comparison fasterq_dump.xml @ 17:c441583adae5 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sra-tools commit e00e33a3405201e8decbbb641ad0a8c3e16c8bef"

16:aad3885b3216

<tool id="fasterq_dump" name="Faster Download and Extract Reads in FASTQ" version="@VERSION@+galaxy1" profile="18.01">
    <description>format from NCBI SRA</description>
    <macros>
        <import>sra_macros.xml</import>
    </macros>
    <expand macro="requirements"/>

    #if $input.input_select == "file":
        acc='${input.file.name}' &&
        ln -s '${input.file}' "\$acc" &&
    #end if
    @CONFIGURE_TIMEOUT@
    fasterq-dump "\$acc" -e \${GALAXY_SLOTS:-1}
    $adv.split
    #if str( $adv.minlen ) != "":
        --min-read-len "$adv.minlen"
    #end if
    $adv.skip_technical >> $log 2>&1 
    &&
    mkdir -p output &&
    mkdir -p outputOther &&
    count=`ls *.fastq | wc -l` &&
    echo "There are \$count fastq" &&
    data=(\$(ls *.fastq)) &&
    if [ "\$count" -eq 1 ]; then
        gzip -c "\${data[0]}" > output/"\${acc}"__single.fastqsanger.gz &&
        rm "\${data[0]}";
    elif [ "$adv.split" = "--split-3" ]; then
        if [ -e "\${acc}".fastq ]; then
            gzip -c "\${acc}".fastq > outputOther/"\${acc}"__single.fastqsanger.gz;
        fi &&
        gzip -c "\${acc}"_1.fastq > output/"\${acc}"_forward.fastqsanger.gz &&
        gzip -c "\${acc}"_2.fastq > output/"\${acc}"_reverse.fastqsanger.gz &&
        rm "\${acc}"*.fastq;
    elif [ "\$count" -eq 2 ]; then
        #if $adv.skip_technical:
            gzip -c "\${data[0]}" > output/"\${acc}"_forward.fastqsanger.gz &&
            gzip -c "\${data[1]}" > output/"\${acc}"_reverse.fastqsanger.gz &&
        #else
            gzip -c "\${data[0]}" > outputOther/"\${data[0]}"sanger.gz &&
            gzip -c "\${data[1]}" > outputOther/"\${data[1]}"sanger.gz &&
        #end if
        rm "\${data[0]}" &&
        rm "\${data[1]}";
    else
        for file in \${data[*]}; do
            gzip -c "\$file" > outputOther/"\$file"sanger.gz &&
            rm "\$file";
        done;
    fi;
    #if $input.input_select=="file_list":
        ) ; done

        <!-- 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;[^_]+)\.fastqsanger.gz" directory="output" ext="fastqsanger.gz" />
        </collection>
        <collection name="output_collection" type='list' label="Single-end data (fasterq-dump)">
            <discover_datasets pattern="(?P&lt;designation&gt;.+)__single\.fastqsanger.gz" directory="output" ext='fastqsanger.gz'/>
        </collection>

------

**Uploading data for a single accession**

When you type a single accession number (e.g., `SRR1582967`) into **Accession** box and click **Execute** the tool will fetch data for you. 

-----

**Uploading multiple datasets using a list of accessions**

-----

**Output**

In every case, fastq datasets produced will be saved in Galaxy's history as a collection_ - a single history element containing multiple datasets. 
In fact, three collections will be produced: one containing paired-end data, another containing single-end data, and a third one which contains reads which could not be classified.
Some collections may be empty if the accessions provided in the list does not contain one of the type of data.

.. class:: warningmark

17:c441583adae5

<tool id="fasterq_dump" name="Faster Download and Extract Reads in FASTQ" version="@VERSION@+galaxy2" profile="18.01">
    <description>format from NCBI SRA</description>
    <macros>
        <import>sra_macros.xml</import>
    </macros>
    <expand macro="requirements"/>

    #if $input.input_select == "file":
        acc='${input.file.name}' &&
        ln -s '${input.file}' "\$acc" &&
    #end if
    @CONFIGURE_TIMEOUT@
    @CONFIGURE_RETRY@
    while [ \$SRA_PREFETCH_ATTEMPT -le \$SRA_PREFETCH_RETRIES ] ; do
        fasterq-dump "\$acc" -e \${GALAXY_SLOTS:-1}
        $adv.split
        #if str( $adv.minlen ) != "":
            --min-read-len "$adv.minlen"
        #end if
        $adv.skip_technical >> $log 2>&1 ;
        if [ \$? == 0 ] ; then
            break ;
        else
            echo "Prefetch attempt \$SRA_PREFETCH_ATTEMPT of \$SRA_PREFETCH_RETRIES exited with code \$?" ;
            SRA_PREFETCH_ATTEMPT=`expr \$SRA_PREFETCH_ATTEMPT + 1` ;
            sleep 1 ;
        fi ;
    done &&
    mkdir -p output &&
    mkdir -p outputOther &&
    count=`ls *.fastq | wc -l` &&
    echo "There are \$count fastq" &&
    data=(\$(ls *.fastq)) &&
    if [ "\$count" -eq 1 ]; then
        @COMPRESS@ "\${data[0]}" > output/"\${acc}"__single.fastqsanger.gz &&
        rm "\${data[0]}";
    elif [ "$adv.split" = "--split-3" ]; then
        if [ -e "\${acc}".fastq ]; then
            @COMPRESS@ "\${acc}".fastq > outputOther/"\${acc}"__single.fastqsanger.gz;
        fi &&
        @COMPRESS@ "\${acc}"_1.fastq > output/"\${acc}"_forward.fastqsanger.gz &&
        @COMPRESS@ "\${acc}"_2.fastq > output/"\${acc}"_reverse.fastqsanger.gz &&
        rm "\${acc}"*.fastq;
    elif [ "\$count" -eq 2 ]; then
        #if $adv.skip_technical:
            @COMPRESS@ "\${data[0]}" > output/"\${acc}"_forward.fastqsanger.gz &&
            @COMPRESS@ "\${data[1]}" > output/"\${acc}"_reverse.fastqsanger.gz &&
        #else
            @COMPRESS@ "\${data[0]}" > outputOther/"\${data[0]}"sanger.gz &&
            @COMPRESS@ "\${data[1]}" > outputOther/"\${data[1]}"sanger.gz &&
        #end if
        rm "\${data[0]}" &&
        rm "\${data[1]}";
    else
        for file in \${data[*]}; do
            @COMPRESS@ "\$file" > outputOther/"\$file"sanger.gz &&
            rm "\$file";
        done;
    fi;
    #if $input.input_select=="file_list":
        ) ; done

        <!-- 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;[^_]+)\.fastqsanger.gz" directory="output" ext="fastqsanger.gz" />
        </collection>
        <collection name="output_collection" type='list' label="Single-end data (fasterq-dump)">
            <discover_datasets pattern="(?P&lt;designation&gt;.+)__single\.fastqsanger.gz" directory="output" ext='fastqsanger.gz'/>
        </collection>

------

**Uploading data for a single accession**

When you type a single accession number (e.g., `SRR1582967`) into **Accession** box and click **Execute** the tool will fetch data for you.

-----

**Uploading multiple datasets using a list of accessions**

-----

**Output**

In every case, fastq datasets produced will be saved in Galaxy's history as a collection_ - a single history element containing multiple datasets.
In fact, three collections will be produced: one containing paired-end data, another containing single-end data, and a third one which contains reads which could not be classified.
Some collections may be empty if the accessions provided in the list does not contain one of the type of data.

.. class:: warningmark