Mercurial > repos > galaxyp > openms_databasesuitability

comparison DatabaseSuitability.xml @ 3:2470b498fc12 draft default tip

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/master/tools/openms commit 5c080b1e2b99f1c88f4557e9fec8c45c9d23b906
author galaxyp
date Fri, 14 Jun 2024 21:46:31 +0000
parents 4890f50ae1a2
children
comparison
equal deleted inserted replaced
2:4890f50ae1a2 3:2470b498fc12
1 <?xml version='1.0' encoding='UTF-8'?>
2 <!--This is a configuration file for the integration of a tools into Galaxy (https://galaxyproject.org/). This file was automatically generated using CTDConverter.--> 1 <!--This is a configuration file for the integration of a tools into Galaxy (https://galaxyproject.org/). This file was automatically generated using CTDConverter.-->
3 <!--Proposed Tool Section: [Quality Control]--> 2 <!--Proposed Tool Section: [Quality Control]-->
4 <tool id="DatabaseSuitability" name="DatabaseSuitability" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05"> 3 <tool id="DatabaseSuitability" name="DatabaseSuitability" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
5 <description>Computes a suitability score for a database which was used for a peptide identification search. Also reports the quality of LC-MS spectra.</description> 4 <description>Computes a suitability score for a database which was used for a peptide identification search. Also reports the quality of LC-MS spectra</description>
6 <macros> 5 <macros>
7 <token name="@EXECUTABLE@">DatabaseSuitability</token> 6 <token name="@EXECUTABLE@">DatabaseSuitability</token>
8 <import>macros.xml</import> 7 <import>macros.xml</import>
9 </macros> 8 </macros>
10 <expand macro="requirements"/> 9 <expand macro="requirements"/>
13 @EXT_FOO@ 12 @EXT_FOO@
14 #import re 13 #import re
15 14
16 ## Preprocessing 15 ## Preprocessing
17 mkdir in_id && 16 mkdir in_id &&
18 ln -s '$in_id' 'in_id/${re.sub("[^\w\-_]", "_", $in_id.element_identifier)}.$gxy2omsext($in_id.ext)' && 17 cp '$in_id' 'in_id/${re.sub("[^\w\-_]", "_", $in_id.element_identifier)}.$gxy2omsext($in_id.ext)' &&
19 mkdir in_spec && 18 mkdir in_spec &&
20 ln -s '$in_spec' 'in_spec/${re.sub("[^\w\-_]", "_", $in_spec.element_identifier)}.$gxy2omsext($in_spec.ext)' && 19 cp '$in_spec' 'in_spec/${re.sub("[^\w\-_]", "_", $in_spec.element_identifier)}.$gxy2omsext($in_spec.ext)' &&
21 mkdir in_novo && 20 mkdir in_novo &&
22 ln -s '$in_novo' 'in_novo/${re.sub("[^\w\-_]", "_", $in_novo.element_identifier)}.$gxy2omsext($in_novo.ext)' && 21 cp '$in_novo' 'in_novo/${re.sub("[^\w\-_]", "_", $in_novo.element_identifier)}.$gxy2omsext($in_novo.ext)' &&
23 mkdir database && 22 mkdir database &&
24 ln -s '$database' 'database/${re.sub("[^\w\-_]", "_", $database.element_identifier)}.$gxy2omsext($database.ext)' && 23 cp '$database' 'database/${re.sub("[^\w\-_]", "_", $database.element_identifier)}.$gxy2omsext($database.ext)' &&
25 mkdir novo_database && 24 mkdir novo_database &&
26 ln -s '$novo_database' 'novo_database/${re.sub("[^\w\-_]", "_", $novo_database.element_identifier)}.$gxy2omsext($novo_database.ext)' && 25 cp '$novo_database' 'novo_database/${re.sub("[^\w\-_]", "_", $novo_database.element_identifier)}.$gxy2omsext($novo_database.ext)' &&
27 #if "out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') 26 #if "out_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
28 mkdir out && 27 mkdir out &&
29 #end if 28 #end if
30 29
31 ## Main program call 30 ## Main program call
62 <configfiles> 61 <configfiles>
63 <inputs name="args_json" data_style="paths"/> 62 <inputs name="args_json" data_style="paths"/>
64 <configfile name="hardcoded_json"><![CDATA[{"log": "log.txt", "threads": "\${GALAXY_SLOTS:-1}", "no_progress": true}]]></configfile> 63 <configfile name="hardcoded_json"><![CDATA[{"log": "log.txt", "threads": "\${GALAXY_SLOTS:-1}", "no_progress": true}]]></configfile>
65 </configfiles> 64 </configfiles>
66 <inputs> 65 <inputs>
67 <param argument="-in_id" type="data" format="idxml" optional="false" label="Input idXML file from a peptide identification search with a combined database" help="PeptideIndexer is needed, FDR is forbidden select idxml data sets(s)"/> 66 <param argument="-in_id" type="data" format="idxml" label="Input idXML file from a peptide identification search with a combined database" help="PeptideIndexer is needed, FDR is forbidden select idxml data sets(s)"/>
