<tool id="abricate" name="ABRicate" version="@VERSION@">
    <description>
        Mass screening of contigs for antimicrobial and virulence genes
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command" />

    <command detect_errors="exit_code"><![CDATA[
        #import re
        #set $sample_name = re.sub('[^\w\-_\.]', '_', $file_input.element_identifier)

        ln -sf '${file_input}' ${sample_name} &&
        
        abricate ${sample_name}
        $adv.no_header
        #if $adv.min_dna_id
            --minid=$adv.min_dna_id
        #end if
        --db=$adv.db
        > '$report'
    ]]></command>

    <inputs>
        <param name="file_input" type="data" format="fasta,genbank,embl" label="Input file (Fasta, Genbank or EMBL file)" help="To screen for antibiotic resistant genes, can be a fasta file, a genbank file or an EMBL file." />
        <section name="adv" title="Advanced options" expanded="False">
            <param argument="--db" type="select" label="Database to use - default is 'resfinder'" help="Option to switch to other AMR/other database">
                <option value="argannot">ARG-ANNOT</option>
                <option value="card">CARD</option>
                <option value="ecoh">EcOH</option>
                <option value="ncbi">NCBI Bacterial Antimicrobial Resistance Reference Gene Database</option>
                <option value="resfinder" selected="true">Resfinder</option>
                <option value="plasmidfinder">PlasmidFinder</option>
                <option value="vfdb">VFDB</option>
            </param>
            <param name="no_header" argument="--noheader" type="boolean" truevalue="--noheader" falsevalue="" label="Suppress header" help="Suppress output file's column headings" />
            <param name="min_dna_id" argument="--minid" type="float" value="75" min="0" max="100" optional="true" label="Minimum DNA identity" />
        </section>
    </inputs>

    <outputs>
        <data name="report" format="tabular" label="${tool.name} on ${on_string} report file" />
    </outputs>

    <tests>
        <!-- Basic test 0 - will produce no results. -->
        <test>
            <param name="file_input" value="Acetobacter.fna"/>
            <output name="report" ftype="tabular" file="output_noresults.txt" />
        </test>

        <!-- Basic test 1 - will produce results. -->
        <test>
            <param name="file_input" value="MRSA0252.fna"/>
            <output name="report" ftype="tabular" file="output_mrsa.txt" compare="contains"/>
        </test>

        <!-- Advanced test 2 - No header. -->
        <test>
            <param name="file_input" value="MRSA0252.fna"/>
            <param name="no_header" value="True"/>
            <output name="report" ftype="tabular" file="output_noheader.txt" compare="contains"/>
        </test>

        <!-- Advanced test 3 - Changed DB to card -->
        <test>
            <param name="file_input" value="MRSA0252.fna"/>
            <param name="db" value="card"/>
            <output name="report" ftype="tabular" file="output_db-card.txt" compare="contains"/>
        </test>

        <!-- Advanced test 4 - Min DNA ID 100 -->
        <test>
            <param name="file_input" value="MRSA0252.fna"/>
            <param name="min_dna_id" value="100"/>
            <output name="report" ftype="tabular" file="output_minid100.txt" compare="contains"/>
        </test>

        <!-- Filetype test 5 - input a gbk -->
        <test>
            <param name="file_input" value="test.gbk"/>
            <output name="report" ftype="tabular" file="output_gbk.txt" compare="contains"/>
        </test>

    </tests>

    <help><![CDATA[
**What it does**

Given a FASTA contig file or a genbank file, ABRicate will perform a mass screening of contigs and identify the presence of antibiotic resistance genes. The user can choose which database to search from a list of available AMR databases.

**Output**

ABRicate will produce a tab-seperated output file with the following outputs:

+---------------+------------------------------------------------+
|  Column       | Description                                    |
+===============+================================================+
|  FILE         | The filename this hit came from                |
+---------------+------------------------------------------------+
|  SEQUENCE     | The sequence in the filename                   |
+---------------+------------------------------------------------+
|  START        | Start coordinate in the sequence               |
+---------------+------------------------------------------------+
|  END          | End coordinate                                 |
+---------------+------------------------------------------------+
|  GENE         | ABR gene                                       |
+---------------+------------------------------------------------+
|  COVERAGE     | What proportion of the gene is in our sequence |
+---------------+------------------------------------------------+
|  COVERAGE_MAP | A visual represenation                         |
+---------------+------------------------------------------------+
|  GAPS         | Was there any gaps in the                      |
|               | alignment - possible pseudogene?               |
+---------------+------------------------------------------------+
|  %COVERAGE    | Proportion of gene covered                     |
+---------------+------------------------------------------------+
|  %IDENTITY    | Proportion of exact nucleotide matches         |
+---------------+------------------------------------------------+
|  DATABASE     | The database this sequence comes from          |
+---------------+------------------------------------------------+
|  ACCESSION    | The genomic source of the sequence             |
+---------------+------------------------------------------------+


**Example Output**

::

        #FILE     SEQUENCE     START   END     GENE     COVERAGE     COVERAGE_MAP     GAPS  %COVERAGE  %IDENTITY  DATABASE   ACCESSION
        6159.fna  NC_017338.1  39177   41186   mecA_15  1-2010/2010  ===============  0/0   100.00     100.000    resfinder  AB505628
        6159.fna  NC_017338.1  727191  728356  norA_1   1-1166/1167  ===============  0/0   99.91      92.367     resfinder  M97169
        6159.fna  NC_017339.1  10150   10995   blaZ_32  1-846/846    ===============  0/0   100.00     100.000    resfinder  AP004832
    ]]></help>

    <expand macro="citations"/>
</tool>