view pilon.xml @ 1:ee888e5fe28f draft

planemo upload for repository https://github.com/SANBI-SA/tools-sanbi-uwc/tree/master/tools/pilon commit fc0659094c338f551b09bd2ba314fe06d7024f33

<tool id="pilon" name="pilon" version="0.1">
    <description>An automated genome assembly improvement and variant detection tool</description>
    <requirements>
      <requirement type="package" version="1.18">pilon</requirement>
      <!--<requirement type="set_environment">CLASSPATH</requirement>-->
      <!-- if CLASSPATH is set to include pilon jar, you can call pilon with
           java com.simontuffs.onejar.Boot -->>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
      #for $input_bam in $input_bams
        ln -f -s "${input_bam.metadata.bam_index}" "${input_bam}.bai" &&
      #end for
      #if $options.selection_mode == "advanced"
        #for $bam in $options.input_frag_bams + $options.input_jump_bams + $options.input_unpaired_bams
          ln -s -f "${bam.metadata.bam_index}" "${bam}.bai" &&
        #end for
      #end if
        ln -s -f
          #if $reference_genome.reference_genome_source == "history"
            $reference_genome.history_item
          #else
            $reference_genome.builtin.fields.path
          #end if
          reference.fasta &&
        pilon
        --genome reference.fasta
        #for $input_bam in $input_bams
          --bam $input_bam
        #end for
        $variant_calling
        $changes
        #if $options.selection_mode == "advanced"
          $options.vcfqe
          $options.vcf_output
          $options.tracks
          --chunksize $options.chunk_size
          $options.diploid
          $options.duplicates
          $options.iupac
          $options.nonpf
          #if len($options.targetlist.strip()) > 0
            --targetlist $options.targetlist
          #end if
          --fix $options.fixes
          $options.verbose
          --defaultqual $options.defaultqual
          --flank $options.flank
          --gapmargin $options.gapmargin
          --K $options.kmersize
          --mindepth $options.mindepth
          --mingap $options.mingap
          --minmq $options.minmq
          --minqual $options.minqual
          $options.nostrays
        #end if
        --threads \${GALAXY_SLOTS:-1}
        --output pilon &&
        if [ -f pilon.fasta ] ; then mv pilon.fasta $output_fasta ; fi &&
        if [ -f pilon.vcf ] ; then mv pilon.vcf $output_vcf ; fi &&
        if [ -f pilon.changes ] ; then mv pilon.changes $output_changes ; fi &&
        if [ -f pilonPilon.bed ] ; then mv pilonPilon.bed $output_pilon_bed ; fi &&
        if [ -f pilonChanges.wig ] ; then mv pilonChanges.wig $output_changes_wig ; fi &&
        if [ -f pilonUnconfirmed.wig ] ; then mv pilonUnconfirmed.wig $output_unconfirmed_wig ; fi &&
        if [ -f pilonCopyNumber.wig ] ; then mv pilonCopyNumber.wig $output_copynumber_wig ; fi &&
        if [ -f pilonCoverage.wig ] ; then mv pilonCoverage.wig $output_coverage_wig ; fi &&
        if [ -f pilonBadCoverage.wig ] ; then mv pilonBadCoverage.wig $output_badcoverage_wig ; fi &&
        if [ -f pilonPctBad.wig ] ; then mv pilonPctBad.wig $output_pctbad_wig ; fi &&
        if [ -f pilonDeltaCoverage.wig ] ; then mv pilonDeltaCoverage.wig $output_deltacoverage_wig ; fi &&
        if [ -f pilonDipCoverage.wig ] ; then mv pilonDipCoverage.wig $output_dipcoverage_wig ; fi &&
        if [ -f pilonPhysicalCoverage.wig ] ; then mv pilonPhysicalCoverage.wig $output_physicalcoverage_wig ; fi &&
        if [ -f pilonClippedAlignments.wig ] ; then mv pilonClippedAlignments.wig $output_clippedalignments_wig ; fi &&
        if [ -f pilonWeightedQual.wig ] ; then mv pilonWeightedQual.wig $output_weightedqual_wig ; fi &&
        if [ -f pilonWeightedMq.wig ] ; then mv pilonWeightedMq.wig $output_weightedmq_wig ; fi &&
        if [ -f pilonGC.wig ] ; then mv pilonGC.wig $output_gc_wig ; fi
    ]]></command>
    <inputs>
      <conditional name="reference_genome">
        <param label="Source for reference genome used for BAM alignments" name="reference_genome_source" type="select">
          <option selected="True" value="history">Use a genome from history</option>
          <option value="builtin">Use a built-in genome"</option>
        </param>
        <when value="history">
          <param format="fasta" type="data" metadata_name="dbkey" name="history_item" />
        </when>
        <when value="builtin">
          <param label="Select a reference genome" name="builtin" type="select">
            <options from_data_table="all_fasta">
              <filter column="2" type="sort_by" />
              <validator message="No genomes are available for the selected input dataset" type="no_options" />
            </options>
          </param>
        </when>
      </conditional>
      <param label="Input BAM file" multiple="true" type="data" format="bam" name="input_bams"/>
      <param name="variant_calling" type="boolean" label="Variant calling mode" checked="true" truevalue="--variant" falsevalue="" />
      <param name="changes" type="boolean" label="Output file describing changes in FASTA output" truevalue="--changes" falsevalue="" />
      <conditional name="options">
        <param label="Use advanced options" name="selection_mode" type="select">
          <option selected="True" value="default">Use default options</option>
          <option value="advanced">Use advanced options</option>
        </param>
        <when value="default"> </when>
        <when value="advanced">
          <param name="vcf_output" type="boolean" checked="false" label="VCF output (even if 'Variant calling mode' is off)"
            truevalue="--vcf" falsevalue="" />
          <param name="tracks" type="boolean" checked="false" label="Output annotation tracks"
            help="Write many track files (*.bed, *.wig) suitable for viewing in a genome browser."
            truevalue="--tracks" falsevalue="" />
          <param name="chunk_size" type="integer" min="1" value="10000000" label="Chunk size"
            help="Input FASTA elements larger than this will be processed in smaller pieces not to
            exceed this size." />
          <param name="vcfqe" type="boolean" checked="false" label="QE (not QP) in VCF" help="If specified the VCF will contain a QE (quality-weighted evidence) field rather
          than the default QP (quality-weighted percentage of evidence) field." truevalue="--vcfqe" falsevalue="" />
          <param name="input_frag_bams" label="Input BAM file (paired end fragments)" multiple="true" type="data" format="bam"
            help="BAM file consisting of fragment paired-end alignments." />
          <param name="input_jump_bams" label="Input BAM file (mate pairs)" multiple="true" type="data" format="bam"
            help="BAM file consisting of jump (mate pair) paired-end alignments." />
