comparison fastq_dump.xml @ 1:462ee06c9358 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sra-tools commit 4defaa3ff1c21e2ec39033bfe63ee69471104ede

0:b723c120161a

<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"/>

        <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 &&

        ## 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":

    #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">

            </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>

1:462ee06c9358

<tool id="fastq_dump" name="Extract reads" version="1.3.0">
    <description>in FASTQ/A format from NCBI SRA.</description>
    <macros>
        <import>sra_macros.xml</import>
    </macros>
    <expand macro="requirements"/>

        <exit_code range="127" level="fatal" description="Could not locate fastq-dump binary"/>
    </stdio>
    <version_command>fastq-dump --version</version_command>
    <command>
        <![CDATA[

    #if $input.input_select=="file_list":
      for acc in `cat $input.file_list` ;
      do
    #elif $input.input_select=="accession_number":
      acc="$input.accession" &&
    #end if

    #if $input.input_select=="file_list" or $input.input_select=="accession_number":
          [ ""\$acc" =~ ^[E|S|D]RR[0-9]{1,}$" ] && (
    #end if
    
    ## 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 &&

        ## 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" "\$acc" &&
            ## 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 "\$acc"
        --split-files
    #end if
    --defline-seq '@\$sn[_\$rn]/\$ri'

    $adv.split
    #if str( $adv.alignments ) == "aligned":
        --aligned
    #end if
    #if str( $adv.alignments ) == "unaligned":

    #if str( $adv.matepairDist ) != "":
        --matepair-distance "$adv.matepairDist"
    #end if
    $adv.clip
    $adv.skip_technical
    
    #if str( $outputformat ) == "fasta":
        --fasta
    #end if
    #if $input.input_select=="file":
        --stdout
        "$input.file" > "$output_file"
    #elif $input.input_select=="file_list":
        "\$acc"
    #else:
         --stdout
        "\$acc" > "$output_accession" )
    #end if

    #if $input.input_select=="file_list":
    ) ; done

    ;


    #if str( $outputformat ) == "fasta":
    
        for f in *_2.fasta ; do   mv "\$f" "`basename \$f _2.fasta`_reverse.fasta" ;  mv "`basename \$f _2.fasta`_1.fasta" "`basename \$f _2.fasta`_forward.fasta"  ; done &&
        for f in *_1.fasta; do mv "\$f" "`basename \$f _1.fasta`__single.fasta"; done
        
    #else:

        for f in *_2.fastq ; do   mv "\$f" "`basename \$f _2.fastq`_reverse.fastq" ;  mv "`basename \$f _2.fastq`_1.fastq" "`basename \$f _2.fastq`_forward.fastq"  ; done &&
        for f in *_1.fastq; do mv "\$f" "`basename \$f _1.fastq`__single.fastq"; done
        
    #end if





    #end if

    
    ]]>
    </command>
    <inputs>
        <expand macro="input_conditional"/>
        <param name="outputformat" type="select" label="select output format">

            </param>
            <param name="skip_technical" type="boolean" truevalue="--skip-technical" falsevalue="" checked="False" label="Dump only biological reads"/>
        </section>
    </inputs>
    <outputs>
      <collection name="list_paired" type="list:paired" label="Pair-end Fast(q|a)">
        <filter>input['input_select'] == "file_list"</filter>
        <!-- Use named regex group to grab pattern
             <identifier_0>_<identifier_1>.fq. Here identifier_0 is the list
             identifier in the nested collection and identifier_1 is either
             forward or reverse (for instance samp1_forward.fq).
        -->
        <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.fastq" ext="fastqsanger" visible="false" />
        <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.fasta" ext="fasta" visible="false" />
      </collection>
      <collection name="output_collection" type='list' label="Single-end Fast(q|a)">
        <filter>input['input_select'] == "file_list"</filter>
        <discover_datasets pattern="(?P&lt;designation&gt;.+)__single\.fastq" directory="." ext='fastqsanger'/>
        <discover_datasets pattern="(?P&lt;designation&gt;.+)__single\.fasta" directory="." ext='fasta'/>
      </collection>
      <data format="fastqsanger" name="output_accession" >
        <filter>input['input_select'] == "accession_number"</filter>
        <change_format>
          <when input="outputformat" value="fasta" format="fasta"/>
        </change_format>
      </data>
      <data format="fastqsanger" 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="fastqsanger"/>
      </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.
        
        NB: Single-end or pair-end collections may be empty if given SRRs LibraryLayout contains only either SINGLE or PAIRED respectively
        @SRATOOLS_ATTRRIBUTION@
    </help>
    <expand macro="citation"/>
  </tool>