annotate diamond.xml @ 0:98037ef3d2a9 draft

Imported from capsule None

<tool id="bg_diamond" name="Diamond" version="0.1.6.0">
    <description>alignment tool for short sequences against a protein database</description>
    <requirements>
        <requirement type="package" version="0.6.13">diamond</requirement>
    </requirements>
    <command>
<![CDATA[

    #if $ref_db_source.db_source == "history":
        ln -s $ref_db_source.reference_database ./database.dmnd
    #else:
        ln -s ${ref_db_source.index.fields.db_path} ./database.dmnd
    #end if

    &&

    diamond
        $method.method_select
        --threads "\${GALAXY_SLOTS:-12}"
        --db ./database
        --query $query
        --out $blast_output
        ##--sam $sam_output
        --compress 0
        --tmpdir ./

        #if str($hit_filter.hit_filter_select) == 'max':
            --max-target-seqs $hit_filter.max
        #else:
            --top $hit_filter.percentage
        #end if

        #if str($filter_score.filter_score_select) == 'evalue':
            --evalue $filter_score.evalue
        #else:
            --evalue $filter_score.bitscore
        #end if

        --id $identity
        $sensitive
        --gapopen $method.gapopen
        --gapextend $method.gapextend
        --matrix $matrix
        $seg
        $salltitles

]]>
    </command>
    <inputs>

        <param name="query" type="data" format="fasta" label="Input query file in FASTA format" />

        <conditional name="ref_db_source">
          <param name="db_source" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
            <option value="indexed">Use a built-in index</option>
            <option value="history">Use one from the history</option>
          </param>
          <when value="indexed">
            <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact your Galaxy admin">
              <options from_data_table="diamond_database">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
              </options>
            </param>
          </when>  <!-- build-in -->
          <when value="history">
            <param name="reference_database" type="data" format="diamond_database" label="Select the reference database" />
          </when>  <!-- history -->
        </conditional>

        <conditional name="method">
            <param name="method_select" type="select" label="What do you want to align" help="(--blastp/--blastx)">
                <option value="blastp">Align amino acid query sequences (blastp)</option>
                <option value="blastx">Align DNA query sequences (blastx)</option>
            </param>
            <when value="blastp">
                <param name="gapopen" type="integer" value="11" label="Gap open panalty" help="(--gapopen)" />
                <param name="gapextend" type="integer" value="1" label="Gap extend panalty" help="(--gapextend)" />
            </when>
            <when value="blastx">
                <param name="gapopen" type="integer" value="-1" label="Gap open panalty" help="(--gapopen)" />
                <param name="gapextend" type="integer" value="-1" label="Gap extend panalty" help="(--gapextend)" />
            </when>
        </conditional>

        <param name="matrix" type="select" label="Select scoring matrix" help="(--matrix)">
            <option value="BLOSUM45">BLOSUM45</option>
            <option value="BLOSUM50">BLOSUM50</option>
            <option value="BLOSUM62" selected="True">BLOSUM62</option>
            <option value="BLOSUM80">BLOSUM80</option>
            <option value="BLOSUM90">BLOSUM90</option>
            <option value="PAM250">PAM250</option>
            <option value="PAM70">PAM70</option>
            <option value="PAM30">PAM30</option>
        </param>

        <conditional name="filter_score">
            <param name="filter_score_select" type="select" label="Filter by score" help="(--evalue/--min-score)">
                <option value="evalue">Maximum e-value to report alignments</option>
                <option value="bit">Minimum bit score to report alignments</option>
            </param>
            <when value="evalue">
                <param name="evalue" type="float" value="0.001" label="Filter by evalue" help="(--evalue)" />
            </when>
            <when value="bit">
                <param name="bitscore" type="integer" value="0" label="Filter by bit score" help="(--min-score)" />
            </when>
        </conditional>

        <conditional name="hit_filter">
            <param name="hit_filter_select" type="select" label="Restrict number of hits by" help="(--max-target-seqs/--top)">
                <option value="max">Maximum number of target sequences</option>
                <option value="percentage">Percentage of top alignment score</option>
            </param>
            <when value="max">
                <param name="max" type="integer" value="25" label="How many hits?" help="(--max-target-seqs)" />
            </when>
            <when value="percentage">
                <param name="percentage" type="integer" value="0" label="How many percentage" help="(--top)" />
            </when>
        </conditional>

        <param name="identity" type="integer" value="0" label="minimum identity to report an alignment" help="in percentage (--id)" />
        <param name="salltitles" type="boolean" truevalue="--salltitles" falsevalue="" checked="false"
            label="Print subject titles into the blast tabular format" help="(--salltitles)"/>
        <param name="seg" type="boolean" truevalue="--seg yes" falsevalue="--seg no" checked="true"
            label="Enable SEG masking of queries" help="(--seg)"/>
        <param name="sensitive" type="boolean" truevalue="--sensitive" falsevalue="" checked="false"
            label="Enable sensitive mode" help="(--sensitive)"/>
    </inputs>
    <outputs>
        <!--data format="sam" name="sam_output"/-->
        <data format="tabular" name="blast_output"/>
    </outputs>
    <tests>
        <test>
            <param name="method" value="blastp"/>
            <param name="query" value="protein.fasta" ftype="fasta"/>
            <param name="reference_database" value="diamond_makedb_result1.dmnd" ftype="diamond_database"/>
            <param name="db_source" value="history"/>
            <output name="blast_output" file="diamond_result1.tabular" ftpye="tabular"/>
        </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 ist about 2,500
times faster than BLASTX, finding more than 94% of all matches.

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


Supported values for gap open and gap extend parameters depending on the selected scoring matrix.

========  ============================================
Matrix    Supported values for (gap open)/(gap extend)
========  ============================================
BLOSUM45  (10-13)/3; (12-16)/2; (16-19)/1
BLOSUM50  (9-13)/3; (12-16)/2; (15-19)/1
BLOSUM62  (6-11)/2; (9-13)/1
BLOSUM80  (6-9)/2; 13/2; 25/2; (9-11)/1
BLOSUM90  (6-9)/2; (9-11)/1
PAM250    (11-15)/3; (13-17)/2; (17-21)/1
PAM70     (6-8)/2; (9-11)/1
PAM30     (5-7)/2; (8-10)/1
========  ============================================


]]>
    </help>
    <citations>
        <citation type="doi">10.1038/nmeth.3176</citation>
    </citations>
</tool>