comparison QDNAseq.xml @ 63:19e91eb3d06b draft

Uploaded

62:bd81b2559c10

<tool id="QDNAseq" name="QDNAseq" version="0.0.1">
  
  <requirements>
    <!-- <requirement type="set_environment">QDNASEQ_SCRIPT_PATH</requirement> -->
    <!-- R 3.1.0 dependency will be used instead when available, now default R see command -->
    <!-- <requirement type="package" version="3.1.0">R</requirement> -->
    <requirement type="package" version="0.1.18">samtools</requirement>
  </requirements>

  <description>Quantitative copy number abberation detection</description>

  <!-- command block to call script with default R environment -->
  <!-- change interpreter to /full/path/to/Rscript if required -->
  <command interpreter="Rscript"> 
    QDNAseq.R 
    $qdnaseq_cfg
  </command>

  <stdio>
    <!-- Anything higher than 0 means the R script didnt finish -->
    <!-- Because different R packages deal with err/warn differently unable to waterproof this -->
    <exit_code range="1:" level="fatal" description="R script didnt finish correctly, check log" />
  </stdio>
  
  <inputs>
    <!-- ==================== -->
    <!-- General inputs -->
    <!-- ==================== -->
    <param name="jobName" type="text" optional="false" label="Analysis/ouput name" help="Supply a name for the outputs to remind you what they contain" value="TEST">
      <validator type="empty_field" />
      <validator type="regex" message="This field should contain some non-whitespace character">.*\S</validator>
    </param>
    <param name="binSize" type="select" label="Select bin-size to use (kb)" help="Larger bin sizes provide faster analysis but lower resolution">
      <option value="1000">1Mb</option>
      <option value="100">100kb</option>
      <option value="30">30kb</option>
      <option value="15">15kb</option>
      <option value="5">5kb</option>
      <option value="1">1kb</option>
    </param>

    <param name="doCall" type="select" label="Also segment and call with CGHcall" help="Segmenting and calling can take significant computational time">
      <option value="TRUE">yes</option>
      <option value="FALSE">no</option>
    </param>

    <param name="experimentType" type="select" label="Type of sequencing data" help="Currently only single end reads of lenght 50 are supported within galaxy">
      <option value="SR50">Single Reads of 50bp</option>
      <!-- <option value="PE1000">PairedEnd1000</option> -->
    </param>

    <!-- Input BAMs -->
    <!-- ==================== -->
    <param name="bams" type="data" multiple="true" optional="false" format="bam" label="Input BAMs" help="Select the BAM files to analyze" />

    <!-- ==================== -->
    <!-- This section contains galaxy history output settings -->
    <!-- ==================== -->
    <conditional name="extra_history_outputs">
      <param name="show" type="select" label="Optional history outputs">
        <option value="NO">Only output Report to history</option>
        <option value="YES">Select additional history outputs</option>
      </param>
      <when value="YES">
        <param name="readcounts_rds" type="select" label="Also output readcounts RDS (R object) to history">
          <option value="FALSE">no</option>
          <option value="TRUE">yes</option>
        </param>
        <param name="copynumbers_rds" type="select" label="Also output copynumbers RDS (R object) to history">
          <option value="FALSE">no</option>
          <option value="TRUE">yes</option>
        </param>
        <param name="calls_rds" type="select" label="Also output called segments RDS (R object) to history">
          <option value="FALSE">no</option>
          <option value="TRUE">yes</option>
        </param>
        <param name="copynumbers_igv" type="select" label="Also output copynumbers IGV file to history">
          <option value="FALSE">no</option>
          <option value="TRUE">yes</option>
        </param>
      </when>
      
      <when value="NO">
        <param name="readcounts_rds" type="hidden" value="FALSE" />
        <param name="copynumbers_rds" type="hidden" value="FALSE" />
        <param name="calls_rds" type="hidden" value="FALSE" />
        <param name="copynumbers_igv" type="hidden" value="FALSE" />
      </when>
    </conditional>

    <!-- ==================== -->
    <!-- Option to use your own bin annotations -->
    <!-- ==================== -->
    <conditional name="use_own_binannotation">
      <param name="show" type="select" label="Use your own bin annotations from history">
        <option value="no">no</option>
        <option value="yes">yes</option>
      </param>
      <when value="yes">
        <param name="binannotation_file" type="data" multiple="false" format="rds" label="R data structure file with bin-annotations" help="If you made your own bin-annotations with the QDNAseq bioconductor package you can upload them to your history and select here" />
      </when>
      <when value="no">
        <param name="binannotation_file" type="hidden" value="" />
      </when>
    </conditional> 
    <!-- ==================== -->
    <!-- Optional advanced options -->
    <!-- ==================== -->
    <conditional name="advanced">
      <param name="show" type="select" label="Show advanced options">
        <option value="no">no</option>
        <option value="yes">yes</option>
      </param>
      <when value="yes">
        