68 <param argument="-in_spec" type="data" format="mzml" optional="false" label="Input MzML file used for the peptide identification" help=" select mzml data sets(s)"/> 67 <param argument="-in_spec" type="data" format="mzml" label="Input MzML file used for the peptide identification" help=" select mzml data sets(s)"/>
69 <param argument="-in_novo" type="data" format="idxml" optional="false" label="Input idXML file containing de novo peptides (unfiltered)" help=" select idxml data sets(s)"/> 68 <param argument="-in_novo" type="data" format="idxml" label="Input idXML file containing de novo peptides (unfiltered)" help=" select idxml data sets(s)"/>
70 <param argument="-database" type="data" format="fasta" optional="false" label="Input FASTA file of the database in question" help=" select fasta data sets(s)"/> 69 <param argument="-database" type="data" format="fasta" label="Input FASTA file of the database in question" help=" select fasta data sets(s)"/>
71 <param argument="-novo_database" type="data" format="fasta" optional="false" label="Input deNovo sequences derived from MzML given in 'in_spec' concatenated to one FASTA entry" help=" select fasta data sets(s)"/> 70 <param argument="-novo_database" type="data" format="fasta" label="Input deNovo sequences derived from MzML given in 'in_spec' concatenated to one FASTA entry" help=" select fasta data sets(s)"/>
72 <section name="algorithm" title="Parameter section for the suitability calculation algorithm" help="" expanded="false"> 71 <section name="algorithm" title="Parameter section for the suitability calculation algorithm" help="" expanded="false">
73 <param name="no_rerank" argument="-algorithm:no_rerank" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use this flag if you want to disable re-ranking" help="Cases, where a de novo peptide scores just higher than the database peptide, are overlooked and counted as a de novo hit. This might underestimate the database quality"/> 72 <param name="no_rerank" argument="-algorithm:no_rerank" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use this flag if you want to disable re-ranking" help="Cases, where a de novo peptide scores just higher than the database peptide, are overlooked and counted as a de novo hit. This might underestimate the database quality"/>
74 <param name="reranking_cutoff_percentile" argument="-algorithm:reranking_cutoff_percentile" type="float" optional="true" min="0.0" max="1.0" value="0.01" label="Swap a top-scoring deNovo hit with a lower scoring DB hit if their xcorr score difference is in the given percentile of all score differences between the first two decoy hits of a PSM" help="The lower the value the lower the decoy cut-off will be. Therefore it will be harder for a lower scoring DB hit to be re-ranked to the top"/> 73 <param name="reranking_cutoff_percentile" argument="-algorithm:reranking_cutoff_percentile" type="float" min="0.0" max="1.0" value="0.01" label="Swap a top-scoring deNovo hit with a lower scoring DB hit if their xcorr score difference is in the given percentile of all score differences between the first two decoy hits of a PSM" help="The lower the value the lower the decoy cut-off will be. Therefore it will be harder for a lower scoring DB hit to be re-ranked to the top"/>
75 <param name="FDR" argument="-algorithm:FDR" type="float" optional="true" min="0.0" max="1.0" value="0.01" label="Filter peptide hits based on this q-value" help="(e.g., 0.05 = 5 % FDR)"/> 74 <param name="FDR" argument="-algorithm:FDR" type="float" min="0.0" max="1.0" value="0.01" label="Filter peptide hits based on this q-value" help="(e.g., 0.05 = 5 % FDR)"/>
