comparison diamond.xml @ 3:830516f9521b draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/diamond commit 0a893f1ee7f73d24004a43ec1ba6a4cc03fbfab0

2:fd14bf35c9fd

<tool id="bg_diamond" name="Diamond" version="@VERSION@">
    <description>alignment tool for short sequences against a protein database</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />

    #end if

    &&

    diamond
        $method_select
        --threads "\${GALAXY_SLOTS:-12}"
        --db ./database
        --query '$query'
        --query-gencode '$query_gencode'

        #if $output.outfmt == "5"
            --outfmt '5'
            --out '$blast_xml'
            $output.salltitles

            --out '$sam_output'
            $output.salltitles
        #end if

        --compress '0'
        $sensitive
        $more_sensitive
        --gapopen '$gapopen'
        --gapextend '$gapextend'
        --matrix '$matrix'
        --seg '$seg'

        --block-size '$block_size'
]]>
    </command>

    <inputs>
        <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>
        <param argument="--query" type="data" format="fasta,fastq" label="Input query file in FASTA or FASTQ 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>
          <when value="history">
            <param name="reference_database" type="data" format="dmnd" label="Select the reference database" />
          </when>
        </conditional>
        <param name="query_gencode" argument="--query-gencode" type="select" label="Genetic code used for translation of query in BLASTX mode" help="">
            <option value="1">The Standard Code</option>
            <option value="2">The Vertebrate Mitochondrial Code</option>
            <option value="3">The Yeast Mitochondrial Code</option>
            <option value="4">The Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
            <option value="5">The Invertebrate Mitochondrial Code</option>
            <option value="6">The Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
            <option value="9">The Echinoderm and Flatworm Mitochondrial Code</option>
            <option value="10">The Euplotid Nuclear Code</option>
            <option value="11">The Bacterial, Archaeal and Plant Plastid Code</option>
            <option value="12">The Alternative Yeast Nuclear Code</option>
            <option value="13">The Ascidian Mitochondrial Code</option>
            <option value="14">The Alternative Flatworm Mitochondrial Code</option>
            <option value="16">Chlorophycean Mitochondrial Code</option>
            <option value="21">Trematode Mitochondrial Code</option>
            <option value="22">Scenedesmus obliquus Mitochondrial Code</option>
            <option value="23">Thraustochytrium Mitochondrial Code</option>
            <option value="24">Pterobranchia Mitochondrial Code</option>
            <option value="5">Candidate Division SR1 and Gracilibacteria Code</option>
            <option value="26">Pachysolen tannophilus Nuclear Code</option>
        </param>
        <conditional name="output">
            <param argument="--outfmt" type="select" label="Format of output file " help="">
                <option value="5">BLAST XML</option>
                <option value="6">BLAST tabular</option>
                <option value="101">SAM</option>

            </when>
            <when value="101">
                <param argument="--salltitles" type="boolean" truevalue="--salltitles" falsevalue="" checked="true" label="Include full length subject titles in output?" help=""/>
            </when>
        </conditional>
        <param argument="--sensitive" type="boolean" truevalue="--sensitive" falsevalue="" checked="false" label="Trigger the sensitive alignment mode with a 16x9 seed shape configuration?" help=""/>
        <param name="more_sensitive" argument="--more-sensitive" type="boolean" truevalue="--more-sensitive" falsevalue="" checked="false" label="Trigger the more sensitive mode?" help="This mode provides some additional sensitivity compared to the sensitive mode."/>
        <param argument="--gapopen" type="integer" value="11" label="Gap open penalty" help="" />
        <param argument="--gapextend" type="integer" value="1" label="Gap extension penalty" help="" />
        <param argument="--matrix" type="select" label="Scoring matrix" help="In brackets are the supported values for (gap open)/(gap extend)">
            <option value="BLOSUM45">BLOSUM45 ((10-13)/3; (12-16)/2; (16-19)/1)</option>
            <option value="BLOSUM50">BLOSUM50 ((9-13)/3; (12-16)/2; (15-19)/1)</option>

        <test>
            <param name="method_select" value="blastp" />
            <param name="query" value="protein.fasta" ftype="fasta"/>
            <param name="db_source" value="history"/>
            <param name="reference_database" value="db.dmnd"/>
            <param name="query_gencode" value="1"/>
            <param name="outfmt" value="6"/>
            <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
            <param name="sensitive" value=""/>
            <param name="more_sensitive" value=""/>
            <param name="gapopen" value="11"/>
            <param name="gapextend" value="1"/>
            <param name="matrix" value="BLOSUM62"/>
            <param name="seg" value="yes"/>
            <param name="hit_filter_select" value="max"/>

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.

The DIAMOND algorithm is designed for the alignment of large datasets. The algorithm is not efficient for a small number of query sequences or only a single one of them, and speed will be low. BLAST is recommend for small datasets.

