view rdeval.xml @ 5:7cfeba6facd1 draft

planemo upload for repository https://github.com/vgl-hub/rdeval commit d55c4b3d6b91d0418950ed6b7806ef779a916099

<tool id="rdeval" name="rdeval" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>Multithreaded read analysis and manipulation tool.</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
    #import re
    #set $mangled_inputs = []
    #for $input in $input_reads
        #set $mangled_base = re.sub(r"[^\w\-\s]", "_", str($input.element_identifier))
        #set $mangled_input = $mangled_base + "." + str($input.ext)
        #silent $mangled_inputs.append($mangled_input)
        ln -s '$input' '$mangled_input' &&
    #end for
    #if $output_options.output_type.type_selector == "combined_reads"
        ln -s '$reads_outfile' 'output.${output_type.format_selector}' &&
    #end if
	rdeval --input-reads
    #for $input in $mangled_inputs
        '$input'
    #end for
	#if $expected_gsize
		'$expected_gsize'
	#end if
	#if $input_filter.include_list
		--include-list '$input_filter.include_list'
    #end if
	#if $input_filter.exclude_list
		--exclude-list '$input_filter.exclude_list'
    #end if
    #set $filter_exp_type = $input_filter.filter_expression.filter_selector
    #if $filter_exp_type != "no_exp"
        #set $l_exp = "l" + str($input_filter.filter_expression.length_comparison) + str($input_filter.filter_expression.length_value)
        #set $q_exp = "q" + str($input_filter.filter_expression.quality_comparison) + str($input_filter.filter_expression.quality_value)
        #if $filter_exp_type == "l_exp"
            #set $filter_exp = $l_exp
        #else if $filter_exp_type == "q_exp"
            #set $filter_exp = $q_exp
        #else if $filter_exp_type == "lq_exp"
            #set $filter_exp = $l_exp + str($input_filter.filter_expression.exp_operator) + $q_exp
        #end if
        --filter '$filter_exp'
    #end if
    #if int($input_subsample.sample) != 1
		--sample '$input_subsample.sample'
    #end if
	#if $input_subsample.random_seed.seed_selector == "yes"
		--random-seed '$input_subsample.random_seed.random_seed'
	#end if
	#if $input_compress.compress_selector == "yes"
		--homopolymer-compress '$input_compress.homopolymer_compress'
	#end if
    #set $stats_type = $output_options.stats_flavor.flavor_selector
    #if $stats_type == "stats"
        #if $output_options.stats_flavor.sequence_report
            --sequence-report
        #end if
    #else if $stats_type == "quality"
		--quality '$output_options.stats_flavor.quality'
    #else if $stats_type == "size"
		--out-size '$output_options.stats_flavor.out_size'
    #end if
    #set $output_type = $output_options.output_type.type_selector
    #if $output_type == "rd_file"
        #if $output_options.output_type.md5
            --md5
        #end if
        -o output.rd
    #else if $output_type == "combined_reads"
        -o 'output.${output_options.output_type.format_selector}'
    #end if
		--verbose
		--tabular
		--threads \${GALAXY_SLOTS:-2}
		> '$stats_outfile'
	]]></command>
    <inputs>
        <param argument="--input-reads" type="data" format="bam,cram,fasta,fasta.gz,fastq,fastq.gz" multiple="true" label="Input dataset" help="BAM, CRAM, FASTA, FASTQ, or RD files"/>
        <param name="expected_gsize" type="integer" label="Expected Genome Size" optional="true" help="Integer (e.g., 3000000000 for human)."/>
        <section name="input_filter" title="Filter input reads" expanded="false">
            <param argument="--include-list" type="data" format="txt" optional="true" label="File containing headers to include"/>
            <param argument="--exclude-list" type="data" format="txt" optional="true" label="File containing headers to exclude"/>
            <conditional name="filter_expression">
                <param name="filter_selector" type="select" label="Filter using length and/or quality" help="filter help">
                    <option value="no_exp" selected="true">No</option>
                    <option value="l_exp">Read length</option>
                    <option value="q_exp">Average read quality</option>
                    <option value="lq_exp">Both read length and average read quality</option>
                </param>
                <when value="no_exp"/>
                <when value="l_exp">
                    <param name="length_comparison" type="select" label="Retain reads with length">
                        <option value="&lt;" selected="true">less than</option>
                        <option value="=">equal to</option>
                        <option value=">">greater than</option>
                        <sanitizer sanitize="false"/>
                    </param>
                    <param name="length_value" type="integer" min="0" value="0" label="Length in bp" />
                </when>
                <when value="q_exp">
                    <param name="quality_comparison" type="select" label="Retain reads with average read quality">
                        <option value="&lt;" selected="true">less than</option>
                        <option value="=">equal to</option>
                        <option value=">">greater than</option>
                        <sanitizer sanitize="false"/>
                    </param>
                    <param name="quality_value" type="integer" min="0" value="0" label="Average read quality" />
                </when>
                <when value="lq_exp">
                    <param name="length_comparison" type="select" label="Retain reads with length">
                        <option value="&lt;" selected="true">less than</option>
                        <option value="=">equal to</option>
                        <option value=">">greater than</option>
                        <sanitizer sanitize="false"/>
                    </param>
                    <param name="length_value" type="integer" min="0" value="0" label="Length in bp" />
                    <param name="exp_operator" type="select" label="Combination operator">
                        <option value="|" selected="true">or</option>
                        <option value="&amp;">and</option>
                        <sanitizer sanitize="false"/>
                    </param>
                    <param name="quality_comparison" type="select" label="Average read quality">
                        <option value="&lt;" selected="true">less than</option>
                        <option value="=">equal to</option>
                        <option value=">">greater than</option>
                        <sanitizer sanitize="false"/>
                    </param>
                    <param name="quality_value" type="integer" min="0" value="0" label="average read quality" />
                </when>
