comparison QDNAseq.xml @ 23:4943308e95fc draft

Uploaded

22:ff41a875ac60

<tool id="QDNAseq" name="QDNAseq" version="0.0.2" force_history_refresh="True">
  
  <requirements>
    
    <!-- <requirement type="package" version="3.1.0">R</requirement> -->
    <requirement type="package" version="0.1.18">samtools</requirement>
    <requirement type="package" version="3.1.1">R_3_1_1</requirement>
    <requirement type="package" version="1.0.5">qdnaseq</requirement>
    <requirement type="set_environment">QDNASEQ_PATH</requirement>
  
  </requirements>

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

  <!-- 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 \$QDNASEQ_PATH
  </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>
    
    <!-- ==================== -->

    <!-- ==================== -->
    
    <!-- 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" selected="true">100kb</option>
      <option value="30">30kb</option>
      <option value="15" selected="true">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>

    <!-- Input BAMs -->
    <!-- ==================== -->
    <param name="bams" type="data" multiple="true" optional="True" 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="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>
      </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" />

  <!-- ==================== -->
  <!-- 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
## -----

## -----
"${htmlFile}" -> outputHtml
"${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

  <!-- ==================== -->
  <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 -->

23:4943308e95fc

<tool id="QDNAseq" name="QDNAseq" version="1.0.0" force_history_refresh="True">
  
  <requirements>
    
    <requirement type="package" version="0.1.18">samtools</requirement>
    <!-- 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="1.2.2">qdnaseq</requirement> -->
    <requirement type="set_environment">QDNASEQ_PATH</requirement>
    
  </requirements>

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

  <!-- 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
    <!-- NOTE: dont forget to change to \$QDNASEQ_PATH after local testing -->
    /home/stef/data/galaxy/galaxy-dist/tools/QDNAseqNew/
  </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 finished too early, check log" />
  </stdio>
  
  <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="No whitespace characters allowed">^[^\s\\]+$</validator>
    </param>

    <!-- Bin Size: only certain sizes are supported by QDNAseq package -->
    <param name="binSizes" type="select" display="checkboxes" optional="false" multiple="true" label="Select bin-sizes to use (kb)" help="Larger bin sizes provide faster analysis but lower resolution. NOTE: BAM files are traversed again for each binsize, so selecting multiple bin-sizes takes extra analysis time!">
      <option value="bin1000kb">1Mb</option>
      <option value="bin100kb">100kb</option>
      <option value="bin30kb">30kb</option>
      <option value="bin15kb" selected="true">15kb</option>
      <option value="bin5kb">5kb</option>
      <option value="bin1kb">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>

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

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

    <!-- ==================== -->
    <!-- Optional calling step -->
    <!-- ==================== -->
    <param name="doCall" type="select" label="Also perform calling" help="Calling tries to determine a state for each segment (GAIN, LOSS, etc)">
      <option value="FALSE">no</option>
      <option value="TRUE">yes</option>
    </param>

    <!-- ==================== -->
    <!-- Optional hisotry output: copynumber TXT file -->
    <!-- ==================== -->
    <param name="txt2history" type="select" label="Also output copynumber TXT file to history">
      <option value="FALSE">no</option>
      <option value="TRUE">yes</option>
    </param>

    <!-- ==================== -->
    <!-- Optional history output: R object RDS file -->
    <!-- ==================== -->
    <param name="rds2history" type="select" label="Also output copynumber RDS files to history">
      <option value="FALSE">no</option>
      <option value="TRUE">yes</option>
    </param>

    <!-- ==================== -->
    <!-- Option to use your own bin annotations file -->
    <!-- ==================== -->
    <!-- NOT IN USE YET -->
    <!--
    <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="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="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>
      </when>

      <!-- need to set defaults because params are passed to R regardless of conditional opened/closed -->
      <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="plot_width" type="hidden" value="1440" />

  <!-- ==================== -->
  <!-- Config file to pass params to R script -->
  <!-- ==================== -->
  <configfiles>
    <configfile name="qdnaseq_cfg">
## Desc: this file is sourced in QDNAseq R wrapper script
##  as means to pass all galaxy params to R

