annotate diamond.xml @ 7:62c9df8382c2 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/diamond commit b2d290a8b609ebbc7f4b93716370143c41062ad4"

<tool id="bg_diamond" name="Diamond" version="@VERSION@.0" profile="19.01">
    <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
        $method_cond.method_select
        --threads "\${GALAXY_SLOTS:-12}"
        --db ./database
        --query '$query'
        #if $method_cond.method_select == "blastx"
          --query-gencode '$method_cond.query_gencode'
          --strand '$method_cond.query_strand'
	  --min-orf $method_cond.min_orf
	  #if $method_cond.frameshift_cond.frameshift_select == 'yes'
	          --frameshift $method_cond.frameshift_cond.frameshift
		  $method_cond.frameshift_cond.range_culling
          #end if
        #end if

        @OUTPUT_ARGS@

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

        #if str($gapopen) != "":
          --gapopen '$gapopen'
        #end if
        #if str($gapextend) != "":
          --gapextend '$gapextend'
        #end if
        --matrix '$matrix'
        --comp-based-stats '$comp_based_stats'
        --masking '$masking'

        @HITFILTER_ARGS@

        #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'
        --subject-cover '$subject_cover'
        --block-size '$block_size'
        #if str($unal) == '1':
            --unal 1 --un '$unalqueries'
        #end if
        $no_self_hits
        #if $tax_cond.tax_select == 'file':
            --taxonlist `cat '$tax_cond.taxonlistfile' | grep -v "^#" | grep -v "^$" | tr "\n" "," | sed 's/,$//'`
        #else if  $tax_cond.tax_select == 'list':
            --taxonlist '$tax_cond.taxonlist'
        #end if
]]>
    </command>
    <inputs>
        <conditional name="method_cond">
            <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="25">Candidate Division SR1 and Gracilibacteria Code</option>
                    <option value="26">Pachysolen tannophilus Nuclear Code</option>
                </param>
                <param argument="--min-orf" name="min_orf" type="integer" value="1" label="ignore translated sequences without an open reading frame of at least this length" help="By default this feature is disabled for sequences of length below 30, set to 20 for sequences of length below 100, and set to 40 otherwise. Setting this option to 1 will disable this feature" />

