comparison tools/spades_2_5/spades.xml @ 1:0f8b2da62d7d draft

Support for SPAdes 2.5.0. Added a tab-separated output with coverage vs. length info for each contig.

1:0f8b2da62d7d

<tool id="spades" name="spades" version="0.4">
  <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
    ## TODO: kmers, threads, other options (-sc for single-cell)
    #if $sc == "true":
      --sc 
    #end if
    #if $careful == "true":
      --careful 
    #end if
    #if $rectangle == "true" 
      --rectangle 
    #end if 
    -t $threads 
    -k $kmers 
    -i $iterations 
    ##--phred-offset
    ## Sequence files
    #for $i, $s in enumerate( $reads )
      #if $s.read_type.type == "pairedend"
      -1 $s.read_type.fwd_reads
      -2 $s.read_type.rev_reads
      #elif $s.read_type.type == "interleaved"
      --12 $s.read_type.interleaved_reads
      #elif $s.read_type.type == "unpaired"
      -s $s.read_type.unpaired_reads
      #end if
    #end for
  </command>
  <inputs>
    <param name="sc" type="select" label="Single-cell?" help="This flag is required for MDA (single-cell) data.">
      <option value="false">No</option>
      <option value="true">Yes</option>
    </param>
    <param name="careful" type="select" 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).">
      <option value="false">No</option>
      <option value="true" selected="true">Yes</option>
    </param>
    <param name="rectangle" type="select" label="Use rectangle correction for repeat resolution?" help="Uses rectangle graph algorithm for repeat resolution stage instead of usual SPAdes repeat resolution module (experimental).">
      <option value="false" selected="true">No</option>
      <option value="true">Yes</option>
    </param>
    <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 and listed in ascending order). The default value is 21,33,55." >
    </param>
    <!-- Reads -->
    <repeat name="reads" title="Reads">
      <conditional name="read_type">
	<param name="type" type="select" label="Select type of reads">
	  <option value="pairedend">Paired-end, separate inputs</option>
	  <option value="interleaved">Paired-end, interleaved</option>
	  <option value="unpaired">Unpaired reads</option>
	</param>
	<when value="pairedend">
	  <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>
  </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>
      <!-- Based on the tests coming along with SPAdes -->
      <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>