Mercurial > repos > galaxyp > openms_databasesuitability
comparison DatabaseSuitability.xml @ 2:4890f50ae1a2 draft default tip
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 3d1e5f37fd16524a415f707772eeb7ead848c5e3
author | galaxyp |
---|---|
date | Thu, 01 Dec 2022 19:02:20 +0000 |
parents | d994c72a91fc |
children |
comparison
equal
deleted
inserted
replaced
1:594a165c069c | 2:4890f50ae1a2 |
---|---|
1 <?xml version='1.0' encoding='UTF-8'?> | 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.--> | 2 <!--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: []--> | 3 <!--Proposed Tool Section: [Quality Control]--> |
4 <tool id="DatabaseSuitability" name="DatabaseSuitability" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@" profile="20.05"> | 4 <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> | 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> |
6 <macros> | 6 <macros> |
7 <token name="@EXECUTABLE@">DatabaseSuitability</token> | 7 <token name="@EXECUTABLE@">DatabaseSuitability</token> |
8 <import>macros.xml</import> | 8 <import>macros.xml</import> |
9 <import>macros_autotest.xml</import> | |
10 <import>macros_test.xml</import> | |
11 </macros> | 9 </macros> |
12 <expand macro="requirements"/> | 10 <expand macro="requirements"/> |
13 <expand macro="stdio"/> | 11 <expand macro="stdio"/> |
14 <command detect_errors="exit_code"><![CDATA[@QUOTE_FOO@ | 12 <command detect_errors="exit_code"><![CDATA[@QUOTE_FOO@ |
15 @EXT_FOO@ | 13 @EXT_FOO@ |
20 ln -s '$in_id' 'in_id/${re.sub("[^\w\-_]", "_", $in_id.element_identifier)}.$gxy2omsext($in_id.ext)' && | 18 ln -s '$in_id' 'in_id/${re.sub("[^\w\-_]", "_", $in_id.element_identifier)}.$gxy2omsext($in_id.ext)' && |
21 mkdir in_spec && | 19 mkdir in_spec && |
22 ln -s '$in_spec' 'in_spec/${re.sub("[^\w\-_]", "_", $in_spec.element_identifier)}.$gxy2omsext($in_spec.ext)' && | 20 ln -s '$in_spec' 'in_spec/${re.sub("[^\w\-_]", "_", $in_spec.element_identifier)}.$gxy2omsext($in_spec.ext)' && |
23 mkdir in_novo && | 21 mkdir in_novo && |
24 ln -s '$in_novo' 'in_novo/${re.sub("[^\w\-_]", "_", $in_novo.element_identifier)}.$gxy2omsext($in_novo.ext)' && | 22 ln -s '$in_novo' 'in_novo/${re.sub("[^\w\-_]", "_", $in_novo.element_identifier)}.$gxy2omsext($in_novo.ext)' && |
23 mkdir database && | |
24 ln -s '$database' 'database/${re.sub("[^\w\-_]", "_", $database.element_identifier)}.$gxy2omsext($database.ext)' && | |
25 mkdir novo_database && | |
26 ln -s '$novo_database' 'novo_database/${re.sub("[^\w\-_]", "_", $novo_database.element_identifier)}.$gxy2omsext($novo_database.ext)' && | |
25 #if "out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') | 27 #if "out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') |
26 mkdir out && | 28 mkdir out && |
27 #end if | 29 #end if |
28 | 30 |
29 ## Main program call | 31 ## Main program call |
36 'in_id/${re.sub("[^\w\-_]", "_", $in_id.element_identifier)}.$gxy2omsext($in_id.ext)' | 38 'in_id/${re.sub("[^\w\-_]", "_", $in_id.element_identifier)}.$gxy2omsext($in_id.ext)' |
37 -in_spec | 39 -in_spec |
38 'in_spec/${re.sub("[^\w\-_]", "_", $in_spec.element_identifier)}.$gxy2omsext($in_spec.ext)' | 40 'in_spec/${re.sub("[^\w\-_]", "_", $in_spec.element_identifier)}.$gxy2omsext($in_spec.ext)' |
39 -in_novo | 41 -in_novo |
40 'in_novo/${re.sub("[^\w\-_]", "_", $in_novo.element_identifier)}.$gxy2omsext($in_novo.ext)' | 42 'in_novo/${re.sub("[^\w\-_]", "_", $in_novo.element_identifier)}.$gxy2omsext($in_novo.ext)' |
43 -database | |
44 'database/${re.sub("[^\w\-_]", "_", $database.element_identifier)}.$gxy2omsext($database.ext)' | |
45 -novo_database | |
46 'novo_database/${re.sub("[^\w\-_]", "_", $novo_database.element_identifier)}.$gxy2omsext($novo_database.ext)' | |
41 #if "out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') | 47 #if "out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') |
42 -out | 48 -out |
43 'out/output.${gxy2omsext("tabular")}' | 49 'out/output.${gxy2omsext("tabular")}' |
44 #end if | 50 #end if |
45 #if len(str($OPTIONAL_OUTPUTS).split(',')) == 0 | 51 #if len(str($OPTIONAL_OUTPUTS).split(',')) == 0 |