                <param name="query_strand" argument="--strand" type="select" label="query strands to search" help="">
                    <option value="both" selected="True">Both</option>
                    <option value="plus">Plus</option>
                    <option value="minus">Minus</option>
                </param>
                <conditional name="frameshift_cond">
                    <param name="frameshift_select" type="select" label="Allow for frameshifts?" help="">
                        <option value="yes">yes</option>
                        <option value="no" selected="true">no</option>
                    </param>
                    <when value="yes">
                        <param argument="--range-culling" name="range_culling" type="boolean" truevalue="--range-culling" falsevalue="" checked="false" label="restrict hit culling to overlapping query ranges" help="This feature is designed for long query DNA sequences that may span several genes. In these cases, the default of reporting the 25 best overall hits could cause hits to a lower scoring gene to be overshadowed. But just increasing the number of alignments reported will bloat the output size and reduce performance. Using this feature along with -k 25 (default), a hit will only be deleted if at least 50% of its query range is spanned by at least 25 higher or equal scoring hits. Using this feature along with --top 10, a hit will only be deleted if its score is more than 10% lower than that of a higher scoring hit over at least 50% of its query range. The percentage is configurable using --range-cover. Note that this feature is currently only available in frameshift alignment mode"/>
                        <param argument="--frameshift" type="integer" value="0" label="frame shift penalty" help="Values around 15 are reasonable for this parameter. Enabling this feature will have the aligner tolerate missing bases in DNA sequences and is most recommended for long, error-prone sequences like MinION reads. In the pairwise output format, frameshifts will be indicated by \ and / for a shift by +1 and -1 nucleotide in the direction of translation respectively." />
                    </when>
                    <when value="no"/>
                </conditional>
            </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>
        <expand macro="output_type_macro" />
        <param name="no_self_hits" argument="--no-self-hits" type="boolean" truevalue="--no-self-hits" falsevalue="" checked="true" label="suppress reporting of identical self hits?" help=""/>
        <param name='sensitivity' type="select" label="Sensitivity Mode" help="Choose one of the sensitivity modes. The default mode is mainly designed for short read alignment, i.e. finding significant matches of >50 bits on 30-40aa fragments. The sensitive mode is a lot more sensitive than the default and generally recommended for aligning longer sequences. The more sensitive mode provides even more sensitivity. 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="--matrix" type="select" label="Scoring matrix" help="In parentheses are the supported values for (gap open)/(gap extend). In brackets are default gap penalties">
            <option value="BLOSUM45">BLOSUM45 ((10-13)/3; (12-16)/2; (16-19)/1) [14/2]</option>
            <option value="BLOSUM50">BLOSUM50 ((9-13)/3; (12-16)/2; (15-19)/1) [13/2]</option>
            <option value="BLOSUM62" selected="True">BLOSUM62 ((6-11)/2; (9-13)/1) [11/1]</option>
            <option value="BLOSUM80">BLOSUM80 ((6-9)/2; 13/2; 25/2; (9-11)/1) [10/1]</option>
            <option value="BLOSUM90">BLOSUM90 ((6-9)/2; (9-11)/1) [10/1]</option>
            <option value="PAM250">PAM250 ((11-15)/3; (13-17)/2; (17-21)/1) [14/2]</option>
            <option value="PAM70">PAM70 ((6-8)/2; (9-11)/1) [10/1]</option>
            <option value="PAM30">PAM30 ((5-7)/2; (8-10)/1) [9/1]</option>
        </param>
        <param argument="--gapopen" type="integer" optional="True" value="" label="Gap open penalty" help="leave empty for default (see scoring matrix)" />
        <param argument="--gapextend" type="integer" optional="True" value="" label="Gap extension penalty" help="leave empty for default (see scoring matrix)" />
        <param name="comp_based_stats" argument="--comp-based-stats" type="boolean" truevalue="1" falsevalue="0" checked="true" label="enable composition based statistics?" help="Compositionally biased sequences often cause false positive matches, which are effectively filtered by this algorithm in a way similar to the composition based statistics used by BLAST"/>
        <param argument="--masking" type="boolean" truevalue="1" falsevalue="0" checked="true" label="enable masking of low complexity regions?" help="Masked residues appear in the output as X"/>
        <conditional name="tax_cond">
            <param name="tax_select" type="select" label="Restrict search taxonomically?" help="Any taxonomic rank can be used, and only reference sequences matching one of the specified taxon ids will be searched against">
                <option value="no" selected="True">No</option>
                <option value="list">list of taxids entered manually</option>
                <option value="file">list of taxids from single column tabular file</option>
            </param>
            <when value="no"/>
            <when value="list">
                <param name="taxonlist" argument="--taxonlist" type="text" value="" label="comma separated list of taxon ids" help="" />
            </when>
            <when value="file">
                <param name="taxonlistfile" argument="--taxonlist" type="data" format="tabular" 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" selected="True">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>