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

**Input**

3:830516f9521b

<tool id="bg_diamond" name="Diamond" version="@VERSION@.1">
    <description>alignment tool for short sequences against a protein database</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />

    #end if

    &&

    diamond
        $method_select.method_select
        --threads "\${GALAXY_SLOTS:-12}"
        --db ./database
        --query '$query'
        #if $method_select.method_select == "blastx"
          --query-gencode '$query_gencode'
        #end if

        #if $output.outfmt == "5"
            --outfmt '5'
            --out '$blast_xml'
            $output.salltitles

            --out '$sam_output'
            $output.salltitles
        #end if

        --compress '0'
        #if $sensitivity == "1"
          --sensitive
        #else if $sensitivity == "2"
          --more-sensitive
        #end if

        --gapopen '$gapopen'
        --gapextend '$gapextend'
        --matrix '$matrix'
        --seg '$seg'

        --block-size '$block_size'
]]>
    </command>

    <inputs>
        <conditional name="method_select">
          <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="blastx">
            <param name="query_gencode" argument="--query-gencode" type="select" label="Genetic code used for translation of query in BLASTX mode" help="">
                <option value="1">The Standard Code</option>
                <option value="2">The Vertebrate Mitochondrial Code</option>
                <option value="3">The Yeast Mitochondrial Code</option>
                <option value="4">The Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
                <option value="5">The Invertebrate Mitochondrial Code</option>
                <option value="6">The Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
                <option value="9">The Echinoderm and Flatworm Mitochondrial Code</option>
                <option value="10">The Euplotid Nuclear Code</option>
                <option value="11">The Bacterial, Archaeal and Plant Plastid Code</option>
                <option value="12">The Alternative Yeast Nuclear Code</option>
                <option value="13">The Ascidian Mitochondrial Code</option>
                <option value="14">The Alternative Flatworm Mitochondrial Code</option>
                <option value="16">Chlorophycean Mitochondrial Code</option>
                <option value="21">Trematode Mitochondrial Code</option>
                <option value="22">Scenedesmus obliquus Mitochondrial Code</option>
                <option value="23">Thraustochytrium Mitochondrial Code</option>
                <option value="24">Pterobranchia Mitochondrial Code</option>
                <option value="5">Candidate Division SR1 and Gracilibacteria Code</option>
                <option value="26">Pachysolen tannophilus Nuclear Code</option>
            </param>
          </when>
          <when value="blastp">
          </when>
        </conditional>
        <param argument="--query" type="data" format="fasta,fastq" label="Input query file in FASTA or FASTQ format" />
        <conditional name="ref_db_source">
          <param name="db_source" type="select" label="Will you select a reference database 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 database" help="If your database 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>
          <when value="history">
            <param name="reference_database" type="data" format="dmnd" label="Select the reference database" />
          </when>
        </conditional>
        <conditional name="output">
            <param argument="--outfmt" type="select" label="Format of output file " help="">
                <option value="5">BLAST XML</option>
                <option value="6">BLAST tabular</option>
                <option value="101">SAM</option>

            </when>
            <when value="101">
                <param argument="--salltitles" type="boolean" truevalue="--salltitles" falsevalue="" checked="true" label="Include full length subject titles in output?" help=""/>
            </when>
        </conditional>
        <param name='sensitivity' type="select" label="Sensitivity Mode" help="Choose one of the sensitivity modes. More sensitivity may increase computation time">
          <option value="0" selected="True">Default</option>
          <option value="1">Sensitive</option>
          <option value="2">More Sensitive</option>
        </param>
        <param argument="--gapopen" type="integer" value="11" label="Gap open penalty" help="" />
        <param argument="--gapextend" type="integer" value="1" label="Gap extension penalty" help="" />
        <param argument="--matrix" type="select" label="Scoring matrix" help="In brackets are the supported values for (gap open)/(gap extend)">
            <option value="BLOSUM45">BLOSUM45 ((10-13)/3; (12-16)/2; (16-19)/1)</option>
            <option value="BLOSUM50">BLOSUM50 ((9-13)/3; (12-16)/2; (15-19)/1)</option>

        <test>
            <param name="method_select" value="blastp" />
            <param name="query" value="protein.fasta" ftype="fasta"/>
            <param name="db_source" value="history"/>
            <param name="reference_database" value="db.dmnd"/>
            <param name="outfmt" value="6"/>
            <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
            <param name="sensitivity" value="0"/>
            <param name="gapopen" value="11"/>
            <param name="gapextend" value="1"/>
            <param name="matrix" value="BLOSUM62"/>
            <param name="seg" value="yes"/>
            <param name="hit_filter_select" value="max"/>

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.

The DIAMOND algorithm is designed for the alignment of large datasets. The algorithm is not efficient for a small number of query sequences or only a single one of them, and speed will be low. BLAST is recommended for small datasets.

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

**Input**