            </conditional>
        </section>
        <section name="input_subsample" title="Subsample input reads" expanded="false">
            <param argument="--sample" type="float" min="0" max="1" value="1" label="fraction of reads to subsample"/>
            <conditional name="random_seed">
                <param name="seed_selector" type="select" label="supply random seed to make subsampling reproducible">
                    <option value="no" selected="true">no</option>
                    <option value="yes">yes</option>
                </param>
                <when value="no"/>
                <when value="yes">
                    <param argument="--random-seed" type="integer" min="0" value="0" label="random seed to make subsampling reproducible"/>
                </when>
            </conditional>
        </section>
        <conditional name="input_compress">
            <param name="compress_selector" type="select" label="Compress homopolymers">
                <option value="no" selected="true">no</option>
                <option value="yes">yes</option>
            </param>
            <when value="no"/>
            <when value="yes">
                <param argument="--homopolymer-compress" type="integer" min="0" value="0" label="Compress homopolymers longer than n in the input"/>
            </when>
        </conditional>
        <section name="output_options" title="Output options">
            <conditional name="stats_flavor">
                <param name="flavor_selector" type="select" label="Stats output">
                    <option value="stats" selected="true">Stats</option>
                    <option value="quality">Quality</option>
                    <option value="size">Size</option>
                </param>
                <when value="stats">
                    <param argument="--sequence-report" type="boolean" checked="false" label="Per read sequence report"/>
                </when>
                <when value="quality">
                    <param argument="--quality" type="select" optional="true" label="quality type">
                        <option value="q" selected="true">Average quality for each read</option>
                        <option value="a">Both length and quality for each read</option>
                    </param>
                </when>
                <when value="size">
                    <param argument="--out-size" type="select" optional="true" label="size list type">
                        <option value="u" selected="true">unsorted</option>
                        <option value="s">sorted</option>
                        <option value="h">histogram</option>
                        <option value="c">inverse cumulative table</option>
                    </param>
                </when>
            </conditional>
            <conditional name="output_type">
                <param name="type_selector" type="select" label="output type">
                    <option value="rd_file" selected="true">RD file</option>
                    <option value="combined_reads">Combined reads</option>
                </param>
                <when value="combined_reads">
                    <param name="format_selector" type="select" optional="true" label="Output format">
                        <option value="fasta.gz" selected="true">fasta</option>
                        <option value="fastq.gz">fastq</option>
                        <option value="bam">bam</option>
                        <option value="cram">cram</option>
                    </param>
                </when>
                <when value="rd_file">
                    <param argument="--md5" type="boolean" checked="false" label="Print md5 of .rd files"/>
                </when>
            </conditional>
        </section>
    </inputs>
    <outputs>
        <data name="stats_outfile" format="tabular" label="Rdeval summary"/>
        <data name="rd_outfile" from_work_dir="output.rd" format="binary" label="RD File">
            <filter>output_options["output_type"]["type_selector"] == "rd_file"</filter>
        </data>
        <data name="reads_outfile" format="binary" label="Output reads">
            <filter>output_options["output_type"]["type_selector"] == "combined_reads"</filter>
            <change_format>
                <when input="format_selector" value="fasta.gz" format="fasta.gz"/>
                <when input="format_selector" value="fastq.gz" format="fastq.gz"/>
                <when input="format_selector" value="bam" format="bam"/>
                <when input="format_selector" value="cram" format="cram"/>
            </change_format>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="input_reads" value="input1.fastq.gz" ftype="fastq.gz"/>
            <output name="stats_outfile" file="output1.tabular" ftype="tabular"/>
            <output name="rd_outfile" ftype="binary">
                <assert_contents>
                    <has_size size="119" delta="1"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <param name="input_reads" value="input1.fastq.gz" ftype="fastq.gz"/>
            <section name="input_filter">
                <conditional name="filter_expression">
                    <param name="filter_selector" value="lq_exp"/>
                    <param name="length_comparison" value=">"/>
                    <param name="length_value" value="10"/>
                    <param name="exp_operator" value="&amp;"/>
                    <param name="quality_comparison" value=">"/>
                    <param name="quality_value" value="10"/>
                </conditional>
            </section>
            <output name="stats_outfile" file="output2.tabular" ftype="tabular"/>
            <output name="rd_outfile" ftype="binary">
                <assert_contents>
                    <has_size size="100" delta="1"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <param name="input_reads" value="input1.fastq.gz" ftype="fastq.gz"/>
            <section name="input_compress">
                <param name="compress_selector" value="yes"/>
                <param name="homopolymer_compress" value="1"/>
            </section>
            <section name="output_options">
                <conditional name="output_type">
                    <param name="type_selector" value="combined_reads"/>
                    <param name="format_selector" value="fastq.gz"/>
                </conditional>
            </section>
            <output name="stats_outfile" file="output3.tabular" ftype="tabular"/>
            <output name="reads_outfile" ftype="fastq.gz" md5="23a14631cb075817967752021deb6ec4">
                <assert_contents>
                    <has_size size="159"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
What it does
============

