annotate abyss-pe.xml @ 15:db9b10824c61 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/abyss commit ff35237f0cebb11f1da08a9a331185c9911eff93

<tool id="abyss-pe" name="ABySS" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.02" license="GPL-3.0">
    <description>de novo sequence assembler</description>
    <macros>
        <token name="@TOOL_VERSION@">2.3.10</token>
        <token name="@VERSION_SUFFIX@">0</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>
                    <option value="paired_il">1 dataset of interleaved reads</option>
                </param>
                <when value="paired">
                    <param name="reads1" type="data" format="fasta,fastq,fastq.gz" label="Paired-end reads 1" />
                    <param name="reads2" type="data" format="fasta,fastq,fastq.gz" label="Paired-end reads 2" />
                </when>
                <when value="paired_collection">
                    <param name="reads_coll" type="data_collection" collection_type="paired" format="fasta,fastq,fastqsanger,fastqillumina" label="Paired-end reads collection" />
                </when>
                <when value="paired_il">
                    <param name="reads_il" type="data" format="fasta,fastq,fastq.gz" label="Interleaved paired-end reads" />
                </when>
            </conditional>
        </xml>
    </macros>
    <xrefs>
        <xref type="bio.tools">abyss</xref>
    </xrefs>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">abyss</requirement>
        <requirement type="package" version="0.7.18">bwa</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <!-- 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[

#def get_link_fname($data, $prefix, $index)
    ## Make a name for symlinked files including extension
    #return ''.join([str($prefix), '_', str($index), '.', str($data.ext)])
#end def

## Go through all inputs and create symbolic links
#for $i, $v in enumerate($lib_repeat)
    #if $v.reads.reads_selector == 'paired'
        ln -s $v.reads.reads1 $get_link_fname($v.reads.reads1, 'lib_reads1', $i) &&
        ln -s $v.reads.reads2 $get_link_fname($v.reads.reads2, 'lib_reads2', $i) &&
    #elif $v.reads.reads_selector == 'paired_collection'
        ln -s $v.reads.reads_coll.forward $get_link_fname($v.reads.reads_coll.forward, 'lib_reads_coll_forward', $i) &&
        ln -s $v.reads.reads_coll.reverse $get_link_fname($v.reads.reads_coll.reverse, 'lib_reads_coll_reverse', $i) &&
    #else
        ln -s $v.reads.reads_il $get_link_fname($v.reads.reads_il, 'lib_reads_il', $i) &&
    #end if
#end for

#for $i, $v in enumerate($mp_repeat)
    #if $v.reads.reads_selector == 'paired'
        ln -s $v.reads.reads1 $get_link_fname($v.reads.reads1, 'mp_reads1', $i) &&
        ln -s $v.reads.reads2 $get_link_fname($v.reads.reads2, 'mp_reads2', $i) &&
    #elif $v.reads.reads_selector == 'paired_collection'
        ln -s $v.reads.reads_coll.forward $get_link_fname($v.reads.reads_coll.forward, 'mp_reads_coll_forward', $i) &&
        ln -s $v.reads.reads_coll.reverse $get_link_fname($v.reads.reads_coll.reverse, 'mp_reads_coll_reverse', $i) &&
    #else
        ln -s $v.reads.reads_il $get_link_fname($v.reads.reads_il, 'mp_reads_il', $i) &&
    #end if
#end for

#if str($se_reads) != 'None'
    #for $i, $v in enumerate($se_reads)
        ln -s $v $get_link_fname($v, 'se_reads', $i) &&
    #end for
#end if

#if str($long_seqs) != 'None'
    #for $i, $v in enumerate($long_seqs)
        ln -s $v $get_link_fname($v, 'long_seqs', $i) &&
    #end for
#end if

abyss-pe
name=abyss
j=\${GALAXY_SLOTS:-1}
B=\$((\${GALAXY_MEMORY_MB:-2048} * 9 /10 ))M

