jasmine_amir@0: <macros>
jasmine_amir@2:     <token name="@TOOL_VERSION@">3.0.3</token>
jasmine_amir@0:     <token name="@VERSION_SUFFIX@">0</token>
jasmine_amir@0:     <xml name="edam_ontology">
jasmine_amir@0:         <edam_topics>
jasmine_amir@0:             <edam_topic>topic_0622</edam_topic> <!-- Genomics -->
jasmine_amir@0:             <edam_topic>topic_0091</edam_topic> <!-- Bioinformatics -->
jasmine_amir@0:         </edam_topics>
jasmine_amir@0:         <edam_operations>
jasmine_amir@0:             <edam_operation>operation_2422</edam_operation> <!-- Data retrieval -->
jasmine_amir@0:             <edam_operation>operation_0335</edam_operation> <!-- Formatting -->
jasmine_amir@0:         </edam_operations>
jasmine_amir@0:     </xml>
jasmine_amir@0:     <macro name="requirements">
jasmine_amir@0:         <requirements>
jasmine_amir@0:             <requirement type="package" version="@TOOL_VERSION@">sra-tools</requirement>
jasmine_amir@0:             <requirement type="package" version="2.6">pigz</requirement>
jasmine_amir@0:             <requirement type="package" version="1.16.1">samtools</requirement>
jasmine_amir@0:             <yield/>
jasmine_amir@0:         </requirements>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <token name="@ACCESSIONS_FROM_FILE@">
jasmine_amir@0:         grep '^[[:space:]]*[E|S|D]RR[0-9]\{1,\}[[:space:]]*$'
jasmine_amir@0:     </token>
jasmine_amir@0:     <token name="@COMPRESS@"><![CDATA[pigz -cqp \${GALAXY_SLOTS:-1}]]></token>
jasmine_amir@0:     <token name="@CONFIGURE_RETRY@"><![CDATA[
jasmine_amir@0:         export SRA_PREFETCH_RETRIES=3 &&
jasmine_amir@0:         export SRA_PREFETCH_ATTEMPT=1 &&
jasmine_amir@0:     ]]></token>
jasmine_amir@0:     <xml name="bio_tools">
jasmine_amir@0:         <xrefs>
jasmine_amir@0:             <xref type="bio.tools">sra-tools</xref>
jasmine_amir@0:         </xrefs>
jasmine_amir@0:     </xml>
jasmine_amir@0:     <token name="@COPY_CONFIGFILE@"><![CDATA[
jasmine_amir@0:         mkdir -p ~/.ncbi &&
jasmine_amir@0:         cp '$user_settings_mkfg' ~/.ncbi/user-settings.mkfg &&
jasmine_amir@0:         vdb-config -s "/repository/user/main/public/root=\$PWD" &&
jasmine_amir@0:         vdb-config -s "/repository/user/ad/public/root=\$PWD" &&
jasmine_amir@0:         vdb-config -s "/repository/user/default-path=\$PWD" &&
jasmine_amir@0:         vdb-config -s "/repository/user/main/public/root=\$PWD" &&
jasmine_amir@0:         vdb-config -s /http/timeout/read=10000 &&
jasmine_amir@0:     ]]></token>
jasmine_amir@0:     <token name="@SET_ACCESSIONS@"><![CDATA[
jasmine_amir@0:         #if $input.input_select == "sra_file":
jasmine_amir@0:             acc='${input.sra_file.name}' &&
jasmine_amir@0:             ln -s '${input.sra_file}' "\$acc" &&
jasmine_amir@0:         #else    
jasmine_amir@0:             #if $input.input_select == "file_list":
jasmine_amir@0:                 #if $input.file_list.is_of_type('sra_manifest.tabular'):
jasmine_amir@0:                     #set $column = $input.file_list.unsanitized.metadata.column_names.index('Run') + 1
jasmine_amir@0:                     cut -f $column '$input.file_list'| tail -n +2 > accessions &&
jasmine_amir@0:                 #else
jasmine_amir@0:                     @ACCESSIONS_FROM_FILE@ '$input.file_list' > accessions &&
jasmine_amir@0:                 #end if
jasmine_amir@0:             #elif $input.input_select == "accession_number":
jasmine_amir@0:                 echo '${input.accession}' | sed -r 's/(\,|\;|__cn__)/\n/g' > accessions &&
jasmine_amir@0:             #end if
jasmine_amir@0:             for acc in \$(cat ./accessions);
jasmine_amir@0:             do (
jasmine_amir@0:                 echo "Downloading accession: \$acc..." &&
jasmine_amir@0:         #end if  
jasmine_amir@0:     ]]></token>
jasmine_amir@0:     <macro name="configfile_hack">
jasmine_amir@0:         <configfiles>
jasmine_amir@0:             <configfile name="user_settings_mkfg"><![CDATA[
jasmine_amir@0: /LIBS/GUID = "3cdc38d0-711a-49ce-9536-f544eaf69eec"
jasmine_amir@0: /config/default = "false"
jasmine_amir@0: /libs/temp_cache = "."
