annotate msfilt.xml @ 5:5d99c9d0615d

performance improvements for MsFilt
author pieter.lukasse@wur.nl
date Mon, 27 Jan 2014 12:11:29 +0100
parents d50f079096ee
children 72d4a37869ee
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="MsFilt" id="msfilt" version="1.0.2">
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
2 <description>Filters annotations based MS/MS peptide identification and annotation quality measures</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 MsFilt.jar
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
10 -apmlFile $apmlFile
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
11 -datasetCode $apmlFile.metadata.base_name
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
12 -rankingMetadataFile $rankingMetadataFile
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
13 -statisticalMeasuresConfigFile $statisticalMeasuresConfigFile
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
14 -annotationSourceConfigFile $annotationSourceConfigFile
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
15 -outApml $outputApml
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
16 -outNewIdsApml $outNewIdsApml
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
17 -outFullCSV $outputCSV
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
18 -outRankingTable $outRankingTable
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
19 -outProteinCoverageCSV $outProteinCoverageCSV
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
20 -fpCriteriaExpression "$fpCriteriaExpression"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
21 -filterOutFPAnnotations $filterOutFPAnnotations
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
22 -fpCriteriaExpressionForIds "$fpCriteriaExpressionForIds"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
23 -filterOutFPIds $filterOutFPIds
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
24 -filterOutUnannotatedAlignments $filterOutUnannotatedAlignments
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
25 -addRawRankingInfo $addRawRankingInfo
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
26 -addScaledIntensityInfo $addScaledIntensityInfo
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
27 -addRawIntensityInfo $addRawIntensityInfo
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
28 -outReport $htmlReportFile
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
29 -outReportPicturesPath $htmlReportFile.files_path
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
30 </command>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
31
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
32 <inputs>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
33
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
34 <param name="apmlFile" type="data" format="apml" optional="true"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
35 label="(Optional) Peptide quantification file (APML)"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
36 help="The APML contents as aligned and annotated feature lists. E.g. produced by
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
37 SEDMAT or Quantiline tools." />
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 <repeat name="annotationSourceFiles" title="(Optional) Peptide identification files" help="Full set of MS/MS peptide identification files, including peptides that could not be quantified.">
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
40 <param name="identificationsFile" type="data" format="apml,mzidentml,prims.fileset.zip" label="Identifications file (APML or MZIDENTML or MZIDENTML fileSet)" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
41 <param name="spectraFile" type="data" format="mzidentml,prims.fileset.zip" optional="true" label="(Optional) Spectra fileSet (mzml file or fileSet)"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
42 help="Select this in case your Identifications file is MZIDENTML or MZIDENTML fileSet" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
43 </repeat>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
44
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="maxNrRankings" type="integer" size="10" value="0" label="Maximum nr. of items to leave in the final ranking (set=0 for no limit) " />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
47 -->
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
48 <!-- TODO add info somewhere that deltaRt is 'corrected deltaRt' -->
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
49 <param name="rankingWeightConfig" type="text" area="true" size="13x70" label="Quality Measures (qm's) and ranking weights configuration"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
50 help="Here you may specify a weight for each of the Quality Measures (QMs). These are used for the final QM score and possibly for ranking (e.g. in case of label-free data
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
51 processed by SEDMAT). The format is: QM alias => QM name,weight. "
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
52 value="qmDRT =&gt; delta rt (standard score),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
53 &#xd;&#xa;qmDMA =&gt; delta mass annotation (standard score),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
54 &#xd;&#xa;qmDMP =&gt; delta mass psm (standard score),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
55 &#xd;&#xa;qmBSCR =&gt; best peptide score (standard score),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
56 &#xd;&#xa;qmALCV =&gt; alignment coverage (fraction),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
57 &#xd;&#xa;qmSTCV =&gt; score type coverage (fraction),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
58 &#xd;&#xa;qmPACV =&gt; peptide's best proteinAnnotCoverage (standard score),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
59 &#xd;&#xa;qmPICV =&gt; peptide's best proteinIdentifCoverage (standard score),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
60 &#xd;&#xa;qmANS =&gt; annotation sources (count),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
61 &#xd;&#xa;qmCSEV =&gt; charge states evidence (count),0.2
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
62 &#xd;&#xa;qmBCSP=&gt; best correlation with source or product peptide (correl),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
63 &#xd;&#xa;qmBCCS =&gt; best correlation with other charge state (correl),1
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
64 &#xd;&#xa;qmBCOS =&gt; best correlation with other sibling peptide (correl),1
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
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
67 <param name="statisticalMeasuresConfig" type="text" area="true" size="6x70" label="Statistical measures configuration"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
68 help="Here you may specify the statistical measures that are found in the ms/ms results (e.g. p or e-values).
