annotate circexplorer2.xml @ 0:465d6578b4d0 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circexplorer2 commit fe03991cd7c43f5266314d1fb9e4108f1ab102e8

<tool id="circexplorer2" name="CIRCexplorer2" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <description>circular RNA analysis</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro='xrefs'/>
    <command detect_errors="exit_code"><![CDATA[
        #if $mode.selector == 'align'
            mkdir -p reads &&
            #set file_paths = []
            #for $i,$input_file in enumerate($mode.fastq)
                #set $fname = 'file' + str($i) + "." + $input_file.ext
                #set $file_path = 'reads/' + $fname
                ln -s '$input_file' '$file_path' &&
                $file_paths.append($file_path)
            #end for
            CIRCexplorer2 align
            @threads@
            --gtf '$mode.gtf'
            -g '$mode.genome'
            --fastq #echo ','.join($file_paths)#
            $mode.bw
            $mode.scale
            $mode.skip_tophat
            $mode.skip_tophat_fusion
            && tar -zcvf alignment.tgz './alignment'
        #else if $mode.selector == 'parse'
            CIRCexplorer2 parse
            -t $mode.aligner.selector
            $mode.aligner.fusion_file
            #if $mode.aligner.selector == 'TopHat-Fusion'
                $mode.aligner.pe
            #end if
            $mode.aligner.f
        #else if  $mode.selector == 'annotate'
            ln -s $mode.genome reference_genome.fa &&
            CIRCexplorer2 annotate
            -r $mode.ref
            -g reference_genome.fa
            -b $mode.bed
            $mode.no_fix
            $mode.low_confidence
        #else if $mode.selector == 'assemble'
            tar -zxf $mode.tophat &&
            CIRCexplorer2 assemble
            @threads@
            -r $mode.ref
            -m ./alignment
            $mode.remove_rRNA
            && tar -zcvf assemble.tgz './assemble'
        #else
            ln -s '$mode.genome' reference_genome.fa &&
            #if $mode.assemble_file.ext.endswith(".gz")
                tar -zxf $mode.assemble_file &&
            #else
                tar -xf $mode.assemble_file &&
            #end if
            #if $mode.as_option.selector == 'enabled'
                tar -zxf $mode.as_option.tophat &&
            #end if
            CIRCexplorer2 denovo
            -d ./assemble
            -r $mode.ref
            -b $mode.bed
            -g reference_genome.fa
            #if $mode.abs
                --abs 'abs'
            #end if
            #if $mode.as_option.selector == 'enabled'
                --as 'as'
                $mode.as_option.type_mapping './alignment'
            #end if
            $mode.no_fix
            $mode.rpkm
        #end if
    ]]></command>
    <inputs>
        <conditional name="mode">
            <param name="selector" type="select" 
                label="Tool module" help="CIRCexplorer2 contains 5 modules. Each module 
                    functions as an independent component owning its distinctive duty. 
                    Meanwhile, they inteact with each other, and different circular RNA 
                    analysis pipelines are derived from different combinations of several 
                    modules.">
                <option value="align">Align: Map circular RNA junction reads with TopHat2/TopHat-Fusion</option>
                <option value="parse">Parse: Parse fusion junction information from other aligners</option>
                <option value="annotate">Annotate: Annotate circular RNA junction reads with gene annotations</option>
                <option value="assemble">Assemble: Assemble transcriptome for circular RNAs</option>
                <option value="denovo">De novo: Fetch de novo circular RNA isoforms</option>
            </param>
            <when value="align">
                <param argument="--gtf" type="data" format="gtf" label="Annotation GTF file" />
                <expand macro="genome_file"/>
                <param argument="--fastq" type="data" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz" multiple="true" label="RNA-seq FASTQ file(s)" 
                    help="Only single-read RNA-seq is supported. It is recommended to convert paired-end RNA-seq to single-read RNA-seq before alignment"/>
                <param argument="--bw" type="boolean" truevalue="--bw" falsevalue="" checked="false" 
                    label="Create BigWig file" help=" It will not consider strand information of read alignment"/>
                <param argument="--scale" type="boolean" truevalue="--scale" falsevalue="" checked="false" 
                    label="Scale BigWig to HPB" help="Expression levels will be scaled to hits per billion-mapped-bases (HPB)" />
                <param argument="--skip-tophat" type="boolean" truevalue="--skip-tophat" falsevalue="" checked="false" 
                    label="Skip TopHat mapping" help="CIRexplorer2 aligns reads onto genome and transcriptome using TopHat2 to 
                        reduce false positive reads aligned in the TopHat-Fusion alignment step" />
                <param argument="--skip-tophat-fusion" type="boolean" truevalue="--skip-tophat-fusion" falsevalue="" checked="false" 
                    label="Skip TopHat fusion" help="It is useful for poly(A)+ RNA-seq" />
            </when>
            <when value="parse">
                <conditional name="aligner">
                    <param argument="-t" name="selector" type="select" label="Aligner" 
                        help="CIRCexplorer2 parse could accept results derived from TopHat-Fusion, 
                            STAR, MapSplice, BWA and segemehl.">
                        <option value="TopHat-Fusion">TopHat-Fusion</option>
                        <option value="STAR">STAR</option>
                        <option value="MapSplice">MapSplice</option>
                        <option value="BWA">BWA</option>
                        <option value="segemehl">segemehl</option>
                    </param>
                    <when value="TopHat-Fusion"> 
                        <expand macro="parse_fusion" format="bam" label="TopHat-Fusion file" 
                            help="The required input file is accepted_hits.bam"/>
