annotate DecoyDatabase.xml @ 11:622bb8ee4942 draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 020906fb54bde7fc143c356f41975c378a741315"

<?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: [Utilities]-->
<tool id="DecoyDatabase" name="DecoyDatabase" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@" profile="20.05">
  <description>Create decoy sequence database from forward sequence database.</description>
  <macros>
    <token name="@EXECUTABLE@">DecoyDatabase</token>
    <import>macros.xml</import>
    <import>macros_autotest.xml</import>
    <import>macros_test.xml</import>
  </macros>
  <expand macro="requirements"/>
  <expand macro="stdio"/>
  <command detect_errors="exit_code"><![CDATA[@QUOTE_FOO@
@EXT_FOO@
#import re

## Preprocessing
mkdir in &&
${ ' '.join(["ln -s '%s' 'in/%s.%s' &&" % (_, re.sub('[^\w\-_]', '_', _.element_identifier), $gxy2omsext(_.ext)) for _ in $in if _]) }
mkdir out &&

## 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
${' '.join(["'in/%s.%s'"%(re.sub('[^\w\-_]', '_', _.element_identifier), $gxy2omsext(_.ext)) for _ in $in if _])}
-out
'out/output.${gxy2omsext("fasta")}'

## Postprocessing
&& mv 'out/output.${gxy2omsext("fasta")}' '$out'
#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 name="in" argument="-in" type="data" format="fasta" multiple="true" optional="false" label="Input FASTA file(s), each containing a database" help="It is recommended to include a contaminant database as well select fasta data sets(s)"/>
    <param name="decoy_string" argument="-decoy_string" type="text" optional="true" value="DECOY_" label="String that is combined with the accession of the protein identifier to indicate a decoy protein" help="">
      <expand macro="list_string_san"/>
    </param>
    <param name="decoy_string_position" argument="-decoy_string_position" display="radio" type="select" optional="false" label="Should the 'decoy_string' be prepended (prefix) or appended (suffix) to the protein accession?" help="">
      <option value="prefix" selected="true">prefix</option>
      <option value="suffix">suffix</option>
      <expand macro="list_string_san"/>
    </param>
    <param name="only_decoy" argument="-only_decoy" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Write only decoy proteins to the output database instead of a combined database" help=""/>
    <param name="type" argument="-type" display="radio" type="select" optional="false" label="Type of sequence" help="RNA sequences may contain modification codes, which will be handled correctly if this is set to 'RNA'">
      <option value="protein" selected="true">protein</option>
      <option value="RNA">RNA</option>
      <expand macro="list_string_san"/>
    </param>
    <param name="method" argument="-method" display="radio" type="select" optional="false" label="Method by which decoy sequences are generated from target sequences" help="Note that all sequences are shuffled using the same random seed, ensuring that identical sequences produce the same shuffled decoy sequences. Shuffled sequences that produce highly similar output sequences are shuffled again (see shuffle_sequence_identity_threshold)">
      <option value="reverse" selected="true">reverse</option>
      <option value="shuffle">shuffle</option>
      <expand macro="list_string_san"/>
    </param>
    <param name="enzyme" argument="-enzyme" type="select" optional="false" label="Enzyme used for the digestion of the sample" help="Only applicable if parameter 'type' is 'protein'">
      <option value="Asp-N">Asp-N</option>
      <option value="Asp-N/B">Asp-N/B</option>
      <option value="Asp-N_ambic">Asp-N_ambic</option>
      <option value="glutamyl endopeptidase">glutamyl endopeptidase</option>
      <option value="Alpha-lytic protease">Alpha-lytic protease</option>
      <option value="Glu-C+P">Glu-C+P</option>
      <option value="PepsinA + P">PepsinA + P</option>
      <option value="cyanogen-bromide">cyanogen-bromide</option>
      <option value="Clostripain/P">Clostripain/P</option>
      <option value="elastase-trypsin-chymotrypsin">elastase-trypsin-chymotrypsin</option>