jasmine_amir@0: /tools/prefetch/download_to_cache = "false"
jasmine_amir@0:             ]]></configfile>
jasmine_amir@0:         </configfiles>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <macro name="sanitize_query">
jasmine_amir@0:         <sanitizer>
jasmine_amir@0:             <valid initial="string.printable">
jasmine_amir@0:                 <remove value=" "/>
jasmine_amir@0:                 <remove value="&apos;" />
jasmine_amir@0:             </valid>
jasmine_amir@0:             <mapping initial="none">
jasmine_amir@0:                 <add source=" " target=""/>
jasmine_amir@0:                 <add source="&apos;" target="&apos;&quot;&apos;&quot;&apos;"/>
jasmine_amir@0:             </mapping>
jasmine_amir@0:         </sanitizer>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <macro name="input_conditional">
jasmine_amir@0:         <conditional name="input">
jasmine_amir@0:             <param name="input_select" type="select" label="select input type">
jasmine_amir@0:                 <option value="accession_number">SRR accession</option>
jasmine_amir@0:                 <option value="file_list">List of SRA accession, one per line</option>
jasmine_amir@0:                 <option value="sra_file">SRA archive in current history</option>
jasmine_amir@0:             </param>
jasmine_amir@0:             <when value="accession_number">
jasmine_amir@0:                 <param name="accession" type="text" label="Accession" multiple="true" help="Must start with SRR, DRR or ERR, e.g. SRR925743, ERR343809">
jasmine_amir@0:                     <expand macro="sanitize_query"/>
jasmine_amir@0:                     <validator type="empty_field" message="An accession is required"/>
jasmine_amir@0:                 </param>
jasmine_amir@0:             </when>
jasmine_amir@0:             <when value="sra_file">
jasmine_amir@0:                 <param format="sra" name="sra_file" type="data" label="sra archive"/>
jasmine_amir@0:             </when>
jasmine_amir@0:             <when value="file_list">
jasmine_amir@0:                 <param format="txt" name="file_list" type="data" label="sra accession list"/>
jasmine_amir@0:             </when>
jasmine_amir@0:         </conditional>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <macro name="alignments">
jasmine_amir@0:         <param name="alignments" type="select" value="both" label="Output aligned or unaligned reads" help="Output reads according to their alignment status." argument="--aligned and --unaligned">
jasmine_amir@0:             <option value="both">both</option>
jasmine_amir@0:             <option value="aligned">aligned only</option>
jasmine_amir@0:             <option value="unaligned">unaligned only</option>
jasmine_amir@0:         </param>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <macro name="minMapq">
jasmine_amir@0:         <param name="minMapq" type="integer" min="0" max="42" label="Minimum mapping quality" optional="true" help="Minimum mapping quality an alignment has to have, to be dumped." argument="--min-mapq"/>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <macro name="region">
jasmine_amir@0:         <param format="text" name="region" type="text" label="aligned region" optional="true"
jasmine_amir@0:                help="Filter by position on genome. Can be either accession.version (ex: NC_000001.10), chromosome name (ex:chr1 or 1) or 1-based coordinates (ex: chr1:1-101)." argument="--aligned-region"/>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <macro name="matepairDist">
jasmine_amir@0:         <param name="matepairDist" type="text" label="mate-pair distance (from-to|unknown)" optional="true"
