<?xml version="1.0"?>
<!--
# Copyright (C) 2015 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="FROGS_itsx" name="FROGS ITSx" version="3.1">
	<description>Extract the highly variable ITS1 and ITS2 subregions from ITS sequences.</description>
    <requirements>
        <requirement type="package" version="3.1.0">frogs</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>
	<command>
		itsx.py
		                --nb-cpus \${GALAXY_SLOTS:-1}
		                --region $region
		                --input-fasta $input_fasta
		                --input-biom $input_biom
		                --out-fasta $out_fasta
		                --out-abundance $out_abundance_biom
		                --out-removed $out_excluded
		                --summary $summary_file
		                $check_only
		                
	</command>
	<inputs>
		<!-- Files -->
		<param format="fasta" name="input_fasta" type="data" label="Sequences file" help="The sequence file to filter (format: fasta)." />
		<param format="biom1" name="input_biom" type="data" label="Abundance file" help="The abundance file to filter (format: BIOM)." />
		<param name="region" type="select" label="ITS region" help="Which fungal ITS region is targeted: either ITS1 or ITS2" >
			<option value="ITS1">ITS1</option>
			<option value="ITS2">ITS2</option>
		</param>
		<param name="check_only" type="boolean" checked="false" truevalue="--check-its-only" falsevalue="" label="Check only if sequence detected as ITS ?" help="If Yes, sequences with ITS signature will be kept without trimming SSU, LSU or 5.8S regions."/>
	</inputs>
	<outputs>
		<data format="fasta" name="out_fasta" label="${tool.name}: itsx.fasta" from_work_dir="itsx.fasta"/>
		<data format="biom1" name="out_abundance_biom" label="${tool.name}: itsx.biom" from_work_dir="itsx.biom"/>
		<data format="fasta" name="out_excluded" label="${tool.name}: out_removed.fasta" from_work_dir="out_removed.fasta"/>
		<data format="html" name="summary_file" label="${tool.name}: report.html" from_work_dir="report.html"/>
	</outputs>
	<tests>
		<test>
			<param name="input_fasta" value="references/04-filters.fasta"/>
			<param name="input_biom" value="references/04-filters.biom"/>
			<param name="region" value="ITS1"/>
			<param name="check_only" value="false"/>
			<output name="summary_file" file="references/05-itsx.html"/>
		</test>
	</tests>
	<help>

.. image:: static/images/frogs_images/FROGS_logo.png 
   :height: 144
   :width: 110


.. class:: infomark page-header h2

What it does

Extract the highly variable ITS1 and ITS2 subregions from ITS sequences.

.. class:: infomark page-header h2

Context

The ITSx software identifies and extracts only ITS regions. It then excludes the highly conserved neighbouring sequences SSU, 5S and ARNr LSU. These sequences can lead to misleading results if they are conserved.
If the ITS1 or ITS2 region is not detected, the observation is discarded.

You can choose to only check if the sequence is detected as an ITS. The sequence is not trimmed, only sequences not detected as ITS are discarded (contaminants by example).

.. class:: infomark page-header h2

Inputs/Outputs

.. class:: h3

Inputs

**Sequence file**:

The sequences (format `FASTA &lt;https://en.wikipedia.org/wiki/FASTA_format&gt;`_).

**Abundance file**:
 
 The abundance of each cluster in each sample (format `BIOM &lt;http://biom-format.org/&gt;`_).

	
.. class:: h3

Outputs

**Sequence file** (itsx.fasta):

 The sequence file with only ITS1 or ITS2 part, or with the original sequence if check-its-only is choosen (format `FASTA &lt;https://en.wikipedia.org/wiki/FASTA_format&gt;`_).

**Abundance file** (itsx.biom):

 The abundance file with only ITS sequences (format `BIOM &lt;http://biom-format.org/&gt;`_).
 
**Discarded file** (out_removed.fasta)

 The sequence file with discarded sequences.

**Summary file** (report.html):

 This file presents the summary of process (format `HTML &lt;https://en.wikipedia.org/wiki/HTML&gt;`_).


.. class:: infomark page-header h2

How it works

.. csv-table:: 
   :header: "Steps", "Description"
   :widths: 10, 90
   :class: table table-striped
   
   "1", "Predicts positions of the ribosomal genes in the sequences (`ITSx &lt;http://microbiology.se/software/itsx/&gt;`_)."
   "2", "Removes the sequences without prediction of the targeted ITS region (ITS1 or ITS2)."


----

**Contact**

Contacts: frogs@inra.fr

Repository: https://github.com/geraldinepascal/FROGS
website: http://frogs.toulouse.inra.fr/

Please cite the **FROGS article**: *Escudie F., et al. Bioinformatics, 2018. FROGS: Find, Rapidly, OTUs with Galaxy Solution.*

	</help>
	<citations>
		<citation type="doi">10.1093/bioinformatics/btx791</citation>
	</citations>

</tool>