Mercurial > repos > pieterlukasse > prims_proteomics
annotate csv2apml.xml @ 19:d31c6978d9d0
fixes for NapQ
| author | pieter.lukasse@wur.nl |
|---|---|
| date | Mon, 26 Jan 2015 06:24:15 +0100 |
| parents | 40ec8770780d |
| children | 125a6afa800c |
| rev | line source |
|---|---|
| 0 | 1 <tool name="Csv2Apml" id="csv2apml" version="1.0.2"> |
| 2 <description>Converts MS/MS data in CSV format to APML format</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 --> | |
| 8 <command interpreter="java -jar "> | |
| 9 Csv2Apml.jar | |
| 10 -peptideAndProteinMatchListCSV $peptideAndProteinMatchListCSV | |
| 11 -attributesMappingCSV $attributesMappingCSV | |
| 12 -apmlFile $apmlFile | |
| 13 </command> | |
| 14 | |
| 15 <inputs> | |
| 16 | |
| 17 <param name="peptideAndProteinMatchListCSV" type="data" | |
| 18 format="csv" label="MS/MS CSV file" | |
| 19 help="MS/MS CSV file containing peptide identifications and protein matches" /> | |
| 20 | |
| 21 <param name="mz" type="text" optional="false" size="30" | |
| 22 label="Column name for precursor m/z" /> | |
| 23 | |
| 24 <param name="rt" type="text" optional="false" size="30" | |
|
17
40ec8770780d
* Added support for pepxml (and more specifically for
pieter.lukasse@wur.nl
parents:
0
diff
changeset
|
25 label="Column name for precursor rt (nb: rt in minutes)" /> |
| 0 | 26 |
| 27 <param name="charge" type="text" optional="false" size="30" | |
| 28 label="Column name for precursor charge (z)" /> | |
| 29 | |
| 30 <param name="pepSequence" type="text" optional="false" size="30" | |
| 31 label="Column name for peptide sequence" /> | |
| 32 | |
| 33 <param name="ppidScore" type="text" optional="false" size="30" | |
| 34 label="Column name for peptide identification score" /> | |
| 35 | |
| 36 <param name="scoringSchemeName" type="text" optional="true" size="30" | |
| 37 label="(Optional) Column name containing scoring scheme name" /> | |
| 38 | |
| 39 <param name="statisticalMeasure" type="text" optional="true" size="30" | |
| 40 label="(Optional) Column name for reported statistical measure values" | |
| 41 help="(e.g. column containing p-values or e-values)" /> | |
| 42 | |
| 43 <param name="ppidTheoreticalMz" type="text" optional="true" size="30" | |
| 44 label="(Optional) Column name for peptide theoretical m/z" /> | |
| 45 | |
| 46 <param name="modifications" type="text" optional="true" size="30" | |
| 47 label="(Optional) Column name for reported modifications" /> | |
| 48 | |
| 49 <param name="proteinAccession" type="text" optional="false" size="30" | |
| 50 label="Column name for protein accession code" /> | |
| 51 | |
| 52 <param name="protSequenceLength" type="text" optional="true" size="30" | |
| 53 label="(Optional) Column name for protein sequence length" /> | |
| 54 | |
| 55 <param name="pepProtStart" type="text" optional="true" size="30" | |
| 56 label="(Optional) Column name for protein match location start" | |
| 57 help="Where peptide sequence starts in protein"/> | |
| 58 | |
| 59 <param name="pepProtEnd" type="text" optional="true" size="30" | |
| 60 label="(Optional) Column name for protein match location end" | |
| 61 help="Where peptide sequence ends in protein"/> | |
| 62 | |
| 63 <param name="sourceName" type="text" optional="true" size="30" | |
| 64 label="(Optional) Column name for sample names" /> | |
| 65 | |
| 66 </inputs> | |
| 67 <configfiles> | |
| 68 <configfile name="attributesMappingCSV">Generic name,name in S1 table CSV | |
| 69 mz,${mz} | |
| 70 rt,${rt} | |
| 71 charge,${charge} | |
| 72 pepSequence,${pepSequence} | |
| 73 ppidScore,${ppidScore} | |
| 74 proteinAccession,${proteinAccession} | |
| 75 #if $ppidTheoreticalMz != "None" | |
| 76 ppidTheoreticalMz,${ppidTheoreticalMz} | |
| 77 #end if | |
| 78 #if $modifications != "None" | |
| 79 modifications,${modifications} | |
| 80 #end if | |
| 81 #if $scoringSchemeName != "None" | |
| 82 scoringSchemeName,${scoringSchemeName} | |
| 83 #end if | |
| 84 #if $statisticalMeasure != "None" | |
| 85 statisticalMeasure,${statisticalMeasure} | |
| 86 #end if | |
| 87 #if $protSequenceLength != "None" | |
| 88 protSequenceLength,${protSequenceLength} | |
| 89 #end if | |
| 90 #if $pepProtStart != "None" | |
| 91 pepProtStart,${pepProtStart} | |
| 92 #end if | |
| 93 #if $pepProtEnd != "None" | |
| 94 pepProtEnd,${pepProtEnd} | |
| 95 #end if | |
| 96 #if $sourceName != "None" | |
| 97 sourceName,${sourceName} | |
| 98 #end if</configfile> | |
| 99 </configfiles> | |
| 100 | |
| 101 <outputs> | |
| 102 <data name="apmlFile" format="apml" label="${tool.name} on ${on_string}: APML" > | |
| 103 </data> | |
| 104 </outputs> | |
| 105 <tests> | |
| 106 </tests> | |
| 107 <help> | |
| 108 | |
| 109 .. class:: infomark | |
| 110 | |
| 111 This tool converts a CSV file containing MS/MS peptide identifications and their respective protein matches | |
| 112 to the APML xml format. | |
| 113 The identifications in APML format can be used for example to annotate unidentified MS features via SEDMAT(*). | |
| 114 This format is also compatible with what is expected by other post-processing tools like Quantifere (for | |
| 115 protein inference). | |
| 116 | |
| 117 (*)SEDMAT can use MS2 identification data | |
| 118 and couple it to this MS1 data, thereby annotating the MS1 feature list with identifications. | |
| 119 | |
| 120 ----- | |
| 121 | |
| 122 **Output** | |
| 123 | |
| 124 This tools returns the input data in APML xml format. | |
| 125 | |
| 126 </help> | |
| 127 </tool> |