<?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_biom_to_tsv" name="FROGS BIOM to TSV" version="3.1">
	<description>Converts a BIOM file in TSV file.</description>
        <requirements>
                <requirement type="package" version="3.1.0">frogs</requirement>
        </requirements>
        <stdio>
                <exit_code range="1:" />
                <exit_code range=":-1" />
        </stdio>
	<command>
		biom_to_tsv.py 
		                --input-biom $biom_file
		              #if $sequence_file
		                --input-fasta $sequence_file
		              #end if
		                --output-tsv $tsv_file
		              #if $extract_multi_align
		                --output-multi-affi $multi_affi_file
		              #end if   
	</command>
	<inputs>
		<!-- Files -->
		<param format="biom1" name="biom_file" type="data" label="Abundance file" help="The BIOM file to convert (format: BIOM)." optional="false" />
		<param format="fasta" name="sequence_file" type="data" label="Sequences file" help="The sequences file (format: fasta). If you use this option the sequences will be add in TSV." optional="true" />
		<!-- Parameters -->
		<param name="extract_multi_align" type="boolean" label="Extract multi-alignments" help="If you have used FROGS affiliation on your data, you can extract information about multiple alignements in a second TSV." checked="true"/>
	</inputs>
	<outputs>
		<data format="tabular" name="tsv_file" label="${tool.name}: abundance.tsv" from_work_dir="abundance.tsv"/>
		<data format="tabular" name="multi_affi_file" label="${tool.name}: multi_hits.tsv" from_work_dir="multi_hits.tsv" >
			<filter>extract_multi_align</filter>
		</data>
	</outputs>
	<tests>
		<test>
			<param name="biom_file" value="references/06-affiliation.biom"/>
			<param name="sequence_file" value="references/04-filters.fasta"/>
			<param name="extract_multi_align" value="true"/>
			<output name="tsv_file" value="references/10-biom2tsv.tsv"/>
			<output name="multi_affi_file" value="references/10-biom2tsv-affiliation_multihit.tsv"/>
		</test>
	</tests>
	<help>

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


.. class:: infomark page-header h2

What it does

Converts a BIOM file in TSV file.

.. class:: h3

Inputs

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

**Sequence file [optional]**:

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

.. class:: h3

Outputs

**Abundance file**:

 The abundance of each cluster in each sample and theirs metadata (format `TSV &lt;https://en.wikipedia.org/wiki/Tab-separated_values&gt;`_).

 If you add the sequences file, this information is added for each cluster.

**Multiple affiliation file**:

 If you have used *FROGS affiliation* on your data, each OTU can have several affiliations: several alignments with same score on reference database. The multiple affiliation file contains details on these possibles affiliations (format `TSV &lt;https://en.wikipedia.org/wiki/Tab-separated_values&gt;`_).


.. class:: infomark page-header h2

How it works

FROGS Biom to Tsv will search if any metadata are available, and the OTU sequence if fasta file is precised. Then it will extract the OTU name, sum the abundance, and extract the detailed abundance for each sample. Finally it will write all these fields separated by tabulation in the TSV file. 


.. class:: infomark page-header h2

Advices

This output tsv file is easily readable in any spreadsheet software. Be aware that these software have a number of line limit (1 048 576 for Excel and LibreOffice calc ate least). If you have more OTU, use **FROGS Filters** to extract for example the most abundant OTU before converting your BIOM abundance table in TSV file.


----

**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>