          <param name="input_unpaired_bams" label="Input BAM file (unpaired)" multiple="true" type="data" format="bam"
            help="BAM file consisting of unpaired alignments." />
          <param name="fixes" label="Issues that pilon should try and fix" type="select" multiple="true">
            <option value="all" selected="true">All non-experimental fixes</option>
            <option value="bases">Individual bases and small indels</option>
            <option value="gaps">Fill gaps</option>
            <option value="local">Detect and fix local misassemblies</option>
            <option value="none">Do none of these fixes (no FASTA will be written)</option>
            <option value="amb">Fix ambigious bases in FASTA output (experimental)</option>
            <option value="breaks">Allow local reassembly to open new gaps (experimental, requires local assembly fixing to be selected)</option>
            <option value="novel">Assemble novel sequence from unaligned non-jump reads (experimental)</option>
          </param>
          <param name="diploid" label="Organism is diploid" type="boolean" checked="false"
            help="Sample is from diploid organism; will eventually affect calling of heterozygous SNPs"
            truevalue="--diploid" falsevalue="" />
          <param name="duplicates" label="Use duplicates" type="boolean" checked="false"
            help="Use reads marked as duplicates in the input BAMs"
            truevalue="--duplicates" falsevalue="" />
          <param name="iupac" label="Use IUPAC codes in FASTA output" type="boolean" checked="false"
            help="Output IUPAC ambiguous base codes in the output FASTA file when appropriate"
            truevalue="--iupac" falsevalue="" />
          <param name="nonpf" label="Use low quality reads" type="boolean" checked="false"
            help="Use reads which failed sequencer quality filtering"
            truevalue="--nonpf" falsevalue="" />
          <param name="targetlist" label="List of targets to process (leave blank for all)" default="" type="text" length="40"
            help="Only process the specified target(s).  Targets are comma-separated, and each target is a fasta element name optionally followed by a base range." />
          <param name="verbose" label="Verbose output (in tool log)" type="boolean" check="false"
            truevalue="--verbose" falsevalue="" />
          <param name="defaultqual" label="Default base quality" type="integer" min="1" value="15"
            help="Assumes bases are of this quality if quals are no present in input BAMs" />
          <param name="flank" label="Flanking bases to ignore" type="integer" min="1" value="10"
            help="This many bases at each end of the good reads will be ignored." />
          <param name="gapmargin" label="Allowable gap margin" type="integer" min="1" value="100000"
            help="Closed gaps must be within this number of bases of true size to be closed" />
          <param name="kmersize" label="Kmer size" type="integer" min="1" value="47"
            help="Kmer size used by internal assembler" />
          <param name="mindepth" label="Minimum depth" type="float" value="0.1"
            help="Minimum depth of coverage required for variants to be called. See complete documentation below." />
          <param name="mingap" label="Mininum gap size" type="integer" value="10"
            help="Minimum size for unclosed gaps" />
          <param name="minmq" label="Minimum mapping quality" type="integer" value="0"
            help="Minimum alignment mapping quality for a read to count in pileups" />
          <param name="minqual" label="Minimum base quality" type="integer" value="0"
            help="Minimum base quality to consider for pileups" />
          <param name="nostrays" label="Disable 'stray read filtering'" type="boolean" checked="false"
            help="See documentation below"
            truevalue="--nostrays" falsevalue="" />
        </when>
      </conditional>
    </inputs>
    <outputs>
      <data format="vcf" label="VCF from ${tool.name} on ${on_string}" name="output_vcf">
        <filter>variant_calling or (options['selection_mode'] == 'advanced' and options['vcf_output'])</filter>
      </data>
      <data format="txt" label="Changes in FASTA from ${tool.name} on ${on_string}" name="output_changes">
        <filter>changes</filter>
      </data>
      <data format="fasta" label="FASTA from ${tool.name} on ${on_string}" name="output_fasta">
        <filter>options['selection_mode'] == 'default' or (options['selection_mode'] == 'advanced' and 'none' not in options['fixes'])</filter>
      </data>
      <data format="bed" label="Features from ${tool.name} on ${on_string} (BED format)" name="output_pilon_bed">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} changes track on ${on_string} (WIG format)" name="output_changes_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} unconfirmed track on ${on_string}" name="output_unconfirmed_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} copy number track on ${on_string}" name="output_copynumber_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} coverage track on ${on_string}" name="output_coverage_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} bad coverage track on ${on_string}" name="output_badcoverage_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} pct bad track on ${on_string}" name="output_pctbad_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} delta coverage track on ${on_string}" name="output_deltacoverage_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} dip coverage track on ${on_string}" name="output_dipcoverage_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} physical coverage track on ${on_string}" name="output_physicalcoverage_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} clipped alignments track on ${on_string}" name="output_clippedalignments_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} weighted quality track on ${on_string}" name="output_weightedqual_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} weighted MQ track on ${on_string}" name="output_weightedmq_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
      <data format="wig" label="${tool.name} GC track on ${on_string}" name="output_gc_wig">
        <filter>options['selection_mode'] == 'advanced' and options['tracks']</filter>
      </data>
    </outputs>
    <tests>
      <test>
        <param name="reference_genome_source" value="history" />
        <param ftype="fasta" name="history_item" value="test1.fasta" />
        <param name="input_bams" value="test1.bam" />
        <param name="variant_calling" value="true" />
        <output file="test1.vcf" ftype="vcf" name="output_vcf" lines_diff="6" />
        <output file="test_output1.fasta" ftype="fasta" name="output_fasta" />
      </test>
    </tests>
    <help><![CDATA[
  Pilon is a software tool which can be used to:

