view sequenza_wrapper.xml @ 39:31adf1afb841 draft default tip

Uploaded
author jbrayet
date Mon, 24 Aug 2015 05:19:14 -0400
parents dcd4ed68a960
children
line wrap: on
line source

<!--Sequenza - developed by Jocelyn Brayet <jocelyn.brayet@curie.fr>
Copyright (C) 2015  Institut Curie

This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program.  If not, see <http://www.gnu.org/licenses/>.-->
<tool id="sequenza_tool" name="Sequenza" version="1.2">
  <description>allele-specific copy number and mutation profiles</description>
  <requirements>
    <requirement type="package" version="2.11.1">fontconfig</requirement>
    <requirement type="package" version="2.7">python</requirement>
    <requirement type="package" version="2.1.1">sequenza</requirement>
    <requirement type="package" version="1.1">samtools</requirement>
  </requirements>
  <command interpreter="python">
    sequenza_wrapper.py -name $sampleName -outGalaxy $HTMLFile -format $fileFormat.format -estimation $usePersonalEstimation.estimation -gcContent $gc_content_file
    #if $fileFormat.format == "BAM":
      #if $fileFormat.reference_source.reference_source_selector=="cached":
        -normal $fileFormat.reference_source.normal_file
        -tumor $fileFormat.reference_source.tumor_file
        -ref_file $fileFormat.reference_source.ref_file.fields.path
	-samtools_options '
	$fileFormat.skip_anomalous_read_pairs
        $fileFormat.disable_probabilistic_realignment
	-d "$fileFormat.max_reads_per_bam"
        -q "$fileFormat.minimum_mapping_quality"
        -Q "$fileFormat.minimum_base_quality"
	'
      #else:
        -normal $fileFormat.reference_source.normal_file
        -tumor $fileFormat.reference_source.tumor_file
        -ref_file $fileFormat.reference_source.ref_file
	-samtools_options '
	$fileFormat.skip_anomalous_read_pairs
        $fileFormat.disable_probabilistic_realignment
	-d "$fileFormat.max_reads_per_bam"
        -q "$fileFormat.minimum_mapping_quality"
        -Q "$fileFormat.minimum_base_quality"
	'
      #end if
    #else:
      -normal $fileFormat.normal_file
      -tumor $fileFormat.tumor_file
    #end if
    #if $usePersonalEstimation.estimation == "yes":
      -cellularity $usePersonalEstimation.cellularity
      -ploidy $usePersonalEstimation.ploidy
    #end if
  </command>
  <inputs>
    <param name="sampleName" type="text" value="sample" size="30" label="Sample name">
      <sanitizer invalid_char="">
        <valid initial="string.letters,string.digits"><add value="_"/></valid>
      </sanitizer>
    </param>
    <conditional name="fileFormat">
      <param name="format" type="select" label="File format" >
        <option value="BAM" selected="true">BAM</option>
        <option value="pileup" >Pileup</option>
        <option value="pileup_gz" >Pileup.gz</option>
      </param>
      <when value="BAM">
        <conditional name="reference_source">
      	  <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
            <option value="cached">Locally cached</option>
            <option value="history">History</option>
          </param>
        <when value="cached">
          <param name="normal_file" type="data" format="bam" label="Normal BAM file" >
	    <validator type="unspecified_build" />
            <validator type="dataset_metadata_in_data_table" table_name="sam_fa_indexes" metadata_name="dbkey" metadata_column="value" message="Sequences are not currently available for the specified build." /> 
          </param>
          <param name="tumor_file" type="data" format="bam" label="Tumor BAM file" >
	    <validator type="unspecified_build" />
            <validator type="dataset_metadata_in_data_table" table_name="sam_fa_indexes" metadata_name="dbkey" metadata_column="value" message="Sequences are not currently available for the specified build." /> 
          </param>
          <param name="ref_file" type="select" label="Using reference genome">
            <options from_data_table="sam_fa_indexes">
          </options>
          </param>
        </when>
        <when value="history">
