comparison rgedgeRpaired_nocamera.xml @ 143:1435811cbf01 draft

Uploaded

142:e7894f37320a

<tool id="rgdifferentialcount" name="Differential_Count" version="0.28">
  <description>models using BioConductor packages</description>
  <requirements>
      <requirement type="package" version="3.1.2">R</requirement>
      <requirement type="package" version="1.3.18">graphicsmagick</requirement>
      <requirement type="package" version="9.10">ghostscript</requirement> 
      <requirement type="package" version="2.14">biocbasics</requirement>
  </requirements>
  
  <command interpreter="python">
     rgToolFactory.py --script_path "$runme" --interpreter "Rscript" --tool_name "Differential_Counts" 
    --output_dir "$html_file.files_path" --output_html "$html_file" --make_HTML "yes"
  </command>
  <inputs>
    <param name="input1"  type="data" format="tabular" label="Select an input matrix - rows are contigs, columns are counts for each sample"
       help="Use the HTSeq based count matrix preparation tool to create these matrices from BAM/SAM files and a GTF file of genomic features"/>
    <param name="title" type="text" value="Differential Counts" size="80" label="Title for job outputs" 
           help="Supply a meaningful name here to remind you what the outputs contain">
      <sanitizer invalid_char="">
        <valid initial="string.letters,string.digits"><add value="_" /> </valid>
      </sanitizer>
    </param>
    <param name="treatment_name" type="text" value="Treatment" size="50" label="Treatment Name"/>
    <param name="Treat_cols" label="Select columns containing treatment." type="data_column" data_ref="input1" numerical="True" 
         multiple="true" use_header_names="true" size="120" display="checkboxes"  force_select="True">
        <validator type="no_options" message="Please select at least one column."/>
    </param>
    <param name="control_name" type="text" value="Control" size="50" label="Control Name"/>
    <param name="Control_cols" label="Select columns containing control." type="data_column" data_ref="input1" numerical="True" 
         multiple="true" use_header_names="true" size="120" display="checkboxes"  force_select="True">
    </param>
    <param name="subjectids" type="text" optional="true" size="120" value = ""
       label="IF SUBJECTS NOT ALL INDEPENDENT! Enter comma separated strings to indicate sample labels for (eg) pairing - must be one for every column in input"
       help="Leave blank if no pairing, but eg if data from sample id A99 is in columns 2,4 and id C21 is in 3,5 then enter 'A99,C21,A99,C21'">
      <sanitizer>
        <valid initial="string.letters,string.digits"><add value="," /> </valid>
      </sanitizer>
    </param>
    <param name="fQ" type="float" value="0.3" size="5" label="Non-differential contig count quantile threshold - zero to analyze all non-zero read count contigs"
     help="May be a good or a bad idea depending on the biology and the question. EG 0.3 = sparsest 30% of contigs with at least one read are removed before analysis"/>
    <param name="useNDF" type="boolean" truevalue="T" falsevalue="F" checked="false" size="1" 
              label="Non differential filter - remove contigs below a threshold (1 per million) for half or more samples"
     help="May be a good or a bad idea depending on the biology and the question. This was the old default. Quantile based is available as an alternative"/>

