Mercurial > repos > jjohnson > encyclopedia_searchtolib

comparison encyclopedia_searchtolib.xml @ 1:a7d52df6763f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/encyclopedia/tools/encyclopedia commit 81e7c4d3d6066b99ad50374292f340302dc4f02d"
author jjohnson
date Tue, 30 Jun 2020 11:43:03 -0400
parents 683b98838cf0
children a74d446c8f5f
comparison
equal deleted inserted replaced
0:683b98838cf0 1:a7d52df6763f
1 <tool id="encyclopedia_searchtolib" name="SearchToLib" version="@VERSION@.0"> 1 <tool id="encyclopedia_searchtolib" name="SearchToLib" version="@VERSION@.0">
2 <description>PeCAn-based Peptide Detection Directly from Data-Independent Acquisition (DIA) MS/MS Data</description> 2 <description>Build a Chromatogram Library from Data-Independent Acquisition (DIA) MS/MS Data</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements" /> 6 <expand macro="requirements" />
7 <command detect_errors="exit_code"><![CDATA[ 7 <command detect_errors="exit_code"><![CDATA[
34 #end if 34 #end if
35 @SCAN_INPUTS@ 35 @SCAN_INPUTS@
36 @FASTA_INPUT@ 36 @FASTA_INPUT@
37 @TARGET_FASTA@ 37 @TARGET_FASTA@
38 @LIB_INPUT@ 38 @LIB_INPUT@
39 ## @COMMON_OPTIONS@
40 ## @MASS_LIBRARY_TOLERANCE@
41 ## @PERCOLATOR_OPTIONS@
42 ## @PEAK_OPTIONS@
43 ## @WINDOW_OPTIONS@
44 ## @MODIFICATION_OPTIONS@
45 ## @SEARCH_OPTIONS@
46 -a $a 39 -a $a
47 -o chromatogram_library.elib 40 -o chromatogram_library.elib
48 | tee -a search2lib.log 41 | tee -a search2lib.log
49 ]]></command> 42 ]]></command>
50 <inputs> 43 <inputs>
51 <expand macro="scan_inputs"/> 44 <expand macro="scan_inputs"/>
52 <expand macro="lib_input" token_optional="true" token_help="If a prosit dlib is supplied, use EncycopeDIA, else use walnut"/> 45 <expand macro="lib_input" optional="true" libhelp="Use a Prosit dlib spectral library to make a chromatogram elib using EncyclopeDIA, or else leave blank to make a Chromatogram library from just the fasta using Walnut"/>
53 <expand macro="fasta_input"/> 46 <expand macro="fasta_input"/>
54 <expand macro="target_fasta"/> 47 <expand macro="target_fasta"/>
55 <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="false" label="match between runs"/> 48 <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="false" label="align between files" help="retention-time alignment of peptides is generally not needed when using narrow-window spectrums"/>
56 <expand macro="common_options"/> 49 <expand macro="common_options"/>
57 <expand macro="mass_library_tolerance"/> 50 <expand macro="mass_library_tolerance"/>
58 <expand macro="percolator_options"/> 51 <expand macro="percolator_options"/>
59 <expand macro="peak_options"/> 52 <expand macro="peak_options"/>
60 <expand macro="window_options"/> 53 <expand macro="window_options"/>
61 <expand macro="modification_options"/> 54 <expand macro="modification_options"/>
62 <expand macro="search_options"/> 55 <expand macro="search_options"/>
63 <param name="select_outputs" type="select" label="Select outputs" multiple="true"> 56 <param name="select_outputs" type="select" label="Select outputs" multiple="true">
64 <option value="log" selected="true">log</option> 57 <option value="log" selected="true">log</option>
65 <option value="elib" selected="true">elib</option> 58 <option value="elib" selected="true">elib</option>
66 <option value="features" selected="true">concatenated_features.txt</option> 59 <option value="features" selected="false">concatenated_features.txt</option>
67 <option value="results" selected="true">concatenated_results.txt</option> 60 <option value="results" selected="false">concatenated_results.txt</option>
68 <option value="decoy" selected="false">concatenated_decoy.txt</option> 61 <option value="decoy" selected="false">concatenated_decoy.txt</option>
69 <option value="peptides" selected="true">peptides.txt (requires match between runs)</option> 62 <!--
70 <option value="proteins" selected="true">proteins.txt (requires match between runs)</option> 63 <option value="peptides" selected="false">peptides.txt (requires align between files)</option>
64 <option value="proteins" selected="false">proteins.txt (requires align between files)</option>
65 -->
71 </param> 66 </param>
72 </inputs> 67 </inputs>
73 <outputs> 68 <outputs>
74 <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="search2lib.log"> 69 <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="search2lib.log">
75 <filter>'log' in select_outputs</filter> 70 <filter>'log' in select_outputs</filter>
93 <filter>'decoy' in select_outputs</filter> 88 <filter>'decoy' in select_outputs</filter>
94 <actions> 89 <actions>
95 <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" /> 90 <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />
96 </actions> 91 </actions>
97 </data> 92 </data>
93 <!--