76 <param name="number_of_subsampled_runs" argument="-algorithm:number_of_subsampled_runs" type="integer" optional="true" min="0" value="1" label="Controls how many runs should be done for calculating corrected suitability" help="(0 : number of runs will be estimated automaticly) ATTENTION: For each run a seperate ID-search is performed. This can result in some serious run time"/> 75 <param name="number_of_subsampled_runs" argument="-algorithm:number_of_subsampled_runs" type="integer" min="0" value="1" label="Controls how many runs should be done for calculating corrected suitability" help="(0 : number of runs will be estimated automaticly) ATTENTION: For each run a seperate ID-search is performed. This can result in some serious run time"/>
77 <param name="keep_search_files" argument="-algorithm:keep_search_files" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Set this flag if you wish to keep the files used by and produced by the internal ID search" help=""/> 76 <param name="keep_search_files" argument="-algorithm:keep_search_files" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Set this flag if you wish to keep the files used by and produced by the internal ID search" help=""/>
78 <param name="disable_correction" argument="-algorithm:disable_correction" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Set this flag to disable the calculation of the corrected suitability" help=""/> 77 <param name="disable_correction" argument="-algorithm:disable_correction" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Set this flag to disable the calculation of the corrected suitability" help=""/>
79 <param name="force" argument="-algorithm:force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Set this flag to enforce re-ranking when no cross correlation score is present" help="For re-ranking the default score found at each peptide hit is used. Use with care!"/> 78 <param name="force" argument="-algorithm:force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Set this flag to enforce re-ranking when no cross correlation score is present" help="For re-ranking the default score found at each peptide hit is used. Use with care!"/>
80 </section> 79 </section>
81 <expand macro="adv_opts_macro"> 80 <expand macro="adv_opts_macro">
82 <param argument="-novo_threshold" type="float" optional="true" min="0.0" value="60.0" label="Minimum score a de novo sequence has to have to be defined as 'correct'" help="The default of 60 is proven to be a good estimate for sequences generated by Novor"/> 81 <param argument="-novo_threshold" type="float" min="0.0" value="60.0" label="Minimum score a de novo sequence has to have to be defined as 'correct'" help="The default of 60 is proven to be a good estimate for sequences generated by Novor"/>
83 <param argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" help=""/> 82 <param argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" help=""/>
84 <param argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help=""> 83 <param argument="-test" type="hidden" value="False" label="Enables the test mode (needed for internal use only)" help="" optional="true">
85 <expand macro="list_string_san" name="test"/> 84 <expand macro="list_string_san" name="test"/>
86 </param> 85 </param>
87 </expand> 86 </expand>
88 <param name="OPTIONAL_OUTPUTS" type="select" optional="true" multiple="true" label="Optional outputs"> 87 <param name="OPTIONAL_OUTPUTS" type="select" optional="true" multiple="true" label="Optional outputs">
89 <option value="out_FLAG">out (Optional tsv output containing database suitability information as well as spectral quality)</option> 88 <option value="out_FLAG">out (Optional tsv output containing database suitability information as well as spectral quality)</option>
99 </data> 98 </data>
100 <data name="ctd_out" format="xml" label="${tool.name} on ${on_string}: ctd"> 99 <data name="ctd_out" format="xml" label="${tool.name} on ${on_string}: ctd">
101 <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter> 100 <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter>
102 </data> 101 </data>
103 </outputs> 102 </outputs>
104 <tests><!-- TOPP_DatabaseSuitability_1 --> 103 <tests>
105 <test expect_num_outputs="2"> 104 <!-- TOPP_DatabaseSuitability -->
106 <section name="adv_opts"> 105 <test expect_num_outputs="2">
107 <param name="novo_threshold" value="60.0"/> 106 <section name="adv_opts">
108 <param name="force" value="false"/> 107 <param name="novo_threshold" value="60.0"/>