        <param name="undo_splits" type="select" label="undoSplits" help="If set to sdundo, see undoSD below">
          <option value="sdundo">sdundo</option>
          <option value="prune">prune</option>
          <option value="none">none</option>
        </param>

          <option value="TRUE">yes</option>
          <option value="FALSE">no</option>
        </param>

        <param name="mappability" type="integer" value="0" min="0" max="100" label="Filter bins with lower mappability" help="Will exclude all bins will lower mappability than this number (0-100)" />

        <param name="debug" type="select" label="DEBUG / TEST" help="Use inbuilt LGG data instead of input BAMs">
          <option value="FALSE">no</option>
          <option value="TRUE">yes</option>
        </param>
      </when>
      <!-- need to set defaults because params are passed to R anyway -->
      <when value="no">
        <param name="undoSD" type="hidden" value="1" />
        <param name="undo_splits" type="hidden" value="sdundo" />
        <param name="blacklist" type="hidden" value="TRUE" />
        <param name="mappability" type="hidden" value="0" />
        <param name="debug" type="hidden" value="FALSE" />
      </when>
    </conditional> 

    <!-- ==================== -->
    <!-- Optional graphical/plotting options -->
    <!-- ==================== -->
    <conditional name="plot_options">
      <param name="show" type="select" label="Show graphical options">
        <option value="no">no</option>
        <option value="yes">yes</option>
      </param>
      <when value="yes">
        <param name="plot_width" size="3" type="integer" value="960" label="Plot width" />
        <param name="plot_height" size="3" type="integer" value="480" label="Plot height" />
        <param name="exclude_chrs" type="select" multiple="true" label="Hide these chromosomes in plots" help="Currently only standard human chromosomes supported. NOTE: other filters might also exclude chromosomes">
          <option value="1">1</option>
          <option value="2">2</option>
          <option value="3">3</option>
          <option value="4">4</option>
          <option value="5">5</option>
          <option value="6">6</option>
          <option value="7">7</option>
          <option value="8">8</option>
          <option value="9">9</option>
          <option value="10">10</option>
          <option value="11">11</option>
          <option value="12">12</option>
          <option value="13">13</option>
          <option value="14">14</option>
          <option value="15">15</option>
          <option value="16">16</option>
          <option value="17">17</option>
          <option value="18">18</option>
          <option value="19">19</option>
          <option value="20">20</option>
          <option value="21">21</option>
          <option value="22">22</option>
          <option value="X" selected="true">X</option>
          <option value="Y" selected="true">Y</option>
        </param>
      </when>
      <when value="no">
        <param name="plot_width" type="hidden" value="960" />
        <param name="plot_height" type="hidden" value="480" />
        <param name="exclude_chrs" type="hidden" value="X,Y" />
      </when>
    </conditional>
  </inputs>
  <!-- ==================== -->
  <!-- This config is sourced in R code -->
  <!-- ==================== -->
  <configfiles>
    <configfile name="qdnaseq_cfg">
## this file was sourced in QDNAseq R wrapper script
## in this way all galaxy params are passes to R

## required params
as.integer( "${binSize}" ) -> binSize
"${experimentType}" -> experimentType
"${jobName}" -> outputName

## extra params
"${htmlFile}" -> outputHtml
"${htmlFile.files_path}" -> outputPath
"${use_own_binannotation.binannotation_file}" -> binAnnotations
as.logical( "${doCall}" ) -> doCall

## advanced options
as.double( "${advanced.undoSD}" ) -> undoSD
as.logical( "${advanced.debug}" ) -> debug
as.logical( "${advanced.blacklist}" ) -> filterBlacklistedBins
as.integer( "${advanced.mappability}" ) -> mappabilityCutoff
"${advanced.undo_splits}" -> undoSplits

## history output params
as.logical( "${extra_history_outputs.readcounts_rds}" ) -> doOutputReadcountsRds
as.logical( "${extra_history_outputs.copynumbers_rds}" ) -> doOutputCopynumbersRds
as.logical( "${extra_history_outputs.calls_rds}" ) -> doOutputCallsRds
as.logical( "${extra_history_outputs.copynumbers_igv}" ) -> doOutputCopynumbersIgv
"${rdsReadCounts}" -> readCountsDatasetFile
"${rdsCopyNumbers}" -> copyNumbersDatasetFile
"${rdsCalls}" -> calledSegmentsDatasetFile
"${igvCopyNumbers}" -> copyNumbersIgvDatasetFile

