annotate fasterq_dump.xml @ 25:69ebb7f46e45 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sra-tools commit a464017f4a599697101dbd26cf5eb902588359b5"

<tool id="fasterq_dump" name="Faster Download and Extract Reads in FASTQ" version="@VERSION@+galaxy0" profile="18.01">
    <description>format from NCBI SRA</description>
    <macros>
        <import>sra_macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <version_command>fasterq-dump --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
    set -o | grep -q pipefail && set -o pipefail;
    @COPY_CONFIGFILE@
    @SET_ACCESSIONS@
    #if $input.input_select == "file":
        acc='${input.file.name}' &&
        ln -s '${input.file}' "\$acc" &&
    #end if
    @CONFIGURE_RETRY@
    ## fetch from public s3 bucket if we can
    export acc_or_path="\$acc" &&
    aws s3 cp --no-sign-request "s3://sra-pub-sars-cov2/run/\$acc/\$acc" "\$acc.sra" 2>&1 | tee '$log' && export acc_or_path="\$acc.sra"|| true &&
    while [ \$SRA_PREFETCH_ATTEMPT -le \$SRA_PREFETCH_RETRIES ] ; do
        fasterq-dump "\$acc_or_path" -e \${GALAXY_SLOTS:-1}
        $adv.split
        #if str( $adv.minlen ) != "":
            --min-read-len "$adv.minlen"
        #end if
        $adv.skip_technical 2>&1 | tee -a '$log';
        if [ \$? == 0 ] && [ \$(ls *.fastq | wc -l) -ge 1 ]; 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

        ;
    #elif  $input.input_select=="accession_number":
    );
    #end if
    ]]>
    </command>
    <expand macro="configfile_hack"/>
    <inputs>
        <expand macro="input_conditional"/>
        <section name="adv" title="Advanced Options" expanded="False">
            <param name="minlen" type="integer" label="Minimum read length" optional="true" help="Filter by sequence length. Will dump only reads longer or equal to this value." argument="--min-read-len"/>
            <param name="split" type="select" display="radio" label="Select how to split the spots" help="This option will only be used when there are multiple reads per spot (for example paired-end).">
                <option value="--split-3">--split-3: write properly paired biological reads into different files and single reads in another file</option>
                <option value="--split-files">--split-files: write reads into different files (forward and reverse may not match if one read is empty)</option>
                <option value="--split-spot">--split-spot: split spots into reads (only one output file)</option>
                <option value="--concatenate-reads">--concatenate-reads: writes whole spots into one file</option>
            </param>
            <param name="skip_technical" type="boolean" truevalue="--skip-technical" falsevalue="--include-technical" checked="True" label="Dump only biological reads" help="Will not be used if --split-3 is selected." argument="--skip-technical/--include-technical"/>
        </section>
    </inputs>
    <outputs>
        <data name="log" format="txt" label="fasterq-dump log"/>
        <collection name="list_paired" type="list:paired" label="Pair-end data (fasterq-dump)">

