annotate diamond.xml @ 1:df7738595640 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/diamond commit cc80b878817d052398db16574917900ebe15292e

<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" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <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
        $method_select
        --threads "\${GALAXY_SLOTS:-12}"
        --db ./database
        --query '$query'
        --query-gencode '$query_gencode'

        #if $output.outfmt == "5"
            --outfmt '5'
            --out '$blast_xml'
            $output.salltitles
        #else if $output.outfmt == "6"
            --outfmt '6' #echo ' '.join(str($output.fields).split(','))
            --out '$blast_tabular'
        #else if $output.outfmt == "101"
            --outfmt '101'
            --out '$sam_output'
            $output.salltitles
        #end if

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

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

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

        --id '$id'
        --query-cover '$query_cover'
        --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>
            </param>
            <when value="5">
                <param argument="--salltitles" type="boolean" truevalue="--salltitles" falsevalue="" checked="true" label="Include full length subject titles in output?" help=""/>
            </when>
            <when value="6">
                <param name="fields" type="select" label="Tabular fields" help="" multiple="true">
                    <option value="qseqid" selected="true">Query Seq - id</option>
                    <option value="sseqid" selected="true">Subject Seq - id</option>
                    <option value="sallseqid">All subject Seq - id(s)</option>
                    <option value="qlen">Query sequence length</option>
                    <option value="slen">Subject sequence length</option>
                    <option value="pident" selected="true">Percentage of identical matches</option>
                    <option value="length" selected="true">Alignment length</option>
                    <option value="nident">Number of identical matches</option>
                    <option value="mismatch" selected="true">Number of mismatches</option>
                    <option value="positive">Number of positive - scoring matches</option>
                    <option value="gapopen" selected="true">Number of gap openings</option>
                    <option value="gaps">Total number of gaps</option>
                    <option value="ppos">Percentage of positive - scoring matches</option>
                    <option value="qstart" selected="true">Start of alignment in query</option>
                    <option value="qend" selected="true">End of alignment in query</option>
                    <option value="sstart" selected="true">Start of alignment in subject</option>
                    <option value="send" selected="true">End of alignment in subject</option>
                    <option value="qseq">Aligned part of query sequence</option>
                    <option value="sseq">Aligned part of subject sequence</option>
                    <option value="evalue" selected="true">Expect value</option>
                    <option value="bitscore" selected="true">Bit score</option>
                    <option value="score">Raw score</option>
                    <option value="qframe">Query frame</option>
                    <option value="stitle">Subject Title</option>
                    <option value="salltitles">All Subject Title(s)</option>
                    <option value="qcovhsp">Query Coverage Per HSP</option>
                </param>
            </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>
            <option value="BLOSUM62" selected="True">BLOSUM62 ((6-11)/2; (9-13)/1)</option>
            <option value="BLOSUM80">BLOSUM80 ((6-9)/2; 13/2; 25/2; (9-11)/1)</option>
            <option value="BLOSUM90">BLOSUM90 ((6-9)/2; (9-11)/1)</option>
            <option value="PAM250">PAM250 ((11-15)/3; (13-17)/2; (17-21)/1)</option>
            <option value="PAM70">PAM70 ((6-8)/2; (9-11)/1)</option>
            <option value="PAM30">PAM30 ((5-7)/2; (8-10)/1)</option>
        </param>
        <param argument="--seg" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Enable SEG masking of low complexity segments in the query?" help=""/>
        <conditional name="hit_filter">
            <param name="hit_filter_select" type="select" label="Method to restrict the number of hits?">
                <option value="max">Maximum number of target sequences</option>
                <option value="top">Percentage of top alignment score</option>
            </param>
            <when value="max">
                <param name="max_target_seqs" argument="--max-target-seqs" type="integer" value="25" label="The maximum number of target sequences per query to keep alignments for" help="" />
            </when>
            <when value="top">
                <param argument="--top" type="integer" value="0" label="Keep alignments within the given percentage range of the top alignment score for a quer" help="" />
            </when>
        </conditional>
        <conditional name="filter_score">
            <param name="filter_score_select" type="select" label="Method to filter?" help="(--evalue/--min-score)">
                <option value="evalue">Maximum e-value to report alignments</option>
                <option value="min-score">Minimum bit score to report alignments</option>
            </param>
            <when value="evalue">
                <param argument="--evalue" type="float" value="0.001" label="Maximum expected value to keep an alignment" />
            </when>
            <when value="min-score">
                <param name="min_score" argument="--min-score" type="integer" value="0" label="Minimum bit score to keep an alignment" help="(--min-score)" />
            </when>
        </conditional>
        <param argument="--id" type="integer" value="0" label="Minimum identity percentage to report an alignment" help="" />
        <param name="query_cover" argument="--query-cover" type="integer" value="0" label="Minimum query cover percentage to report an alignment" help="" />
        <param name="block_size" argument="--block-size" type="float" value="2" label="Block size in billions of sequence letters to be processed at a time" help="" />
    </inputs>

    <outputs>
        <data format="xml" name="blast_xml" label="${tool.name} on ${on_string}">
            <filter>output["outfmt"] == "5"</filter>
        </data>
        <data format="tabular" name="blast_tabular" label="${tool.name} on ${on_string}">
            <filter>output["outfmt"] == "6"</filter>
        </data>
        <data format="sam" name="sam_output" label="${tool.name} on ${on_string}">
            <filter>output["outfmt"] == "101"</filter>
        </data>
    </outputs>

    <tests>
        <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"/>
            <param name="max_target_seqs" value="25" />
            <param name="filter_score_select" value="evalue"/>
            <param name="evalue" value="0.001" />
            <param name="id" value="0"/>
            <param name="query_cover" value="0"/>
            <param name="block_size" value="2"/>
            <output name="blast_tabular" file="diamond_results.tabular"/>
        </test>
    </tests>

    <help>
<![CDATA[

**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.

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**

Input data is a large protein or nucleotide sequence file.


**Output**

Diamond gives you a tabular output file with 12 columns:

Column 	Description
1 	    Query Seq-id (ID of your sequence)
2 	    Subject Seq-id (ID of the database hit)
3 	    Percentage of identical matches
4 	    Alignment length
5 	    Number of mismatches
6 	    Number of gap openings
7 	    Start of alignment in query
8 	    End of alignment in query
9 	    Start of alignment in subject (database hit)
10 	    End of alignment in subject (database hit)
11 	    Expectation value (E-value)
12 	    Bit score


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