## plotting params
as.integer( "${plot_options.plot_width}" ) -> PLOT_WIDTH
as.integer( "${plot_options.plot_height}" ) -> PLOT_HEIGHT
"${plot_options.exclude_chrs}" -> excludeChrsString

## input BAMs init
c() -> bamsPaths
c() -> bamsNames

#for bam in $bams# 
c( bamsPaths, "${bam}" ) -> bamsPaths

    </configfile>
  </configfiles>

  <!-- ==================== -->
  <!-- Main output is an html based report, additional on request -->
  <!-- ==================== -->
  <outputs>

    <data format="html" name="htmlFile" label="QDNAseq Report ${binSize}kb (${jobName})" />
    
    <data format="rds" name="rdsReadCounts" label="${jobName}_readCounts_${binSize}kb.rds">
      <filter> extra_history_outputs['readcounts_rds'] == "TRUE" </filter><!-- <filter>("readcounts_rds" in outputs)</filter> -->
    </data>

    <data format="rds" name="rdsCopyNumbers" label="${jobName}_copyNumbers_${binSize}kb.rds">
      <filter> extra_history_outputs['copynumbers_rds'] == "TRUE" </filter>
    </data>

    <data format="rds" name="rdsCalls" label="${jobName}_calls_${binSize}kb.rds">
      <filter> extra_history_outputs['calls_rds'] == "TRUE" </filter>
    </data>

    <data format="txt" name="igvCopyNumbers" label="${jobName}_copyNumbers_${binSize}kb.igv">
      <filter> extra_history_outputs['copynumbers_igv'] == "TRUE" </filter>
    </data>

  </outputs>

  <!-- ==================== -->
  <!-- Tests still to be done -->

For questions/remarks about the galaxy part of this tool, see contact form here_

.. _here: http://www.stefs.nl/wp/contact

-----

.. class:: warningmark

As there is no R 3.1.0 package yet (which is required), the **dependencies** need to be installed by hand and available to the user under which galaxy runs: R (3.1.0) and bioconductor package QDNAseq (>= 1.0.5)

.. class:: warningmark

The input BAMs are expected to be **single end reads of 50bp length** mapped to GRCh37/hg19 genome build. Other experiment setups are currently not supported within galaxy. See the documentation of QDNAseq at bioconductor on how to deal with different setups.

.. class:: warningmark

Requires **internet access** for downloading bin-annotations from bitbucket and to show some styling (css) of the final report

-----

**Citation**

For the underlying tool please cite: llari Scheinin, Daoud Sie et al. DNA copy number analysis of fresh and formalin-fixed specimens by whole-genome sequencing: improved correction of systematic biases and exclusion of problematic regions, (submitted). See also the bioconductor package_ documentation.

.. _package: http://www.bioconductor.org/packages/release/bioc/html/QDNAseq.html


.. image:: LGG150_copynumber_example.png
.. image:: LGG150_calls_example.png
  </help>

</tool>

63:19e91eb3d06b

<tool id="QDNAseq" name="QDNAseq" version="0.0.2" force_history_refresh="True">
  
  <requirements>
    
    <!-- R 3.1.0 dependency will be used instead when available, now default R is used, see command -->
    <!-- <requirement type="package" version="3.1.0">R</requirement> -->
    <!-- <requirement type="package" version="1.0.5">qdnaseq</requirement> -->
    <requirement type="package" version="0.1.18">samtools</requirement>
    <requirement type="set_environment">TOOL_DIR</requirement>
  </requirements>

  <description>Quantitative copy number abberation detection</description>

  <!-- command block to call script with default R installation -->
  <!-- change to /full/path/to/Rscript if required (eg /ccagc/lib/R/R-3.1.0/bin/Rscript) -->
  <command interpreter="Rscript"> 
    QDNAseq.R 
    $qdnaseq_cfg
  </command>

  <stdio>
    <!-- Anything higher than 0 means the R script didnt finish (correctly) -->
    <!-- Because different R packages deal with err/warn differently unable to waterproof this -->
    <exit_code range="1:" level="fatal" description="R script didnt finish correctly, check log" />
  </stdio>
  
  <inputs>
    
    <!-- ==================== -->
    <!-- General inputs -->
    <!-- ==================== -->
    
    <!-- Job name: must contain non-whitespace chars -->
    <param name="jobName" type="text" optional="false" label="Analysis/ouput name" help="Supply a name for the outputs to remind you what they contain" value="TEST">
      <validator type="empty_field" />
      <validator type="regex" message="This field should contain some non-whitespace character">.*\S</validator>
    </param>

