annotate GNPSExport.xml @ 5:87a970d1514b draft default tip

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 5c080b1e2b99f1c88f4557e9fec8c45c9d23b906

<!--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: [File Converter]-->
<tool id="GNPSExport" name="GNPSExport" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
  <description>Tool to export representative consensus MS/MS scan per consensusElement into a .MGF file format</description>
  <macros>
    <token name="@EXECUTABLE@">GNPSExport</token>
    <import>macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <expand macro="stdio"/>
  <command detect_errors="exit_code"><![CDATA[@QUOTE_FOO@
@EXT_FOO@
#import re

## Preprocessing
mkdir in_cm &&
cp '$in_cm' 'in_cm/${re.sub("[^\w\-_]", "_", $in_cm.element_identifier)}.$gxy2omsext($in_cm.ext)' &&
mkdir in_mzml_cond.in_mzml &&
#if $in_mzml_cond.in_mzml_select == "no"
mkdir ${' '.join(["'in_mzml_cond.in_mzml/%s'" % (i) for i, f in enumerate($in_mzml_cond.in_mzml) if f])} && 
${' '.join(["cp '%s' 'in_mzml_cond.in_mzml/%s/%s.%s' && " % (f, i, re.sub('[^\w\-_]', '_', f.element_identifier), $gxy2omsext(f.ext)) for i, f in enumerate($in_mzml_cond.in_mzml) if f])}
#else
cp '$in_mzml_cond.in_mzml' 'in_mzml_cond.in_mzml/${re.sub("[^\w\-_]", "_", $in_mzml_cond.in_mzml.element_identifier)}.$gxy2omsext($in_mzml_cond.in_mzml.ext)' &&
#end if
mkdir out &&
mkdir out_quantification &&
#if "out_pairs_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  mkdir out_pairs &&
#end if
#if "out_meta_values_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  mkdir out_meta_values &&
#end if

## Main program call

set -o pipefail &&
@EXECUTABLE@ -write_ctd ./ &&
python3 '$__tool_directory__/fill_ctd.py' '@EXECUTABLE@.ctd' '$args_json' '$hardcoded_json' &&
@EXECUTABLE@ -ini @EXECUTABLE@.ctd
-in_cm
'in_cm/${re.sub("[^\w\-_]", "_", $in_cm.element_identifier)}.$gxy2omsext($in_cm.ext)'
-in_mzml
#if $in_mzml_cond.in_mzml_select == "no"
${' '.join(["'in_mzml_cond.in_mzml/%s/%s.%s'"%(i, re.sub('[^\w\-_]', '_', f.element_identifier), $gxy2omsext(f.ext)) for i, f in enumerate($in_mzml_cond.in_mzml) if f])}
#else
'in_mzml_cond.in_mzml/${re.sub("[^\w\-_]", "_", $in_mzml_cond.in_mzml.element_identifier)}.$gxy2omsext($in_mzml_cond.in_mzml.ext)'
#end if
-out
'out/output.${gxy2omsext("mgf")}'
-out_quantification
'out_quantification/output.${gxy2omsext("txt")}'
#if "out_pairs_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  -out_pairs
  'out_pairs/output.${gxy2omsext("csv")}'
#end if
#if "out_meta_values_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  -out_meta_values
  'out_meta_values/output.${gxy2omsext("tabular")}'
#end if
#if len(str($OPTIONAL_OUTPUTS).split(',')) == 0
  | tee '$stdout'
#end if

