view circlator.xml @ 2:c27229938e09 draft default tip

planemo upload

<tool id="circlator" name="A tool to circularize genome assemblies" version="0.1.0">
  <description>
     This task runs the complete Circlator pipeline. It runs the tasks: progcheck, mapreads, bam2reads, assemble, merge, clean, fixstart.
  </description>
  <requirements>
    <requirement type="package" version="1.5.5=py_2">circlator</requirement>
    <requirement type="package" version="3.23">mummer</requirement>
    <requirement type="package" version="1.6">canu</requirement>
  </requirements>
  <command detect_errors="exit_code"><![CDATA[
    circlator all 
    --threads \${GALAXY_SLOTS:-4}
    #if str($assembly.canu_or_spades.assembler) == "spades"
      --assembler spades
      ${assembly.canu_or_spades.not_careful}
      ${assembly.canu_or_spades.not_only_assembler}
    #else if str($assembly.canu_or_spades.assembler) == "canu"
      --assembler canu 
      --data_type ${assembly.canu_or_spades.datatype}
    #end if
    ${assembly.split_all_reads}
    ${assembly.assemble_spades_use_first}
    #if str($mapreads.bwa_opts) != ""
      --bwa_opts "$mapreads.bwa_opts"
    #end if
    ${bam2read.b2r_discard}
    #if str($bam2read.b2r_length_cutoff) != ""
      --b2r_length_cutoff ${bam2read.b2r_length_cutoff}
    #end if
    #if str($bam2read.b2r_min_read_length) != ""
      --b2r_min_read_length ${bam2read.b2r_min_read_length}
    #end if
    #if str($fix.fixstart_mincluster) != ""
      --fixstart_mincluster $fix.fixstart_mincluster
    #end if
    #if str($fix.fixstart_min_id) != ""
      --fixstart_min_id $fix.fixstart_min_id
    #end if
    $file_contigs $file_reads outdir
    ]]></command>
  <environment_variables>
    <environment_variable name="LC_ALL">C</environment_variable>
  </environment_variables>
  <inputs>
    <param type="data" name="file_reads" label="Reads to be mapped to contig, in any format BWA MEM accepts" format="fastqsanger,fastqsanger.gz,fasta, fasta.gz" />
    <param type="data" name="file_contigs" label="Assembly (contigs)" format="fasta" />

    <section name="assembly" title="Assembly">
      <conditional name="canu_or_spades">
        <param name="assembler" type="select" label="Assembler to use for reassemblies" >
          <option value="spades" selected="true">SPAdes</option>
          <option value="canu">Canu</option>
        </param>
        <when value="canu">
          <param name="datatype" type="select" label="one of the 4 types of data analysed" >
            <option value="pacbio-corrected" selected="true">pacbio corrected</option>
            <option value="pacbio-raw">pacbio raw</option>
            <option value="nanopore-corrected">nanopore corrected</option>
            <option value="nanopore-raw">nanopore raw</option>
          </param>
        </when>
        <when value="spades">
          <param name="not_careful" argument="--assemble_not_careful" type="boolean" truevalue="--assemble_not_careful" falsevalue="" checked="false" 
            label="Do not use the --careful option with SPAdes" help="note that this circlator option is to NOT use an option from SPAdes; if unsure, leave it unchekced" />
          <param name="not_only_assembler" argument="--assemble_not_only_assembler" truevalue="--assemble_not_only_assembler" falsevalue=""
            type="boolean" checked="false" label="Do not use the --assemble-only option with SPAdes. Important: with this option, the input reads must 
            be in FASTQ format, otherwise SPAdes will crash because it needs quality scores to correct the reads." 
            help="note that this circlator option is to NOT use an option from SPAdes; if unsure, leave it unchecked"/>
        </when>
      </conditional>
      <param name="split_all_reads" argument="--split_all_reads" type="boolean" truevalue="--split_all_reads" falsevalue="" checked="false" 
        label="By default, reads mapped to shorter contigs are left unchanged. This option splits them into two, broken at the middle of the 
        contig to try to force circularization. May help if the assembler does not detect circular contigs (eg canu)" />
      <param name="assemble_spades_use_first" argument="--assemble_spades_use_first" truevalue="--assemble_spades_use_first" falsevalue=""
        checked="false" type="boolean" label="Use the first successful SPAdes assembly. Default is to try all kmers and use the assembly with 
        the largest N50" />

    </section>
    <section name="mapreads" title="mapreads options">
      <param name="bwa_opts" type="text" label="text with BWA options (exactly as used by BWA MEM)"/>
    </section>

    <section name="bam2read" title="bam2reads options">
      <param name="b2r_discard" argument="--b2r_discard_unmapped" truevalue="--b2r_discard_unmapped" falsevalue="" checked="false" type="boolean"
        label="Check this to not keep unmapped reads" />
      <param name="b2r_length_cutoff" type="integer" label="All reads mapped to contigs shorter than this will be kept (default=100000)" optional="true"/>
      <param name="b2r_min_read_length" type="integer" label="Minimum length of read to output (defaul=250)" optional="true"/>
    </section>

    <section name="fix" title="fixstart options">
      <param name="fixstart_mincluster" type="integer" label="The -c|mincluster option of promer. Overrides promer's default value" optional="true"/>
      <param name="fixstart_min_id" type="float" label="Minimum percent identity of promer match between contigs and gene(s) to use as start point (dafault=70)" optional="true"/>
    </section>

  </inputs>
  <outputs>
    <data name="output_fasta" label="Output file of rearranged contigs" format="fasta" from_work_dir="outdir/06.fixstart.fasta" />
    <data name="output_log" label="Log information" format="tabular" from_work_dir="outdir/06.fixstart.log" />
  </outputs>
  <tests>
    <test>
      <param name="file_contigs" value="test_contigs.fa"/>
      <param name="file_reads" value="test_reads.fq.gz"/>
      <output name="output_log" file="06.fixstart.log"/>
    </test>
  </tests>
  <help><![CDATA[
    The input is a genome assembly in FASTA format and corrected PacBio or nanopore reads in FASTA or FASTQ format. 
    Circlator will attempt to identify each circular sequence and output a linearised version of it. 
    It does this by assembling all reads that map to contig ends and comparing the resulting contigs with the input assembly.  

    The input assembly must not be too fragmented. Although Circlator will join contigs together, whenever it can identify contigs that can be 
    unambiguously joined, its main aim is to circularize the core genome and plasmids.

    Any contigs that were identified as circular then have their start position changed.

    Currently it does not download the uniprot database and it does not run the minimus2 pipeline. Even when running canu it may give warning messages about the SPAdes version, 
    you can safely ignore those.
    ]]></help>
  <citations>
    <citation type="bibtex">
      @misc{github,
      publisher = {GitHub},
      journal = {GitHub repository},
      url = {https://github.com/sanger-pathogens/circlator/},
      }</citation>
  </citations>
</tool>