k=$k

#if str($K)
    K=$K
#end if
#if str($q)
    q=$q
#end if
#if str($Q)
    Q=$Q
#end if
#if str($e)
    e=$e
#end if
#if str($E)
    E=$E
#end if
#if str($t)
    t=$t
#end if
#if str($c)
    c=$c
#end if
#if str($b)
    b=$b
#end if
#if $SS
    SS=--SS
#end if
#if str($m)
    m=$m
#end if
#if str($p)
    p=$p
#end if
#if str($a)
    a=$a
#end if
#if str($l)
    l=$l
#end if
#if str($s)
    s=$s
#end if
#if str($n)
    n=$n
#end if
#if str($d)
    d=$d
#end if
#if $S
    S='$S'
#end if
#if $N
    N='$N'
#end if
#if $lib_repeat
    lib='${' '.join(['lib'+str($i) for $i in range(len($lib_repeat))])}'
    #for $i, $v in enumerate($lib_repeat)
        #if $v.reads.reads_selector == 'paired'
            lib${i}='${get_link_fname($v.reads.reads1, "lib_reads1", $i)} ${get_link_fname($v.reads.reads2, "lib_reads2", $i)}'
        #elif $v.reads.reads_selector == 'paired_collection'
            lib${i}='$get_link_fname($v.reads.reads_coll.forward, "lib_reads_coll_forward", $i)} ${get_link_fname($v.reads.reads_coll.reverse, "lib_reads_coll_reverse", $i)}'
        #else
            lib${i}='${get_link_fname($v.reads.reads_il, "lib_reads_il", $i)}'
        #end if
    #end for
#end if
#if str($se_reads) != 'None'
    se='${' '.join([$get_link_fname($v, "se_reads", $i) for $i, $v in enumerate($se_reads)])}'
#end if
#if $mp_repeat
    mp='${' '.join(['mp'+str($i) for $i in range(len($mp_repeat))])}'
    #for $i, $v in enumerate($mp_repeat)
        #if $v.reads.reads_selector == 'paired'
            mp${i}='${get_link_fname($v.reads.reads1, "mp_reads1", $i)} ${get_link_fname($v.reads.reads2, "mp_reads2", $i)}'
        #elif $v.reads.reads_selector == 'paired_collection'
            mp${i}='$get_link_fname($v.reads.reads_coll.forward, "mp_reads_coll_forward", $i)} ${get_link_fname($v.reads.reads_coll.reverse, "mp_reads_coll_reverse", $i)}'
        #else
            mp${i}='${get_link_fname($v.reads.reads_il, "mp_reads_il", $i)}'
        #end if
    #end for
#end if
#if str($long_seqs) != 'None'
    long='${' '.join(['long'+str($i) for $i in range(len($long_seqs))])}'
    #for $i, $v in enumerate($long_seqs)
        long$i='${get_link_fname($v, "long_seqs", $i)}'
    #end for
#end if
    ]]></command>

    <inputs>
        <repeat name="lib_repeat" title="Paired-end library" help="(lib)">
            <expand macro="reads_conditional" />
        </repeat>
        <param name="se_reads" argument="se" type="data" multiple="true" optional="true" format="fasta,fastq,fastq.gz" label="Single-end reads" />
        <repeat name="mp_repeat" title="Mate-pair library" help="The mate-pair libraries are used only for scaffolding and do not contribute towards the consensus sequence (mp)">
            <expand macro="reads_conditional" />
        </repeat>
        <param name="long_seqs" argument="long" type="data" multiple="true" optional="true" format="fasta,fastq,fastq.gz" label="Long sequences" help="Long sequence libraries are used only for rescaffolding and do not contribute towards the consensus sequence" />
        <param argument="k" type="integer" value="41" label="K-mer length (in bp)" help="The length of a k-mer (when -K is not set) or the span of a k-mer pair (when K is set)" />
        <param argument="K" type="integer" value="" optional="true" label="The length (in bp) of a single k-mer in a k-mer pair" help="Optional" />
        <param argument="q" type="integer" value="3" max="40" optional="true" label="Minimum base quality when trimming" help="Trim bases from the ends of reads whose quality is less than this value" />
        <param argument="Q" type="integer" value="0" max="40" optional="true" label="Minimum base quality" help="Mask all bases of reads whose quality is less than this value as 'N'" />
        <param argument="e" type="integer" value="" min="0" optional="true" label="Minimum erosion k-mer coverage" help="Erode bases at the ends of blunt contigs with coverage less than this value. Defaults to round(sqrt(median))" />
        <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 ${on_string}: contigs" from_work_dir="abyss-contigs.fa">
            <filter>lib_repeat</filter>
        </data>
        <data name="scaffolds" format="fasta" label="${tool.name} on ${on_string}: scaffolds" from_work_dir="abyss-scaffolds.fa">
            <filter>lib_repeat or mp_repeat</filter>
        </data>
        <data name="long_scaffolds" format="fasta" label="${tool.name} on ${on_string}: long scaffolds" from_work_dir="abyss-long-scaffs.fa">
            <filter>long_seqs</filter>
        </data>
        <data name="indels" format="fasta" label="${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 expect_num_outputs="5">
            <repeat name="lib_repeat">
                <conditional name="reads">
                    <param name="reads_selector" value="paired" />
                    <param name="reads1" ftype="fastqsanger.gz" value="assembly_sample-R1.fastq.gz" />
                    <param name="reads2" ftype="fastqsanger.gz" value="assembly_sample-R2.fastq.gz" />
                </conditional>
            </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 expect_num_outputs="3">
            <param name="se_reads" ftype="fastq.gz" 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 expect_num_outputs="4">
            <param name="se_reads" ftype="fasta" value="assembly_sample-R1.fasta,assembly_sample-R2.fasta" />
            <param name="long_seqs" ftype="fasta" value="assembly_sample-R2.fasta" />
            <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**

Input files should be FASTA or FASTQ files.

For paired reads, a pair of reads must be named with the suffixes /1 and /2 to identify the first and second read, or the reads may be named identically. The paired reads may be in separate files or interleaved in a single file.

At least a paired-end library or a single-end library must be provided.

Contigs are generated only if at least a paired-end library is provided. Scaffolds are generated only if at least a paired-end library or a mate-pair library is provided.

**Description**

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`_

.. _Earlham Institute: http://www.earlham.ac.uk/

.. _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>