## Postprocessing
&& mv 'out/output.${gxy2omsext("mgf")}' '$out'
&& mv 'out_quantification/output.${gxy2omsext("txt")}' '$out_quantification'
#if "out_pairs_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  && mv 'out_pairs/output.${gxy2omsext("csv")}' '$out_pairs'
#end if
#if "out_meta_values_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
  && mv 'out_meta_values/output.${gxy2omsext("tabular")}' '$out_meta_values'
#end if
#if "ctd_out_FLAG" in $OPTIONAL_OUTPUTS
  && mv '@EXECUTABLE@.ctd' '$ctd_out'
#end if]]></command>
  <configfiles>
    <inputs name="args_json" data_style="paths"/>
    <configfile name="hardcoded_json"><![CDATA[{"log": "log.txt", "threads": "\${GALAXY_SLOTS:-1}", "no_progress": true}]]></configfile>
  </configfiles>
  <inputs>
    <param argument="-in_cm" type="data" format="consensusxml" label="Input consensusXML file containing only consensusElements with &quot;peptide&quot; annotations" help=" select consensusxml data sets(s)"/>
    <conditional name="in_mzml_cond">
      <param name="in_mzml_select" type="select" label="Run tool in batch mode for -in_mzml">
        <option value="no">No: process all datasets jointly</option>
        <option value="yes">Yes: process each dataset in an independent job</option>
      </param>
      <when value="no">
        <param argument="-in_mzml" type="data" format="mzml" multiple="true" label="Original mzml files containing the ms2 spectra (aka peptide annotation)" help="Must be in order that the consensusXML file maps the original mzML files select mzml data sets(s)"/>
      </when>
      <when value="yes">
        <param argument="-in_mzml" type="data" format="mzml" label="Original mzml files containing the ms2 spectra (aka peptide annotation)" help="Must be in order that the consensusXML file maps the original mzML files select mzml data sets(s)"/>
      </when>
    </conditional>
    <param argument="-output_type" type="select" label="specificity of mgf output information" help="">
      <option value="merged_spectra">merged_spectra</option>
      <option value="most_intense" selected="true">most_intense</option>
      <expand macro="list_string_san" name="output_type"/>
    </param>
    <param argument="-peptide_cutoff" type="integer" min="-1" value="5" label="Number of most intense peptides to consider per consensus element; '-1' to consider all identifications" help=""/>
    <param argument="-ms2_bin_size" type="float" min="0.0" value="0.019999999552965" label="Bin size (Da) for fragment ions when merging ms2 scans" help=""/>
    <section name="merged_spectra" title="Options for exporting mgf file with merged spectra per consensusElement" help="" expanded="false">
      <param name="cos_similarity" argument="-merged_spectra:cos_similarity" type="float" min="0.0" value="0.9" label="Cosine similarity threshold for merged_spectra output" help=""/>
    </section>
    <expand macro="adv_opts_macro">
      <param argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" 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>
    <param name="OPTIONAL_OUTPUTS" type="select" optional="true" multiple="true" label="Optional outputs">
      <option value="out_pairs_FLAG">out_pairs (Output supplementary pairs table for IIMN)</option>
      <option value="out_meta_values_FLAG">out_meta_values (Output meta value file)</option>
      <option value="ctd_out_FLAG">Output used ctd (ini) configuration file</option>
    </param>
  </inputs>
  <outputs>
    <data name="out" label="${tool.name} on ${on_string}: out" format="mgf"/>
    <data name="out_quantification" label="${tool.name} on ${on_string}: out_quantification" format="txt"/>
    <data name="out_pairs" label="${tool.name} on ${on_string}: out_pairs" format="csv">
      <filter>OPTIONAL_OUTPUTS is not None and "out_pairs_FLAG" in OPTIONAL_OUTPUTS</filter>
    </data>
    <data name="out_meta_values" label="${tool.name} on ${on_string}: out_meta_values" format="tabular">
      <filter>OPTIONAL_OUTPUTS is not None and "out_meta_values_FLAG" in OPTIONAL_OUTPUTS</filter>
    </data>
    <data name="ctd_out" format="xml" label="${tool.name} on ${on_string}: ctd">
      <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter>
    </data>
  </outputs>
  <tests>
    <!-- TOPP_GNPSExport_1 -->
    <test expect_num_outputs="3">
      <section name="adv_opts">
        <param name="force" value="false"/>
        <param name="test" value="true"/>
      </section>
      <param name="in_cm" value="GNPSExport_cons1.consensusXML"/>
      <conditional name="in_mzml_cond">
        <param name="in_mzml" value="GNPSExport_mzml1.mzML,GNPSExport_mzml2.mzML"/>