          <param name="normal_file" type="data" format="bam" label="Normal BAM file" >
            <validator type="metadata" check="bam_index" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue."/>
          </param>
          <param name="tumor_file" type="data" format="bam" label="Tumor BAM file" >
            <validator type="metadata" check="bam_index" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue."/>
          </param>
          <param name="ref_file" type="data" format="fasta" label="Using reference file" />
        </when>
        </conditional>
	<param name="skip_anomalous_read_pairs" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Do not skip anomalous read pairs in variant calling" />
        <param name="disable_probabilistic_realignment" type="boolean" truevalue="-B" falsevalue="" checked="False" label="Disable probabilistic realignment for the computation of base alignment quality (BAQ)" />
        <param name="max_reads_per_bam" type="integer" value="100000" label="Max reads per BAM" />
        <param name="minimum_mapping_quality" type="integer" value="20" label="Minimum mapping quality for an alignment to be used" />
        <param name="minimum_base_quality" type="integer" value="13" label="Minimum base quality for a base to be considered" />
      </when>
      <when value="pileup">
        <param name="normal_file" type="data" format="pileup" label="Normal pileup file" />
        <param name="tumor_file" type="data" format="pileup" label="Tumor pileup file" />
      </when>
      <when value="pileup_gz">
        <param name="normal_file" type="data" format="pileup.gz" label="Normal pileup.gz file" />
        <param name="tumor_file" type="data" format="pileup.gz" label="Tumor pileup.gz file" />
      </when>
    </conditional >
    <param name="gc_content_file" type="data" format="txt" label="GC content file" />
    <conditional name="usePersonalEstimation">
      <param name="estimation" type="select" label="Do you want to use personal cellularity and ploidy? Otherwise Sequenza estimates cellularity and ploidy" >
        <option value="no" selected="true">No</option>
        <option value="yes" >Yes</option>
      </param>
      <when value="no" />
      <when value="yes">
        <param name="cellularity" type="integer" value="30" min="0" max="100" label="Cellularity used (%)" />
        <param name="ploidy" type="integer" value="2" label="Ploidy used" />
      </when>
    </conditional >
  </inputs>
  <outputs>
    <data format="html" name="HTMLFile" label="HTML output - Sequenza results" />
  </outputs>
  <tests>
    <test>
      <param name="sampleName" value="test_curie"/>
      <param name="fileFormat" value="pileup"/>
      <param name="normal_file" value="constit_2.pileup"/>
      <param name="tumor_file" value="tumor_2.pileup"/>
      <param name="gc_content_file" value="hg19_chro1.gc50Base.txt"/>
      <param name="estimation" value="yes"/>
      <param name="cellularity" value="30"/>
      <param name="ploidy" value="2"/>
      <output name="HTMLFile" file="test_sequenza_1.dat" ftype="html"/>
    </test>
  </tests>
  <help>

**What it does**

Tools to analyze genomic sequencing data from paired normal-tumor samples, including cellularity and ploidy estimation; mutation and copy number (allele-specific and total copy number) detection, quantification and visualization.

  </help>
  <citations>
    <citation type="bibtex">@article{Favero01012015,
      author = {Favero, F. and Joshi, T. and Marquard, A. M. and Birkbak, N. J. and Krzystanek, M. and Li, Q. and Szallasi, Z. and Eklund, A. C.}, 
      title = {Sequenza: allele-specific copy number and mutation profiles from tumor sequencing data},
      volume = {26}, 
      number = {1}, 
      pages = {64-70}, 
      year = {2015}, 
      doi = {10.1093/annonc/mdu479}, 
      URL = {http://annonc.oxfordjournals.org/content/26/1/64.abstract}, 
      eprint = {http://annonc.oxfordjournals.org/content/26/1/64.full.pdf+html}, 
      journal = {Annals of Oncology} 
      }</citation>
    </citations>
</tool>