109 <param name="test" value="true"/> 108 <param name="force" value="false"/>
110 </section> 109 <param name="test" value="true"/>
111 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/> 110 </section>
112 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/> 111 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/>
113 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/> 112 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/>
114 <param name="database" value="DatabaseSuitability_database.fasta"/> 113 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/>
115 <param name="novo_database" value="DatabaseSuitability_novo_database.FASTA"/> 114 <param name="database" value="DatabaseSuitability_database.fasta"/>
116 <output name="out" file="DatabaseSuitability_out_1.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/> 115 <param name="novo_database" value="DatabaseSuitability_novo_database.FASTA"/>
116 <output name="out" value="DatabaseSuitability_out.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/>
117 <section name="algorithm"> 117 <section name="algorithm">
118 <param name="no_rerank" value="false"/> 118 <param name="no_rerank" value="false"/>
119 <param name="reranking_cutoff_percentile" value="0.01"/> 119 <param name="reranking_cutoff_percentile" value="0.01"/>
120 <param name="FDR" value="0.01"/> 120 <param name="FDR" value="0.01"/>
121 <param name="number_of_subsampled_runs" value="1"/> 121 <param name="number_of_subsampled_runs" value="1"/>
122 <param name="keep_search_files" value="false"/> 122 <param name="keep_search_files" value="false"/>
123 <param name="disable_correction" value="true"/>
124 <param name="force" value="false"/>
125 </section>
126 <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,out_FLAG"/>
127 <output name="ctd_out" ftype="xml">
128 <assert_contents>
129 <is_valid_xml/>
130 </assert_contents>
131 </output>
132 <assert_stdout>
133 <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/>
134 </assert_stdout>
135 </test>
136 <!-- TOPP_DatabaseSuitability_1 -->
137 <test expect_num_outputs="2">
138 <section name="adv_opts">
139 <param name="novo_threshold" value="60.0"/>
140 <param name="force" value="false"/>
141 <param name="test" value="true"/>
142 </section>
143 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/>
144 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/>
145 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/>
146 <param name="database" value="DatabaseSuitability_database.fasta"/>
147 <param name="novo_database" value="DatabaseSuitability_novo_database.FASTA"/>
148 <output name="out" value="DatabaseSuitability_out_1.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/>
149 <section name="algorithm">
150 <param name="no_rerank" value="false"/>
151 <param name="reranking_cutoff_percentile" value="0.01"/>
152 <param name="FDR" value="0.01"/>
153 <param name="number_of_subsampled_runs" value="1"/>
154 <param name="keep_search_files" value="false"/>
123 <param name="disable_correction" value="false"/> 155 <param name="disable_correction" value="false"/>
124 <param name="force" value="false"/> 156 <param name="force" value="false"/>
125 </section> 157 </section>
126 <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,out_FLAG"/> 158 <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,out_FLAG"/>
127 <output name="ctd_out" ftype="xml"> 159 <output name="ctd_out" ftype="xml">
128 <assert_contents> 160 <assert_contents>
129 <is_valid_xml/> 161 <is_valid_xml/>
130 </assert_contents> 162 </assert_contents>
131 </output> 163 </output>
164 <assert_stdout>
165 <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/>
166 </assert_stdout>
132 </test> 167 </test>
133 <!-- TOPP_DatabaseSuitability_2 --> 168 <!-- TOPP_DatabaseSuitability_2 -->
134 <test expect_num_outputs="2"> 169 <test expect_num_outputs="2">
135 <section name="adv_opts"> 170 <section name="adv_opts">
136 <param name="novo_threshold" value="60.0"/> 171 <param name="novo_threshold" value="60.0"/>
140 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/> 175 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/>
141 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/> 176 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/>