  * Automatically improve draft assemblies

  * Find variation among strains, including large event detection

  Pilon requires as input a FASTA file of the genome along with one or more BAM files of reads aligned to the input FASTA file. Pilon uses read alignment analysis to identify inconsistencies between the input genome and the evidence in the reads. It then attempts to make improvements to the input genome, including:

  * Single base differences

  * Small indels

  * Larger indel or block substitution events

  * Gap filling

  * Identification of local misassemblies, including optional opening of new gaps

  Pilon then outputs a FASTA file containing an improved representation of the genome from the read data and an optional VCF file detailing variation seen between the read data and the input genome.

  To aid manual inspection and improvement by an analyst, Pilon can optionally produce tracks that can be displayed in genome viewers such as IGV and GenomeView, and it reports other events (such as possible large collapsed repeat regions) in its standard output.

  Note on **mindepth**:

  Variants (snps and indels) will only be called if there is coverage of good pairs
  at the value set for *mindepth* depth or more; if this value is >= 1, it is an absolute depth, if it is a
  fraction < 1, then minimum depth is computed by multiplying this value by the mean
  coverage for the region, with a minumum value of 5 (default 0.1: min depth to call
  is 10% of mean coverage or 5, whichever is greater).

  Note on **stray read filtering**

  By default a pass is made through the input BAM files to identify stray pairs, that is,
  those pairs in which both reads are aligned but not marked valid because they have
  inconsistent orientation or separation. Identifying stray pairs can help fill gaps
  and assemble larger insertions, especially of repeat content.  However, doing so
  sometimes consumes considerable memory.
    ]]></help>
    <citations>
        <citation type="bibtex">@article{Walker_2014, 
          title={Pilon: An Integrated Tool for Comprehensive Microbial Variant Detection and Genome Assembly Improvement},
          volume={9}, ISSN={1932-6203}, url={http://dx.doi.org/10.1371/journal.pone.0112963},
          DOI={10.1371/journal.pone.0112963}, number={11}, journal={PLoS ONE},
          publisher={Public Library of Science (PLoS)},
          author={Walker, Bruce J. and Abeel, Thomas and Shea, Terrance and
          Priest, Margaret and Abouelliel, Amr and Sakthikumar, Sharadha and Cuomo, Christina A. and
          Zeng, Qiandong and Wortman, Jennifer and Young, Sarah K. and et al.},
          editor={Wang, Junwen}, year={2014}, month={Nov}, pages={e112963}}</citation>
    </citations>
</tool>