    <conditional name="edgeR">
        <param name="doedgeR" type="select" 
           label="Run this model using edgeR"
           help="edgeR uses a negative binomial model and seems to be powerful, even with few replicates">
          <option value="F">Do not run edgeR</option>
          <option value="T" selected="true">Run edgeR</option>
         </param>
         <when value="T">
          <param name="edgeR_priordf" type="integer" value="10" size="3" 
           label="prior.df for tagwise dispersion - larger value = more squeezing of tag dispersions to common dispersion. Replaces prior.n  and prior.df = prior.n * residual.df"
           help="10 = edgeR default. Use a larger value to 'smooth' small samples. See edgeR docs and note below"/>
          <param name="edgeR_robust_method" type="select" value="20" size="3" 
           label="Use robust dispersion method"
           help="Use ordinary, anscombe or deviance robust deviance estimates">
             <option value="ordinary" selected="true">Use ordinary deviance estimates</option>
             <option value="deviance">Use robust deviance estimates</option>
             <option value="anscombe">use Anscombe robust deviance estimates</option>
          </param>
         </when>
         <when value="F"></when>
    </conditional>
    <conditional name="DESeq2">
    <param name="doDESeq2" type="select" 
       label="Run the same model with DESeq2 and compare findings"
       help="DESeq2 is an update to the DESeq package. It uses different assumptions and methods to edgeR">
      <option value="F" selected="true">Do not run DESeq2</option>
      <option value="T">Run DESeq2</option>
     </param>
     <when value="T">
         <param name="DESeq_fitType" type="select">
            <option value="parametric" selected="true">Parametric (default) fit for dispersions</option>
            <option value="local">Local fit - this will automagically be used if parametric fit fails</option>
            <option value="mean">Mean dispersion fit- use this if you really understand what you're doing - read the fine manual linked below in the documentation</option>
         </param> 
     </when>
     <when value="F"> </when>
    </conditional>
    <param name="doVoom" type="select" 
       label="Run the same model with Voom/limma and compare findings"
       help="Voom uses counts per million and a precise transformation of variance so count data can be analysed using limma">
      <option value="F" selected="true">Do not run VOOM</option>
      <option value="T">Run VOOM</option>
     </param>
    <param name="fdrthresh" type="float" value="0.05" size="5" label="P value threshold for FDR filtering for amily wise error rate control"
     help="Conventional default value of 0.05 recommended"/>
    <param name="fdrtype" type="select" label="FDR (Type II error) control method" 
         help="Use fdr or bh typically to control for the number of tests in a reliable way">
            <option value="fdr" selected="true">fdr</option>
            <option value="BH">Benjamini Hochberg</option>
            <option value="BY">Benjamini Yukateli</option>
            <option value="bonferroni">Bonferroni</option>
            <option value="hochberg">Hochberg</option>
            <option value="holm">Holm</option>
            <option value="hommel">Hommel</option>
            <option value="none">no control for multiple tests</option>
    </param>
  </inputs>
  <outputs>
    <data format="tabular" name="out_edgeR" label="${title}_topTable_edgeR.xls">
         <filter>edgeR['doedgeR'] == "T"</filter>
    </data>
    <data format="tabular" name="out_DESeq2" label="${title}_topTable_DESeq2.xls">
         <filter>DESeq2['doDESeq2'] == "T"</filter>
    </data>
    <data format="tabular" name="out_VOOM" label="${title}_topTable_VOOM.xls">
         <filter>doVoom == "T"</filter>
    </data>
    <data format="html" name="html_file" label="${title}.html"/>
  </outputs>
 <stdio>
     <exit_code range="4"   level="fatal"   description="Number of subject ids must match total number of samples in the input matrix" />
 </stdio>
 <tests>
<test>
<param name='input1' value='test_bams2mx.xls' ftype='tabular' />
 <param name='treatment_name' value='liver' />
 <param name='title' value='edgeRtest' />
 <param name='useNDF' value='' />
 <param name='doedgeR' value='T' />
 <param name='doVoom' value='T' />
 <param name='doDESeq2' value='T' />
 <param name='fdrtype' value='fdr' />
 <param name='edgeR_priordf' value="8" />
 <param name='edgeR_robust' value="ordinary" />
 <param name='fdrthresh' value="0.05" />
 <param name='control_name' value='heart' />
 <param name='subjectids' value='' />
 <param name='Control_cols' value='3,4,5,9' />
 <param name='Treat_cols' value='2,6,7,8' />
 <output name='out_edgeR' file='edgeRtest1out.xls' compare='diff' lines_diff='20' />
 <output name='html_file' file='edgeRtest1out.html'  compare='diff' lines_diff='20' />
</test>
</tests>

<configfiles>
<configfile name="runme">
<![CDATA[
# 
# edgeR.Rscript
# updated feb 2014 adding outlier-robust deviance estimate options by ross for R 3.0.2/bioc 2.13
# updated npv 2011 for R 2.14.0 and edgeR 2.4.0 by ross
# Performs DGE on a count table containing n replicates of two conditions

sessionInfo()

sink()
]]>
</configfile>
</configfiles>
<help>

**What it does**

Allows short read sequence counts from controlled experiments to be analysed for differentially expressed genes.
Optionally adds a term for subject if not all samples are independent or if some other factor needs to be blocked in the design.

.. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
.. _DESeq2: http://www.bioconductor.org/packages/release/bioc/html/DESeq2.html
.. _limma_VOOM: http://www.bioconductor.org/packages/release/bioc/html/limma.html
.. _Galaxy: http://getgalaxy.org
</help>
<citations>
    <citation type="doi">doi: 10.1093/bioinformatics/btp616</citation>
</citations>

</tool>

143:1435811cbf01

<?xml version="1.0"?>
<tool id="rgdifferentialcount" name="Differential_Count" version="0.28">
  <description>models using BioConductor packages</description>
  <requirements>
    <requirement type="package" version="3.1.2">R</requirement>
    <requirement type="package" version="1.3.18">graphicsmagick</requirement>
    <requirement type="package" version="9.10">ghostscript</requirement>
    <requirement type="package" version="2.14">biocbasics</requirement>
  </requirements>
  <command interpreter="python">
     rgToolFactory.py --script_path "$runme" --interpreter "Rscript" --tool_name "Differential_Counts" 
    --output_dir "$html_file.files_path" --output_html "$html_file" --make_HTML "yes"
  </command>
  <inputs>
    <param name="input1" type="data" format="tabular" label="Select an input matrix - rows are contigs, columns are counts for each sample" help="Use the HTSeq based count matrix preparation tool to create these matrices from BAM/SAM files and a GTF file of genomic features"/>
    <param name="title" type="text" value="Differential Counts" size="80" label="Title for job outputs" help="Supply a meaningful name here to remind you what the outputs contain">
      <sanitizer invalid_char="">
        <valid initial="string.letters,string.digits">
          <add value="_"/>
        </valid>
      </sanitizer>
    </param>
    <param name="treatment_name" type="text" value="Treatment" size="50" label="Treatment Name"/>
    <param name="Treat_cols" label="Select columns containing treatment." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
      <validator type="no_options" message="Please select at least one column."/>
    </param>
    <param name="control_name" type="text" value="Control" size="50" label="Control Name"/>
    <param name="Control_cols" label="Select columns containing control." type="data_column" data_ref="input1" numerical="True" multiple="true" use_header_names="true" size="120" display="checkboxes" force_select="True">
    </param>
    <param name="subjectids" type="text" optional="true" size="120" value="" label="IF SUBJECTS NOT ALL INDEPENDENT! Enter comma separated strings to indicate sample labels for (eg) pairing - must be one for every column in input" help="Leave blank if no pairing, but eg if data from sample id A99 is in columns 2,4 and id C21 is in 3,5 then enter 'A99,C21,A99,C21'">
      <sanitizer>
        <valid initial="string.letters,string.digits">
          <add value=","/>
        </valid>
      </sanitizer>
    </param>
    <param name="fQ" type="float" value="0.3" size="5" label="Non-differential contig count quantile threshold - zero to analyze all non-zero read count contigs" help="May be a good or a bad idea depending on the biology and the question. EG 0.3 = sparsest 30% of contigs with at least one read are removed before analysis"/>
    <param name="useNDF" type="boolean" truevalue="T" falsevalue="F" checked="false" size="1" label="Non differential filter - remove contigs below a threshold (1 per million) for half or more samples" help="May be a good or a bad idea depending on the biology and the question. This was the old default. Quantile based is available as an alternative"/>
    <conditional name="edgeR">
      <param name="doedgeR" type="select" label="Run this model using edgeR" help="edgeR uses a negative binomial model and seems to be powerful, even with few replicates">
        <option value="F">Do not run edgeR</option>
        <option value="T" selected="true">Run edgeR</option>
      </param>
      <when value="T">
        <param name="edgeR_priordf" type="integer" value="10" size="3" label="prior.df for tagwise dispersion - larger value = more squeezing of tag dispersions to common dispersion. Replaces prior.n  and prior.df = prior.n * residual.df" help="10 = edgeR default. Use a larger value to 'smooth' small samples. See edgeR docs and note below"/>
        <param name="edgeR_robust_method" type="select" value="20" size="3" label="Use robust dispersion method" help="Use ordinary, anscombe or deviance robust deviance estimates">
          <option value="ordinary" selected="true">Use ordinary deviance estimates</option>
          <option value="deviance">Use robust deviance estimates</option>
          <option value="anscombe">use Anscombe robust deviance estimates</option>
