view picard_NormalizeFasta.xml @ 5:3d4f1fa26f0e draft

Uploaded
author devteam
date Tue, 16 Dec 2014 19:03:21 -0500
parents
children 3a3234d7a2e8
line wrap: on
line source

<tool name="NormalizeFasta" id="picard_NormalizeFasta" version="1.126.0">
  <description>normalize fasta datasets</description>
  <requirements>
    <requirement type="package" version="1.126.0">picard</requirement>
  </requirements>
  
  <macros>
    <import>picard_macros.xml</import>
  </macros>
  
  <command>
    @java_options@
    
  
    ## Two lines below are due to the fact that picard likes fasta files to have extension .fa  
    #set $fasta_file="local_fasta.fa"
    ln -s "${inputFile}" "${fasta_file}" &amp;&amp;    
    
    java -jar \$JAVA_JAR_PATH/picard.jar
    NormalizeFasta
    
    INPUT="${fasta_file}"
    OUTPUT="${outFile}"
    LINE_LENGTH="${line_length}"
    TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE="${truncate_sequence_names_at_whitespaces}"
    
    QUIET=true
    VERBOSITY=ERROR
  
  </command>
  <inputs>
    <param format="fasta" name="inputFile" type="data" label="FASTA dataset or dataset collection" help="If empty, upload or import a FASTA dataset" />
    <param name="line_length" type="integer" value="100" min="1" max="200" label="The line length to be used for the output fasta file" help="LINE_LENGTH; default=100"/>
    <param name="truncate_sequence_names_at_whitespaces" type="boolean" label="Truncate sequence names at first whitespace" help="TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE; default=False"/>
  </inputs> 
  
  <outputs>
    <data format="fasta" name="outFile" label="${tool.name} on ${on_string}: Normalized FASTA dataset"/>
  </outputs>
  
  <tests>
    <test>
      <param name="inputFile" value="picard_NormalizeFasta_ref.fa" ftype="fasta"/>
      <param name="line_length" value="40"/>
      <param name="truncate_sequence_names_at_whitespaces" value="False"/>
      <output name="outFile" file="picard_NormalizeFasta_test1.fa" ftype="fasta"/>
    </test>
  </tests>
  
  <stdio>
    <exit_code range="1:"  level="fatal"/>
  </stdio>
  
  <help>

**Purpose**

Takes any dataset that conforms to the fasta format and normalizes it so that all lines of sequence except the last line per named sequence are of the same length.

@dataset_collections@

@description@

  LINE_LENGTH=Integer           The line length to be used for the output fasta file.  Default value: 100. 
  
  TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE=Boolean
                                Truncate sequence names at first whitespace.  Default value: false. Possible values: {true, false} 

@more_info@

  </help>
</tool>