annotate fastq_dump.xml @ 0:b723c120161a draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sra-tools commit d555f296be01d0c0fa5ac28d28a48cf4ada98297

<tool id="fastq_dump" name="Extract reads" version="1.2.5">
    <description>in FASTQ/A format from NCBI SRA.</description>
    <macros>
        <import>sra_macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <stdio>
        <exit_code range="127" level="fatal" description="Could not locate fastq-dump binary"/>
    </stdio>
    <version_command>fastq-dump --version</version_command>
    <command>
        <![CDATA[
    ## Need to set the home directory to the current working directory,
    ## else the tool tries to write to home/.ncbi and fails when used 
    ## with a cluster manager. 
    export HOME=\$PWD &&
    vdb-config --restore-defaults &&
    #if $input.input_select == "file":
        fastq-dump --log-level fatal --accession '${input.file.name}'
    #else:
        vdb-config -s "/repository/user/main/public/root=\$PWD" &&
        ## Do not use prefetch if region is specified, to avoid downloading
        ## the complete sra file.
        #if ( str( $adv.region ) == "" ) and ( str( $adv.minID ) == "" ) and ( str( $adv.maxID ) == "" ):
            ASCP_PATH=`command -v ascp` &&
            ASCP_KEY=`dirname \$ASCP_PATH`/asperaweb_id_dsa.openssh || true &&
            prefetch --ascp-path "\$ASCP_PATH|\$ASCP_KEY" $input.accession &&
            ## Duplicate vdb-config, in case settings changed between prefetch and
            ## dump command.
            vdb-config -s "/repository/user/main/public/root=\$PWD" &&
            #end if
        fastq-dump --accession "$input.accession"
    #end if
    --defline-seq '@\$sn[_\$rn]/\$ri'
    --stdout
    $adv.split
    #if str( $adv.alignments ) == "aligned":
        --aligned
    #end if
    #if str( $adv.alignments ) == "unaligned":
        --unaligned
    #end if
    #if str( $adv.minID ) != "":
        --minSpotId "$adv.minID"
    #end if
    #if str( $adv.maxID ) != "":
        --maxSpotId "$adv.maxID"
    #end if
    #if str( $adv.minlen ) != "":
        --minReadLen "$adv.minlen"
    #end if
    #if str( $adv.readfilter ) != "":
        --read-filter "$adv.readfilter"
    #end if
    #if str( $adv.region ) != "":
        --aligned-region "$adv.region"
    #end if
    #if str( $adv.spotgroups ) != "":
        --spot-groups "$adv.spotgroups"
    #end if
    #if str( $adv.matepairDist ) != "":
        --matepair-distance "$adv.matepairDist"
    #end if
    $adv.clip
    $adv.skip_technical
    #if str( $outputformat ) == "fasta":
        --fasta
    #end if
    #if $input.input_select=="file":
        "$input.file" > "$output_file"
    #else:
        "$input.accession" > "$output_accession"
    #end if
    ]]>
    </command>
    <inputs>
        <expand macro="input_conditional"/>
        <param name="outputformat" type="select" label="select output format">
            <option value="fastqsanger">fastq</option>
            <option value="fasta">fasta</option>
        </param>
        <section name="adv" title="Advanced Options" expanded="False">
            <param name="minID" type="integer" label="minimum spot ID" optional="true"/>
            <param name="maxID" type="integer" label="maximum spot ID" optional="true"/>
            <param name="minlen" type="integer" label="minimum read length" optional="true"/>
            <param name="split" type="boolean" checked="true" truevalue="--split-spot" falsevalue="">
                <label>split spot by read pairs</label>
            </param>
            <expand macro="alignments"/>
            <expand macro="region"/>
            <expand macro="matepairDist"/>
            <param name="readfilter" type="select" value="">
                <label>filter by value</label>
                <option value="">None</option>
                <option value="pass">pass</option>
                <option value="reject">reject</option>
                <option value="criteria">criteria</option>
                <option value="redacted">redacted</option>
            </param>
            <param name="spotgroups" type="text" label="filter by spot-groups" optional="true"/>
            <param name="clip" type="boolean" truevalue="--clip" falsevalue="">
                <label>apply left and right clips</label>
            </param>
            <param name="skip_technical" type="boolean" truevalue="--skip-technical" falsevalue="" checked="False" label="Dump only biological reads"/>
        </section>
    </inputs>
    <outputs>
        <data format="fastq" name="output_accession" label="${input.accession}.${outputformat}">
            <filter>input['input_select'] == "accession_number"</filter>
            <change_format>
                <when input="outputformat" value="fasta" format="fasta"/>
            </change_format>
        </data>
        <data format="fastq" name="output_file" label="${input.file.name}.${outputformat}">
            <filter>input['input_select'] == "file"</filter>
            <change_format>
                <when input="outputformat" value="fasta" format="fasta"/>
            </change_format>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input_select" value="accession_number"/>
            <param name="outputformat" value="fastqsanger"/>
            <param name="accession" value="SRR044777"/>
            <param name="skip_technical" value="True"/>
            <output name="output_accession">
                <assert_contents>
                    <not_has_text text="rRNA_primer"/>
                    <has_text text="F47USSH02GNP1D" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_select" value="accession_number"/>
            <param name="outputformat" value="fastqsanger"/>
            <param name="accession" value="SRR925743"/>
            <param name="maxID" value="5"/>
            <output name="output_accession" file="fastq_dump_result.fastq" ftype="fastq"/>
        </test>
    </tests>
    <help>
        This tool extracts reads from SRA archives using fastq-dump.
        The fastq-dump program is developed at NCBI, and is available at
        http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software.
        @SRATOOLS_ATTRRIBUTION@
    </help>
    <expand macro="citation"/>
</tool>