    <!-- Bin Size: only certain sizes are supported by QDNAseq package -->
    <param name="binSizes" type="select" optional="false" multiple="true" label="Select bin-sizes to use (kb)" help="Larger bin sizes provide faster analysis but lower resolution">
      <option value="1000" selected="true">1Mb</option>
      <option value="100">100kb</option>
      <option value="30">30kb</option>
      <option value="15">15kb</option>
      <option value="5">5kb</option>
      <option value="1">1kb</option>
    </param>

    <!-- Experiment type: only one type (SR50) supported now, maybe more in the future-->
    <param name="experimentType" type="select" label="Type of sequencing data" help="Currently only single end reads of lenght 50 are supported within galaxy">
      <option value="SR50">Single Reads of 50bp</option>
      <!-- <option value="PE1000">PairedEnd1000</option> -->
    </param>

    <!-- Input BAMs -->
    <!-- ==================== -->
    <param name="bams" type="data" multiple="true" optional="false" format="bam" label="Input BAMs" help="Select the BAM files to analyze" />

    <!-- ==================== -->
    <!-- Optional segmenting -->
    <!-- ==================== -->
    <param name="doSegment" type="select" label="Also perform segmentation" help="Segmentation collects bins with similar ratio into regions">
      <option value="TRUE">yes</option>
      <option value="FALSE">no</option>
    </param>

    <!-- ==================== -->
    <!-- Option to use your own bin annotations file -->
    <!-- ==================== -->
    <conditional name="binannotations_source">
      <param name="show" type="select" label="Bin annotations to use" help="Default bin-annotations are for GRCh37/hg19 and tuned for 50bp reads (single end)">
        <option value="default">Default</option>
        <option value="history">From history</option>
      </param>
      <when value="history">
        <param name="binannotation_file" type="data" multiple="false" label="R data structure file (*.rds) with bin-annotations" help="If you made your own bin-annotations with the QDNAseq bioconductor package you can upload them to your history and select here" />
      </when>
      <when value="default">
        <param name="binannotation_file" type="hidden" value="" />
      </when>
      
    </conditional> 

    <!-- ==================== -->
    <!-- Optional advanced options -->
    <!-- ==================== -->
    <conditional name="advanced">
      <param name="show" type="select" label="Use advanced options" help="Select yes to show and use filter and output options">
        <option value="no">no</option>
        <option value="yes">yes</option>
      </param>
      <when value="yes">
        
        <param name="copynumbers_igv" type="select" label="Also output copynumber IGV file to history">
          <option value="FALSE">no</option>
          <option value="TRUE">yes</option>
        </param>

        <param name="undo_splits" type="select" label="undoSplits" help="If set to sdundo, see undoSD below">
          <option value="sdundo">sdundo</option>
          <option value="prune">prune</option>
          <option value="none">none</option>
        </param>

          <option value="TRUE">yes</option>
          <option value="FALSE">no</option>
        </param>

        <param name="mappability" type="integer" value="0" min="0" max="100" label="Filter bins with lower mappability" help="Will exclude all bins will lower mappability than this number (0-100)" />
      
        <!-- ==================== -->
        <!-- Optional graphical/plotting options -->
        <!-- ==================== -->
        <param name="plot_width" size="3" type="integer" value="1440" label="Width of the png image produced" />
        <param name="plot_height" size="3" type="integer" value="720" label="Height of the png image produced" />
        <param name="exclude_chrs" type="select" multiple="true" label="Hide these chromosomes in plots" help="Currently only standard human chromosomes supported. NOTE: other filters might also exclude chromosomes">
          <option value="1">1</option><option value="2">2</option>
          <option value="3">3</option><option value="4">4</option>
          <option value="5">5</option><option value="6">6</option>
          <option value="7">7</option><option value="8">8</option>
          <option value="9">9</option><option value="10">10</option>
          <option value="11">11</option><option value="12">12</option>
          <option value="13">13</option><option value="14">14</option>
          <option value="15">15</option><option value="16">16</option>
          <option value="17">17</option><option value="18">18</option>
          <option value="19">19</option><option value="20">20</option>
          <option value="21">21</option><option value="22">22</option>
          <option value="X" selected="true">X</option>
          <option value="Y" selected="true">Y</option>
        </param>
      </when>

