comparison disco.xml @ 2:dfefaf2bab95 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/disco/ commit d9fc31caa31f1f0c63a0dd5ffe136d765d607080"

1:6de3e77073ad

<tool id="disco" name="DISCO" version="@WRAPPER_VERSION@.0">
    <description>to assemble metagenomics data using an overlap-layout-consensus (OLC) approach</description>
    <macros>
        <token name="@WRAPPER_VERSION@">1.2</token>
        <xml name="assembly_params">
            <param argument="minSequenceLengthTobePrinted" type="integer" value="1000" min="0" label="Minimum length of contigs or scaffolds to be printed"/>

        </xml>
    </macros>
    <requirements>
        <requirement type="package" version="@WRAPPER_VERSION@">disco</requirement>
    </requirements>
    <version_command>runDisco.sh --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
runDisco.sh
    -n \${GALAXY_SLOTS:-4}
    -m \${DISCO_MAX_MEMORY:-4}
    -d .
    -o disco
    #if $input.library_type == "single"
        -inS '$input.inS'
    #else
        #if $input.paired_input.type == "separated"
            -in1 '$input.paired_input.in1'
            -in2 '$input.paired_input.in2'
        #else
            -inP '$input.paired_input.inP'
        #end if
    #end if
    $obg
    $osg
    -p '$first_assembly_iteration_params'

minReadsCountInEdgeToBe1MinFlow = $third_assembly_iter_param.minReadsCountInEdgeToBe1MinFlow
minEdgeLengthToBe1MinFlow = $third_assembly_iter_param.minEdgeLengthToBe1MinFlow
        ]]></configfile>
    </configfiles>
    <inputs>
        <conditional name="input">
            <param name="library_type" type="select" label="Type of library?">
                <option value="single">Single-end reads</option>
                <option value="paired">Paired-end reads</option>
            </param>
            <when value="single">
                <param argument="-inS" type="data" format="fastq,fasta" multiple="true" label="Single-read files"/>
            </when>
            <when value="paired">
                <conditional name="paired_input">
                    <param name="type" type="select" label="Type of library?">
                        <option value="separated">Separated forward/reverse paired-read files</option>
                        <option value="interleaved">Interleaved paired-read files</option>
                    </param>
                    <when value="separated">
                        <param argument="-in1" type="data" format="fastq,fasta" label="Forward read file" />
                        <param argument="-in2" type="data" format="fastq,fasta" label="Reverse read file" />
                    </when>
                    <when value="interleaved">
                        <param argument="-inP" type="data" format="fastq,fasta" multiple="true" label="Interleaved paired-read files" />
                    </when>
                </conditional>
            </when>
        </conditional>
        <param argument="-obg" type="boolean" truevalue="-obg" falsevalue="" checked="false" label="Only build overlap graph?"/>

            <discover_datasets pattern="disco_Graph_(?P&lt;designation&gt;.+)\.gfa2" format="txt" directory="assembly" />
        </collection>
    </outputs>
    <tests>
        <test>
            <conditional name="input">
                <param name="library_type" value="paired"/>
                <conditional name="paired_input">
                    <param name="type" value="separated"/>
                    <param name="in1" value="ecoli_1K_1.fq"/>
                    <param name="in2" value="ecoli_1K_2.fq"/>

            <output_collection name="gfa2_graphs" type="list">
                <element name="1" file="test1_graph_1.gfa2" compare="sim_size" delta="6000"/>
            </output_collection>
        </test>
        <test>
            <conditional name="input">
                <param name="library_type" value="paired"/>
                <conditional name="paired_input">
                    <param name="type" value="interleaved"/>
                    <param name="inP" value="ecoli_1K_interleaved.fq,ecoli_1K_interleaved.fq"/>
                </conditional>

            </output>
            <output name="contigs" value="test2_contigs.fasta" compare="sim_size" delta="5"/>
            <output name="scaffolds" value="test2_scaffolds.fasta" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="input">
                <param name="library_type" value="single"/>
                <param name="inS" value="ecoli_1K_1.fq"/>
            </conditional>
            <param name="obg" value=""/>
            <param name="osg" value=""/>
            <param name="MinOverlap4BuildGraph" value="20"/>
            <param name="log" value="false"/>

        </test>
    </tests>
    <help><![CDATA[
DISCO is a multi threaded and multiprocess distributed memory overlap-layout-consensus (OLC) metagenome assembler. Disco was developed as a scalable assembler to assemble large metagenomes from billions of Illumina sequencing reads of complex microbial communities. Disco was parallelized for computer clusters in a hybrid architecture that integrated shared-memory multi-threading, point-to-point message passing, and remote direct memory access. The assembly and scaffolding were performed using an iterative overlap graph approach.

The detailed user manual of the assembler and how to use it to acheive best results is provided here: http://disco.omicsbio.org/user-manual. This is a quick start guide generally for developers and testers. Users with limited experience with genome assembly are advised to use the user manual.
    ]]></help>
    <citations>
    </citations>
</tool>

2:dfefaf2bab95

<tool id="disco" name="DISCO" version="@WRAPPER_VERSION@.1" profile="20.01">
    <description>to assemble metagenomics data using an overlap-layout-consensus (OLC) approach</description>
    <macros>
        <token name="@WRAPPER_VERSION@">1.2</token>
        <xml name="assembly_params">
            <param argument="minSequenceLengthTobePrinted" type="integer" value="1000" min="0" label="Minimum length of contigs or scaffolds to be printed"/>