      <option value="Chymotrypsin">Chymotrypsin</option>
      <option value="Chymotrypsin/P">Chymotrypsin/P</option>
      <option value="CNBr">CNBr</option>
      <option value="Formic_acid">Formic_acid</option>
      <option value="Lys-C">Lys-C</option>
      <option value="Lys-N">Lys-N</option>
      <option value="Lys-C/P">Lys-C/P</option>
      <option value="PepsinA">PepsinA</option>
      <option value="TrypChymo">TrypChymo</option>
      <option value="Trypsin/P">Trypsin/P</option>
      <option value="V8-DE">V8-DE</option>
      <option value="V8-E">V8-E</option>
      <option value="leukocyte elastase">leukocyte elastase</option>
      <option value="proline endopeptidase">proline endopeptidase</option>
      <option value="no cleavage">no cleavage</option>
      <option value="unspecific cleavage">unspecific cleavage</option>
      <option value="Arg-C">Arg-C</option>
      <option value="Arg-C/P">Arg-C/P</option>
      <option value="2-iodobenzoate">2-iodobenzoate</option>
      <option value="iodosobenzoate">iodosobenzoate</option>
      <option value="staphylococcal protease/D">staphylococcal protease/D</option>
      <option value="proline-endopeptidase/HKR">proline-endopeptidase/HKR</option>
      <option value="Trypsin" selected="true">Trypsin</option>
      <expand macro="list_string_san"/>
    </param>
    <section name="Decoy" title="Decoy parameters section" help="" expanded="false">
      <param name="non_shuffle_pattern" argument="-Decoy:non_shuffle_pattern" type="text" optional="true" value="" label="Residues to not shuffle (keep at a constant position when shuffling)" help="Separate by comma, e.g. use 'K,P,R' here">
        <expand macro="list_string_san"/>
      </param>
      <param name="keepPeptideNTerm" argument="-Decoy:keepPeptideNTerm" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Whether to keep peptide N terminus constant when shuffling / reversing" help=""/>
      <param name="keepPeptideCTerm" argument="-Decoy:keepPeptideCTerm" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Whether to keep peptide C terminus constant when shuffling / reversing" help=""/>
    </section>
    <expand macro="adv_opts_macro">
      <param name="shuffle_max_attempts" argument="-shuffle_max_attempts" type="integer" optional="true" value="30" label="shuffle: maximum attempts to lower the amino acid sequence identity between target and decoy for the shuffle algorithm" help=""/>
      <param name="shuffle_sequence_identity_threshold" argument="-shuffle_sequence_identity_threshold" type="float" optional="true" value="0.5" label="shuffle: target-decoy amino acid sequence identity threshold for the shuffle algorithm" help="If the sequence identity is above this threshold, shuffling is repeated. In case of repeated failure, individual amino acids are 'mutated' to produce a different amino acid sequence"/>
      <param name="seed" argument="-seed" type="text" optional="true" value="1" label="Random number seed (use 'time' for system time)" help="">
        <expand macro="list_string_san"/>
      </param>
      <param name="force" argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overwrite tool specific checks" help=""/>
      <param name="test" argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help="">
        <expand macro="list_string_san"/>
      </param>
    </expand>
    <param name="OPTIONAL_OUTPUTS" type="select" multiple="true" label="Optional outputs" optional="true">
      <option value="ctd_out_FLAG">Output used ctd (ini) configuration file</option>
    </param>
  </inputs>
  <outputs>
    <data name="out" label="${tool.name} on ${on_string}: out" format="fasta"/>
    <data name="ctd_out" format="xml" label="${tool.name} on ${on_string}: ctd">
      <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter>
    </data>
  </outputs>
  <tests>
    <expand macro="autotest_DecoyDatabase"/>
    <expand macro="manutest_DecoyDatabase"/>
  </tests>
  <help><![CDATA[Create decoy sequence database from forward sequence database.


For more information, visit http://www.openms.de/documentation/UTILS_DecoyDatabase.html]]></help>
  <expand macro="references"/>
</tool>