<tool id="prokka" name="Prokka" version="1.13+galaxy1">
    <description>Prokaryotic genome annotation</description>
    <requirements>
        <requirement type="package" version="1.13">prokka</requirement>
    </requirements>

    <version_command>prokka --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
prokka
--cpus \${GALAXY_SLOTS:-8}
--quiet ## to avoid non-error messages written to stderr
--outdir outdir --prefix prokka ## used in outputs section
#if $locustag
    --locustag '$locustag'
#end if
#if str($increment)
    --increment $increment
#end if
--gffver $gffver
#if $compliant.compliant_select == "no"
    #if $compliant.addgenes
        --addgenes
    #end if
    #if str($compliant.mincontig)
        --mincontig $compliant.mincontig
    #end if
#else
    --compliant
#end if
#if $centre
    --centre '$centre'
#end if
#if $genus
    --genus '$genus'
#end if
#if $species
    --species '$species'
#end if
#if $strain
    --strain '$strain'
#end if
#if $plasmid
    --plasmid '$plasmid'
#end if
--kingdom $kingdom.kingdom_select
#if str($kingdom.gcode)
    --gcode $kingdom.gcode
#end if
#if $usegenus
    --usegenus
#end if
#if $proteins
    --proteins '$proteins'
#end if
#if $metagenome
    --metagenome
#end if
#if $fast
    --fast
#end if
#if str($evalue)
    --evalue $evalue
#end if
#if $rfam
    --rfam
#end if
#if $norrna
    --norrna
#end if
#if $notrna
    --notrna
#end if
$input
    ]]></command>
    <inputs>
        <param name="input" type="data" format="fasta" label="Contigs to annotate" help="FASTA format" />
        <param name="locustag" type="text" value="" label="Locus tag prefix (--locustag)" />
        <param name="increment" type="integer" value="1" min="1" optional="true" label="Locus tag counter increment (--increment)" />
        <param name="gffver" type="select" label="GFF version (--gffver)">
            <option value="3">3</option>
            <option value="2">2</option>
            <option value="1">1</option>
        </param>
        <conditional name="compliant">
            <param name="compliant_select" type="select" label="Force GenBank/ENA/DDJB compliance (--compliant)" help="Equivalent to --addgenes --mincontiglen 200 --centre Prokka (or other centre specified below)">
                <option value="no">No</option>
                <option value="yes">Yes</option>
            </param>
            <when value="no">
                <param name="addgenes" type="boolean" checked="false" label="Add 'gene' features for each 'CDS' feature (--addgenes)" />
                <param name="mincontig" type="integer" value="200" optional="true" label="Minimum contig size (--mincontiglen)" help="NCBI needs 200" />
            </when>
            <when value="yes" />
        </conditional>
        <param name="centre" type="text" value="" label="Sequencing centre ID (--centre)" />
        <param name="genus" type="text" value="" label="Genus name (--genus)" help="May be used to aid annotation, see --usegenus below" />
        <param name="species" type="text" value="" label="Species name (--species)" />
        <param name="strain" type="text" value="" label="Strain name (--strain)" />
        <param name="plasmid" type="text" value="" label="Plasmid name or identifier (--plasmid)" />
        <conditional name="kingdom">
            <param name="kingdom_select" type="select" label="Kingdom (--kingdom)">
                <option value="Archaea">Archaea</option>
                <option value="Bacteria" selected="true">Bacteria</option>
                <option value="Viruses">Viruses</option>
            </param>
            <when value="Archaea">
                <param name="gcode" type="integer" value="11" min="1" max="23" optional="true" label="Genetic code (transl_table)" /><!-- max should be 25, but prodigal would crash -->
            </when>
            <when value="Bacteria">
                <param name="gcode" type="integer" value="11" min="1" max="23" optional="true" label="Genetic code (transl_table)" /><!-- max should be 25, but prodigal would crash -->
                <!-- <param name="gram" type="select" display="radio" label="Gram (- -gram)">
                    <option selected="true" value="none">N/A</option>
                    <option value="pos">positive</option>
                    <option value="neg">negative</option>
                </param> SignalP is not FOSS -->
            </when>
            <when value="Viruses">
                <param name="gcode" type="integer" value="1" min="1" max="23" optional="true" label="Genetic code (transl_table)" /><!-- max should be 25, but prodigal would crash -->
            </when>
        </conditional>
        <param name="usegenus" type="boolean" checked="false" label="Use genus-specific BLAST database (--usegenus)" help="Will use the BLAST database for the genus specified above, if installed" />
        <param name="proteins" type="data" format="fasta" optional="true" label="Optional FASTA file of trusted proteins to first annotate from (--proteins)" />
        <param name="metagenome" type="boolean" checked="false" label="Improve gene predictions for highly fragmented genomes (--metagenome)" help="Will set --meta option for Prodigal" />
        <param name="fast" type="boolean" checked="false" label="Fast mode (--fast)" help="Skip CDS /product searching" />
        <param name="evalue" type="float" value="1e-06" min="0" optional="true" label="Similarity e-value cut-off" />
        <param name="rfam" type="boolean" checked="false" label="Enable searching for ncRNAs with Infernal+Rfam (SLOW!) (--rfam)" />
        <param name="norrna" type="boolean" checked="false" label="Don't run rRNA search with Barrnap" />
        <param name="notrna" type="boolean" checked="false" label="Don't run tRNA search with Aragorn" />