142 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/> 177 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/>
143 <param name="database" value="DatabaseSuitability_database.fasta"/> 178 <param name="database" value="DatabaseSuitability_database.fasta"/>
144 <param name="novo_database" value="DatabaseSuitability_novo_database.FASTA"/> 179 <param name="novo_database" value="DatabaseSuitability_novo_database.FASTA"/>
145 <output name="out" file="DatabaseSuitability_out_2.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/> 180 <output name="out" value="DatabaseSuitability_out_2.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/>
146 <section name="algorithm"> 181 <section name="algorithm">
147 <param name="no_rerank" value="false"/> 182 <param name="no_rerank" value="false"/>
148 <param name="reranking_cutoff_percentile" value="0.01"/> 183 <param name="reranking_cutoff_percentile" value="0.01"/>
149 <param name="FDR" value="0.05"/> 184 <param name="FDR" value="0.05"/>
150 <param name="number_of_subsampled_runs" value="1"/> 185 <param name="number_of_subsampled_runs" value="1"/>
156 <output name="ctd_out" ftype="xml"> 191 <output name="ctd_out" ftype="xml">
157 <assert_contents> 192 <assert_contents>
158 <is_valid_xml/> 193 <is_valid_xml/>
159 </assert_contents> 194 </assert_contents>
160 </output> 195 </output>
196 <assert_stdout>
197 <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/>
198 </assert_stdout>
161 </test> 199 </test>
162 <!-- TOPP_DatabaseSuitability_3 --> 200 <!-- TOPP_DatabaseSuitability_3 -->
163 <test expect_num_outputs="2"> 201 <test expect_num_outputs="2">
164 <section name="adv_opts"> 202 <section name="adv_opts">
165 <param name="novo_threshold" value="60.0"/> 203 <param name="novo_threshold" value="60.0"/>
169 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/> 207 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/>
170 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/> 208 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/>
171 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/> 209 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/>
172 <param name="database" value="DatabaseSuitability_database.fasta"/> 210 <param name="database" value="DatabaseSuitability_database.fasta"/>
173 <param name="novo_database" value="DatabaseSuitability_novo_database.FASTA"/> 211 <param name="novo_database" value="DatabaseSuitability_novo_database.FASTA"/>
174 <output name="out" file="DatabaseSuitability_out_3.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/> 212 <output name="out" value="DatabaseSuitability_out_3.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/>
175 <section name="algorithm"> 213 <section name="algorithm">
176 <param name="no_rerank" value="false"/> 214 <param name="no_rerank" value="false"/>
177 <param name="reranking_cutoff_percentile" value="0.5"/> 215 <param name="reranking_cutoff_percentile" value="0.5"/>
178 <param name="FDR" value="0.5"/> 216 <param name="FDR" value="0.5"/>
179 <param name="number_of_subsampled_runs" value="1"/> 217 <param name="number_of_subsampled_runs" value="1"/>
185 <output name="ctd_out" ftype="xml"> 223 <output name="ctd_out" ftype="xml">
186 <assert_contents> 224 <assert_contents>
187 <is_valid_xml/> 225 <is_valid_xml/>
188 </assert_contents> 226 </assert_contents>
189 </output> 227 </output>
228 <assert_stdout>
229 <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/>
230 </assert_stdout>
190 </test> 231 </test>
191 </tests> 232 </tests>
192 <help><![CDATA[Computes a suitability score for a database which was used for a peptide identification search. Also reports the quality of LC-MS spectra. 233 <help><![CDATA[Computes a suitability score for a database which was used for a peptide identification search. Also reports the quality of LC-MS spectra.
193 234
194 235
195 For more information, visit http://www.openms.de/doxygen/release/2.8.0/html/TOPP_DatabaseSuitability.html]]></help> 236 For more information, visit https://openms.de/doxygen/release/3.1.0/html/TOPP_DatabaseSuitability.html]]></help>
196 <expand macro="references"/> 237 <expand macro="references"/>
197 </tool> 238 </tool>