## -----
## required params
## -----

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

list() -> historyOutputFiles

"${txt_1}" -> historyOutputFiles[[ 'txt_1' ]]
"${txt_5}" -> historyOutputFiles[[ 'txt_5' ]]
"${txt_15}" -> historyOutputFiles[[ 'txt_15' ]]
"${txt_30}" -> historyOutputFiles[[ 'txt_30' ]]
"${txt_100}" -> historyOutputFiles[[ 'txt_100' ]]
"${txt_1000}" -> historyOutputFiles[[ 'txt_1000' ]]

"${rds_1}" -> historyOutputFiles[[ 'rds_1' ]]
"${rds_5}" -> historyOutputFiles[[ 'rds_5' ]]
"${rds_15}" -> historyOutputFiles[[ 'rds_15' ]]
"${rds_30}" -> historyOutputFiles[[ 'rds_30' ]]
"${rds_100}" -> historyOutputFiles[[ 'rds_100' ]]
"${rds_1000}" -> historyOutputFiles[[ 'rds_1000' ]]


"${htmlFile.files_path}" -> outputPath
as.logical( "${doSegment}" ) -> doSegment
as.logical( "${doCall}" ) -> doCall
as.logical( "${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( "${txt2history}" ) -> txt2history
as.logical( "${rds2history}" ) -> rds2history

## -----
## plot options
## -----
as.integer( "${advanced.plot_width}" ) -> PLOT_WIDTH

  <!-- ==================== -->
  <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} report" />

    <!-- WHY does there seem to be no way to use split() within this code in galaxy!!! -->
    <!-- now have to fall back to using unique names within binSizes instead of just integers -->
    <!-- Problem with integers is that both "1" and "5" are also present in eg "15,100" -->
    <data format="tsv" name="txt_1000" label="QDNAseq: ${jobName} txt 1000kb">
      <filter>( "bin1000kb" in binSizes and txt2history == 'TRUE')</filter>
    </data>
    <data format="tsv" name="txt_100" label="QDNAseq: ${jobName} txt 100kb">
      <filter>("bin100kb" in binSizes and txt2history == 'TRUE')</filter>
    </data>
    <data format="tsv" name="txt_30" label="QDNAseq: ${jobName} txt 30kb">
      <filter>("bin30kb" in binSizes and txt2history == 'TRUE')</filter>
    </data>
    <data format="tsv" name="txt_15" label="QDNAseq: ${jobName} txt 15kb">
      <filter>("bin15kb" in binSizes and txt2history == 'TRUE')</filter>
    </data>
    <data format="tsv" name="txt_5" label="QDNAseq: ${jobName} txt 5kb">
      <filter>("bin5kb" in binSizes and txt2history == 'TRUE')</filter>
    </data>
    <data format="tsv" name="txt_1" label="QDNAseq: ${jobName} txt 1kb">
      <filter>("bin1kb" in binSizes and txt2history == 'TRUE')</filter>
    </data>

    <data format="rds" name="rds_1000" label="QDNAseq: ${jobName} rds 1000kb">
      <filter>( "bin1000kb" in binSizes and rds2history == 'TRUE')</filter>
    </data>
    <data format="rds" name="rds_100" label="QDNAseq: ${jobName} rds 100kb">
      <filter>( "bin100kb" in binSizes and rds2history == 'TRUE')</filter>
    </data>
    <data format="rds" name="rds_30" label="QDNAseq: ${jobName} rds 30kb">
      <filter>( "bin30kb" in binSizes and rds2history == 'TRUE')</filter>
    </data>
    <data format="rds" name="rds_15" label="QDNAseq: ${jobName} rds 15kb">
      <filter>( "bin15kb" in binSizes and rds2history == 'TRUE')</filter>
    </data>
    <data format="rds" name="rds_5" label="QDNAseq: ${jobName} rds 5kb">
      <filter>( "bin5kb" in binSizes and rds2history == 'TRUE')</filter>
    </data>
    <data format="rds" name="rds_1" label="QDNAseq: ${jobName} rds 1kb">
      <filter>( "bin1kb" in binSizes and rds2history == 'TRUE')</filter>
    </data>

  </outputs>

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