        </param>
      </when>
      <when value="F"/>
    </conditional>
    <conditional name="DESeq2">
      <param name="doDESeq2" type="select" label="Run the same model with DESeq2 and compare findings" help="DESeq2 is an update to the DESeq package. It uses different assumptions and methods to edgeR">
        <option value="F" selected="true">Do not run DESeq2</option>
        <option value="T">Run DESeq2</option>
      </param>
      <when value="T">
        <param name="DESeq_fitType" type="select">
          <option value="parametric" selected="true">Parametric (default) fit for dispersions</option>
          <option value="local">Local fit - this will automagically be used if parametric fit fails</option>
          <option value="mean">Mean dispersion fit- use this if you really understand what you're doing - read the fine manual linked below in the documentation</option>
        </param>
      </when>
      <when value="F"> </when>
    </conditional>
    <param name="doVoom" type="select" label="Run the same model with Voom/limma and compare findings" help="Voom uses counts per million and a precise transformation of variance so count data can be analysed using limma">
      <option value="F" selected="true">Do not run VOOM</option>
      <option value="T">Run VOOM</option>
    </param>
    <param name="fdrthresh" type="float" value="0.05" size="5" label="P value threshold for FDR filtering for amily wise error rate control" help="Conventional default value of 0.05 recommended"/>
    <param name="fdrtype" type="select" label="FDR (Type II error) control method" help="Use fdr or bh typically to control for the number of tests in a reliable way">
      <option value="fdr" selected="true">fdr</option>
      <option value="BH">Benjamini Hochberg</option>
      <option value="BY">Benjamini Yukateli</option>
      <option value="bonferroni">Bonferroni</option>
      <option value="hochberg">Hochberg</option>
      <option value="holm">Holm</option>
      <option value="hommel">Hommel</option>
      <option value="none">no control for multiple tests</option>
    </param>
  </inputs>
  <outputs>
    <data format="tabular" name="out_edgeR" label="${title}_topTable_edgeR.xls">
      <filter>edgeR['doedgeR'] == "T"</filter>
    </data>
    <data format="tabular" name="out_DESeq2" label="${title}_topTable_DESeq2.xls">
      <filter>DESeq2['doDESeq2'] == "T"</filter>
    </data>
    <data format="tabular" name="out_VOOM" label="${title}_topTable_VOOM.xls">
      <filter>doVoom == "T"</filter>
    </data>
    <data format="html" name="html_file" label="${title}.html"/>
  </outputs>
  <stdio>
    <exit_code range="4" level="fatal" description="Number of subject ids must match total number of samples in the input matrix"/>
  </stdio>
  <tests>
    <test>
      <param name="input1" value="test_bams2mx.xls" ftype="tabular"/>
      <param name="treatment_name" value="liver"/>
      <param name="title" value="edgeRtest"/>
      <param name="useNDF" value=""/>
      <param name="doedgeR" value="T"/>
      <param name="doVoom" value="T"/>
      <param name="doDESeq2" value="T"/>
      <param name="fdrtype" value="fdr"/>
      <param name="edgeR_priordf" value="8"/>
      <param name="edgeR_robust" value="ordinary"/>
      <param name="fdrthresh" value="0.05"/>
      <param name="control_name" value="heart"/>
      <param name="subjectids" value=""/>
      <param name="Control_cols" value="3,4,5,9"/>
      <param name="Treat_cols" value="2,6,7,8"/>
      <output name="out_edgeR" file="edgeRtest1out.xls" compare="diff" lines_diff="20"/>
      <output name="html_file" file="edgeRtest1out.html" compare="diff" lines_diff="20"/>
    </test>
  </tests>
  <configfiles>
    <configfile name="runme"><![CDATA[
# 
# edgeR.Rscript
# updated feb 2014 adding outlier-robust deviance estimate options by ross for R 3.0.2/bioc 2.13
# updated npv 2011 for R 2.14.0 and edgeR 2.4.0 by ross
# Performs DGE on a count table containing n replicates of two conditions

sessionInfo()

sink()
]]>
</configfile>
  </configfiles>
  <help>

**What it does**

Allows short read sequence counts from controlled experiments to be analysed for differentially expressed genes.
Optionally adds a term for subject if not all samples are independent or if some other factor needs to be blocked in the design.

.. _edgeR: http://www.bioconductor.org/packages/release/bioc/html/edgeR.html
.. _DESeq2: http://www.bioconductor.org/packages/release/bioc/html/DESeq2.html
.. _limma_VOOM: http://www.bioconductor.org/packages/release/bioc/html/limma.html
.. _Galaxy: http://getgalaxy.org
</help>
  <citations>
    <citation type="doi">doi: 10.1093/bioinformatics/btp616</citation>
  </citations>
</tool>