annotate abims_anova.xml @ 11:102049093b7d draft default tip

planemo upload for repository https://github.com/workflow4metabolomics/anova commit 4922313a0e9569326b7723c41babb89f998dbfd9

<tool id="abims_anova" name="Anova" version="1.2.1">

    <description>N-way anova. With ou Without interactions</description>

    <requirements>
	<requirement type="package" version="1.1_4">r-batch</requirement>
	<requirement type="package" version="1.2">r-venn</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:" level="fatal" />
    </stdio>

    <command>
Rscript $__tool_directory__/abims_anova.r file '$input' sampleinfo '$sampleinfo' varinfo '$varinfo' mode '$mode'
condition "c('$condition_1'
#for $i, $s in enumerate( $conditions )
,'${s.condition}'
#end for
)"
interaction $interaction
method $method
threshold $threshold
selection_method $selection_method
sep '$sep'
dec '$dec'
outputdatapvalue '$varMetaPValue'
outputdatasignif '$dataSignif'
    </command>

    <inputs>
        <param name="input" type="data" label="Data Matrix file" format="tabular,csv" help="Matrix of numeric data with headers." />
        <param name="sampleinfo" type="data" label="Sample Metadata file" format="tabular" help="Tabular file with the data metadata : one sample per line and at least two columns : ids and one condition" />
        <param name="varinfo" type="data" label="Variable Metadata file" format="tabular" help="Tabular file with information about your tested variables. Only used to aggregate generated information." />

        <param name="mode" type="select" help="Perform the anova tests on column/row; for W4M 3-tables format, use 'row'." format="text" optional="true">
            <label>Mode</label>
            <option value="row" selected="True">row</option>
            <option value="column">column</option>
        </param>

        <param name="condition_1" type="text" label="Condition" value="" help="The column name of the condition. ex: hour or treatment" optional="false" />
        <repeat name="conditions" title="Conditions for N-ways anova">
            <param name="condition" type="text" label="Condition" value="" help="The column name of the condition. ex: hour or treatment" />
        </repeat>

        <param name="interaction" type="boolean" label="Enable interaction response p-values" truevalue="T" falsevalue="F" help="Used if more than 1 conditon. The anova will produse p-value according to the interaction between your condition (ex: condition1:conditions2, condition1:conditions3, condition2:conditions3 and condition1:condition2:conditions3)" />

        <param name="method" type="select" help="Method used to apply a correction on the pvalue because of the number of test" >
            <label>PValue adjusted method</label>
            <option value="BH">BH</option>
            <option value="holm">holm</option>
            <option value="bonferroni">bonferroni</option>
            <option value="hochberg">hochberg</option>
            <option value="hommel">hommel</option>
            <option value="BY">BY</option>
            <option value="fdr">fdr</option>
            <option value="none" selected="True">none</option>
        </param>

        <param name="threshold" type="float" label="Threshold" value="0.01" help="max adjusted p.value accepted" />

        <param name="selection_method" type="select" help="Intersection: all condition p-value must be under the threshold. Union: at least condition p-value must be under the threshold. ">
            <label>Selection method</label>
            <option value="intersection" selected="true">intersection / strong</option>
            <option value="union">union / weak</option>
        </param>

        <param name="sep" type="select" format="text">
            <label>Separator of columns</label>
            <option value="tabulation">tabulation</option>
            <option value="semicolon">;</option>
            <option value="comma">,</option>
        </param>

        <param name="dec" type="text" label="Decimal separator" value="." help="" />

    </inputs>

    <outputs>
        <data name="varMetaPValue" format_source="varinfo" label="${varinfo.name}_anova_pvalue.${varinfo.ext}"/>
        <data name="dataSignif" format="pdf" label="${input.name}_anova_signif"/>
    </outputs>

    <tests>
        <test>
            <param name="input" value="dataMatrix.tsv"/>
            <param name="sampleinfo" value="sampleMetadata.tsv"/>
            <param name="varinfo" value="variableMetadata.tsv"/>
            <param name="mode" value="row"/>
            <param name="condition_1" value="age"/>
            <param name="conditions_0|condition" value="gender"/>
            <param name="interaction" value="F"/>
            <param name="method" value="BH"/>
            <param name="threshold" value="0.05"/>
            <param name="selection_method" value="union"/>
            <param name="sep" value="tabulation"/>
            <param name="dev" value="."/>
            <output name="varMetaPValue" file="variableMetadata.tsv_anova_pvalue.tabular" />
            <output name="dataSignif" file="dataMatrix.tsv_anova_signif.pdf" compare="sim_size" delta="600" />
        </test>
    </tests>

    <help>

.. class:: infomark

**Authors** Gildas Le Corguille  ABiMS - UPMC/CNRS - Station Biologique de Roscoff - gildas.lecorguille|at|sb-roscoff.fr
Melanie Petera - PFEM ; INRA ; MetaboHUB

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

=====
Anova
=====

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

Analysis of variance (ANOVA) is used to analyze the differences between group means and their associated procedures,
in which the observed variance in a particular variable is partitioned into components attributable to different sources of variation.

**Note about sum of squares (SS) calculation of N-way ANOVA in this module.**
This module use R function *manova()* (and thus R function *aov()*) to establish N-way ANOVA. 
Therefore calculated sum of squares are sequential ones (sometimes called "Type I SS"). 
If your design is unbalanced, this may not correspond to the type of hypothesis being of interest. 
Note that you can obtain adjusted sums of squares ("Type II SS") by running several times this module with different orders in factors. 


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

+----------------------------+------------+
| Parameter : num + label    |   Format   |
+============================+============+
| 1 : Data Matrix file       | Tabular    |
+----------------------------+------------+
| 2 : Sample Metadata file   | Tabular    |
+----------------------------+------------+
| 3 : Variable Metadata file | Tabular    |
+----------------------------+------------+


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



***.anova_pvalue.tabular**

    | Your variable metadata file completed with columns of p-values, result of selection method and means of subgroups.

***.anova_signif.pdf**

    | A pdf file containing a Venn diagram and boxplots of significant variables.


------

.. class:: infomark

The outputs ***.anova_filtered.tabular** is a tabular file. You can continue your analysis using it in the following tools:

    | Generic_filter
    | Hierarchical Clustering



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



    </help>

    <citations>
        <citation type="bibtex">@ARTICLE{fisher,
           author = {Ronald A. Fisher},
           title = {The Correlation between Relatives on the Supposition of Mendelian Inheritance},
           journal = {Philosophical Transactions of the Royal Society of Edinburgh},
           year = {1918},
           volume = {52},
           pages = {399-433}
        }</citation>
    </citations>

</tool>