Mercurial > repos > galaxyp > openms_percolatoradapter
diff PercolatorAdapter.xml @ 9:02796e3ddec1 draft default tip
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 5c080b1e2b99f1c88f4557e9fec8c45c9d23b906
| author | galaxyp |
|---|---|
| date | Fri, 14 Jun 2024 21:34:28 +0000 |
| parents | 016964c597f5 |
| children |
line wrap: on
line diff
--- a/PercolatorAdapter.xml Thu Dec 01 18:56:56 2022 +0000 +++ b/PercolatorAdapter.xml Fri Jun 14 21:34:28 2024 +0000 @@ -1,8 +1,7 @@ -<?xml version='1.0' encoding='UTF-8'?> <!--This is a configuration file for the integration of a tools into Galaxy (https://galaxyproject.org/). This file was automatically generated using CTDConverter.--> -<!--Proposed Tool Section: [ID Processing]--> +<!--Proposed Tool Section: [Identification Processing]--> <tool id="PercolatorAdapter" name="PercolatorAdapter" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05"> - <description>Facilitate input to Percolator and reintegrate.</description> + <description>Facilitate input to Percolator and reintegrate</description> <macros> <token name="@EXECUTABLE@">PercolatorAdapter</token> <import>macros.xml</import> @@ -18,23 +17,23 @@ mkdir in_cond.in && #if $in_cond.in_select == "no" mkdir ${' '.join(["'in_cond.in/%s'" % (i) for i, f in enumerate($in_cond.in) if f])} && - ${' '.join(["ln -s '%s' 'in_cond.in/%s/%s.%s' && " % (f, i, re.sub('[^\w\-_]', '_', f.element_identifier), $gxy2omsext(f.ext)) for i, f in enumerate($in_cond.in) if f])} + ${' '.join(["cp '%s' 'in_cond.in/%s/%s.%s' && " % (f, i, re.sub('[^\w\-_]', '_', f.element_identifier), $gxy2omsext(f.ext)) for i, f in enumerate($in_cond.in) if f])} #else - ln -s '$in_cond.in' 'in_cond.in/${re.sub("[^\w\-_]", "_", $in_cond.in.element_identifier)}.$gxy2omsext($in_cond.in.ext)' && + cp '$in_cond.in' 'in_cond.in/${re.sub("[^\w\-_]", "_", $in_cond.in.element_identifier)}.$gxy2omsext($in_cond.in.ext)' && #end if #end if #if $in_decoy_cond.in_decoy: mkdir in_decoy_cond.in_decoy && #if $in_decoy_cond.in_decoy_select == "no" mkdir ${' '.join(["'in_decoy_cond.in_decoy/%s'" % (i) for i, f in enumerate($in_decoy_cond.in_decoy) if f])} && - ${' '.join(["ln -s '%s' 'in_decoy_cond.in_decoy/%s/%s.%s' && " % (f, i, re.sub('[^\w\-_]', '_', f.element_identifier), $gxy2omsext(f.ext)) for i, f in enumerate($in_decoy_cond.in_decoy) if f])} + ${' '.join(["cp '%s' 'in_decoy_cond.in_decoy/%s/%s.%s' && " % (f, i, re.sub('[^\w\-_]', '_', f.element_identifier), $gxy2omsext(f.ext)) for i, f in enumerate($in_decoy_cond.in_decoy) if f])} #else - ln -s '$in_decoy_cond.in_decoy' 'in_decoy_cond.in_decoy/${re.sub("[^\w\-_]", "_", $in_decoy_cond.in_decoy.element_identifier)}.$gxy2omsext($in_decoy_cond.in_decoy.ext)' && + cp '$in_decoy_cond.in_decoy' 'in_decoy_cond.in_decoy/${re.sub("[^\w\-_]", "_", $in_decoy_cond.in_decoy.element_identifier)}.$gxy2omsext($in_decoy_cond.in_decoy.ext)' && #end if #end if #if $in_osw: mkdir in_osw && - ln -s '$in_osw' 'in_osw/${re.sub("[^\w\-_]", "_", $in_osw.element_identifier)}.$gxy2omsext($in_osw.ext)' && + cp '$in_osw' 'in_osw/${re.sub("[^\w\-_]", "_", $in_osw.element_identifier)}.$gxy2omsext($in_osw.ext)' && #end if mkdir out && #if "out_pin_FLAG" in str($OPTIONAL_OUTPUTS).split(',') @@ -55,15 +54,17 @@ #if "weights_FLAG" in str($OPTIONAL_OUTPUTS).split(',') mkdir weights && #end if +## advanced options #if $adv_opts.init_weights: mkdir adv_opts.init_weights && - ln -s '$adv_opts.init_weights' 'adv_opts.init_weights/${re.sub("[^\w\-_]", "_", $adv_opts.init_weights.element_identifier)}.$gxy2omsext($adv_opts.init_weights.ext)' && + cp '$adv_opts.init_weights' 'adv_opts.init_weights/${re.sub("[^\w\-_]", "_", $adv_opts.init_weights.element_identifier)}.$gxy2omsext($adv_opts.init_weights.ext)' && #end if #if $adv_opts.fasta: mkdir adv_opts.fasta && - ln -s '$adv_opts.fasta' 'adv_opts.fasta/${re.sub("[^\w\-_]", "_", $adv_opts.fasta.element_identifier)}.$gxy2omsext($adv_opts.fasta.ext)' && + cp '$adv_opts.fasta' 'adv_opts.fasta/${re.sub("[^\w\-_]", "_", $adv_opts.fasta.element_identifier)}.