**rdeval** accepts an arbitrary number of sequencing files and optionally **filters**, **subsamples**, and/or **compresses homopolymers** within the reads. The retained reads can be saved in multiple formats, and metrics on these reads can be stored in a '*sketch*' file. Statistics can then be efficiently retrieved from these sketch files for further processing.

.. image:: pipeline.svg

Filtering
=========

Input reads can be filtered using one of the three methods listed below, applied sequentially in the specified order.

1. Retain reads whose header lines are listed in the include dataset.
2. Discard reads whose header lines are listed in the exclude dataset.
3. Retain reads that match the provided filter expression.

The filter expression can be used to select reads based on read length (l), average read quality (q), or a combination of both. The grammar for constructing filter expressions is outlined below:

     * filter-expression ::= <length-expression> | <quality-expression> | <length-expression> <combination-operator> <quality-expression> | <quality-expression> <combination-operator> <length-expression>
     * length-expression ::= "l" <comparison-operator> <integer>
     * quality-expression ::= "q" <comparison-operator> <integer>
     * combination-operator := "&" | "|"
     * comparison-operator ::= "<" | "=" | ">"
     * integer ::= <digit> | <digit><integer>
     * digit ::= "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"

Retain reads longer than 10 base pairs

    l>10

Retain reads with average quality greather than 20

     q>20

Retain reads longer than 10 base pairs with average quality greather than 20

     l>10 & q>20

.. _sampling-label:

Sub-sampling
============

4. Retain a subsample of the reads by specifying the fraction to be kept. Use the *random seed* option to keep subsampling reproducible.

Homopolymer Compression
=======================

5. Runs of repeated nucleotides in each read are collapsed, with any associated quality data discarded. For example, CAGGCTTT would become CAGCT.
    ]]></help>
    <expand macro="citations"/>
</tool>