<tool id="bg_diamond_makedb" name="Diamond makedb" version="@VERSION@" profile="19.01">
    <description>Build database from a FASTA file</description>
    <macros>
        <import>macros.xml</import>
    </macros>

    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />

    <command detect_errors="aggressive">
    <!-- DB has two files, *.dmnd and *.tx -->
    <![CDATA[
    diamond makedb
        --threads "\${GALAXY_SLOTS:-12}"
        --in '$infile'
        --db ./database

      #if str($tax_cond.tax_select) == 'yes':
        --taxonmap '$tax_cond.taxonmap'
        --taxonnodes '$tax_cond.taxonnodes'
        --taxonnames '$tax_cond.taxonnames'
      #end if
    ]]>
    </command>

    <inputs>
      <param name="infile" type="data" format="fasta" label="Input reference file in FASTA format" />
      <conditional name="tax_cond">
        <param name="tax_select" type="select" label="Add taxonomic data?" help="Needs to be supplied in order to provide taxonomy features of the aligner">
          <option value="yes">Yes</option>
          <option value="no" selected="true">No</option>
        </param>
        <when value="yes">
          <param argument="--taxonmap" type="data" format="tabular" label="protein accession to taxid mapping file" help="" />
          <param argument="--taxonnodes" type="data" format="tabular" label="taxonomy nodes.dmp from NCBI" help="" />
          <param argument="--taxonnames" type="data" format="tabular" label="taxonomy names.dmp from NCBI" help="" />
        </when>
        <when value="no"/>
      </conditional>
    </inputs>

    <outputs>
        <data format="dmnd" name="outfile" from_work_dir="database.dmnd" label="${tool.name} on ${on_string}"/>
    </outputs>

    <tests>
        <test>
            <param name="infile" value="db.fasta" ftype="fasta"/>
            <output name="outfile" value="db.dmnd" compare="sim_size" delta="2"/>
        </test>
        <test>
            <param name="infile" value="db.fasta" ftype="fasta"/>
            <conditional name="tax_cond">
                <param name="tax_select" value="yes"/>
                <param name="taxonmap" ftype="tabular" value="prot.accession2taxid" />
                <param name="taxonnodes" ftype="tabular" value="nodes.dmp" />
                <param name="taxonnames" ftype="tabular" value="names.dmp" />
            </conditional>
            <output name="outfile" value="db-wtax.dmnd" compare="sim_size" delta="2"/>
        </test>
    </tests>

    <help>
<![CDATA[

.. class:: infomark

**What it does**

DIAMOND_ is a new alignment tool for aligning short DNA sequencing reads to a protein reference database such as NCBI-NR.
On Illumina reads of length 100-150bp, in fast mode, DIAMOND is about 20,000 times faster than BLASTX, while reporting
about 80-90% of all matches that BLASTX finds, with an e-value of at most 1e-5. In sensitive mode, DIAMOND is about 2,500
times faster than BLASTX, finding more than 94% of all matches.

.. _DIAMOND: http://ab.inf.uni-tuebingen.de/software/diamond/


- taxonmap: Path to mapping file that maps NCBI protein accession numbers to taxon ids (gzip compressed). This parameter is optional and needs to be supplied in order to provide taxonomy features. The file can be downloaded from NCBI: ftp.ncbi.nlm.nih.gov/pub/taxonomy/accession2taxid/prot.accession2taxid.FULL.gz

- taxonnames: Path to the names.dmp file from the NCBI taxonomy. This parameter is optional and needs to be supplied in order to provide taxonomy features. The file is contained within this archive downloadable at NCBI: ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdmp.zip

- taxonnodes: Path to the nodes.dmp file from the NCBI taxonomy. This parameter is optional and needs to be supplied in order to provide taxonomy features. The file is contained within this archive downloadable at NCBI: ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdmp.zip
]]>
    </help>

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