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
69 The format is: SM alias => SM name,type,mode[min/max]. "
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
70 value="smXTD =&gt; MS:1001330,XSLASH!Tandem:expect,min
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
71 &#xd;&#xa;pvCSVEX =&gt; p_value,CSV_EXPORT,min
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
72 &#xd;&#xa;smAUTO_LIKELIHOOD =&gt; AUTOMOD_LOGLIKELIHOOD,PLGS/Auto-mod,max
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
73 &#xd;&#xa;smLIKELIHOOD =&gt; LOGLIKELIHOOD,PLGS/Databank-search,max
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
74 "/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
75
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
76 <param name="filterOutUnannotatedAlignments" type="boolean" checked="true"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
77 label="Filter out unannotated alignments"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
78 help="This helps decrease the output file size (features with no annotation are then not reported anymore)"/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
79
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
80 <param name="filterOutFPAnnotations" type="boolean" checked="true"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
81 label="Filter out False Positive (FP) annotations" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
82
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
83 <param name="fpCriteriaExpression" type="text" size="120" label="False Positive (FP) criteria for annotations"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
84 help="Criteria (in standard score measures) for classifying an annotation as False Positive (FP).
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
85 You can build logical rules using the QM aliases above, the keywords 'and', 'or' and parenthesis.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
86 Comparisons can be made with '==,&lt;,&gt;&lt;=,&gt;='"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
87 value="qmDRT &lt;0 or qmDMA &lt;-0.5 or (qmDMP &lt;-0.5 and qmBSCR&lt;-0.5) or (!isNaN(smXTD) and smXTD &gt;0.01)"/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
88
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
89
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
90 <param name="filterOutFPIds" type="boolean" checked="true"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
91 label="Filter out False Positive (FP) peptide identifications" />
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
92
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
93 <param name="fpCriteriaExpressionForIds" type="text" size="120"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
94 label="False Positive (FP) criteria for identifications"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
95 help="Criteria (in standard score measures) for classifying a peptide identification as False Positive (FP).
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
96 Here you can use a subset of the quality measures (qmDMP, qmBSCR, qmSTCV, qmPICV, qmCSEV) and all statistical measures."
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
97 value="(qmDMP &lt;-0.5 and qmBSCR&lt;-0.5) or (!isNaN(smXTD) and smXTD &gt;0.01)"/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
98
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
99
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
100 <param name="addRawRankingInfo" type="boolean" checked="false"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
101 label="Include the raw scores/values of the ranking attributes in the CSV output"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
102 help="This will result in one extra column per ranking attribute, each column holding the original data for this attribute (before normalization)."/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
103
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
104 <param name="addScaledIntensityInfo" type="boolean" checked="false"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
105 label="Include computed scaled intensity values in the CSV output"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
106 help="The autoscaled and 'z-score'scaled (aka 'standard-score'scaled) intensity values are then added to the full CSV output file"/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
107
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
108 <param name="addRawIntensityInfo" type="boolean" checked="false"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
109 label="Include the raw intensity values in the CSV output"
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
110 help="The original intensity values (as found in the input file) are then added to the full CSV output file"/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
111
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
112
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
113 </inputs>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
114 <configfiles>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
115 <configfile name="rankingMetadataFile">${rankingWeightConfig}</configfile>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
116 <configfile name="statisticalMeasuresConfigFile">${statisticalMeasuresConfig}</configfile>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
117 <configfile name="annotationSourceConfigFile">## start comment
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
118 ## iterate over the selected files and store their names in the config file
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
119 #for $i, $s in enumerate( $annotationSourceFiles )
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
120 ${s.identificationsFile}|${s.spectraFile}
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
121 ## also print out the datatype in the next line, based on previously configured datatype
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
122 #if isinstance( $s.identificationsFile.datatype, $__app__.datatypes_registry.get_datatype_by_extension('apml').__class__):
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
123 apml
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
124 #else:
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
125 mzid
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
126 #end if
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
127 #end for
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
128 ## end comment</configfile>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
129 </configfiles>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
130 <outputs>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
131 <data name="outputApml" format="apml" label="${apmlFile.metadata.base_name} - ${tool.name} on ${on_string}: quantifications (filtered APML)" metadata_source="apmlFile">
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
132 <!-- If the expression is false, the file is not created -->
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
133 <filter>( apmlFile != None )</filter>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
134 </data>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
135 <data name="outNewIdsApml" format="apml" label="${tool.name} on ${on_string}: identifications (filtered APML)" >
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
136 <filter>( filterOutFPIds == True )</filter>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
137 </data>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
138 <data name="outputCSV" format="csv" label="${apmlFile.metadata.base_name} - ${tool.name} on ${on_string}: Full CSV" metadata_source="apmlFile">
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
139 <filter>( apmlFile != None )</filter>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
140 </data>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
141 <data name="outRankingTable" format="csv" label="${apmlFile.metadata.base_name} - ${tool.name} on ${on_string}: Ranking table (CSV)" metadata_source="apmlFile">
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
142 <filter>( apmlFile != None )</filter>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