$gxy2omsext($adv_opts.fasta.ext)' && #end if + ## Main program call set -o pipefail && @@ -116,6 +117,7 @@ -weights 'weights/output.${gxy2omsext("tabular")}' #end if +## advanced options #if $adv_opts.init_weights: -init_weights 'adv_opts.init_weights/${re.sub("[^\w\-_]", "_", $adv_opts.init_weights.element_identifier)}.$gxy2omsext($adv_opts.init_weights.ext)' @@ -124,6 +126,7 @@ -fasta 'adv_opts.fasta/${re.sub("[^\w\-_]", "_", $adv_opts.fasta.element_identifier)}.$gxy2omsext($adv_opts.fasta.ext)' #end if + #if len(str($OPTIONAL_OUTPUTS).split(',')) == 0 | tee '$stdout' #end if @@ -165,7 +168,7 @@ <param argument="-in" type="data" format="idxml,mzid" multiple="true" optional="true" label="Input file(s)" help=" select idxml,mzid data sets(s)"/> </when> <when value="yes"> - <param argument="-in" type="data" format="idxml,mzid" multiple="false" optional="true" label="Input file(s)" help=" select idxml,mzid data sets(s)"/> + <param argument="-in" type="data" format="idxml,mzid" optional="true" label="Input file(s)" help=" select idxml,mzid data sets(s)"/> </when> </conditional> <conditional name="in_decoy_cond"> @@ -177,17 +180,18 @@ <param argument="-in_decoy" type="data" format="idxml,mzid" multiple="true" optional="true" label="Input decoy file(s) in case of separate searches" help=" select idxml,mzid data sets(s)"/> </when> <when value="yes"> - <param argument="-in_decoy" type="data" format="idxml,mzid" multiple="false" optional="true" label="Input decoy file(s) in case of separate searches" help=" select idxml,mzid data sets(s)"/> + <param argument="-in_decoy" type="data" format="idxml,mzid" optional="true" label="Input decoy file(s) in case of separate searches" help=" select idxml,mzid data sets(s)"/> </when> </conditional> <param argument="-in_osw" type="data" format="osw" optional="true" label="Input file in OSW format" help=" select osw data sets(s)"/> - <param argument="-out_type" display="radio" type="select" optional="false" label="Output file type -- default: determined from file extension or content" help=""> + <param argument="-out_type" type="select" label="Output file type -- default: determined from file extension or content" help=""> <option value="idXML">idxml</option> <option value="mzid">mzid</option> <option value="osw">osw</option> + <validator type="expression" message="A value needs to be selected">value != "select a value"</validator> <expand macro="list_string_san" name="out_type"/> </param> - <param argument="-enzyme" type="select" optional="true" label="Type of enzyme: no_enzyme,elastase,pepsin,proteinasek,thermolysin,chymotrypsin,lys-n,lys-c,arg-c,asp-n,glu-c,trypsin,trypsinp" help=""> + <param argument="-enzyme" type="select" label="Type of enzyme: no_enzyme,elastase,pepsin,proteinasek,thermolysin,chymotrypsin,lys-n,lys-c,arg-c,asp-n,glu-c,trypsin,trypsinp" help=""> <option value="no_enzyme">no_enzyme</option> <option value="elastase">elastase</option> <option value="pepsin">pepsin</option> @@ -205,13 +209,13 @@ </param> <param argument="-peptide_level_fdrs" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Calculate peptide-level FDRs instead of PSM-level FDRs" help=""/> <param argument="-protein_level_fdrs" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use the picked protein-level FDR to infer protein probabilities" help="Use the -fasta option and -decoy_pattern to set the Fasta file and decoy pattern"/> - <param argument="-osw_level" type="select" optional="true" label="OSW: the data level selected for scoring" help=""> + <param argument="-osw_level" type="select" label="OSW: the data level selected for scoring" help=""> <option value="ms1">ms1</option> <option value="ms2" selected="true">ms2</option> <option value="transition">transition</option> <expand macro="list_string_san" name="osw_level"/> </param> - <param argument="-score_type" type="select" optional="true" label="Type of the peptide main