comparison abyss-pe.xml @ 7:841084c5fc46 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/abyss commit e14b8554ee2a7d00b98c7cb863a07245d29ab93f"

6:0e93176640ac

    <description>de novo sequence assembler</description>
    <xrefs>
        <xref type="bio.tools">abyss</xref>
    </xrefs>
    <macros>
        <token name="@TOOL_VERSION@">2.3.1</token>
        <xml name="reads_conditional">
            <conditional name="reads">
                <param name="reads_selector" type="select" label="Type of paired-end datasets">
                    <option value="paired">2 separate datasets</option>
                    <option value="paired_collection">1 paired dataset collection</option>

        <!-- In case the return code has not been set propery check stderr too -->
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <version_command>ABYSS --version | head -n 1</version_command>
    <command>
abyss-pe
name=abyss
j=\${GALAXY_SLOTS:-1}
k=$k

#if str($K)
    K=$K
#end if

    n=$n
#end if
#if str($d)
    d=$d
#end if
#if str($S)
    S=$S
#end if
#if str($N)
    N=$N
#end if
#if $lib_repeat
    lib='
    #for $i in range(len($lib_repeat))
        lib$i

    '
    #for $i, $v in enumerate($long_seqs)
        long${i}='$v'
    #end for
#end if
    </command>

    <inputs>
        <repeat name="lib_repeat" title="Paired-end library" help="(lib)">
            <expand macro="reads_conditional" />
        </repeat>

        <param argument="E" type="integer" value="" min="0" optional="true" label="Minimum erosion k-mer coverage per strand" help="Erode bases at the ends of blunt contigs with coverage less than this value on either strand. Defaults to 1 if sqrt(median) &gt; 2 else 0" />
        <param argument="t" type="integer" value="" optional="true" label="Maximum length of blunt contigs to trim" help="Defaults to the value of k" />
        <param argument="c" type="float" value="" optional="true" label="Minimum mean k-mer coverage of a unitig" help="Defaults to sqrt(median)" />
        <param argument="b" type="integer" value="" optional="true" label="Maximum length of a bubble (in bp)" help="abyss-pe has two bubble popping stages. The default limits are 3*k bp for ABYSS and 10000 bp for PopBubbles" />
        <param argument="SS" type="boolean" label="Assemble in strand-specific mode" help="Requires that all libraries are strand-specific RNA-Seq libraries. Assumes that the first read in a read pair is reveresed with respect to the transcripts sequenced" />
        <param argument="m" type="integer" value="50" min="0" optional="true" label="Minimum overlap of two unitigs (in bp)" />
        <param argument="p" type="float" value="0.9" optional="true" label="Minimum sequence identity of a bubble" />
        <param argument="a" type="integer" value="2" min="0" optional="true" label="Maximum number of branches of a bubble" />
        <param argument="l" type="integer" value="" min="1"  optional="true" label="Minimum alignment length of a read (in bp)" help="Defaults to the value of k" />
        <param argument="s" type="integer" value="200" min="0" optional="true" label="Minimum unitig length required for building contigs (in bp)" help="The seed length should be at least twice the value of k. If more sequence is assembled than the expected genome size, try increasing this value" />
        <param argument="n" type="integer" value="10" min="0" optional="true" label="Minimum number of pairs required for building contigs" />
        <param argument="d" type="integer" value="6" min="0" optional="true" label="Allowable error of a distance estimate (in bp)" />
        <param argument="S" type="integer" value="" min="0" optional="true" label="Minimum contig length required for building scaffolds (in bp)" help="Defaults to the value of s" />
        <param argument="N" type="integer" value="" min="0" optional="true" label="Minimum number of pairs required for building scaffolds" help="Defaults to the value of n" />
    </inputs>

    <outputs>
        <data name="unitigs" format="fasta" label="${tool.name} on ${on_string}: unitigs" from_work_dir="abyss-unitigs.fa" />
        <data name="contigs_outfile" format="fasta" label="${tool.name} on ${on_string}: contigs" from_work_dir="abyss-contigs.fa">

            <filter>lib_repeat or mp_repeat</filter>
        </data>
        <data name="long_scaffolds" format="fasta" label="${tool.name} on ${on_string}: scaffolds" from_work_dir="abyss-long-scaffs.fa">
            <filter>long_seqs</filter>
        </data>
        <data name="bubbles" format="fasta" label="${tool.name} on ${on_string}: bubbles" from_work_dir="abyss-bubbles.fa" />
        <data name="indels" format="fasta" label="${tool.name} on ${on_string}: indels" from_work_dir="abyss-indel.fa" />
        <data name="coverage_histogram_outfile" format="tabular" label="${tool.name} on ${on_string}: coverage histogram" from_work_dir="coverage.hist" />
        <data name="stats" format="tabular" label="${tool.name} on ${on_string}: stats" from_work_dir="abyss-stats.tab" />
    </outputs>

