view masurca_simple.xml @ 1:86aa445e75d6 draft default tip

Uploaded

<tool id="masurca_simple" name="MaSuRCA simple" version="@TOOL_VERSION@+galaxy0"> 
    <description>The MaSuRCA (Maryland Super Read Cabog Assembler) genome assembly and analysis toolkit without config</description>
    <macros>
        <token name="@TOOL_VERSION@">4.0.6</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">masurca</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #set $long = 'false'
        #if $nanopore_input.np_input == "Yes":
            #if $pacbio_input.pb_input == "Yes":
                cat '$nanopore_input.nano' '$pacbio_input.pacbio' > \$_GALAXY_JOB_TMP_DIR/long.fastq.gz &&
            #else:
                ln -s '$nanopore_input.nano' \$_GALAXY_JOB_TMP_DIR/long.fastq.gz &&
            #end if
            #set $long = 'true'
        #elif $pacbio_input.pb_input == "Yes":
            ln -s '$pacbio_input.pacbio' \$_GALAXY_JOB_TMP_DIR/long.fastq.gz &&
            #set $long = 'true'
        #end if
        masurca -t \${GALAXY_SLOTS:-8} -i
        #if str( $illumina_input.input_type ) == "single"
            '$illumina_input.fastq_input1'
        #elif str( $illumina_input.input_type ) == "paired"
            '$illumina_input.fastq_input1','$illumina_input.fastq_input2'
        #elif str( $illumina_input.input_type ) == "paired_collection"
            '$illumina_input.fastq_input1','$illumina_input.fastq_input2'
        #end if
        #if $long == "true":
            -r \$_GALAXY_JOB_TMP_DIR/long.fastq.gz
        #end if
    ]]></command>
    <inputs>
        <conditional name="illumina_input">
            <param name="input_type" type="select" label="Paired-end reads" help="Select between paired and paired collection">
                <option value="single">Single</option>
                <option value="paired">Paired</option>
                <option value="paired_collection">Paired Collection</option>
            </param>
            <when value="single">
                <param type="data" name="fastq_input1" format="fastqsanger,fastqsanger.gz"
                    label="Select unpaired reads" help="Specify dataset with unpaired reads"/>
            </when>
            <when value="paired">
                <param type="data" name="fastq_input1" format="fastqsanger,fastqsanger.gz"
                    label="Select first set of reads" help="Specify dataset with forward reads"/>
                <param type="data" name="fastq_input2" format="fastqsanger,fastqsanger.gz"
                    label="Select second set of reads" help="Specify dataset with reverse reads"/>
            </when>
            <when value="paired_collection">
                <param name="fastq_input1" format="fastqsanger,fastqsanger.gz" type="data_collection" collection_type="paired" label="Select a paired collection" />
            </when>
        </conditional>
        <conditional name="nanopore_input">
            <param name="np_input" type="select" label="Use Nanopore long reads" help="Optional Nanopore reads must be in a single fasta or fastq file">
                <option value="No" selected="true">No</option>
                <option value="Yes">Yes</option>
            </param>
            <when value="No"/>
            <when value="Yes">
                <param type="data" name="nano" format="fastqsanger,fastqsanger.gz,fasta,fasta.gz" label="nanopore reads" />
            </when>
        </conditional>
        <conditional name="pacbio_input">
            <param name="pb_input" type="select" label="Use Pacbio long reads" help="Optional Pacbio reads must be in a single fasta or fastq file">
                <option value="No" selected="true">No</option>
                <option value="Yes">Yes</option>
            </param>
            <when value="No"/>
            <when value="Yes">
                <param type="data" name="pacbio" format="fastqsanger,fastqsanger.gz,fasta,fasta.gz" label="pacbio reads" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="superReads" format="fasta" from_work_dir="work1/superReadSequences.fasta" label="${tool.name} on ${on_string}: superReads" />
        <data name="scaffold_prm" format="fasta" from_work_dir="CA.mr.*/primary.genome.scf.fasta" label="${tool.name} on ${on_string}: primary_genome" />
        <data name="scaffold_alt" format="fasta" from_work_dir="CA.mr.*/alternative.genome.scf.fasta" label="${tool.name} on ${on_string}: alternative_genome" />
    </outputs>
    <tests>
        <test>
            <conditional name="illumina_input">
                <param name="input_type" value="paired" />
                <param name="fastq_input1" value="phix_f.fq.gz"/>
                <param name="fastq_input2" value="phix_r.fq.gz"/>
            </conditional>
            <conditional name="nanopore_input">
                <param name="np_input" value="Yes" />
                <param name="nano" value="onp.fa"/>
            </conditional>
            <conditional name="pacbio_input">
                <param name="pb_input" value="No" />
            </conditional>
            <output name="superReads" ftype="fasta">
                <assert_contents>
                    <has_line_matching expression="^TCCGAAAGTGTTAACTT.*"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

        This implementation of MaSuRCA is for small projects that only have PE
        Illumina reads (mandatory) and long reads from PACBIO or Oxford
        Nanopore or both. For larger projects and if you want to change the
        default options, you will need to run masurca_complex

    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btt476</citation>
    </citations>
</tool>