9 Csv2Apml.jar
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
10 -peptideAndProteinMatchListCSV $peptideAndProteinMatchListCSV
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
11 -attributesMappingCSV $attributesMappingCSV
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
12 -apmlFile $apmlFile
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
13 </command>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
14
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
15 <inputs>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
16
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
17 <param name="peptideAndProteinMatchListCSV" type="data"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
18 format="csv" label="MS/MS CSV file"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
19 help="MS/MS CSV file containing peptide identifications and protein matches" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
20
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
21 <param name="mz" type="text" optional="false" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
22 label="Column name for precursor m/z" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
23
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
24 <param name="rt" type="text" optional="false" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
25 label="Column name for precursor rt" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
26
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
27 <param name="charge" type="text" optional="false" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
28 label="Column name for precursor charge (z)" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
29
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
30 <param name="pepSequence" type="text" optional="false" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
31 label="Column name for peptide sequence" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
32
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
33 <param name="ppidScore" type="text" optional="false" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
34 label="Column name for peptide identification score" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
35
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
36 <param name="scoringSchemeName" type="text" optional="true" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
37 label="(Optional) Column name containing scoring scheme name" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
38
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
39 <param name="statisticalMeasure" type="text" optional="true" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
40 label="(Optional) Column name for reported statistical measure values"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
41 help="(e.g. column containing p-values or e-values)" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
42
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
43 <param name="ppidTheoreticalMz" type="text" optional="true" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
44 label="(Optional) Column name for peptide theoretical m/z" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
45
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
46 <param name="modifications" type="text" optional="true" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
47 label="(Optional) Column name for reported modifications" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
48
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
49 <param name="proteinAccession" type="text" optional="false" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
50 label="Column name for protein accession code" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
51
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
52 <param name="protSequenceLength" type="text" optional="true" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
53 label="(Optional) Column name for protein sequence length" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
54
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
55 <param name="pepProtStart" type="text" optional="true" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
56 label="(Optional) Column name for protein match location start"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
57 help="Where peptide sequence starts in protein"/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
58
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
59 <param name="pepProtEnd" type="text" optional="true" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
60 label="(Optional) Column name for protein match location end"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
61 help="Where peptide sequence ends in protein"/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
62
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
63 <param name="sourceName" type="text" optional="true" size="30"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
64 label="(Optional) Column name for sample names" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
65
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
66 </inputs>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
67 <configfiles>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
68 <configfile name="attributesMappingCSV">Generic name,name in S1 table CSV
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
69 mz,${mz}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
70 rt,${rt}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
71 charge,${charge}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
72 pepSequence,${pepSequence}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
73 ppidScore,${ppidScore}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
74 proteinAccession,${proteinAccession}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
75 #if $ppidTheoreticalMz != "None"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
76 ppidTheoreticalMz,${ppidTheoreticalMz}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
77 #end if
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
78 #if $modifications != "None"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
79 modifications,${modifications}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
80 #end if
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
81 #if $scoringSchemeName != "None"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
82 scoringSchemeName,${scoringSchemeName}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
83 #end if
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
84 #if $statisticalMeasure != "None"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
85 statisticalMeasure,${statisticalMeasure}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
86 #end if
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
87 #if $protSequenceLength != "None"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
88 protSequenceLength,${protSequenceLength}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
89 #end if
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
90 #if $pepProtStart != "None"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
91 pepProtStart,${pepProtStart}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
92 #end if
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
93 #if $pepProtEnd != "None"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
94 pepProtEnd,${pepProtEnd}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
95 #end if
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
96 #if $sourceName != "None"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
97 sourceName,${sourceName}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
98 #end if</configfile>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
99 </configfiles>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
100
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
101 <outputs>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
102 <data name="apmlFile" format="apml" label="${tool.name} on ${on_string}: APML" >
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
103 </data>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
104 </outputs>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
105 <tests>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
106 </tests>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
107 <help>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
108
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
109 .. class:: infomark
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
110
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
111 This tool converts a CSV file containing MS/MS peptide identifications and their respective protein matches
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
112 to the APML xml format.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
113 The identifications in APML format can be used for example to annotate unidentified MS features via SEDMAT(*).
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
114 This format is also compatible with what is expected by other post-processing tools like Quantifere (for
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
115 protein inference).
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
116
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
117 (*)SEDMAT can use MS2 identification data
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
118 and couple it to this MS1 data, thereby annotating the MS1 feature list with identifications.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
119
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
120 -----
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
121
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
122 **Output**
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
123
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
124 This tools returns the input data in APML xml format.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
125
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
126 </help>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
127 </tool>