view skesa.xml @ 16:43e83ec28faa draft

Uploaded
author estrain
date Thu, 16 Aug 2018 14:28:43 -0400
parents 06d5e64a0586
children 53297c68021b
line wrap: on
line source

<tool id="skesa" name="skesa" version="0.1">
    <requirements>
      <requirement type="package" version="2.2">skesa</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
    #if $jobtype.select != "cl"
	skesa
      #if $jobtype.select == "srr"
        -sra_run $srrnum
      #else if $jobtype.select == "asm"
        --fasta $draft
      #else if $jobtype.select == "se"
        --fastq $fastq1
      #else if $jobtype.select == "pe"
	--fastq $fastq1,$fastq2 --use_paired_ends
      #else if $jobtype.select == "rp"
	--fastq $pairedf['forward'],$pairedf['reverse'] --use_paired_ends
      #end if
      #if $cores != 0
      --cores $cores
      #end if
      --memory $memory	> results.skesa.fasta
    #end if 

    ]]></command>
    <inputs>
      <conditional name="jobtype">
        <when value="srr">
         <param name="srrnum" type="text" label="Sra run number"/>
         </when>
        <param name="select" type="select" label="Assembly or FASTQ Reads?">
          <option value="sra">SRR  number</option>
          <option value="asm">Genome Assembly</option>
          <option value="se">Single-End Reads</option>
          <option value="pe">Paired-End Reads (Separate Files)</option>
          <option value="rp">Paired-End Reads (Paired Data Set)</option>
          <option value="cl">Collection of Reads</option>
        </param>
        <when value="asm">
          <param name="draft" type="data" format="fasta" label="FASTA" />
        </when>
        <when value="se">
          <param name="fastq1" type="data" format="fastq" label="FASTQ" />
        </when>
        <when value="pe">
          <param name="fastq1" type="data" format="fastq" label="FASTQ" />
          <param name="fastq2" type="data" format="fastq" label="FASTQ" />
        </when>
         <when value="cl">
              <param type="data_collection" name="collection_files" format="fastq" collection_type="list" label="FASTQS: Must be a Data Set list built from multiple fastq files" />
        </when>
         <when value="rp">
              <param type="data_collection" collection_type="paired" name="pairedf" format="fastq" label="FASTQS: Must be a paired set of forward and reverse fastq files" />
        </when>
      </conditional>
      <param name="memory" type="integer" label="Memory available (GB) [integer]" value="16" />
      <param name="cores" type="integer" label="Number of cores to use (default all) [integer]" value="0" />
      <param name="kmer" type="integer" label="Minimal kmer length for assembly [default 21] if non are specified " value="0" />
      <param name="min_count" type="integer" label="Minimal count for kmers retained for comparing alternate choices [integer]" value="0" />
    
    </inputs>
    <outputs>
            <data format="fasta" label="skesa Results" name="${input.name}.skesa.fasta" from_work_dir="*.fasta"/>
    </outputs>

    <help><![CDATA[
    
**Usage: skesa**

**INPUT**

A fasta assembly or single or paired end reads test or data set list of fastqs

**Memory available**

--memory arg (=32)         Memory available (GB) [integer]
     

**Number of cores**

--cores arg (=0)           Number of cores to use (default all) [integer]

https://github.com/ncbi/ngs-tools/tree/master/tools/skesa/

    ]]></help>
     <citations>
        <citation type="bibtex">
        @misc{pope_dashnow_zobel_holt_raven_schultz_inouye_tomita_2014,
        title={skesa: eSKESA is a de-novo sequence read assembler for cultured single isolate genomes
    based on DeBruijn graphs. It uses conservative heuristics and is designed to
    create breaks at repeat regions in the genome. This leads to excellent sequence
    quality but not necessarily a large N50 statistic. It is a multi-threaded
    application that scales well with the number of processors. For different runs
    with the same inputs, including the order of reads, the order and orientation
    of contigs in the output is deterministic. },
        url={https://github.com/ncbi/ngs-tools/tree/master/tools/skesa/},
        author={National Center for Biotechnology Information },
       }</citation>
    </citations>
</tool>