Mercurial > repos > jjohnson > encyclopedia_fasta_to_prosit_csv

comparison encyclopedia_searchtolib.xml.bak @ 1:c394bccd6f64 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 11:44:27 -0400
parents
children
comparison
equal deleted inserted replaced
0:d0202c597434 1:c394bccd6f64
1 <tool id="encyclopedia_searchtolib" name="SearchToLib" version="@VERSION@.0">
2 <description>Build a Chromatogram Library or quantify samples from Data-Independent Acquisition (DIA) MS/MS Data</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7 <command detect_errors="exit_code"><![CDATA[
8 @CMD_IMPORTS@
9 @LINK_SCAN_INPUTS@
10 @LINK_FASTA_INPUT@
11 @LINK_TARGET_FASTA@
12 @LINK_LIB_INPUT@
13 for SCAN_FILE in `ls -1 inputs/*`; do
14 echo "\$SCAN_FILE" &&
15 EncyclopeDIA -Djava.awt.headless=true -Xmx20g
16 #if not $l
17 -walnut
18 #end if
19 -i \$SCAN_FILE
20 @FASTA_INPUT@
21 @TARGET_FASTA@
22 @LIB_INPUT@
23 @COMMON_OPTIONS@
24 @MASS_LIBRARY_TOLERANCE@
25 @PERCOLATOR_OPTIONS@
26 @PEAK_OPTIONS@
27 @WINDOW_OPTIONS@
28 @MODIFICATION_OPTIONS@
29 @SEARCH_OPTIONS@ | tee -a search2lib.log
30 ; done &&
31 EncyclopeDIA -Djava.awt.headless=true -Xmx12g -libexport
32 #if not $l
33 -pecan
34 #end if
35 @SCAN_INPUTS@
36 @FASTA_INPUT@
37 @TARGET_FASTA@
38 @LIB_INPUT@
39 -a $a
40 -o chromatogram_library.elib
41 | tee -a search2lib.log
42 ]]></command>
43 <inputs>
44 <expand macro="scan_inputs"/>
45 <expand macro="lib_input" optional="true" libhelp="Use a Chromatogram elib for quantification, or a Prosit dlib spectral library to make a chromatogram elib using EncyclopeDIA, or else leave blank to make a Chromatogram library from just the fasta using Walnut"/>
46 <expand macro="fasta_input"/>
47 <expand macro="target_fasta"/>
48 <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="false" label="align between files" help="retention-time alignment of peptides should be enabled when quantifying samples"/>
49 <expand macro="common_options"/>
50 <expand macro="mass_library_tolerance"/>
51 <expand macro="percolator_options"/>
52 <expand macro="peak_options"/>
53 <expand macro="window_options"/>
54 <expand macro="modification_options"/>
55 <expand macro="search_options"/>
56 <param name="select_outputs" type="select" label="Select outputs" multiple="true">
57 <option value="log" selected="true">log</option>
58 <option value="elib" selected="true">elib</option>
59 <option value="features" selected="true">concatenated_features.txt</option>
60 <option value="results" selected="true">concatenated_results.txt</option>
61 <option value="decoy" selected="false">concatenated_decoy.txt</option>
62 <option value="peptides" selected="true">peptides.txt (requires match between runs)</option>
63 <option value="proteins" selected="true">proteins.txt (requires match between runs)</option>
64 </param>
65 </inputs>
66 <outputs>
67 <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="search2lib.log">
68 <filter>'log' in select_outputs</filter>
69 </data>
70 <data name="elib" format="elib" label="${tool.name} ${on_string} elib" from_work_dir="chromatogram_library.elib">
71 <filter>'elib' in select_outputs</filter>
72 </data>
73 <data name="features" format="tabular" label="${tool.name} ${on_string} concatenated_features.txt" from_work_dir="inputs/chromatogram_library_concatenated_features.txt">
74 <filter>'features' in select_outputs</filter>
75 <actions>
76 <action name="column_names" type="metadata" default="id,TD,ScanNr,topN,rank,peakZScore,peakCalibratedScore,deltaSn,avgIdotp,midIdotp,peakScore,peakWeightedScore,NCI,CIMassErrMean,CIMassErrVar,precursorMassErrMean,precursorMassErrVar,peakSimilarity,sampledTimes,midTime,spectraNorm,pepLength,charge2,charge3,precursorMz,sequence,protein" />
77 </actions>
78 </data>
79 <data name="results" format="tabular" label="${tool.name} ${on_string} concatenated_results.txt" from_work_dir="inputs/chromatogram_library_concatenated_results.txt">
80 <filter>'results' in select_outputs</filter>
81 <actions>
82 <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />
83 </actions>
84 </data>
85 <data name="decoy" format="tabular" label="${tool.name} ${on_string} concatenated_decoy.txt" from_work_dir="inputs/chromatogram_library_concatenated_decoy.txt">
86 <filter>'decoy' in select_outputs</filter>
87 <actions>
88 <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />
89 </actions>
90 </data>
91 <data name="peptides" format="tabular" label="${tool.name} ${on_string} peptides.txt" from_work_dir="chromatogram_library.peptides.txt">
92 <filter>a and 'peptides' in select_outputs</filter>
93 <actions>
94 <action name="column_names" type="metadata" default="Peptide,Protein,numFragments" />
95 </actions>
96 </data>
97 <data name="proteins" format="tabular" label="${tool.name} ${on_string} proteins.txt" from_work_dir="chromatogram_library.proteins.txt">
98 <filter>a and 'proteins' in select_outputs</filter>
99 <actions>
100 <action name="column_names" type="metadata" default="Protein,NumPeptides,PeptideSequences" />
101 </actions>
102 </data>
103 </outputs>
104 <help><![CDATA[
105
106 **SearchToLIB**
107
108 @ENCYCLOPEDIA_WIKI@
109
110 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.
111
112 SearchToLIB can also quantify peptides from the chromatogram library.
113
114 @MSCONVERT_HELP@
115
116 **Typical DIA SearchToLib Workflow**
117
118 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.
119
120 1. SearchToLib is first run with the pooled narrow-window mzML files to create a combined DIA elib chromatogram library.
121 If a Spectral library argument is provided, for example from **Prosit**, SearchToLIB uses EncyclopeDIA to search each input spectrum mzML file.
122 Otherwise, SearchToLIB uses Walnut, a FASTA database search engine for DIA data that uses PECAN-style scoring.
123
124
125 * 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.
126
127
128 2. SearchToLib is then run on the wide-window quantitative replicate mzML files using that chromatogram library, with the *align between files* option, to produce quantification results.
129
130 .. image:: SearchToLib_Workflow.png
131 :height: 439
132 :width: 768
133
134 .. _Prosit: https://www.proteomicsdb.org/prosit
135
136 ]]></help>
137 <expand macro="citations" />
138 </tool>