        <expand macro="hit_filter_macro" />
        <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="subject_cover" argument="--subject-cover" type="integer" value="0" label="Minimum subject 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="" />
        <param argument="--unal" type="boolean" truevalue="1" falsevalue="0" checked="false" label="report unaligned queries" help=""/>
    </inputs>
    <outputs>
        <expand macro="output_macro" />
        <data format="fasta" name="unalqueries" label="${tool.name} on ${on_string} (unaligned queries)">
            <filter>unal == "1"</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <conditional name="method_cond">
                <param name="method_select" value="blastp" />
            </conditional>
            <param name="query" value="protein.fasta" ftype="fasta"/>
            <conditional name="ref_db_source">
                <param name="db_source" value="history"/>
                <param name="reference_database" value="db.dmnd"/>
            </conditional>
            <conditional name="output">
                <param name="outfmt" value="6"/>
                <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
            </conditional>
            <param name="sensitivity" value="0"/>
            <param name="matrix" value="BLOSUM62"/>
            <param name="comp-based-stat" value="1"/>
            <param name="masking" value="1"/>
            <conditional name="hit_filter">
                <param name="hit_filter_select" value="max"/>
                <param name="max_target_seqs" value="25" />
            </conditional>
            <conditional name="filter_score">
                <param name="filter_score_select" value="evalue"/>
                <param name="evalue" value="0.001" />
            </conditional>
            <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>
        <test>
            <conditional name="method_cond">
                <param name="method_select" value="blastp" />
            </conditional>
            <param name="query" value="protein.fasta" ftype="fasta"/>
            <conditional name="ref_db_source">
                <param name="db_source" value="history"/>
                <param name="reference_database" value="db-wtax.dmnd"/>
            </conditional>
            <conditional name="tax_cond">
		    <param name="tax_select" value="list"/>
                    <param name="taxonlist" value="2" />
            </conditional>
            <conditional name="output">
                <param name="outfmt" value="6"/>
                <param name="fields" value="qseqid,sseqid,pident,length,mismatch,gapopen,qstart,qend,sstart,send,evalue,bitscore"/>
            </conditional>
            <param name="sensitivity" value="0"/>
            <param name="matrix" value="BLOSUM62"/>
            <param name="comp-based-stat" value="1"/>
            <param name="masking" value="1"/>
            <conditional name="hit_filter">
                <param name="hit_filter_select" value="max"/>
                <param name="max_target_seqs" value="25" />
            </conditional>
            <conditional name="filter_score">
                <param name="filter_score_select" value="evalue"/>
                <param name="evalue" value="0.001" />
            </conditional>
            <param name="id" value="0"/>
            <param name="query_cover" value="0"/>
            <param name="block_size" value="2"/>
            <output name="blast_tabular" file="diamond_results.wtax.tabular"/>
        </test>
        <test>
            <conditional name="method_cond">
                <param name="method_select" value="blastx" />
                <conditional name="frameshift_cond">
                    <param name="frameshift_select" value="yes"/>
                </conditional>
            </conditional>
            <param name="query" value="nucleotide.fasta" ftype="fasta"/>
            <conditional name="ref_db_source">
                <param name="db_source" value="history"/>
                <param name="reference_database" value="db.dmnd"/>
            </conditional>
            <conditional name="output">
                <param name="outfmt" value="0"/>
            </conditional>
            <param name="sensitivity" value="0"/>
            <param name="matrix" value="BLOSUM62"/>
            <param name="comp-based-stat" value="1"/>
            <param name="masking" value="1"/>
            <conditional name="hit_filter">
                <param name="hit_filter_select" value="top"/>
                <param name="top" value="10" />
            </conditional>
            <conditional name="filter_score">
                <param name="filter_score_select" value="score"/>
                <param name="evalue" value="1" />
            </conditional>
            <param name="id" value="0"/>
            <param name="query_cover" value="0"/>
            <param name="block_size" value="2"/>
            <output name="blast_tabular" file="diamond_results.pairwise"/>
        </test>
        <test>
            <conditional name="method_cond">
                <param name="method_select" value="blastp" />
            </conditional>
            <param name="query" value="protein.fasta" ftype="fasta"/>
            <conditional name="ref_db_source">
                <param name="db_source" value="history"/>
                <param name="reference_database" value="db-wtax.dmnd"/>
            </conditional>
            <conditional name="output">
                <param name="outfmt" value="100"/>
            </conditional>
            <output name="daa_output" file="diamond_results.daa" compare="sim_size" delta="10"/>
        </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 recommended 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>