score" help=""> + <param argument="-score_type" type="select" label="Type of the peptide main score" help=""> <option value="q-value" selected="true">q-value</option> <option value="pep">pep</option> <option value="svm">svm</option> @@ -219,37 +223,37 @@ </param> <expand macro="adv_opts_macro"> <param argument="-generic_feature_set" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use only generic" help="(i.e. not search engine specific) features. Generating search engine specific features for common search engines by PSMFeatureExtractor will typically boost the identification rate significantly"/> - <param argument="-subset_max_train" type="integer" optional="true" value="0" label="Only train an SVM on a subset of <x> PSMs, and use the resulting score vector to evaluate the other PSMs" help="Recommended when analyzing huge numbers (>1 million) of PSMs. When set to 0, all PSMs are used for training as normal"/> - <param argument="-cpos" type="float" optional="true" value="0.0" label="Cpos, penalty for mistakes made on positive examples" help="Set by cross validation if not specified"/> - <param argument="-cneg" type="float" optional="true" value="0.0" label="Cneg, penalty for mistakes made on negative examples" help="Set by cross validation if not specified"/> - <param argument="-testFDR" type="float" optional="true" value="0.01" label="False discovery rate threshold for evaluating best cross validation result and the reported end result" help=""/> - <param argument="-trainFDR" type="float" optional="true" value="0.01" label="False discovery rate threshold to define positive examples in training" help="Set to testFDR if 0"/> - <param argument="-maxiter" type="integer" optional="true" value="10" label="Maximal number of iterations" help=""/> - <param argument="-nested_xval_bins" type="integer" optional="true" value="1" label="Number of nested cross-validation bins in the 3 splits" help=""/> + <param argument="-subset_max_train" type="integer" value="0" label="Only train an SVM on a subset of <x> PSMs, and use the resulting score vector to evaluate the other PSMs" help="Recommended when analyzing huge numbers (>1 million) of PSMs. When set to 0, all PSMs are used for training as normal"/> + <param argument="-cpos" type="float" value="0.0" label="Cpos, penalty for mistakes made on positive examples" help="Set by cross validation if not specified"/> + <param argument="-cneg" type="float" value="0.0" label="Cneg, penalty for mistakes made on negative examples" help="Set by cross validation if not specified"/> + <param argument="-testFDR" type="float" value="0.01" label="False discovery rate threshold for evaluating best cross validation result and the reported end result" help=""/> + <param argument="-trainFDR" type="float" value="0.01" label="False discovery rate threshold to define positive examples in training" help="Set to testFDR if 0"/> + <param argument="-maxiter" type="integer" value="10" label="Maximal number of iterations" help=""/> + <param argument="-nested_xval_bins" type="integer" value="1" label="Number of nested cross-validation bins in the 3 splits" help=""/> <param argument="-quick_validation" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Quicker execution by reduced internal cross-validation" help=""/> <param argument="-init_weights" type="data" format="tabular" optional="true" label="Read initial weights to the given file" help=" select tabular data sets(s)"/> <param argument="-static" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use static model (requires init-weights parameter to be set)" help=""/> <param argument="-default_direction" type="text" optional="true" value="" label="The most informative feature given as the feature name, can be negated to indicate that a lower value is bette" help=""> <expand macro="list_string_san" name="default_direction"/> </param> - <param argument="-verbose" type="integer" optional="true" value="2" label="Set verbosity of output: 