view abims_sartools_edger.xml @ 4:05c9b1a7f44e draft default tip

Uploaded new release 1.7.3

<tool id="sartools_edger" name="SARTools edgeR" version="@TOOL_VERSION@+galaxy0">
    
    <description>Compare two or more biological conditions in a RNA-Seq framework with edgeR</description>
    
    <macros>
        <import>macros.xml</import>
    </macros>
    
    <expand macro="requirements"/>
    <expand macro="stdio"/>

    
    <command><![CDATA[
 
python '$__tool_directory__/abims_sartools_edger_wrapper.py'
## parameters
@COMMAND_BASIC_PARAMETERS@
@COMMAND_BATCH_PARAM@
--alpha '$advanced_parameters.alpha'
--pAdjustMethod '$advanced_parameters.pAdjustMethod'
--cpmCutoff '$advanced_parameters.cpmCutoff'
--geneSelection '$advanced_parameters.geneSelection'
--normalizationMethod '$advanced_parameters.normalizationMethod'
--colors "'$advanced_parameters.colors'"
--forceCairoGraph '$advanced_parameters.forceCairoGraph'
## ouputs
@COMMAND_OUTPUTS@
        
    ]]></command>
    
    <inputs>
        
        <expand macro="basic_parameters" />
 
        <section name="advanced_parameters" title="Advanced Parameters" expanded="false" >
            <expand macro="batch_param" />
            <expand macro="alpha_param" />
            <expand macro="padjustmethod_param" />
            <param type="integer" value="1" min="0" label="Counts-per-million cut-off to filter low counts" argument="--cpmCutoff" help="Set to 0 to disable filtering. Default is 1." />
            <param name="geneSelection" type="select" label="Selection of the features in MDSPlot" argument="--gene.selection" help="Default is 'pairwise'." >
                <option value="pairwise" selected="true">pairwise</option>
                <option value="common">common</option>
            </param>
            <param type="select" label="Normalization method in calcNormFactors" argument="--normalizationMethod" help="'TMM' (default), 'RLE' (DESeq method) or 'upperquartile'." >
                <option value="TMM" selected="true">TMM</option>
                <option value="RLE">RLE</option>
                <option value="upperquartile">upperquartile</option>
            </param>
            <expand macro="colors_param" />
            <expand macro="forceCairoGraph_param" />
        </section>

    </inputs>
    
    <outputs>
        
        <expand macro="outputs" /> 
              
    </outputs>
    
    <tests>
        <test>
     <!-- Test with 2 conditions, 2 replicates, 10 features -->
            <param name="targetFile" dbkey="?" value="target_small.txt" />
            <param name="rawDir" value="raw_small.zip" dbkey="?" ftype="zip"/>
            <output name="log">
                <assert_contents>
                    <has_text text="KO vs WT    5      4    9" />
                    <has_text text="HTML report created" />
                </assert_contents>
            </output>
        </test>
<!--    <test>
-->        <!-- NOT WORKING YET: Test with 3 conditions, 3 replicates, 10 features, with batch effect -->
<!--        <param name="targetFile" dbkey="?" value="targetT048_small.txt" />
            <param name="rawDir"   value="rawT048_small.zip" dbkey="?" ftype="no_unzip.zip"/>
            <param name="condRef" value="T0"/>
            <param name="condition" value="true"/>
            <output name="tables_html" file="SARTools_edgeR_targetT048_small_tables.html" lines_diff="12">
                <extra_files type="file" name="T4vsT0.complete.txt" value="SARTools_edgeR_T4vsT0_small.complete.txt"/>
                <extra_files type="file" name="T8vsT0.complete.txt" value="SARTools_edgeR_T8vsT0_small.complete.txt"/>
                <extra_files type="file" name="T8vsT4.complete.txt" value="SARTools_edgeR_T8vsT4_small.complete.txt"/>
            </output>
        </test>
-->     <test>
        <!-- Test with 2 conditions, 2 replicates, 8217 features -->
            <param name="targetFile" dbkey="?" value="target.txt" />
            <param name="rawDir"   value="raw.zip" dbkey="?" ftype="zip"/>
            <output name="log">
                <assert_contents>
                    <has_text text="KO vs WT    2691   2713 5404" />
                    <has_text text="HTML report created" />
                </assert_contents>
            </output>
        </test>
<!--    <test>
-->        <!-- NOT WORKING YET: Test with 3 conditions, 3 replicates, 10160 features, with batch effect -->
<!--        <param name="targetFile" dbkey="?" value="targetT048.txt" />
            <param name="rawDir"   value="rawT048.zip" dbkey="?" ftype="no_unzip.zip"/>
            <param name="condRef" value="T0"/>
            <param name="condition" value="true"/>
            <output name="tables_html" file="SARTools_edgeR_targetT048_tables.html" lines_diff="14">
                <extra_files type="file" name="T4vsT0.complete.txt" value="SARTools_edgeR_T4vsT0.complete.txt"/>
                <extra_files type="file" name="T8vsT0.complete.txt" value="SARTools_edgeR_T8vsT0.complete.txt"/>
                <extra_files type="file" name="T8vsT4.complete.txt" value="SARTools_edgeR_T8vsT4.complete.txt"/>
            </output>
        </test>
--> </tests>
    
    <help><![CDATA[

@HELP_AUTHORS@

==============
SARTools edgeR
==============

-----------
Description
-----------

@HELP_DESCRIPTION@


-----------
Input files
-----------

@HELP_INPUT_FILES@


----------
Parameters
----------

 @HELP_BASIC_PARAMETERS@
 * **batch:** adjustment variable to use as a batch effect, must be a column of the target file (NULL if no batch effect needs to be taken into account);
 * **alpha:** significance threshold applied to the adjusted p-values to select the differentially expressed features (default is 0.05);
 * **pAdjustMethod:** p-value adjustment method for multiple testing [4, 5] ("BH" by default, "BY" or any value of p.adjust.methods);
 * **cpmCutoff:** counts-per-million cut-off to filter low counts (default is 1, set to 0 to disable filtering);
 * **gene.selection:** method of selection of the features for the MultiDimensional Scaling plot ("pairwise" by default or common);
 * **normalizationMethod:** normalization method in calcNormFactors(): "TMM" (default), "RLE" (DESeq method) or "upperquartile";
 * **colors:** colors used for the figures (one per biological condition), 8 are given by default.
 * **forceCairoGraph:** TRUE or FALSE (default) to force the use of cairo with options(bitmapType="cairo").


------------
Output files
------------

@HELP_OUTPUT_FILES@

  
---------------------------------------------------

[1] G.-K. Smyth. Limma: linear models for microarray data. In R. Gentleman, V. Carey, S. Dudoit, R. Irizarry, and W. Huber, editors, Bioinformatics and Computational Biology Solutions Using R and Bioconductor, pages 397–420. Springer, New York, 2005.

[2] S. Anders. HTSeq: Analysing high-throughput sequencing data with Python. http://www-huber.embl.de/users/anders/HTSeq/, 2011.

[3] S. Anders, P.-T. Pyl, and W. Huber. HTSeq - A Python framework to work with high-throughput sequencing data. bioRxiv preprint, 2014. URL: http://dx.doi.org/10.1101/002824.

[4] Y. Benjamini and Y. Hochberg. Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal Statistical Society B, 57:289–300, 1995.

[5] Y. Benjamini and D. Yekutieli. The control of the false discovery rate in multiple testing under dependency. Ann. Statist., 29(4):1165–1188, 2001.


    ]]></help>

   <citations>
        <expand macro="common_citations" /> 
   </citations>
    
</tool>