    <tests>
        <test>

            </repeat>
            <param name="k" value="50" />
            <output name="unitigs" file="abyss-unitigs1.fa" />
            <output name="contigs_outfile" file="abyss-contigs1.fa" />
            <output name="scaffolds" file="abyss-scaffolds1.fa" />
            <output name="bubbles" file="empty_file.fasta" />
            <output name="indels" file="empty_file.fasta" />
            <output name="coverage_histogram_outfile" file="coverage1.hist" />
            <output name="stats" file="abyss-stats1.tab" />
        </test>
        <test>
            <param name="se_reads" ftype="fastqsanger" value="assembly_sample-R1.fastq.gz,assembly_sample-R2.fastq.gz" />
            <param name="k" value="50" />
            <output name="unitigs" file="abyss-unitigs2.fa" />
            <output name="bubbles" file="empty_file.fasta" />
            <output name="indels" file="empty_file.fasta" />
            <output name="coverage_histogram_outfile" file="coverage2.hist" />
            <output name="stats" file="abyss-stats2.tab" />
        </test>
        <test>
            <param name="se_reads" ftype="fastqsanger" value="assembly_sample-R1.fastq.gz,assembly_sample-R2.fastq.gz" />
            <param name="long_seqs" ftype="fastqsanger" value="assembly_sample-R2.fastq.gz" />
            <param name="k" value="50" />
            <output name="unitigs" file="abyss-unitigs3.fa" />
            <output name="long_scaffolds" file="abyss-long-scaffolds3.fa" />
            <output name="bubbles" file="empty_file.fasta" />
            <output name="indels" file="empty_file.fasta" />
            <output name="coverage_histogram_outfile" file="coverage3.hist" />
            <output name="stats" file="abyss-stats3.tab" />
        </test>
    </tests>
    <help>
**What it does**

`ABySS`_ is a de novo sequence assembler intended for short paired-end reads and large genomes.

**Input**

This tool performs the complete ABySS pipeline using abyss-pe, described in https://github.com/bcgsc/abyss/blob/master/doc/flowchart.pdf .

**License and citation**

This Galaxy tool is Copyright © 2015-2016 `Earlham Institute`_ and is released under the `MIT license`_.

.. _Earlham Institute: http://www.earlham.ac.uk/
.. _MIT license: https://opensource.org/licenses/MIT

You can use this tool only if you agree to the license terms of: `ABySS`_.

.. _ABySS: https://github.com/bcgsc/abyss
    </help>
    <citations>
        <citation type="doi">10.1101/gr.089532.108</citation>
    </citations>
</tool>

7:841084c5fc46

    <description>de novo sequence assembler</description>
    <xrefs>
        <xref type="bio.tools">abyss</xref>
    </xrefs>
    <macros>
        <token name="@TOOL_VERSION@">2.3.2</token>
        <xml name="reads_conditional">
            <conditional name="reads">
                <param name="reads_selector" type="select" label="Type of paired-end datasets">
                    <option value="paired">2 separate datasets</option>
                    <option value="paired_collection">1 paired dataset collection</option>

        <!-- In case the return code has not been set propery check stderr too -->
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <version_command>ABYSS --version | head -n 1</version_command>
    <command><![CDATA[
abyss-pe
name=abyss
j=\${GALAXY_SLOTS:-1}
B=\${GALAXY_MEMORY_MB:-2048}M
k=$k

#if str($K)
    K=$K
#end if

    n=$n
#end if
#if str($d)
    d=$d
#end if
#if $S
    S='$S'
#end if
#if $N
    N='$N'
#end if
#if $lib_repeat
    lib='
    #for $i in range(len($lib_repeat))
        lib$i

    '
    #for $i, $v in enumerate($long_seqs)
        long${i}='$v'
    #end for
#end if
    ]]></command>

    <inputs>
        <repeat name="lib_repeat" title="Paired-end library" help="(lib)">
            <expand macro="reads_conditional" />
        </repeat>