      <!-- need to set defaults because params are passed to R regardless of conditional opened/closed -->
      <when value="no">
        <param name="copynumbers_igv" type="hidden" value="FALSE" />
        <param name="undoSD" type="hidden" value="1" />
        <param name="undo_splits" type="hidden" value="sdundo" />
        <param name="blacklist" type="hidden" value="TRUE" />
        <param name="mappability" type="hidden" value="0" />
        <param name="plot_width" type="hidden" value="1440" />
        <param name="plot_height" type="hidden" value="720" />
        <param name="exclude_chrs" type="hidden" value="X,Y" />
      </when>
    </conditional>

    <!-- ==================== -->
    <!-- Option to perform a test run with built in data -->
    <!-- ==================== -->
    <param name="debug" type="select" label="Run with test data" help="Use inbuilt LGG150 data instead of input BAMs">
      <option value="FALSE">no</option>
      <option value="TRUE">yes</option>
    </param>
    
  </inputs>
  <!-- ==================== -->
  <!-- Config file to pass params to R script -->
  <!-- ==================== -->
  <configfiles>
    <configfile name="qdnaseq_cfg">
## Desc: this file was sourced in QDNAseq R wrapper script
##  as means to pass all galaxy params to R

## -----
## required params
## -----
"${binSizes}" -> binSizesString
"${experimentType}" -> experimentType
"${jobName}" -> outputName

## -----
## extra main params
## -----
"${htmlFile}" -> outputHtml
"${htmlFile.id}" -> outputId
"${__new_file_path__}" -> newFilePath

"${htmlFile.files_path}" -> outputPath
as.logical( "${doSegment}" ) -> doSegment
as.logical( "${debug}" ) -> debug

## -----
## own bin-annotations file options
## -----
"${binannotations_source.binannotation_file}" -> binAnnotations

## -----
## advanced options
## -----
as.double( "${advanced.undoSD}" ) -> undoSD
as.logical( "${advanced.blacklist}" ) -> filterBlacklistedBins
as.integer( "${advanced.mappability}" ) -> mappabilityCutoff
"${advanced.undo_splits}" -> undoSplits
as.logical( "${advanced.copynumbers_igv}" ) -> doOutputCopynumbersIgv

## #for binSize in $binSizes}.split(",")# 
## "${binSize}kbp_${igvCopyNumbers}" -> copyNumbersIgvDatasetFile
## #end for

## -----
## plot options
## -----
as.integer( "${advanced.plot_width}" ) -> PLOT_WIDTH
as.integer( "${advanced.plot_height}" ) -> PLOT_HEIGHT
"${advanced.exclude_chrs}" -> excludeChrsString
  
## -----
## input BAMs init
## -----
c() -> bamsPaths
c() -> bamsNames

#for bam in $bams# 
c( bamsPaths, "${bam}" ) -> bamsPaths

    </configfile>
  </configfiles>

  <!-- ==================== -->
  <!-- Main output is an html based report -->
  <!-- ==================== -->
  <outputs>

    <!-- main output is a html report -->
    <!-- ...but there can be more outputs using the id of the htmlFile output -->
    <data format="html" name="htmlFile" label="QDNAseq: ${jobName}" />

  </outputs>

  <!-- ==================== -->
  <!-- Tests still to be done -->

For questions/remarks about the galaxy part of this tool, see contact form here_

.. _here: http://www.stefs.nl/wp/contact

You can **test this tool** with built-in data by selecting the option "Run with test data" and press execute.

-----

.. class:: warningmark

As there is no R 3.1.0 galaxy-package yet (a requirement for QDNAseq), the **dependencies** need to be installed by hand and available to the user under which galaxy runs: R (3.1.0) and bioconductor package QDNAseq (>= 1.0.5). In case the default R is not 3.1.0, also the wrapper xml must be updated to include the correct path during installation of this tool.

.. class:: warningmark

The input BAMs are expected to be **single end reads of 50bp length** mapped to GRCh37/hg19 genome build. Other experiment setups are currently not tested or supported within galaxy. See the documentation of QDNAseq at bioconductor on how to deal with different setups (or keep fingers crossed ;) )

.. class:: warningmark

Requires **internet access** for downloading bin-annotations from bitbucket and to show some styling (css) of the final report

-----

**Citation**

For the underlying QDNAseq R package please cite: llari Scheinin, Daoud Sie et al. DNA copy number analysis of fresh and formalin-fixed specimens by whole-genome sequencing: improved correction of systematic biases and exclusion of problematic regions, (submitted). See also the bioconductor package_ documentation.

.. _package: http://www.bioconductor.org/packages/release/bioc/html/QDNAseq.html

.. image:: ./LGG150_copynumber_example.png :height: 240 :width: 480

  </help>

</tool>