view tools/spades_2_5/spades.xml @ 2:b5ce24f34dd7 draft

Uploaded
author lionelguy
date Thu, 05 Sep 2013 07:43:48 -0400
parents 0f8b2da62d7d
children d82f18c76309
line wrap: on
line source

<tool id="spades" name="spades" version="0.5">
  <description>SPAdes genome assembler for regular and single-cell projects</description>
  <requirements>
    <requirement type="package" version="2.5.0">spades</requirement>
  </requirements>
  <command interpreter="perl">spades.pl 
     $out_contigs 
     $out_contig_stats 
     $out_scaffolds 
     $out_scaffold_stats 
     $out_log 
    ## A real command looks like: spades.py -k 21,33,55,77,99,127 --careful -1 Y.fastq.gz -2 X.fastq.gz -t 24 -o output
    spades.py
    $sc
    $onlyassembler
    $careful
    $rectangle
    -t $threads 
    -k $kmers 
    -i $iterations 
    ##--phred-offset
    ## Sequence files
    #for $i, $library in enumerate( $libraries )
      #set num=$i+1
      #if str( $library.lib_type ) == "paired_end":
        #set prefix = 'pe'
      #else:
        #set prefix = 'mp'
      #end if
      --$prefix$num-$library.orientation    
      #for $file in $library.files
	#if $file.file_type.type == "separate"
          --$prefix$num-1 $file.file_type.fwd_reads
          --$prefix$num-2 $file.file_type.rev_reads
        #elif $file.file_type.type == "interleaved"
          --$prefix$num-12 $file.file_type.interleaved_reads
        #elif $file.file_type.type == "unpaired"
          --$prefix$num-s $file.file_type.unpaired_reads
        #end if
      #end for
    #end for
  </command>
  <inputs>
    <param name="sc" type="boolean" truevalue="--sc" falsevalue="" label="Single-cell?" help="This option is required for MDA (single-cell) data.">
      <option value="false">No</option>
      <option value="true">Yes</option>
    </param>
    <param name="onlyassembler" type="boolean" truevalue="--only-assembler" falsevalue="" checked="False" label="Run only assembly? (without read error correction)" />
    <param name="careful" type="boolean" truevalue="--careful" falsevalue="" checked="True" label="Careful correction?" help="Tries to reduce number of mismatches and short indels. Also runs MismatchCorrector – a post processing tool, which uses BWA tool (comes with SPAdes)." />
    <param name="rectangle" type="boolean" truevalue="--rectangle" falsevalue="" checked="False" label="Use rectangle correction for repeat resolution?" help="Uses rectangle graph algorithm for repeat resolution stage instead of usual SPAdes repeat resolution module (experimental, use at your own risks)." />
    <param name="threads" type="integer" label="Number of threads to use" value="16">
    </param>
    <param name="iterations" type="integer" label="Number of iterations for read error correction." value="1">
    </param>    
    <param name="kmers" type="text" label="K-mers to use, separated by commas" value="21,33,55" help="Comma-separated list of k-mer sizes to be used (all values must be odd, less than 128, listed in ascending order, and smaller than the read length). The default value is 21,33,55." >
    </param>
    <!-- Reads -->
    <repeat name="libraries" title="Libraries">
      <param name="lib_type" type="select" label="Library type">
	<option value="paired_end">Paired end / Single reads</option>
	<option value="mate_paired">Mate pairs</option>
      </param>
      <param name="orientation" type="select" label="Orientation">
	<option value="fr" selected="true">-> &lt;- (fr)</option>
	<option value="rf">&lt;- -> (rf)</option>
	<option value="ff">-> -> (ff)</option>
      </param>
      <repeat name="files" title="Files">
	<conditional name="file_type">
	  <param name="type" type="select" label="Select file format">
	    <option value="separate">Separate input files</option>
	    <option value="interleaved">Interleaved files</option>
	    <option value="unpaired">Unpaired/Single reads</option>
	  </param>
	  <when value="separate">
	    <param name="fwd_reads" type="data" format="fastq" label="Forward reads" help="FASTQ format" />
	    <param name="rev_reads" type="data" format="fastq" label="Reverse reads" help="FASTQ format" />
	  </when>
	  <when value="interleaved">
	    <param name="interleaved_reads" type="data" format="fastq" label="Interleaved paired reads" help="FASTQ format" />
	  </when>
	  <when value="unpaired">
	    <param name="unpaired_reads" type="data" format="fastq" label="Unpaired reads" help="FASTQ format" />
	  </when>
	</conditional>
      </repeat>
    </repeat>
  </inputs>
  <outputs>
    <data name="out_contigs" format="fasta" label="SPAdes contigs (fasta)" />
    <data name="out_contig_stats" format="tabular" label="SPAdes contig stats" />
    <data name="out_scaffolds" format="fasta" label="SPAdes scaffolds (fasta)" />
    <data name="out_scaffold_stats" format="tabular" label="SPAdes scaffold stats" />
    <data name="out_log" format="txt" label="SPAdes log" />
  </outputs>
  <!--  <tests>
    <test>
      
      <param name="sc" value="false" />
      <param name="careful" value="false" />
      <param name="rectangle" value="false" />
      <param name="threads" value="16" />
      <param name="kmers" value="33,55" />
      <param name="type" value="pairedend" />
      <param name="fwd_reads" value="ecoli_1K_1.fq" ftype="fastq" />
      <param name="rev_reads" value="ecoli_1K_2.fq" ftype="fastq" />
      <output name="out_contigs" file="reference_1K.fa" ftype="fasta" compare="re_match" lines_diff="1" />
    </test>
  </tests> -->
  <help>
**What it does**

Runs SPAdes 2.5.0, collects the output, and throws away all the temporary files. It also produces a tab file with contig names, length and coverage.

**Citation**

Anton Bankevich, Sergey Nurk, Dmitry Antipov, Alexey A. Gurevich, Mikhail Dvorkin, Alexander S. Kulikov, Valery M. Lesin, Sergey I. Nikolenko, Son Pham, Andrey D. Prjibelski, Alexey V. Pyshkin, Alexander V. Sirotkin, Nikolay Vyahhi, Glenn Tesler, Max A. Alekseyev, and Pavel A. Pevzner. Journal of Computational Biology. May 2012, 19(5): 455-477. doi:10.1089/cmb.2012.0021. 
    
  </help>
</tool>