        <param argument="E" type="integer" value="" min="0" optional="true" label="Minimum erosion k-mer coverage per strand" help="Erode bases at the ends of blunt contigs with coverage less than this value on either strand. Defaults to 1 if sqrt(median) &gt; 2 else 0" />
        <param argument="t" type="integer" value="" optional="true" label="Maximum length of blunt contigs to trim" help="Defaults to the value of k" />
        <param argument="c" type="float" value="" optional="true" label="Minimum mean k-mer coverage of a unitig" help="Defaults to sqrt(median)" />
        <param argument="b" type="integer" value="" optional="true" label="Maximum length of a bubble (in bp)" help="abyss-pe has two bubble popping stages. The default limits are 3*k bp for ABYSS and 10000 bp for PopBubbles" />
        <param argument="SS" type="boolean" label="Assemble in strand-specific mode" help="Requires that all libraries are strand-specific RNA-Seq libraries. Assumes that the first read in a read pair is reveresed with respect to the transcripts sequenced" />
        <param argument="m" type="integer" value="" min="0" optional="true" label="Minimum overlap of two unitigs (in bp)" help="Defaults to 0 (interpreted as k - 1) if mate-pair libraries are provided or if k&lt;=50, otherwise 50" />
        <param argument="p" type="float" value="0.9" optional="true" label="Minimum sequence identity of a bubble" />
        <param argument="a" type="integer" value="2" min="0" optional="true" label="Maximum number of branches of a bubble" />
        <param argument="l" type="integer" value="" min="1"  optional="true" label="Minimum alignment length of a read (in bp)" help="Defaults to the value of k" />
        <param argument="s" type="integer" value="200" min="0" optional="true" label="Minimum unitig length required for building contigs (in bp)" help="The seed length should be at least twice the value of k. If more sequence is assembled than the expected genome size, try increasing this value" />
        <param argument="n" type="integer" value="10" min="0" optional="true" label="Minimum number of pairs required for building contigs" />
        <param argument="d" type="integer" value="6" min="0" optional="true" label="Allowable error of a distance estimate (in bp)" />
        <param argument="S" type="text" value="" label="Minimum contig size required for building scaffolds (in bp)" help="It can be an interval. Defaults to 100-5000">
            <validator type="regex" message="Must be a an integer or an interval">^([0-9]+(-[0-9]+)?)?$</validator>
        </param>
        <param argument="N" type="text" value="" label="Minimum number of pairs required for building scaffolds" help="It can be an interval. Defaults to 15-20">
            <validator type="regex" message="Must be a an integer or an interval">^([0-9]+(-[0-9]+)?)?$</validator>
        </param>
    </inputs>

    <outputs>
        <data name="unitigs" format="fasta" label="${tool.name} on ${on_string}: unitigs" from_work_dir="abyss-unitigs.fa" />
        <data name="contigs_outfile" format="fasta" label="${tool.name} on ${on_string}: contigs" from_work_dir="abyss-contigs.fa">

            <filter>lib_repeat or mp_repeat</filter>
        </data>
        <data name="long_scaffolds" format="fasta" label="${tool.name} on ${on_string}: scaffolds" from_work_dir="abyss-long-scaffs.fa">
            <filter>long_seqs</filter>
        </data>
        <data name="indels" format="fasta" label="${tool.name} on ${on_string}: indels" from_work_dir="abyss-indel.fa" />
        <data name="stats" format="tabular" label="${tool.name} on ${on_string}: stats" from_work_dir="abyss-stats.tab" />
    </outputs>

    <tests>
        <test>

            </repeat>
            <param name="k" value="50" />
            <output name="unitigs" file="abyss-unitigs1.fa" />
            <output name="contigs_outfile" file="abyss-contigs1.fa" />
            <output name="scaffolds" file="abyss-scaffolds1.fa" />
            <output name="indels" file="empty_file.fasta" />
            <output name="stats" file="abyss-stats1.tab" />
        </test>
        <test>
            <param name="se_reads" ftype="fastqsanger" value="assembly_sample-R1.fastq.gz,assembly_sample-R2.fastq.gz" />
            <param name="k" value="50" />
            <output name="unitigs" file="abyss-unitigs2.fa" />
            <output name="indels" file="empty_file.fasta" />
            <output name="stats" file="abyss-stats2.tab" />
        </test>
        <test>
            <param name="se_reads" ftype="fastqsanger" value="assembly_sample-R1.fastq.gz,assembly_sample-R2.fastq.gz" />
            <param name="long_seqs" ftype="fastqsanger" value="assembly_sample-R2.fastq.gz" />
            <param name="k" value="50" />
            <output name="unitigs" file="abyss-unitigs3.fa" />
            <output name="long_scaffolds" file="abyss-long-scaffolds3.fa" />
            <output name="indels" file="empty_file.fasta" />
            <output name="stats" file="abyss-stats3.tab" />
        </test>
    </tests>
    <help><![CDATA[
**What it does**

`ABySS`_ is a de novo sequence assembler intended for short paired-end reads and large genomes.

**Input**

This tool performs the complete ABySS pipeline using abyss-pe, described in https://github.com/bcgsc/abyss/blob/master/doc/flowchart.pdf .

**License and citation**

This Galaxy tool is Copyright © 2015-2021 `Earlham Institute`_ and is released under the `MIT license`_.

.. _Earlham Institute: http://www.earlham.ac.uk/
.. _MIT license: https://opensource.org/licenses/MIT

You can use this tool only if you agree to the license terms of: `ABySS`_.

.. _ABySS: https://github.com/bcgsc/abyss
    ]]></help>
    <citations>
        <citation type="doi">doi:10.1101/gr.214346.116</citation>
        <citation type="doi">10.1101/gr.089532.108</citation>
    </citations>
</tool>