<?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_Phyloseq_Composition_Visualisation" name="FROGSSTAT Phyloseq Composition Visualisation" version="@TOOL_VERSION@+galaxy2">
    <description>with bar plot and composition plot</description>

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

    <expand macro="requirements_phyloseq" >
        <requirement type="package" version="4.9.3">r-plotly</requirement>
    </expand>

    <stdio>
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>
    <command>phyloseq_composition.py
                          --rdata '$data'
                          --varExp '$varExp'
                          --taxaRank1 '$taxaRank1'
                          --taxaSet1 '$taxaSet1'
                          --taxaRank2 '$taxaRank2'
                          --numberOfTaxa $numberOfTaxa
                          --html '$html'
    </command>
    <inputs>
        <!-- Files -->
        <param format="rdata" name="data" type="data" label="Phyloseq object (format rdata)" help="This is the result of FROGS Phyloseq Import Data tool." optional="false">
            <validator type="empty_field" message="This parameter is required." />
        </param>
        <!-- Parameters -->
        <param name="varExp" type="text" label="Grouping variable" help="Experimental variable used to group samples (Treatment, Host type, etc)." optional="false" value="" size="20">
            <validator type="empty_field" message="This parameter is required." />
        </param>
        <param name="taxaRank1" type="text" label="Taxonomic level to filter your data" help="ex: Kingdom, Phylum, Class, Order, Family, Genus, Species" value="Kingdom"  size="20">
            <validator type="empty_field" message="This parameter is required." />
        </param>
        <param name="taxaSet1" type="text" label="Taxa (at the above taxonomic level) to keep in the dataset" help="ex: Bacteria (when filtering at the Kingdom level), Firmicutes (when filtering at the Phylum level). Multiple taxa (separated by a space) can be specified, i.e. Firmicutes Proteobacteria" value="Bacteria" size="20">
            <validator type="empty_field" message="This parameter is required." />
        </param>
        <param name="taxaRank2" type="text" label="Taxonomic level used for aggregation" help="ex: Family (when filtering at the Phylum level). The aggregation level must be below the filtering level." value="Phylum" size="20">
            <validator type="empty_field" message="This parameter is required." />
        </param>
        <param name="numberOfTaxa" type="integer" label="Number of most abundant taxa to keep" help="ex: 9, i.e. Tool keeps the 9 most abundant taxa and the remaining taxa are aggregated in a group 'Other'" value="9" >
            <validator type="empty_field" message="This parameter is required." />
        </param>
    </inputs>
    <outputs>
        <data format="html" name="html" label="${tool.name}: composition.nb.html" from_work_dir="composition.nb.html"/>
    </outputs>
    <tests>
        <test>
            <param name="data" value="references/16-phylo_import.Rdata" />
            <param name="varExp" value="EnvType" />
            <param name="taxaRank1" value="Kingdom" />
            <param name="taxaSet1" value="Bacteria" />
            <param name="taxaRank2" value="Phylum" />
            <param name="numberOfTaxa" value="9" />
            <output name="html">
                <assert_contents>
                    <!-- "<br />" is replaced by ".*" -->
                    <has_text_matching expression="Phylum: Actinobacteria.*Sample: BHT0.LOT07.*Abundance: 0.3806484555" />
                    <has_text_matching expression="Phylum: Bacteroidetes.*Sample: BHT0.LOT07.*Abundance: 0.0026380734" />
                    <has_text_matching expression="Phylum: Cyanobacteria.*Sample: BHT0.LOT07.*Abundance: 0.0000000000" />
                    <has_text_matching expression="Phylum: Firmicutes.*Sample: BHT0.LOT07.*Abundance: 0.6024168156" />
                    <has_text_matching expression="Phylum: Fusobacteria.*Sample: BHT0.LOT07.*Abundance: 0.0002552974" />
                    <has_text_matching expression="Phylum: Proteobacteria.*Sample: BHT0.LOT07.*Abundance: 0.0137860608" />
                    <has_text_matching expression="Phylum: Spirochaetes.*Sample: BHT0.LOT07.*Abundance: 0.0000000000" />
                    <has_text_matching expression="Phylum: Tenericutes.*Sample: BHT0.LOT07.*Abundance: 0.0002552974" />
                    <has_text_matching expression="Phylum: Other.*Sample: BHT0.LOT07.*Abundance: 0.0000000000" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
        
@HELP_LOGO@

.. class:: infomark page-header h2

What it does

Using `phyloseq &lt;https://joey711.github.io/phyloseq/&gt;`_ and custom R function, this tool constructs two plots to visualise the sample composition: one at the OTU level and another one at the specified aggregation level (*e.g.* Phylum) after keeping only a subset of taxa (*e.g.* Bacteria at the level Kingdom). It helps answer the question: "What is the composition at the Phylum level within Bacteria?". By default, the plot exhibits only the abundance of the 9 most abundant taxa (as specified). In general, the representation of more than 10 taxa is hard to read on plots.


.. class:: infomark page-header h2

Inputs/Outputs

.. class:: h3

Input

**data file** (format rdata):
One phyloseq object containing the OTU abundance table, their taxonomies and optionnaly a phylogenetic tree, and the sample experiment metadata.
this file is the result of FROGS Phyloseq Import Data tool.

.. class:: h3

Output

**html file** (format `HTML &lt;https://en.wikipedia.org/wiki/HTML&gt;`_): data composition plots.

Bar plot of OTUs is colored with aggregated taxonomic level *i.e* "Phylum" :

 .. image:: static/images/FROGS_Phyloseq_bar_plot.png
     :height: 646
     :width: 800

Composition plot: plot the most abundant sub taxonomic level among a selection of OTUs.

- Selection of OTUs:

    - Taxonomic level name to subset: Kingdom
    - Taxon name: Bacteria

- Aggregation of OTUs :

    - Taxonomic level used to agglomerate: Phylum

- Number of the most abundant taxa to keep: 9

 .. image:: static/images/FROGS_Phyloseq_composition_plot.png
     :height: 644
     :width: 800

.. class:: infomark page-header h2

@HELP_CONTACT@

    </help>

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