56 <configfiles> | 62 <configfiles> |
57 <inputs name="args_json" data_style="paths"/> | 63 <inputs name="args_json" data_style="paths"/> |
58 <configfile name="hardcoded_json"><![CDATA[{"log": "log.txt", "threads": "\${GALAXY_SLOTS:-1}", "no_progress": true}]]></configfile> | 64 <configfile name="hardcoded_json"><![CDATA[{"log": "log.txt", "threads": "\${GALAXY_SLOTS:-1}", "no_progress": true}]]></configfile> |
59 </configfiles> | 65 </configfiles> |
60 <inputs> | 66 <inputs> |
61 <param name="in_id" argument="-in_id" type="data" format="idxml" optional="false" label="Input idXML file from peptide search with combined database with added de novo peptide" help="PeptideIndexer is needed, FDR is forbidden select idxml data sets(s)"/> | 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)"/> |
62 <param name="in_spec" argument="-in_spec" type="data" format="mzml" optional="false" label="Input MzML file used for the peptide identification" help=" select mzml 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)"/> |
63 <param name="in_novo" argument="-in_novo" type="data" format="idxml" optional="false" label="Input idXML file containing de novo peptides (unfiltered)" help=" select idxml 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)"/> |
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)"/> | |
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)"/> | |
64 <section name="algorithm" title="Parameter section for the suitability calculation algorithm" help="" expanded="false"> | 72 <section name="algorithm" title="Parameter section for the suitability calculation algorithm" help="" expanded="false"> |
65 <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"/> | 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"/> |
66 <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"/> | 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"/> |
67 <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)"/> | 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)"/> |
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"/> | |
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=""/> | |
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=""/> | |
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!"/> | |
68 </section> | 80 </section> |
69 <expand macro="adv_opts_macro"> | 81 <expand macro="adv_opts_macro"> |
70 <param name="force" argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" help=""/> | 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"/> |
71 <param name="test" argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help=""> | 83 <param argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" help=""/> |
72 <expand macro="list_string_san"/> | 84 <param argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help=""> |
85 <expand macro="list_string_san" name="test"/> | |
73 </param> | 86 </param> |
74 </expand> | 87 </expand> |
75 <param name="OPTIONAL_OUTPUTS" type="select" optional="true" multiple="true" label="Optional outputs"> | 88 <param name="OPTIONAL_OUTPUTS" type="select" optional="true" multiple="true" label="Optional outputs"> |
76 <option value="out_FLAG">out (Optional tsv output containing database suitability information as well as spectral quality)</option> | 89 <option value="out_FLAG">out (Optional tsv output containing database suitability information as well as spectral quality)</option> |
77 <option value="ctd_out_FLAG">Output used ctd (ini) configuration file</option> | 90 <option value="ctd_out_FLAG">Output used ctd (ini) configuration file</option> |
86 </data> | 99 </data> |
87 <data name="ctd_out" format="xml" label="${tool.name} on ${on_string}: ctd"> | 100 <data name="ctd_out" format="xml" label="${tool.name} on ${on_string}: ctd"> |
88 <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter> | 101 <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter> |
89 </data> | 102 </data> |
90 </outputs> | 103 </outputs> |
91 <tests> | 104 <tests><!-- TOPP_DatabaseSuitability_1 --> |
92 <expand macro="autotest_DatabaseSuitability"/> | 105 <test expect_num_outputs="2"> |