      </conditional>
      <output name="out" value="GNPSExport_1_out.mgf" compare="sim_size" delta_frac="0.7" ftype="mgf"/>
      <output name="out_quantification" value="GNPSExport_1_out_quant.txt" compare="sim_size" delta_frac="0.7" ftype="txt"/>
      <param name="output_type" value="most_intense"/>
      <param name="peptide_cutoff" value="10"/>
      <param name="ms2_bin_size" value="2.0"/>
      <section name="merged_spectra">
        <param name="cos_similarity" value="0.85"/>
      </section>
      <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG"/>
      <output name="ctd_out" ftype="xml">
        <assert_contents>
          <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_GNPSExport_2 -->
    <test expect_num_outputs="3">
      <section name="adv_opts">
        <param name="force" value="false"/>
        <param name="test" value="true"/>
      </section>
      <param name="in_cm" value="GNPSExport_cons1.consensusXML"/>
      <conditional name="in_mzml_cond">
        <param name="in_mzml" value="GNPSExport_mzml1.mzML,GNPSExport_mzml2.mzML"/>
      </conditional>
      <output name="out" value="GNPSExport_2_out.mgf" compare="sim_size" delta_frac="0.7" ftype="mgf"/>
      <output name="out_quantification" value="GNPSExport_2_out_quant.tmp" compare="sim_size" delta_frac="0.7" ftype="txt"/>
      <param name="output_type" value="merged_spectra"/>
      <param name="peptide_cutoff" value="10"/>
      <param name="ms2_bin_size" value="2.0"/>
      <section name="merged_spectra">
        <param name="cos_similarity" value="0.85"/>
      </section>
      <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG"/>
      <output name="ctd_out" ftype="xml">
        <assert_contents>
          <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_GNPSExport_3 -->
    <test expect_num_outputs="3">
      <section name="adv_opts">
        <param name="force" value="false"/>
        <param name="test" value="true"/>
      </section>
      <param name="in_cm" value="GNPSExport_cons1.consensusXML"/>
      <conditional name="in_mzml_cond">
        <param name="in_mzml" value="GNPSExport_mzml1.mzML,GNPSExport_mzml2.mzML"/>
      </conditional>
      <output name="out" value="GNPSExport_3_out.mgf" compare="sim_size" delta_frac="0.7" ftype="mgf"/>
      <output name="out_quantification" value="GNPSExport_3_out_quant.tmp" compare="sim_size" delta_frac="0.7" ftype="txt"/>
      <param name="output_type" value="most_intense"/>
      <param name="peptide_cutoff" value="10"/>
      <param name="ms2_bin_size" value="0.02"/>
      <section name="merged_spectra">
        <param name="cos_similarity" value="0.85"/>
      </section>
      <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG"/>
      <output name="ctd_out" ftype="xml">
        <assert_contents>
          <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_GNPSExport_4 -->
    <test expect_num_outputs="5">
      <section name="adv_opts">
        <param name="force" value="false"/>
        <param name="test" value="true"/>
      </section>
      <param name="in_cm" value="GNPSExport_cons2.consensusXML"/>
      <conditional name="in_mzml_cond">
        <param name="in_mzml" value="GNPSExport_mzml1.mzML,GNPSExport_mzml2.mzML"/>
      </conditional>
      <output name="out" value="GNPSExport_4_out.tmp" compare="sim_size" delta_frac="0.7" ftype="mgf"/>
      <output name="out_quantification" value="GNPSExport_4_out_quant.txt" compare="sim_size" delta_frac="0.7" ftype="txt"/>
      <output name="out_pairs" value="GNPSExport_4_out_pairs.csv" compare="sim_size" delta_frac="0.7" ftype="csv"/>
      <output name="out_meta_values" value="GNPSExport_4_out_meta_values.tsv" compare="sim_size" delta_frac="0.7" ftype="tabular"/>
      <param name="output_type" value="most_intense"/>
      <param name="peptide_cutoff" value="5"/>
      <param name="ms2_bin_size" value="0.019999999552965"/>
      <section name="merged_spectra">
        <param name="cos_similarity" value="0.9"/>
      </section>
      <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,out_pairs_FLAG,out_meta_values_FLAG"/>
      <output name="ctd_out" ftype="xml">
        <assert_contents>
          <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[Tool to export representative consensus MS/MS scan per consensusElement into a .MGF file format.
See the documentation on https://ccms-ucsd.github.io/GNPSDocumentation/featurebasedmolecularnetworking-with-openms


For more information, visit https://openms.de/doxygen/release/3.1.0/html/TOPP_GNPSExport.html]]></help>
  <expand macro="references"/>
</tool>