view cd_hit_dup.xml @ 1:0fb894bd8eba draft default tip

planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty

<tool id="cd_hit_dup" name="cd-hit-dup" version="0.0.1">
    <description>
        remove duplicates and detect chimaeras in sequencing reads
    </description>
    <requirements>
        <requirement type="package" version="0.5-2012-03-07-fix-dan-gh-0.0.1">cd-hit-auxtools</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>

    <command><![CDATA[
        cd-hit-dup
        -i "${ fastq_input.fastq_input1 }"
        #if str( $fastq_input.fastq_input_selector ) == "paired":
            -i2 "${ fastq_input.fastq_input2 }"
        #elif str( $fastq_input.filter_chimeras.filter_chimeras_selector ) == "true":
            -f "true"
            -s "${ fastq_input.filter_chimeras.min_chimeric_length }"
            -a "${ fastq_input.filter_chimeras.abundance_cutoff }"
            -b "${ fastq_input.filter_chimeras.abundance_ratio }"
            -p "${ fastq_input.filter_chimeras.dissimilarity_control }"
        #end if
        -u "${ prefix_length }"
        -m "${ match_length }"
        #if str( $mismatches_allowed ) != "":
            #if float( str( $mismatches_allowed ) ) == int( float( str( $mismatches_allowed ) ) ):
                -e "${ int( float( str( $mismatches_allowed ) ) ) }"
            #else:
                -e "${ mismatches_allowed }"
            #end if
        #end if
        -d "${ description_length }"
        -o "output"
    ]]>
    </command>
    <inputs>
        <conditional name="fastq_input">
            <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="For joined Paired-end reads choose Single.">
                <option value="paired">Paired</option>
                <option value="single" selected="True">Single</option>
            </param>
            <when value="paired">
                <param name="fastq_input1" type="data" format="fastqsanger,fasta" label="Select first set of reads" help="Specify dataset with forward reads"/>
                <param name="fastq_input2" type="data" format="fastqsanger,fasta" label="Select second set of reads" help="Specify dataset with reverse reads"/>
            </when>
            <when value="single">
                <param name="fastq_input1" type="data" format="fastqsanger,fasta" label="Select reads" help="Specify dataset with single reads"/>
                <conditional name="filter_chimeras">
                    <param name="filter_chimeras_selector" type="select" label="Filter out chimeric clusters">
                        <option value="true">Yes</option>
                        <option value="false" selected="True">No</option>
                    </param>
                    <when value="true">
                        <param name="min_chimeric_length" type="integer" value="30" min="20" label="Minimum length of common sequence shared between a chimeric read and each of its parents" help="-s"/>
                        <param name="abundance_cutoff" type="integer" value="1" min="1" label="Abundance cutoff" help="-a; Tool Author recommend default of 2, but this would require the chimera itself to need 2 copies"/>
                        <param name="abundance_ratio" type="integer" value="1" min="1" label="Abundance ratio between a parent read and a chimeric read" help="-b"/>
                        <param name="dissimilarity_control" type="integer" value="1" min="1" label="Dissimilarity control for chimeric filtering" help="-p"/>
                    </when>
                    <when value="false">
                        <!-- do nothing here -->
                    </when>
                </conditional>
            </when>
        </conditional>
        <param name="prefix_length" type="integer" value="0" min="0" label="Length of prefix to be used in the analysis" help="-u"/>
        <param name="match_length" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Match length" help="-m; specifies whether the lengths of two reads should be exactly the same to be considered as duplicates. "/>
        <param name="mismatches_allowed" type="float" optional="True" value="" min="0" label="Maximum number/percent of mismatches allowed" help="-e"/>
        <param name="description_length" type="integer" value="0" min="0" label="Description length" help="-d; 0 means truncate at the first whitespace character"/>
    </inputs>
    <outputs>
        <data format="fastqsanger" format_source="fastq_input1" name="output_reads" label="${tool.name} on ${on_string} (filtered reads)" from_work_dir="output"/>
        <data format="tabular" name="output_duplicate_clusters" label="${tool.name} on ${on_string} (duplicate clusters)" from_work_dir="output.clstr"/>
        <data format="tabular" name="output_chimeric_clusters" label="${tool.name} on ${on_string} (chimeric clusters)" from_work_dir="output2.clstr">
            <filter>str( fastq_input['filter_chimeras']['filter_chimeras_selector'] ) == "true"</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="fastq_input|fastq_input_selector" value="single" />
            <param name="fastq_input|fastq_input1" ftype="fastqsanger" value="cd-hit-dup_in.fastqsanger"/>
            <output name="output_reads" ftype="fastqsanger" file="cd-hit-dup_out.fastqsanger" />
            <output name="output_duplicate_clusters" ftype="tabular" file="cd-hit-dup_out.dup_clusters.tabular" />
        </test>
        <test>
            <param name="fastq_input|fastq_input_selector" value="single" />
            <param name="fastq_input|fastq_input1" ftype="fastqsanger" value="cd-hit-dup_in.fastqsanger"/>
            <param name="fastq_input|filter_chimeras|filter_chimeras_selector" value="true"/>
            <output name="output_reads" ftype="fastqsanger" file="cd-hit-dup_out_chimera.fastqsanger" />
            <output name="output_duplicate_clusters" ftype="tabular" file="cd-hit-dup_out_chimera.dup_clusters.tabular" />
            <output name="output_chimeric_clusters" ftype="tabular" file="cd-hit-dup_out_chimera.chimeric_clusters.tabular" />
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**

cd-hit-dup is a simple tool for removing duplicates from sequencing reads, with optional step to detect and remove chimeric reads. 

**Options**

cd-hit-dup provides a number of options to tune how the duplicates are removed::

 -d     Description length (default 0, truncate at the first whitespace character)
 -u     Length of prefix to be used in the analysis (default 0, for full/maximum length)
 -m     Match length (true/false, default true)
 -e     Maximum number/percent of mismatches allowed
 -f     Filter out chimeric clusters (true/false, default false)
 -s     Minimum length of common sequence shared between a chimeric read and each of
        its parents (default 30, minimum 20)
 -a     Abundance cutoff (default 1 without chimeric filtering, 2 with chimeric filtering)
 -b     Abundance ratio between a parent read and a chimeric read (default 1)
 -p     Dissimilarity control for chimeric filtering (default 1)


        ]]>
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/bts565</citation>
    </citations>
</tool>