93 <expand macro="manutest_DatabaseSuitability"/> | 106 <section name="adv_opts"> |
107 <param name="novo_threshold" value="60.0"/> | |
108 <param name="force" value="false"/> | |
109 <param name="test" value="true"/> | |
110 </section> | |
111 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/> | |
112 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/> | |
113 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/> | |
114 <param name="database" value="DatabaseSuitability_database.fasta"/> | |
115 <param name="novo_database" value="DatabaseSuitability_novo_database.FASTA"/> | |
116 <output name="out" file="DatabaseSuitability_out_1.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/> | |
117 <section name="algorithm"> | |
118 <param name="no_rerank" value="false"/> | |
119 <param name="reranking_cutoff_percentile" value="0.01"/> | |
120 <param name="FDR" value="0.01"/> | |
121 <param name="number_of_subsampled_runs" value="1"/> | |
122 <param name="keep_search_files" value="false"/> | |
123 <param name="disable_correction" value="false"/> | |
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 </test> | |
133 <!-- TOPP_DatabaseSuitability_2 --> | |
134 <test expect_num_outputs="2"> | |
135 <section name="adv_opts"> | |
136 <param name="novo_threshold" value="60.0"/> | |
137 <param name="force" value="false"/> | |
138 <param name="test" value="true"/> | |
139 </section> | |
140 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/> | |
141 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/> | |
142 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/> | |
143 <param name="database" value="DatabaseSuitability_database.fasta"/> | |
144 <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"/> | |
146 <section name="algorithm"> | |
147 <param name="no_rerank" value="false"/> | |
148 <param name="reranking_cutoff_percentile" value="0.01"/> | |
149 <param name="FDR" value="0.05"/> | |
150 <param name="number_of_subsampled_runs" value="1"/> | |
151 <param name="keep_search_files" value="false"/> | |
152 <param name="disable_correction" value="false"/> | |
153 <param name="force" value="false"/> | |
154 </section> | |
155 <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,out_FLAG"/> | |
156 <output name="ctd_out" ftype="xml"> | |
157 <assert_contents> | |
158 <is_valid_xml/> | |
159 </assert_contents> | |
160 </output> | |
161 </test> | |
162 <!-- TOPP_DatabaseSuitability_3 --> | |
163 <test expect_num_outputs="2"> | |
164 <section name="adv_opts"> | |
165 <param name="novo_threshold" value="60.0"/> | |
166 <param name="force" value="false"/> | |
167 <param name="test" value="true"/> | |
168 </section> | |
169 <param name="in_id" value="DatabaseSuitability_in_id.idXML"/> | |
170 <param name="in_spec" value="DatabaseSuitability_in_spec.mzML"/> | |
171 <param name="in_novo" value="DatabaseSuitability_in_novo.idXML"/> | |
172 <param name="database" value="DatabaseSuitability_database.fasta"/> | |
173 <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"/> | |
175 <section name="algorithm"> | |
176 <param name="no_rerank" value="false"/> | |
177 <param name="reranking_cutoff_percentile" value="0.5"/> | |
178 <param name="FDR" value="0.5"/> | |
179 <param name="number_of_subsampled_runs" value="1"/> | |
180 <param name="keep_search_files" value="false"/> | |
181 <param name="disable_correction" value="false"/> | |
182 <param name="force" value="false"/> | |
183 </section> | |
184 <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,out_FLAG"/> | |
185 <output name="ctd_out" ftype="xml"> | |
186 <assert_contents> | |
187 <is_valid_xml/> | |
188 </assert_contents> | |
189 </output> | |
190 </test> | |
94 </tests> | 191 </tests> |
95 <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. | 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. |
96 | 193 |
97 ]]></help> | 194 |
195 For more information, visit http://www.openms.de/doxygen/release/2.8.0/html/TOPP_DatabaseSuitability.html]]></help> | |
98 <expand macro="references"/> | 196 <expand macro="references"/> |
99 </tool> | 197 </tool> |