0=no processing info, 5=all" help=""/> + <param argument="-verbose" type="integer" value="2" label="Set verbosity of output: 0=no processing info, 5=all" help=""/> <param argument="-unitnorm" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use unit normalization [0-1] instead of standard deviation normalization" help=""/> <param argument="-test_each_iteration" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Measure performance on test set each iteration" help=""/> <param argument="-override" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Override error check and do not fall back on default score vector in case of suspect score vecto" help=""/> - <param argument="-seed" type="integer" optional="true" value="1" label="Setting seed of the random number generato" help=""/> - <param argument="-doc" type="integer" optional="true" value="0" label="Include description of correct features" help=""/> + <param argument="-seed" type="integer" value="1" label="Setting seed of the random number generato" help=""/> + <param argument="-doc" type="integer" value="0" label="Include description of correct features" help=""/> <param argument="-klammer" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Retention time features calculated as in Klammer et al" help="Only available if -doc is set"/> <param argument="-fasta" type="data" format="fasta" optional="true" label="Provide the fasta file as the argument to this flag, which will be used for protein grouping based on an in-silico digest (only valid if option -protein_level_fdrs is active)" help=" select fasta data sets(s)"/> - <param argument="-decoy_pattern" type="text" optional="true" value="random" label="Define the text pattern to identify the decoy proteins and/or PSMs, set this up if the label that identifies the decoys in the database is not the default (Only valid if option -protein_level_fdrs is active)" help=""> + <param argument="-decoy_pattern" type="text" value="random" label="Define the text pattern to identify the decoy proteins and/or PSMs, set this up if the label that identifies the decoys in the database is not the default (Only valid if option -protein_level_fdrs is active)" help=""> <expand macro="list_string_san" name="decoy_pattern"/> </param> <param argument="-post_processing_tdc" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use target-decoy competition to assign q-values and PEPs" help=""/> <param argument="-train_best_positive" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Enforce that, for each spectrum, at most one PSM is included in the positive set during each training iteration" help="If the user only provides one PSM per spectrum, this filter will have no effect"/> - <param argument="-ipf_max_peakgroup_pep" type="float" optional="true" value="0.7" label="OSW/IPF: Assess transitions only for candidate peak groups until maximum posterior error probability" help=""/> - <param argument="-ipf_max_transition_isotope_overlap" type="float" optional="true" value="0.5" label="OSW/IPF: Maximum isotope overlap to consider transitions in IPF" help=""/> - <param argument="-ipf_min_transition_sn" type="float" optional="true" value="0.0" label="OSW/IPF: Minimum log signal-to-noise level to consider transitions in IPF" help="Set -1 to disable this filter"/> + <param argument="-ipf_max_peakgroup_pep" type="float" value="0.7" label="OSW/IPF: Assess transitions only for candidate peak groups until maximum posterior error probability" help=""/> + <param argument="-ipf_max_transition_isotope_overlap" type="float" value="0.5" label="OSW/IPF: Maximum isotope overlap to consider transitions in IPF" help=""/> + <param argument="-ipf_min_transition_sn" type="float" value="0.0" label="OSW/IPF: Minimum log signal-to-noise level to consider transitions in IPF" help="Set -1 to disable this filter"/> <param argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" help=""/> - <param argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help=""> + <param argument="-test" type="hidden" value="False" label="Enables the test mode (needed for internal use only)" help="" optional="true"> <expand macro="list_string_san" name="test"/> </param> </expand> @@ -292,7 +296,8 @@ <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter> </data> </outputs> - <tests><!