        </xml>
    </macros>
    <requirements>
        <requirement type="package" version="@WRAPPER_VERSION@">disco</requirement>
    </requirements>
    <version_command>echo @WRAPPER_VERSION@</version_command>
    <command detect_errors="exit_code"><![CDATA[
#if $input_cond.library_type == "single"
    #for i, e in enumerate($input_cond.inS)
        cp '$e'
        #if $e.ext.endswith(".gz")
            input_${i}.fastq.gz &&
        #else
            input_${i}.fastq &&
        #end if
    #end for
#else
    #if $input_cond.paired_input.type == "separated"
        #if $input_cond.paired_input.in1.ext.endswith(".gz")
           cp '$input_cond.paired_input.in1' forward.fastq.gz &&
           cp '$input_cond.paired_input.in2' reverse.fastq.gz &&
        #else
           cp '$input_cond.paired_input.in1' forward.fastq &&
           cp '$input_cond.paired_input.in2' reverse.fastq &&
        #end if
    #else
        #for i, e in enumerate($input_cond.paired_input.inP)
            cp '$e'
            #if $e.ext.endswith(".gz")
                input_${i}.fastq.gz &&
            #else
                input_${i}.fastq &&
            #end if
        #end for
    #end if
#end if
runDisco.sh
    -n \${GALAXY_SLOTS:-4}
    -m \${DISCO_MAX_MEMORY:-4}
    -d .
    -o disco
    #if $input_cond.library_type == "single"
        -inS \$(find . -name "*fastq*" -print | tr '\n' ',' | sed 's/,$//')
    #else
        #if $input_cond.paired_input.type == "separated"
            #if $input_cond.paired_input.in1.ext.endswith(".gz") 
                -in1 forward.fastq.gz
                -in2 reverse.fastq.gz
            #else
                -in1 forward.fastq
                -in2 reverse.fastq
            #end if
        #else
            -inP \$(find . -name "*fastq*" -print | tr '\n' ',' | sed 's/,$//')
        #end if
    #end if
    $obg
    $osg
    -p '$first_assembly_iteration_params'

minReadsCountInEdgeToBe1MinFlow = $third_assembly_iter_param.minReadsCountInEdgeToBe1MinFlow
minEdgeLengthToBe1MinFlow = $third_assembly_iter_param.minEdgeLengthToBe1MinFlow
        ]]></configfile>
    </configfiles>
    <inputs>
        <conditional name="input_cond">
            <param name="library_type" type="select" label="Type of library?">
                <option value="single">Single-end reads</option>
                <option value="paired">Paired-end reads</option>
            </param>
            <when value="single">
                <param argument="-inS" type="data" format="fastq,fastq.gz,fasta" multiple="true" label="Single-read files"/>
            </when>
            <when value="paired">
                <conditional name="paired_input">
                    <param name="type" type="select" label="Type of library?">
                        <option value="separated">Separated forward/reverse paired-read files</option>
                        <option value="interleaved">Interleaved paired-read files</option>
                    </param>
                    <when value="separated">
                        <param argument="-in1" type="data" format="fastq,fastq.gz,fasta" label="Forward read file" />
                        <param argument="-in2" type="data" format="fastq,fastq.gz,fasta" label="Reverse read file" />
                    </when>
                    <when value="interleaved">
                        <param argument="-inP" type="data" format="fastq,fastq.gz,fasta" multiple="true" label="Interleaved paired-read files" />
                    </when>
                </conditional>
            </when>
        </conditional>
        <param argument="-obg" type="boolean" truevalue="-obg" falsevalue="" checked="false" label="Only build overlap graph?"/>

            <discover_datasets pattern="disco_Graph_(?P&lt;designation&gt;.+)\.gfa2" format="txt" directory="assembly" />
        </collection>
    </outputs>
    <tests>
        <test>
            <conditional name="input_cond">
                <param name="library_type" value="paired"/>
                <conditional name="paired_input">
                    <param name="type" value="separated"/>
                    <param name="in1" value="ecoli_1K_1.fq"/>
                    <param name="in2" value="ecoli_1K_2.fq"/>

            <output_collection name="gfa2_graphs" type="list">
                <element name="1" file="test1_graph_1.gfa2" compare="sim_size" delta="6000"/>
            </output_collection>
        </test>
        <test>
            <conditional name="input_cond">
                <param name="library_type" value="paired"/>
                <conditional name="paired_input">
                    <param name="type" value="interleaved"/>
                    <param name="inP" value="ecoli_1K_interleaved.fq,ecoli_1K_interleaved.fq"/>
                </conditional>

            </output>
            <output name="contigs" value="test2_contigs.fasta" compare="sim_size" delta="5"/>
            <output name="scaffolds" value="test2_scaffolds.fasta" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="input_cond">
                <param name="library_type" value="single"/>
                <param name="inS" value="ecoli_1K_1.fq.gz" ftype="fastq.gz"/>
            </conditional>
            <param name="obg" value=""/>
            <param name="osg" value=""/>
            <param name="MinOverlap4BuildGraph" value="20"/>
            <param name="log" value="false"/>

        </test>
    </tests>
    <help><![CDATA[
DISCO is a multi threaded and multiprocess distributed memory overlap-layout-consensus (OLC) metagenome assembler. Disco was developed as a scalable assembler to assemble large metagenomes from billions of Illumina sequencing reads of complex microbial communities. Disco was parallelized for computer clusters in a hybrid architecture that integrated shared-memory multi-threading, point-to-point message passing, and remote direct memory access. The assembly and scaffolding were performed using an iterative overlap graph approach.

The detailed user manual of the assembler and how to use it to acheive best results is provided here:
 http://disco.omicsbio.org/user-manual. This is a quick start guide generally for developers and testers. Users with limited experience with genome assembly are advised to use the user manual.
    ]]></help>
    <citations>
    </citations>
</tool>