annotate map_aligner_identification.xml @ 6:42b843627623 draft default tip

Uploaded
author galaxyp
date Fri, 21 Jun 2013 17:01:53 -0400
parents 1183846e70a1
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
4
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
1 <tool id="openms_map_aligner_identification" version="0.1.0" name="Map Aligner (Identification)">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
2 <description>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
3 Corrects retention time distortions between maps based on common peptide identifications.
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
4 </description>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
5 <macros>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
6 <import>macros.xml</import>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
7 </macros>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
8 <expand macro="stdio" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
9 <expand macro="requires" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
10 <command interpreter="python">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
11 openms_wrapper.py --executable 'MapAlignerIdentification' --config $config
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
12 </command>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
13 <configfiles>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
14 <configfile name="config">[simple_options]
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
15 #set $inputs_as_str = ",".join(map(str, $type.input))
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
16 in=$inputs_as_str
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
17 out=@MULTI_OUTPUT($output.extra_files_path,$inputs_as_str)@
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
18 #if $generate_transformations
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
19 trafo_out=@MULTI_OUTPUT($transformations.extra_files_path,$inputs_as_str)@
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
20 #end if
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
21 algorithm!peptide_score_threshold=$peptide_score_threshold
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
22 algorithm!min_run_occur=$min_run_occur
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
23 algorithm!max_rt_shift=$max_rt_shift
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
24 algorithm!use_unassigned_peptides=$use_unassigned_peptides
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
25 algorithm!use_feature_rt=$use_feature_rt
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
26 #set $model_type = $model.model_type
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
27 model!type=$model_type
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
28 #if $model_type == "interpolated"
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
29 model!interpolated!interpolation_type=$model.interpolation_type
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
30 #end if
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
31 </configfile>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
32 </configfiles>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
33 <inputs>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
34 <conditional name="type">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
35 <param name="input_type" type="select" label="Input Type">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
36 <option value="featurexml">Features (FeatureXML)</option>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
37 <option value="consensusxml">Consensus (ConsensusXML)</option>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
38 <option value="idxml">Identifications (IdXML)</option>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
39 </param>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
40 <when value="featurexml">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
41 <param format="m:featurexml" name="input" type="data" label="Input Features" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
42 </when>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
43 <when value="consensusxml">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
44 <param format="m:consensusxml" name="input" type="data" label="Input Consensus Files" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
45 </when>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
46 <when value="idxml">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
47 <param format="m:idxml" name="input" type="data" label="Input Identifications" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
48 </when>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
49 </conditional>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
50 <param name="generate_transformations" type="boolean" label="Generate Transformations" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
51 <param name="peptide_score_threshold" type="float" value="0" label="Peptide Score Threshold" help="Score threshold for peptide hits to be used in the alignment. Select a value that allows only 'high confidence' matches." />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
52 <param name="min_run_occur" type="integer" value="2" label="Minimum Runs" help="Minimum number of runs (incl. reference, if any) a peptide must occur in to be used for the alignment. Unless you have very few runs or identifications, increase this value to focus on more informative peptides." />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
53 <param name="max_rt_shift" type="float" value="0.5" label="Max RT Shift" help="Maximum realistic RT difference for a peptide (median per run vs. reference). Peptides with higher shifts (outliers) are not used to compute the alignment. If 0, no limit (disable filter); if &gt; 1, the final value in seconds; if &lt;= 1, taken as a fraction of the range of the reference RT scale." />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
54 <param name="use_unassigned_peptides" type="boolean" label="Use Unassigned Peptides" help="Should unassigned peptide identifications be used when computing an alignment of feature maps? If 'false', only peptide IDs assigned to features will be used." truevalue="true" falsevalue="false" checked="true" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
55 <param name="use_feature_rt" type="boolean" label="Use Feature RT" help="When aligning feature maps, don't use the retention time of a peptide identification directly; instead, use the retention time of the centroid of the feature (apex of the elution profile) that the peptide was matched to. If different identifications are matched to one feature, only the peptide closest to the centroid in RT is used. Precludes 'use_unassigned_peptides'." truevalue="true" falsevalue="false" checked="false" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
56 <expand macro="aligner_model" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
57 </inputs>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
58 <outputs>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
59 <data format="m:consensusxml" name="output" label="Alignment of ${on_string}">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
60 <change_format>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
61 <when input="type.input_type" value="featurexml" format="m:featurexml" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
62 <when input="type.input_type" value="idxml" format="m:idxml" />
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
63 </change_format>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
64 </data>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
65 <data format="m:trafoxml" name="transformations" label="Aligned Transformations for ${on_string}">
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
66 <filter>generate_transformations</filter>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
67 </data>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
68 </outputs>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
69 <help>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
70 **What it does**
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
71
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
72 This tool provides an algorithm to align the retention time scales of multiple input files, correcting shifts and distortions between them. Retention time adjustment may be necessary to correct for chromatography differences e.g. before data from multiple LC-MS runs can be combined (feature grouping), or when one run should be annotated with peptide identifications obtained in a different run.
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
73
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
74 All map alignment tools (MapAligner...) collect retention time data from the input files and - by fitting a model to this data - compute transformations that map all runs to a common retention time scale.
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
75
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
76 The map alignment tools differ in how they obtain retention time data for the modeling of transformations, and consequently what types of data they can be applied to. The alignment algorithm implemented here is based on peptide identifications, and thus applicable to files containing peptide IDs (idXML, annotated featureXML/consensusXML). It finds peptide sequences that different input files have in common and uses them as points of correspondence between the inputs.
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
77
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
78 Note that alignment is based on the sequence including modifications, thus an exact match is required. I.e., a peptide with oxidised methionine will not be matched to its unmodified version. For some applications this behaviour is desired, while for others its not, but you can always remove all modifications from the input files if you want to ignore modifications.
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
79
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
80 **Citation**
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
81
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
82 For the underlying tool, please cite ``Weisser et al.: An automated pipeline for high-throughput label-free quantitative proteomics (J. Proteome Res., 2013, PMID: 23391308).``
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
83
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
84 If you use this tool in Galaxy, please cite Chilton J, et al. https://bitbucket.org/galaxyp/galaxyp-toolshed-openms
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
85 </help>
1183846e70a1 Uploaded
galaxyp
parents:
diff changeset
86 </tool>