-- TOPP_PercolatorAdapter_1 --> + <tests> + <!-- TOPP_PercolatorAdapter_1 --> <test expect_num_outputs="2"> <section name="adv_opts"> <param name="generic_feature_set" value="false"/> @@ -325,7 +330,7 @@ <conditional name="in_cond"> <param name="in" value="PercolatorAdapter_1.idXML"/> </conditional> - <output name="out" file="PercolatorAdapter_1_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> + <output name="out" value="PercolatorAdapter_1_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> <param name="out_type" value="idXML"/> <param name="enzyme" value="trypsin"/> <param name="peptide_level_fdrs" value="false"/> @@ -338,6 +343,9 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> <!-- TOPP_PercolatorAdapter_2 --> <test expect_num_outputs="2"> @@ -370,7 +378,7 @@ <param name="test" value="true"/> </section> <param name="in_osw" value="PercolatorAdapter_2.osw"/> - <output name="out" file="PercolatorAdapter_2_out1.osw" compare="sim_size" delta_frac="0.7" ftype="osw"/> + <output name="out" value="PercolatorAdapter_2_out1.osw" compare="sim_size" delta_frac="0.7" ftype="osw"/> <param name="out_type" value="osw"/> <param name="enzyme" value="trypsin"/> <param name="peptide_level_fdrs" value="false"/> @@ -383,6 +391,9 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> <!-- TOPP_PercolatorAdapter_3 --> <test expect_num_outputs="2"> @@ -415,7 +426,7 @@ <param name="test" value="true"/> </section> <param name="in_osw" value="PercolatorAdapter_2_out1.osw"/> - <output name="out" file="PercolatorAdapter_3_out1.osw" compare="sim_size" delta_frac="0.7" ftype="osw"/> + <output name="out" value="PercolatorAdapter_3_out1.osw" compare="sim_size" delta_frac="0.7" ftype="osw"/> <param name="out_type" value="osw"/> <param name="enzyme" value="trypsin"/> <param name="peptide_level_fdrs" value="false"/> @@ -428,6 +439,9 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> <!-- TOPP_PercolatorAdapter_4 --> <test expect_num_outputs="2"> @@ -460,7 +474,7 @@ <param name="test" value="true"/> </section> <param name="in_osw" value="PercolatorAdapter_3_out1.osw"/> - <output name="out" file="PercolatorAdapter_4_out1.osw" compare="sim_size" delta_frac="0.7" ftype="osw"/> + <output name="out" value="PercolatorAdapter_4_out1.osw" compare="sim_size" delta_frac="0.7" ftype="osw"/> <param name="out_type" value="osw"/> <param name="enzyme" value="trypsin"/> <param name="peptide_level_fdrs" value="false"/> @@ -473,6 +487,9 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> <!-- TOPP_PercolatorAdapter_5 --> <test expect_num_outputs="3"> @@ -507,8 +524,8 @@ <conditional name="in_cond"> <param name="in" value="PercolatorAdapter_1.idXML"/> </conditional> - <output name="out" file="PercolatorAdapter_1_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> - <output name="out_pin" file="PercolatorAdapter_1_out1.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/> + <output name="out" value="PercolatorAdapter_1_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> + <output name="out_pin" value="PercolatorAdapter_1_out1.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/> <param name="out_type" value="idXML"/> <param name="enzyme" value="trypsin"/> <param name="peptide_level_fdrs" value="false"/> @@ -521,11 +538,14 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> </tests> <help><![CDATA[Facilitate input to Percolator and reintegrate. -For more information, visit http://www.openms.de/doxygen/release/2.8.0/html/TOPP_PercolatorAdapter.html]]></help> +For more information, visit https://openms.de/doxygen/release/3.1.0/html/TOPP_PercolatorAdapter.html]]></help> <expand macro="references"/> </tool>