annotate sam_dump.xml @ 10:8c00bc7fd8de draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sra-tools commit 48c9d7f30655d48c9b46b9ca7a17c454eb54694d

<tool id="sam_dump" name="Download and Extract Reads in BAM" version="@VERSION@.3">
    <description>format from NCBI SRA</description>
    <macros>
        <import>sra_macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <version_command>sam-dump --version</version_command>
    <command detect_errors="exit_code">
<![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 &&
        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 ) == "" ):
            ASCP_PATH=`command -v ascp` &&
            ASCP_KEY=`dirname \$ASCP_PATH`/asperaweb_id_dsa.openssh || true &&
            prefetch -X 200G --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
        sam-dump --log-level fatal --disable-multithreading
        #if str( $adv.region ) != "":
            --aligned-region '$adv.region'
        #end if
        #if str( $adv.matepairDist ) != "":
            --matepair-distance '$adv.matepairDist'
        #end if
        #if str( $adv.minMapq ) != "":
            --min-mapq '$adv.minMapq'
        #end if
        --header
        #if str( $adv.alignments ) == "both":
            --unaligned
        #end if
        #if str( $adv.alignments ) == "unaligned":
            --unaligned-spots-only
        #end if
        #if (str( $adv.primary ) == "yes") and (str ( $adv.alignments != "unaligned") ):
            --primary
        #end if
        #if $input.input_select == "file":
            '$input.file'
        #elif $input.input_select == "accession_number":
            "\$acc"
        #elif $input.input_select=="file_list":
            "\$acc"
        #end if

        #if str( $outputformat ) == "bam":
            | samtools view -Sb - 2> /dev/null
        #end if
        #if $input.input_select == "file":
            > '$output_file'
        #elif $input.input_select == "accession_number":
            > '$output_accession' )
        #end if

        #if $input.input_select=="file_list":
                 #if str( $outputformat ) == "bam":
                      > "\$acc.bam"
                 #elif str( $outputformat ) == "sam":
                      > "\$acc.sam"
                 #end if
        ) ; done
        #end if

        ]]>
    </command>
    <inputs>
        <expand macro="input_conditional"/>
        <param name="outputformat" type="select" display="radio" label="select output format" help="In vast majority of cases you want to download data in bam format. It is more compact and is accepted by all downstream tools.">
            <option value="bam">bam</option>
            <option value="sam">sam</option>
        </param>
        <section name="adv" title="Advanced Options" expanded="False">
            <expand macro="alignments"/>
            <expand macro="region"/>
            <expand macro="matepairDist"/>
            <param name="primary" type="select" value="no">
                <label>only primary aligments</label>
                <option value="no">No</option>
                <option value="yes">Yes</option>
            </param>
            <expand macro="minMapq"></expand>
        </section>
    </inputs>
    <outputs>
        <collection name="output_collection" type="list" label="SAM/BAM data (fastq-dump)">
          <filter>input['input_select'] == "file_list"</filter>
          <discover_datasets pattern="(?P&lt;designation&gt;.+)\.bam" directory="." ext='bam'/>
          <discover_datasets pattern="(?P&lt;designation&gt;.+)\.sam" directory="." ext='sam'/>
        </collection>
        <data name="output_accession" format="bam" label="${input.accession} (sam-dump)">
            <filter>input['input_select'] == "accession_number"</filter>
            <change_format>
                <when input="outputformat" value="sam" format="sam"/>
            </change_format>
        </data>
        <data name="output_file" format="bam" label="${input.file.name} (sam-dump)">
            <filter>input['input_select'] == "file"</filter>
            <change_format>
                <when input="outputformat" value="sam" format="sam"/>
            </change_format>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input_select" value="accession_number"/>
            <param name="accession" value="SRR925743"/>
            <param name="outputformat" value="sam"/>
            <param name="region" value="17:41243452-41277500"/>
            <output name="output_accession" file="sam_dump_result.sam" compare="contains" ftype="sam"/>
        </test>
    </tests>
    <help><![CDATA[

**What it does?**

This tool extracts data (in BAM_ format) from the Short Read Archive (SRA) at the National Center for Biotechnology Information (NCBI). It is based on the sam-dump_ utility of the SRA Toolkit.

**How to use it?**

There are three ways in which you can download data:

 1. Data for single accession
 2. Multiple datasets using a list of accessions
 3. Extract data from already uploaded SRA dataset

Below we discuss each in detail.

------

**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. As a result you will get a single BAM (or SAM) dataset in the history. 

-----

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

A more realistic scenario is when you want to upload a number of datasets at once. To do this you need a list of accession, where there is only one accession per line (see below for information on how to generate such a file). Once you have this file:

 1. Upload it into your history using Galaxy's upload tool
 2. Once the list of accessions is uploaded choose *List of SRA accessions, one per line* from **select input type** dropdown
 3. Choose uploaded file within the **sra accession list** field
 4. Click **Execute**

.. class:: warningmark

BAM datasets produced by this option will be saved in Galaxy's history as a collection_ - a single history element containing multiple datasets. 

-----

**Extract data from already uploaded SRA dataset**

If a SRA dataset is present in the history, it can be converted into BAM dataset by setting **select input type** drop-down to *SRA archive in current history*. Just like in the case of extracting data for single accession number a single BAM dataset will be generated in the history. 

@ACCESSION_LIST_HOWTO@

-----

.. _BAM: https://samtools.github.io/hts-specs/SAMv1.pdf
.. _sam-dump: http://ncbi.github.io/sra-tools/sam-dump.html
.. _collection: https://galaxyproject.org/tutorials/collections/
.. _link: http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=studies

@SRATOOLS_ATTRRIBUTION@
    ]]></help>
    <expand macro="citation"/>
</tool>