<tool id="selenzy-wrapper" name="Selenzyme" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.09">
    <description>Performs enzyme selection from a reaction query</description>
    <macros>
        <token name="@VERSION_SUFFIX@">0</token>
        <token name="@TOOL_VERSION@">0.3.0</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">selenzy_wrapper</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        python -m selenzy_wrapper '$pathway' '$uniprot_ids'
        --nb_targets '$adv.nb_targets'
        --d '$adv.direction'
        $adv.NoMSA
        --host_taxID '$adv.host_taxID'
        #if str($adv.enzyme_taxIDs) != "":
            --enzyme_taxIDs '$adv.enzyme_taxIDs'
        #end if
        --nb_ids '$adv.nb_ids'
        --to_csv '$uniprot_ids_csv'
        --data-path "\${TMPDIR:-.}"
    ]]></command>
    <inputs>
        <param name="pathway" type="data" format="sbml" label="Pathway (SBML)" />
        <section name="adv" title="Advanced Options" expanded="false">
            <param name="host_taxID" type="integer" value="83333" label="Host taxon ID" help="Taxon ID of the chassis (default: 83333 [E. coli K12])" />
            <param name="enzyme_taxIDs" type="text" value="" label="Comma separated taxon IDs of output enzyme sequences" />
            <param name="nb_ids" type="integer" value="-1" label="Number of uniprot IDs with top score to keep" help=" Number of enzyme IDs to display in results (after taxon IDs filtering) [default = -1 (no limit)]" />
            <param name="nb_targets" type="integer" value="500" min="1" label="Number of targets to display in results" help="Number of targets to display in results (before taxon IDs filtering) [default = 500]" />
            <param name="direction" type="float" value="0" label="Use similarity values for preferred reaction direction only" help="You can choose to rank similarities in both reaction directions or to use only the direction of the reaction based on a consensus list that has been generated according to reaction information based on curated information from MetaCyc (Metabolic Pathway Database) [default=0 (OFF)]" />
            <param argument="--NoMSA" type="boolean" falsevalue="--NoMSA" truevalue="" checked="true" display="checkboxes" label="Do not compute MSA/conservation scores ?" help="Do not compute Multiple Sequence Alignment and conservation scores ? (MSA scores are computed by default)" />
        </section>
    </inputs>
    <outputs>
        <data name="uniprot_ids" format="sbml" label="Uniprot IDs (SBML)" />
        <data name="uniprot_ids_csv" format="csv" label="Uniprot IDs (CSV)" />
    </outputs>
    <tests>
        <test>
        <!-- test 1: check if identical outputs are produced with default parameters  -->
            <param name="pathway" value="pathway.xml" />
            <output name="uniprot_ids" file="uniprod_ids_out.xml" compare="diff" sort="true"/>
            <output name="uniprot_ids_csv" file="uniprod_ids_out.csv" ftype="csv" compare="diff"/>
        </test>
    </tests>
    <help><![CDATA[
Selenzyme
================

Selenzyme searches for enzymes corresponding to each reaction of the pathway. It performs a reaction similarity search in the reference reaction database `MetaNetX <https://www.metanetx.org/>`_ and outputs an updated SBML file annotated with the enzyme UniProt IDs, as well as in CSV format.

Input
-----

* **Pathway (SBML)**\ : SBML pathway file
* **Number of targets to display in results**\ : (integer) Number of targets to display in results (before taxon IDs filtering) [default = 500]
* **Number of uniprot IDs with top score to keep**\ : (integer) Number of enzyme IDs to display in results (after taxon IDs filtering) [default = -1 (no limit)]
* **Use similarity values for preferred reaction direction only**\ : (float) Use similarity values for preferred reaction direction only [default=0 (OFF)]
* **Do not compute MSA/conservation scores ?**\ : (boolean) Do not compute Multiple Sequence Alignment and conservation scores ? (MSA scores are computed by default)
* **Host taxon ID**\ : (string) Taxon ID of the chassis (default: 83333 [E. coli K12])
* **Comma separated taxon IDs of output enzyme sequences**\ : (string) Comma separated taxon IDs of output enzyme sequences

Output
------

* **Uniprot IDs (SBML)**\ : Annotated SBML pathway.
* **Uniprot IDs (CSV)**\ : Annotated CSV pathway.

Project Links
------------------

* `GitHub <https://github.com/brsynth/selenzy-wrapper>`_

Version
----------

0.3.0

Authors
-------
* **Joan Hérisson**

License
-------

* `MIT <https://github.com/brsynth/selenzy-wrapper/blob/master/LICENSE>`_

Acknowledgments
---------------

* Thomas Duigou

    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/bty065</citation>
    </citations>
</tool>