<tool id="sartools_deseq2" name="SARTools DESeq2" version="@TOOL_VERSION@+galaxy0">
    
    <description>Compare two or more biological conditions in a RNA-Seq framework with DESeq2</description>
    
    <macros>
        <import>macros.xml</import>
    </macros>
    
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    
    <command><![CDATA[
 
python '$__tool_directory__/abims_sartools_deseq2_wrapper.py'
## parameters
@COMMAND_BASIC_PARAMETERS@
@COMMAND_BATCH_PARAM@
--fitType '$advanced_parameters.fitType'
--cooksCutoff '$advanced_parameters.cooksCutoff'
--independentFiltering '$advanced_parameters.independentFiltering'
--alpha '$advanced_parameters.alpha'
--pAdjustMethod '$advanced_parameters.pAdjustMethod'
--typeTrans '$advanced_parameters.typeTrans'
--locfunc '$advanced_parameters.locfunc'
--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" />
            <param type="select" label="Mean-variance relationship" argument="--fitType" help="Type of model for the mean-dispersion relationship. Parametric by default." >
                <option value="parametric" selected="true">parametric</option>
                <option value="local">local</option>
                <option value="mean">mean</option>
            </param>
            <param type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Perform the outliers detection" argument="--cooksCutoff" help="Checked by default."/>
            <param type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Perform independent filtering" argument="--independentFiltering" help="Checked by default."/>
            <expand macro="alpha_param" />
            <expand macro="padjustmethod_param" />
            <param type="select" label="Transformation for PCA/clustering" argument="--typeTrans" help="Method of transformation of the counts for the clustering and the PCA: 'VST' (default) for Variance Stabilizing Transformation, or 'rlog' for Regularized Log Transformation." >
                <option value="VST" selected="true">VST</option>
                <option value="rlog">rlog</option>
            </param>
            <param type="select" label="Estimation of the size factors" argument="--locfunc" help="'median' (default) or 'shorth' from the genefilter package." >
                <option value="median" selected="true">median</option>
                <option value="shorth">shorth</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, 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    0.1                171" />
                    <has_text text="KO vs WT    2583   2663 5246" />
                    <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_DESeq2_targetT048_tables.html" lines_diff="14">
                <extra_files type="file" name="T4vsT0.complete.txt" value="SARTools_DESeq2_T4vsT0.complete.txt"/>
                <extra_files type="file" name="T8vsT0.complete.txt" value="SARTools_DESeq2_T8vsT0.complete.txt"/>
                <extra_files type="file" name="T8vsT4.complete.txt" value="SARTools_DESeq2_T8vsT4.complete.txt"/>
            </output>
        </test>
--> </tests>
    
    <help><![CDATA[

@HELP_AUTHORS@

===============
SARTools DESeq2
===============

-----------
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);
 * **fitType:** type of model for the mean-dispersion relationship ("parametric" by default, or "local");
 * **cooksCutoff:** TRUE (default) of FALSE to execute or not the detection of the outliers [4];
 * **independentFiltering:** TRUE (default) of FALSE to execute or not the independent filtering [5];
 * **pAdjustMethod:** p-value adjustment method for multiple testing [6, 7] ("BH" by default, "BY" or any value of p.adjust.methods);
 * **typeTrans:** method of transformation of the counts for the clustering and the PCA (default is "VST" for Variance Stabilizing Transformation, or "rlog" for Regularized Log Transformation);
 * **locfunc:** function used for the estimation of the size factors (default is "median", or "shorth" from the genefilter package);
 * **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] R.-D. Cook. Detection of Influential Observation in Linear Regression. Technometrics, February 1977.

[5] R. Bourgon, R. Gentleman, and W. Huber. Independent filtering increases detection power for high-throughput experiments. PNAS, 107(21):9546–9551, 2010. URL: http://www.pnas.org/content/107/21/9546.long.

[6] 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.

[7] 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" /> 
        <citation type="bibtex">@ARTICLE{Cook77,
            author = {R.-D. Cook},
            title = {Detection of Influential Observation in Linear Regression},
            journal = {Technometrics},
            year = {1977},
            month = {February}
        }</citation>
        <citation type="bibtex">@ARTICLE{Bourgon10,
            author = {R. Bourgon, R. Gentleman, and W. Huber},
            title = {Independent filtering increases detection power for high-throughput experiments},
            journal = {PNAS},
            year = {2010},
            volume = {107},
            number = {21},
            pages = {9546–9551},
            note = {URL: http://www.pnas.org/content/107/21/9546.long}
        }</citation>
    </citations>
    
</tool>