<?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_affiliation_OTU" name="FROGS Affiliation OTU" version="0.8.0">
	<description>Step 4 in metagenomics analysis : Taxonomic affiliation of each OTU's seed by RDPtools and BLAST</description>
 	<requirements>
                <requirement type="package" version="2.0.1">frogs</requirement>
        </requirements>
     	<stdio>
                <exit_code range="1:" />
                <exit_code range=":-1" />
        </stdio>
	<command>
		#set $reference_fasta_filename = str( $ref_file.fields.path )
		affiliation_OTU.py 
		                       --reference "${reference_fasta_filename}"
					--input-biom $biom_abundance 
					--input-fasta $fasta_sequences
					--output-biom $biom_affiliation 
					--summary $summary 
					--nb-cpus $nb_cpu
					--java-mem $mem 
					#if $rdp
		                       		--rdp
		                       	#end if
	</command>
	<inputs>
		<!-- JOB Parameter -->
		<param name="nb_cpu" type="hidden" label="CPU number" help="The maximum number of CPUs used." value="1"></param>
		<param name="mem" type="hidden" label="Memory allocation" help="The number of Go to allocation for java" value="20"></param>
		<param name="ref_file" type="select" label="Using reference database" help="Select reference from the list">
	       		<options from_data_table="frogs_db"></options>
			<validator type="no_options" message="A built-in database is not available" />
		</param> 
   		<param name="rdp" type="boolean" label="Also perform RDP assignation?" help="Taxonomy affiliation will be perform thanks to Blast. This option allow you to perform it also with RDP classifier (default No)" />
	        <!-- Files -->
	        <param format="fasta" name="fasta_sequences" type="data" label="OTU seed sequence" help="OTU sequences (format: fasta)."/>
	        <param format="biom1" name="biom_abundance" type="data" label="Abundance file" help="OTU abundances (format: BIOM)."/>
	</inputs>
	<outputs>
		<data format="biom1" name="biom_affiliation" label="${tool.name}: affiliation.biom" from_work_dir="affiliation.biom" />
		<data format="html" name="summary" label="${tool.name}: report.html" from_work_dir="report.html"/>
	</outputs>
        <tests>
                <test>
                        <param name="ref_file" value="db"/>
                        <param name="fasta_sequences" value="swarm.fasta"/>
                        <param name="biom_abundance" value="swarm.biom"/>
                        <output name="biom_affiliation" file="references/Blast_affiliation.biom"/>
                        <output name="summary" file="references/Blast_affiliation.html" compare="sim_size" delta="0" />
                </test>
        </tests>

  	<help>

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


.. class:: infomark page-header h2

What it does

Add taxonomic affiliation in abundance file.


.. 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 OTU in each sample (format `BIOM &lt;http://biom-format.org/&gt;`_).

.. class:: h3

Outputs

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

 The abundance file with affiliation (format `BIOM &lt;http://biom-format.org/&gt;`_).

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

 This file presents the number of sequences affiliated by blast, and the number of multi-affiliation (format `HTML &lt;https://en.wikipedia.org/wiki/HTML&gt;`_).
 
 .. image:: static/images/FROGS_affiliation_summary.png 
    :height: 800
    :width: 600


.. class:: infomark page-header h2

Reference database

The databases come from `SILVA &lt;http://www.arb-silva.de/&gt;`_ a comprehensive and quality checked rRNA database.

FROGS database(s) pre-process:

1. The non-redondant small sub-unit database is retrieved from SILVA.

2. This database is processed to keep only the taxonomy level: Domain - Phylum - Class - Order - Family - Genus - Species

3. The database is splitted in two databses: prokaryote and eukaryote.


.. class:: infomark page-header h2

How it works

.. csv-table:: 
   :header: "Steps", "Description"
   :widths: 5, 150
   :class: table table-striped

   "1", "`RDPClassifier &lt;https://rdp.cme.msu.edu/tutorials/classifier/RDPtutorial_RDP_classifier.html&gt;`_ is used with database to associate to each OTU a taxonomy and a bootstrap (example: *Bacteria;(1.0);Firmicutes;(1.0);Clostridia;(1.0);Clostridiales;(1.0);Clostridiaceae 1;(1.0);Clostridium sensu stricto;(1.0);*)."
   "2", "`blastn+ &lt;http://blast.ncbi.nlm.nih.gov/&gt;`_ is used to find alignment between each OTU and the database. Only the bests hits with the same score has reported."
   "3", "For each OTU with several blastn+ results a consensus is determined on each taxonomic level. If all the taxa in a taxonomic rank are identical the taxon name is reported otherwise *Multi-affiliation* is reported. By example, if you have an OTU with two corresponding sequences, the first is a *Bacteria;Proteobacteria;Gamma Proteobacteria;Enterobacteriales*, the second is a *Bacteria;Proteobacteria;Beta Proteobacteria;Methylophilales*, the consensus will be *Bacteria;Proteobacteria;Multi-affiliation;Multi-affiliation*."


.. class:: infomark page-header h2

Advices

This tool can take large time. It is recommended to filter your abundance and your sequence file before this tool (see **FROGS Filters**).

As you can see the affiliation of each OTU is not human readable in outputed abundance file. We provide a tools to convert these BIOM file in tabulated file, see the **FROGS BIOM to TSV** tool.


----

**Contact**

Contacts: frogs@inra.fr

Repository: https://github.com/geraldinepascal/FROGS

Please cite the FROGS Publication: *Escudie F., Auer L., Bernard M., Cauquil L., Vidal K., Maman S., Mariadassou M., Hernadez-Raquet G., Pascal G., 2015. FROGS: Find Rapidly OTU with Galaxy Solution. In: The environmental genomic Conference, Montpellier, France,* http://bioinfo.genotoul.fr/fileadmin/user_upload/FROGS_2015_GE_Montpellier_poster.pdf

Depending on the help provided you can cite us in acknowledgements, references or both.
	</help>
	<citations>
		<citation type="doi">10.1186/1471-2105-10-421</citation>
		<citation type="doi">10.1128/AEM.00062-07</citation>
	</citations>
</tool>