98 <data name="peptides" format="tabular" label="${tool.name} ${on_string} peptides.txt" from_work_dir="chromatogram_library.peptides.txt"> 94 <data name="peptides" format="tabular" label="${tool.name} ${on_string} peptides.txt" from_work_dir="chromatogram_library.peptides.txt">
99 <filter>a and peptides' in select_outputs</filter> 95 <filter>a and 'peptides' in select_outputs</filter>
100 <actions> 96 <actions>
101 <action name="column_names" type="metadata" default="Peptide,Protein,numFragments" /> 97 <action name="column_names" type="metadata" default="Peptide,Protein,numFragments" />
102 </actions> 98 </actions>
103 </data> 99 </data>
104 <data name="proteins" format="tabular" label="${tool.name} ${on_string} proteins.txt" from_work_dir="chromatogram_library.proteins.txt"> 100 <data name="proteins" format="tabular" label="${tool.name} ${on_string} proteins.txt" from_work_dir="chromatogram_library.proteins.txt">
105 <filter>a and 'proteins' in select_outputs</filter> 101 <filter>a and 'proteins' in select_outputs</filter>
106 <actions> 102 <actions>
107 <action name="column_names" type="metadata" default="Protein,NumPeptides,PeptideSequences" /> 103 <action name="column_names" type="metadata" default="Protein,NumPeptides,PeptideSequences" />
108 </actions> 104 </actions>
109 </data> 105 </data>
110 <!-- 106 -->
111 -->
112 </outputs> 107 </outputs>
113 <help><![CDATA[ 108 <help><![CDATA[
114 SearchToLIB uses EncyclopeDIA, Walnut (Pecan), or XCorDIA to create an DIA Elib for EncyclopeDIA DIA search
115 Walnut is a FASTA database search engine for DIA data that uses PECAN-style scoring.
116 You should prefix your arguments with a high memory setting, e.g. "-Xmx8g" for 8gb
117 109
118 Required Parameters: 110 **SearchToLIB**
119 -i input .DIA or .MZML file
120 -f background FASTA file
121 111
122 Other Parameters: 112 @ENCYCLOPEDIA_WIKI@
123 -t target FASTA file (default: background FASTA file) 113
124 -tp true/false target FASTA file contains peptides (default: false) 114 SearchToLIB uses the EncyclopeDIA algorithm, or the Walnut (Pecan) algorithm to search Data-Independent Acquisition (DIA) MS/MS spectrum files and creates a DIA elib chromatogram library for EncyclopeDIA DIA quantitation search.
125 -o output report file (default: [input file].pecan.txt) 115
126 -acquisition (default: overlapping dia) 116 SearchToLIB can also quantify peptides from the chromatogram library.
127 -addDecoysToBackground (default: false) 117
128 -alpha (default: 1.8) 118 @MSCONVERT_HELP@
129 -beta (default: 0.4) 119
130 -dontRunDecoys (default: false) 120 **Typical DIA Workflow**
131 -enzyme (default: trypsin) 121
132 -filterPeaklists (default: false) 122 Two sets of Mass Spec MS/MS DIA data are collected for the experiment. In addition to collecting wide-window DIA experiments on each quantitative replicate, a pool containing peptides from every condition is measured using several staggered narrow-window DIA experiments.
133 -fixed (default: C=57.0214635) 123
134 -foffset (default: 0) 124 1. SearchToLib is first run with the pooled narrow-window mzML files to create a combined DIA elib chromatogram library.
135 -frag (default: YONLY) 125 If a Spectral library argument is provided, for example from **Prosit**, SearchToLIB uses EncyclopeDIA to search each input spectrum mzML file.
136 -ftol (default: 10) 126 Otherwise, SearchToLIB uses Walnut, a FASTA database search engine for DIA data that uses PECAN-style scoring.
137 -ftolunits (default: ppm) 127
138 -maxCharge (default: 3) 128
139 -maxLength (default: 100) 129 * Prosit_ generates a predicted spectrum library of fragmentation patterns and retention times for every +2H and +3H tryptic peptide in a FASTA database, with up to one missed cleavage.
140 -maxMissedCleavage (default: 1) 130
141 -minCharge (default: 2) 131
142 -minEluteTime (default: 12) 132 2. EncyclopeDIA Quantify is then run on the wide-window quantitative replicate mzML files using that chromatogram library to produce quantification results.
143 -minIntensity (default: -1.0) 133
144 -minLength (default: 5) 134 .. image:: SearchToLib_Workflow.png
145 -minNumOfQuantitativePeaks (default: 3) 135 :height: 439
146 -minQuantitativeIonNumber (default: 3) 136 :width: 768
147 -numberOfQuantitativePeaks (default: 5) 137
148 -numberOfReportedPeaks (default: 1) 138 .. _Prosit: https://www.proteomicsdb.org/prosit
149 -numberOfThreadsUsed (default: 12)
150 -percolatorProteinThreshold (default: 0.01)
151 -percolatorThreshold (default: 0.01)
152 -percolatorVersionNumber (default: 3)
153 -poffset (default: 0)
154 -precursorIsolationMargin (default: 0)
155 -precursorWindowSize (default: -1)
156 -ptol (default: 10)
157 -ptolunits (default: ppm)
158 -requireVariableMods (default: false)
159 -variable (default: -)
160 139
161 ]]></help> 140 ]]></help>
162 <expand macro="citations" /> 141 <expand macro="citations" />
163 </tool> 142 </tool>