jasmine_amir@0:                help="Filter by distance between matepairs. Use unknown to find matepairs split between the references. Use from-to (inclusive) to limit matepair distance on the same reference" argument="--matepair-distance"/>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <macro name="citation">
jasmine_amir@0:         <citations>
jasmine_amir@0:             <citation type="doi">10.1093/nar/gkq1019</citation>
jasmine_amir@0:             <citation type="bibtex">
jasmine_amir@0: @misc{github_sratools,
jasmine_amir@0:   author = {NCBI},
jasmine_amir@0:   title = {sra-tools},
jasmine_amir@0:   publisher = {GitHub},
jasmine_amir@0:   journal = {GitHub repository},
jasmine_amir@0:   url = {https://github.com/ncbi/sra-tools},
jasmine_amir@0: }</citation>
jasmine_amir@0:         </citations>
jasmine_amir@0:     </macro>
jasmine_amir@0:     <token name="@HOW_TO_USE_IT@">
jasmine_amir@0:     **How to use it?**
jasmine_amir@0: 
jasmine_amir@0: There are three ways in which you can download data:
jasmine_amir@0: 
jasmine_amir@0:  1. Plain text input of accession number(s)
jasmine_amir@0:  2. Providing a list of accessions from file
jasmine_amir@0:  3. Extracting data from an already uploaded SRA dataset
jasmine_amir@0: 
jasmine_amir@0: Below we discuss each in detail.
jasmine_amir@0: 
jasmine_amir@0: ------
jasmine_amir@0: 
jasmine_amir@0: **Plain text input of accession number(s)**
jasmine_amir@0: 
jasmine_amir@0: When you type an accession number (e.g., `SRR1582967`) into **Accession** box and click **Execute** the tool will fetch the data for you. You can also provide a list of multiple accession numbers (e.g. `SRR3141592, SRR271828, SRR112358`).
jasmine_amir@0: 
jasmine_amir@0: -----
jasmine_amir@0: 
jasmine_amir@0: **Providing a list of accessions from file**
jasmine_amir@0: 
jasmine_amir@0: 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:
jasmine_amir@0: 
jasmine_amir@0:  1. Upload it into your history using Galaxy's upload tool
jasmine_amir@0:  2. Once the list of accessions is uploaded choose *List of SRA accessions, one per line* from **select input type** dropdown
jasmine_amir@0:  3. Choose uploaded file within the **sra accession list** field
jasmine_amir@0:  4. Click **Execute**
jasmine_amir@0: 
jasmine_amir@0: -----
jasmine_amir@0: 
jasmine_amir@0: **Extract data from an already uploaded SRA dataset**
jasmine_amir@0: 
jasmine_amir@0: If an SRA dataset is already present in the history, the sequencing data can be extracted in a human-readable data format (fastq, sam, bam) by setting **select input type** drop-down to *SRA archive in current history*.
jasmine_amir@0:     </token>
jasmine_amir@0:     <token name="@ACCESSION_LIST_HOWTO@">
jasmine_amir@0: -----
jasmine_amir@0: 
jasmine_amir@0: **How to generate accession lists**
jasmine_amir@0: 
jasmine_amir@0:  1. Go to **SRA Run Selector** by clicking this link_
jasmine_amir@0:  2. Find the study you are interested in by typing a search term within the **Search** box. This can be a word (e.g., *mitochondria*) or an accession you have gotten from a paper (e.g., *SRR1582967*).
jasmine_amir@0:  3. Once you click on the study of interest you will see the number of datasets in this study within the **Related SRA data** box
jasmine_amir@0:  4. Click on the Runs number
jasmine_amir@0:  5. On the page that would open you will see **Accession List** button
jasmine_amir@0:  6. Clicking of this button will produce a file that you will need to upload into Galaxy and use as the input to this tool.
jasmine_amir@0:     </token>
jasmine_amir@0:     <token name="@SRATOOLS_ATTRRIBUTION@">
jasmine_amir@0: For credits, information, support and bug reports, please refer ato https://github.com/galaxyproject/tools-iuc.
jasmine_amir@0:     </token>
jasmine_amir@0: </macros>