143 </data>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
144 <data name="outProteinCoverageCSV" format="csv" label="${tool.name} on ${on_string}: Protein coverage details (CSV)">
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
145 <!-- If the expression is false, the file is not created -->
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
146 <filter>( len(list(enumerate(annotationSourceFiles))) > 0 )</filter>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
147 </data>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
148 <data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - HTML report"/>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
149 </outputs>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
150 <tests>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
151 </tests>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
152 <help>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
153
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
154 .. class:: infomark
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
155
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
156 This tool takes in peptide quantification results (e.g. either by SEDMAT for label-free data or by Quantiline for labeled data)
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
157 and calculates a number of quality measures that can help in assessing the correctness of the quantification assignment and of the MS/MS peptide
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
158 identification itself. The user can use any combination of quality measures (qm's) and statistical measures (sm's) to filter out
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
159 low scoring entries.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
160
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
161 .. class:: infomark
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
162
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
163 In the label-free data processed by SEDMAT it is possible that a feature quantification gets assigned to different peptides. This means
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
164 we have an ambiguous assignment. In such a case
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
165 this tool also does a ranking of the different assignments according to their quality measures so that the best scoring assignment
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
166 gets ranked as first.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
167
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
168 -----
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
169
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
170 **List of abbreviations**
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
171
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
172 QM: Quality Measure
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
173
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
174 SM: Statistical Measure (e.g. p-value, e-value from MS/MS identification)
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
175
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
176 PSM: "Peptide to Spectrum Match" (aka peptide identification)
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
177
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
178 FP: False Positive
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
179
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
180 -----
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
181
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
182 **Filtering options details**
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
183
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
184 The FP criteria will be applied to an annotation even if the corresponding quality measures involved
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
185 in the expression can NOT ALL be determined. QMs that cannot be determined, get the value 0 (zero) which is
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
186 equal to giving it the average value.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
187
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
188 The output report shows some plots that visualize the filtering done. This can help in fine-tuning the right filtering
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
189 criteria.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
190
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
191 -----
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
192
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
193 **Output details**
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
194
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
195 *APML output*
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
196
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
197 This tools returns the given APML alignment file further annotated at the alignment level with the best ranking
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
198 peptides of each respective alignment. This APML can be used in subsequent Galaxy tools like the proteomics tools
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
199 from NBIC.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
200
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
201 The APML output can also be used for the Protein Inference step (see Quantifere tool).
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
202
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
203 *CSV output*
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
204
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
205 It also returns a CSV format output with the full quality measures and scoring and ranking details. The user could use
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
206 this to manually determine new weights for some of the quality measures by techniques such as
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
207 linear regression. In other words, this CSV can then be used to fine-tune the weights in a next run.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
208
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
209 Many of the quality measures (QMs) are normalized to their Standard Score (aka z-score).
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
210 `See Standard Score for more details...`__
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
211
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
212 Next to giving insight into how the ranking was established, a more complete version of this CSV file is also
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
213 generated for tools that cannot or won't process the APML output format.
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
214
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
215 Below an brief overview of the CSV and an illustration of the ranking done in case of ambiguous peptides to feature assignments
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
216 (explained above, can happen in case of label-free data processing by SEDMAT).
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
217
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
218
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
219 .. image:: $PATH_TO_IMAGES/msfilt_csv_out.png
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
220
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
221
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
222
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
223 .. __: javascript:window.open('http://en.wikipedia.org/wiki/Standard_score','popUpWindow','height=700,width=800,left=10,top=10,resizable=yes,scrollbars=yes,toolbar=yes,menubar=no,location=no,directories=no,status=yes')
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
224
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
225
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
226
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
227
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
228 </help>
d50f079096ee Push to main toolshed
pieter.lukasse@wur.nl
parents:
diff changeset
229 </tool>