        <param name="outputs" type="select" multiple="true" display="checkboxes" label="Additional outputs">
            <option value="gff" selected="True">Annotation in GFF3 format, containing both sequences and annotations (.gff)</option>
            <option value="gbk" selected="True">Standard GenBank file. If the input was a multi-FASTA, then this will be a multi-GenBank, with one record for each sequence (.gbk)</option>
            <option value="fna" selected="True">Nucleotide FASTA file of the input contig sequences (.fna)</option>
            <option value="faa" selected="True">Protein FASTA file of the translated CDS sequences (.faa)</option>
            <option value="ffn" selected="True">Nucleotide FASTA file of all the annotated sequences, not just CDS (.ffn)</option>
            <option value="sqn" selected="True">An ASN1 format "Sequin" file for submission to GenBank. It needs to be edited to set the correct taxonomy, authors, related publication, etc. (.sqn)</option>
            <option value="fsa" selected="True">Nucleotide FASTA file of the input contig sequences, with extra Sequin tags in the sequence description lines (.fsa)</option>
            <option value="tbl" selected="True">Feature Table file (.tbl)</option>
            <option value="tsv" selected="True">Annotations in tabular format including COGs etc.</option>
            <option value="err" selected="True">Unacceptable annotations - the NCBI discrepancy report (.err)</option>
            <option value="txt" selected="True">Statistics relating to the annotated features found (.txt)</option>
        </param>

    </inputs>
    <outputs>
        <data name="out_gff" format="gff" label="${tool.name} on ${on_string}: gff" from_work_dir="outdir/prokka.gff">
            <filter>outputs and 'gff' in outputs</filter>
        </data>
        <data name="out_gbk" format="txt" label="${tool.name} on ${on_string}: gbk" from_work_dir="outdir/prokka.gbk">
            <filter>outputs and 'gbk' in outputs</filter>
        </data>
        <data name="out_fna" format="fasta" label="${tool.name} on ${on_string}: fna" from_work_dir="outdir/prokka.fna">
            <filter>outputs and 'fna' in outputs</filter>
        </data>
        <data name="out_faa" format="fasta" label="${tool.name} on ${on_string}: faa" from_work_dir="outdir/prokka.faa">
            <filter>outputs and 'faa' in outputs</filter>
        </data>
        <data name="out_ffn" format="fasta" label="${tool.name} on ${on_string}: ffn" from_work_dir="outdir/prokka.ffn">
             <filter>outputs and 'ffn' in outputs</filter>
        </data>
        <data name="out_sqn" format="asn1" label="${tool.name} on ${on_string}: sqn" from_work_dir="outdir/prokka.sqn">
             <filter>outputs and 'sqn' in outputs</filter>
        </data>
        <data name="out_fsa" format="fasta" label="${tool.name} on ${on_string}: fsa" from_work_dir="outdir/prokka.fsa">
             <filter>outputs and 'fsa' in outputs</filter>
        </data>
        <data name="out_tbl" format="txt" label="${tool.name} on ${on_string}: tbl" from_work_dir="outdir/prokka.tbl">
             <filter>outputs and 'tbl' in outputs</filter>
        </data>
        <data name="out_tsv" format="tabular" label="${tool.name} on ${on_string}: tsv" from_work_dir="outdir/prokka.tsv">
             <filter>outputs and 'tsv' in outputs</filter>
        </data>
        <data name="out_err" format="txt" label="${tool.name} on ${on_string}: err" from_work_dir="outdir/prokka.err">
             <filter>outputs and 'err' in outputs</filter>
        </data>
        <data name="out_txt" format="txt" label="${tool.name} on ${on_string}: txt" from_work_dir="outdir/prokka.txt">
             <filter>outputs and 'txt' in outputs</filter>
        </data>
        <data name="out_log" format="txt" label="${tool.name} on ${on_string}: log" from_work_dir="outdir/prokka.log" />
    </outputs>
    <tests>
        <test>
            <param name="input" ftype="fasta" value="phiX174.fasta" />
            <param name="outputs" value="gff,gbk,fna,faa,ffn,sqn,fsa,tbl,tsv,err,txt" />
            <output name="out_gff" file="out.gff" />
            <output name="out_gbk" >
                <assert_contents>
                    <has_text_matching expression="LOCUS" />
                    <has_text_matching expression="//" />
                </assert_contents>
            </output>
            <output name="out_fna" file="out.fna" />
            <output name="out_faa" file="out.faa" />
            <output name="out_ffn" file="out.ffn" />
            <output name="out_sqn" >
                <assert_contents>
                    <has_text_matching expression="Seq-entry" />
                    <has_text_matching expression="contig2" />
                </assert_contents>
            </output>
            <output name="out_fsa" file="out.fsa" />
            <output name="out_tbl" file="out.tbl" />
            <output name="out_tsv" file="out.tsv" />
            <output name="out_err" file="out.err" lines_diff="14" />
            <output name="out_txt" file="out.txt" />
            <output name="out_log">
                <assert_contents>
                    <has_text text="Type 'prokka --citation' for more details." />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

Prokka_ is a software tool to rapidly annotate bacterial, archaeal and viral genomes, and produce output files that require only minor tweaking to submit to GenBank/ENA/DDBJ.

.. _Prokka: http://github.com/tseemann/prokka

**Output files**

Prokka creates several output files, which are described in the **Additional outputs** section above.

**License and citation**

This Galaxy tool is Copyright © 2013 Lionel Guy, © 2013-2014 `CRS4 Srl.`_, © 2015-2016 `Earlham Institute`_, 2018 `Galaxy IUC` and is released under the `MIT license`_.

.. _CRS4 Srl.: http://www.crs4.it/
.. _Earlham Institute: http://earlham.ac.uk/
.. _MIT license: https://opensource.org/licenses/MIT

You can use this tool only if you agree to the license terms of: `Prokka`_.

.. _Prokka: http://github.com/tseemann/prokka
    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btu135</citation>
        <citation type="doi">10.1093/bioinformatics/btu153</citation>
    </citations>
</tool>