        <!-- 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>
        <collection name="output_collection_other" type='list' label="Other data (fasterq-dump)">
            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fastqsanger\.gz" directory="outputOther" format="fastqsanger.gz"/>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="4">
            <param name="input_select" value="accession_number"/>
            <param name="accession" value="ERR086330"/>
            <output_collection name="list_paired" type="list:paired" count="1">
                <element name="ERR086330">
                    <element name="forward" file="ERR086330_1.fastq.gz" decompress="True">
                    </element>
                    <element name="reverse" file="ERR086330_2.fastq.gz" decompress="True">
                    </element>
                </element>
            </output_collection>
        </test>
        <test expect_num_outputs="4">
            <param name="input_select" value="accession_number"/>
            <param name="accession" value="SRR002702"/>
            <param name="split" value="--split-files"/>
            <param name="skip_technical" value="False"/>
            <output_collection name="output_collection_other" type="list" count="2">
                <element name="SRR002702_1" file="SRR002702_1.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
                <element name="SRR002702_2" file="SRR002702_2.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
            </output_collection>
        </test>
        <test expect_num_outputs="4">
            <param name="input_select" value="file"/>
            <param name="file" value="SRR522874.sra"/>
            <param name="split" value="--split-files"/>
            <param name="skip_technical" value="True"/>
            <output_collection name="list_paired" type="list:paired" count="1">
                <element name="SRR522874.sra">
                    <element name="forward" file="SRR522874.sra_2.fastq.gz" decompress="True">
                    </element>
                    <element name="reverse" file="SRR522874.sra_4.fastq.gz" decompress="True">
                    </element>
                </element>
            </output_collection>
        </test>
        <test expect_num_outputs="4">
            <param name="input_select" value="file"/>
            <param name="file" value="SRR522874.sra"/>
            <param name="split" value="--split-files"/>
            <param name="skip_technical" value="False"/>
            <output_collection name="output_collection_other" type="list" count="4">
                <element name="SRR522874_1" file="SRR522874.sra_1.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
                <element name="SRR522874_2" file="SRR522874.sra_2.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
                <element name="SRR522874_3" file="SRR522874.sra_3.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
                <element name="SRR522874_4" file="SRR522874.sra_4.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
            </output_collection>
        </test>
        <test expect_num_outputs="4">
            <param name="input_select" value="file_list"/>
            <param name="file_list" value="list_sra"/>
            <param name="minlen" value="21"/>
            <output_collection name="output_collection_other" type="list">
                <element name="SRR522874__single" file="SRR522874.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
            </output_collection>
            <output_collection name="list_paired" type="list:paired" count="1">
                <element name="SRR522874">
                    <element name="forward" file="SRR522874_1.fastq.gz" decompress="True"/>
                    <element name="reverse" file="SRR522874_2.fastq.gz" decompress="True"/>
                </element>
            </output_collection>
            <output_collection name="output_collection" type="list">
                <element name="SRR002702" file="SRR002702_2.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
            </output_collection>
        </test>
        <test expect_num_outputs="4">
            <param name="input_select" value="file_list"/>
            <param name="file_list" value="sra_manifest.tabular" ftype="sra_manifest.tabular"/>
            <output_collection name="list_paired" type="list:paired" count="1">
                <element name="SRR11953971">
                    <element name="forward" file="SRR11953971_1.fastq.gz" decompress="True"/>
                    <element name="reverse" file="SRR11953971_2.fastq.gz" decompress="True"/>
                </element>
            </output_collection>
        </test>
        <test expect_num_outputs="4">
             <!-- test accession downloaded from public bucket -->
            <param name="input_select" value="accession_number"/>
            <param name="accession" value="SRR11859153"/>
            <output_collection name="output_collection" type="list" count="1">
                <element name="SRR11859153" file="SRR11859153.fastq.gz" decompress="True"/>
            </output_collection>
            <output name="log">
                <assert_contents>
                    <has_text text="download: s3://sra-pub-sars-cov2/"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**What it does?**

This tool extracts data (in fastq_ format) from the Short Read Archive (SRA) at the National Center for Biotechnology Information (NCBI). It is based on the fasterq-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.

-----

**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**

-----

**Extract data from already uploaded SRA dataset**

If a SRA dataset is present in the history, it can be converted into fastq 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 the following applies:

 - if data is paired-ended (or mate-pair) the tool will generate a single *interleaved* dataset, in which forward and reverse mates are alternating (see example below).
 - if data is single ended, a standard fastq dataset will be produced

-----

**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

When you decide to dump technical reads (in Advanced Options Dump only biological reads is set to No), you will probably find your PAIRED data in the other data collection as it is impossible to determine if it was 2 biological reads or one biological and one technical.

.. class:: warningmark

By default, only biological reads are dumped and in case of PAIRED dataset only the spots which have both reads will be in the paired-end collection. The remaining single reads will be in the other colletion.
To keep all reads, and maybe do not have the same number of reads in forward and reverse use the --split-files option in Advanced Options, Select how to split the spots.

@ACCESSION_LIST_HOWTO@

-----


.. _fastq: https://en.wikipedia.org/wiki/FASTQ_format
.. _fastq-dump: https://ncbi.github.io/sra-tools/fastq-dump.html
.. _fasterq-dump: https://github.com/ncbi/sra-tools/wiki/HowTo:-fasterq-dump
.. _collection: https://galaxyproject.org/tutorials/collections/
.. _link: https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=studies

@SRATOOLS_ATTRRIBUTION@

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