<?xml version="1.0"?>
<!--
# Copyright (C) 2017 INRA
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
-->
<tool id="FROGSSTAT_DESeq2_Preprocess" name="FROGSSTAT DESeq2 Preprocess" version="@TOOL_VERSION@+galaxy2">
  <description>import a Phyloseq object and prepare it for DESeq2 differential abundance analysis </description>

    <macros>
        <import>macros.xml</import>
    </macros>

    <expand macro="requirements_phyloseq">
        <requirement type="package" version="1.30.1">bioconductor-deseq2</requirement>
        <requirement type="package" version="1.6.6">r-optparse</requirement>
    </expand>

  <stdio>
      <exit_code range="1:" />
      <exit_code range=":-1" />
  </stdio>
	<command>deseq2_preprocess.py --data '$data'
                                #if $multiple.seconde
                                  --var '$var1${multiple.mod}${multiple.var2}'
                                #else
                                  --var '$var1'
                                #end if
                                --out-Rdata '$dds'
	</command>
    <inputs>
		  <!-- Files -->
      <param format="rdata" name="data" type="data" label="Phyloseq object (format rdata)" help="This is the result of FROGSSTAT Phyloseq Import Data with normalise option set to NO (DESeq2 is more powerful on unnormalised counts)." optional="false">
        <validator type="empty_field" message="This parameter is required." />
      </param>
      <!-- Parameters -->
		  <param name="var1" type="text" label="Experimental variable" help="The factor suspected to have an effect on OTUs' abundances. Ex: Treatment, etc." optional="false" value="" size="20">
        <validator type="empty_field" message="This parameter is required." />
      </param>
		  <conditional name="multiple">
        <param name="seconde" type="boolean" label="Do you want to correct for a confounding factor?" help="If yes, specifiy counfouding factor." optional="false" />
		    <when value="false"></when>
		    <when value="true">
          <param name="var2" type="text" label="Variable 2" help="Confounding factor. Ex: Gender, etc." optional="false" value="" size="20"/>
          <param name="mod" type="select" multiple="false" help="Choose an additive model (+) if the effects of Treatment and Gender are independent. Choose a model with interaction (*) if the effect of Treatment is expected to depend on Gender." label="Type of model">
            <option value="+" selected="true">Linear (+)</option>
            <option value="*">Interaction (*)</option>
          </param>
        </when>
      </conditional>
    </inputs>
    <outputs>
      <data format="rdata" name="dds" label="${tool.name}: dds.Rdata" from_work_dir="DESeq2_preprocess.Rdata"/>
    </outputs>
    <tests>
      <test>
         <param name="data" value="references/16-phylo_import.Rdata" />
         <param name="var1" value="EnvType"/>
         <output name="dds" file="references/23-deseq2_preprocess.Rdata" compare="sim_size" delta="50"/>
      </test>
    </tests>
    <help>

@HELP_LOGO@

.. class:: infomark page-header h2

What it does

Launch Rscript to compute differential abundance analysis using `DESeq2 &lt;https://bioconductor.org/packages/release/bioc/html/DESeq2.html&gt;`_ on a `Phyloseq &lt;https://joey711.github.io/phyloseq/&gt;`_ object.

.. class:: infomark page-header h2

Inputs/Outputs

.. class:: h3

Input

**phyloseq object** (format rdata):
A phyloseq object stored in a rdata file.
This file is the result of FROGSSTAT Phyloseq Import Data.

.. class:: warningmark

We need unnormalised data to analyse the abundance differencies.

.. class:: h3

Ouput

**dds object** (format rdata):
A DESeq2 dataset (dds) stored in rdata file.
This result will be one of the input of the FROGSSTAT DESeq Visualisation tool.

.. class:: infomark page-header h2

How it works

The DESeq function performs a default analysis through the steps:

       1. estimation of size factors: ‘estimateSizeFactors’

       2. estimation of dispersion: ‘estimateDispersions’

       3. Negative Binomial GLM fitting and Wald statistics:
          ‘nbinomWaldTest’

You must precise at least on variable on which the differential abundances will be compared.

You may precise a confounding factor, by adding an other variable and precise the relation between the two variables:

- + for independant variables
- * for interacting variables

@HELP_CONTACT@

  </help>

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