                        <expand macro="parse_statistics"/>
                        <param argument="--pe" type="boolean" truevalue="--pe" falsevalue="" checked="false" label="Paired-end aligner file" 
                            help="Parse paired-end alignment file. If this is set, then -f is set automatically." />
                    </when>
                    <when value="STAR">
                        <expand macro="parse_fusion" format="interval,tabular" label="STAR fusion file" 
                            help="The required input file is Chimeric.out.junction"/>
                        <expand macro="parse_statistics"/>
                    </when>
                    <when value="MapSplice">
                        <expand macro="parse_fusion" format="txt" label="MapSplice fusion file" 
                            help="The required input file is fusions_raw.txt"/>
                        <expand macro="parse_statistics"/>
                    </when>
                    <when value="BWA">
                        <expand macro="parse_fusion" format="sam" label="BWA fusion file" 
                            help="The required input file is the output sam file"/>
                        <expand macro="parse_statistics"/>
                    </when>
                    <when value="segemehl">
                        <expand macro="parse_fusion" format="bed" label="segemehl fusion file" 
                            help="The required input file is splicesites.bed"/>
                        <expand macro="parse_statistics"/>
                    </when>
                </conditional>
            </when>
            <when value="annotate">
                <expand macro="annotation_file"/>
                <expand macro="genome_file"/>
                <expand macro="junction_file"/>
                <param argument="--no-fix" type="boolean" truevalue="--no-fix" falsevalue="" checked="false" label="No fix mode" 
                    help="When enabled, realignment step of fusion junction reads will be skipped. It is useful for species with 
                        poor gene annotations, but the accuracy of circular RNA prediction would decrease." />
                <param argument="--low-confidence" type="boolean" truevalue="--low-confidence" falsevalue="" checked="false" label="Low confidence" 
                    help="By default, it extracts fusion junction reads exactly matching the boundaries of exons of the same isoform by default. 
                        If you set the --low-confidence, it will also extract fusion junction reads matching the boundaries of exons of the different 
                        isofoms of the same gene" />
            </when>
            <when value="assemble">
                <expand macro="annotation_file"/>
                <expand macro="tophat_file"/>
                <param argument="--remove-rRNA" type="boolean" truevalue="--remove-rRNA" falsevalue="" checked="false" 
                    label="Remove rRNA" help="Ignore rRNA during assembling (only for human hg19)" />
            </when>
            <when value="denovo">
                <expand macro="annotation_file"/>
                <expand macro="junction_file"/>
                <expand macro="genome_file"/>
                <param name="assemble_file" type="data" format="tgz,tar" label="Assemble file" 
                    help="Generated by the module CIRCexplorer2 assemble" />
                <param argument="--abs" type="boolean" truevalue="--abs" falsevalue="" checked="false" 
                    label="Detect alternative back-splicing" help="When set, it will characterize the 
                        alternative back-splicing of circular RNAs" />
                <conditional name="as_option">
                    <param name="selector" type="select" label="Characterize alternative splicing of cirRNAs" 
                        help="If enabled,  it will characterize the alternative splicing of circular RNAs, including 
                            cassette exons, retained introns, A5SS and A3SS">
                            <option value="disabled">Disabled</option>
                            <option value="enabled">Enabled</option>
                    </param>
                    <when value="disabled"/>
                    <when value="enabled">
                        <expand macro="tophat_file"/>
                        <param name="type_mapping" type="select" label="Type of mapping" 
                            help="In this mode, you should also offer the path of TopHat mapping directory for 
                                p(A)-/p(A)+ RNA-seq via -m/-n option">
                            <option value="-m">p(A)-</option>
                            <option value="-n">p(A)+ RNA-seq</option>
                        </param>
                    </when>
                </conditional>
                <param argument="--no-fix" type="boolean" truevalue="--no-fix" falsevalue="" checked="false" label="No-fix mode" 
                    help="If enabled,  realignment step of fusion junction reads will be skipped. It is useful for species with 
                        poor gene annotations, but the accuracy of circular RNA prediction would decrease." />
                <param argument="--rpkm" type="boolean" truevalue="--rpkm" falsevalue="" checked="false" label="Calculate RPKM for cassete exons" 
                    help="If enabled, RPKM of cassette exons would be calculated" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="alignment" format="tgz" from_work_dir="alignment.tgz" label="${tool.name} on ${on_string}: alignment file   ">
            <filter>mode['selector'] == 'align'</filter>
        </data>
        <data name="fusion_junction_bw" format="bigwig" from_work_dir="./alignment/tophat/accepted_hits.bw" label="${tool.name} on ${on_string}: BigWig">
            <filter>mode['selector'] == 'align'</filter>
            <filter>mode['bw']</filter>
        </data>
        <data name="parse" format="bed" from_work_dir="back_spliced_junction.bed" label="${tool.name} on ${on_string}: back spliced junction (BED)">
            <filter>mode['selector'] == 'parse'</filter>
        </data>
        <data name="annotate" format="tabular" from_work_dir="circularRNA_known.txt" label="${tool.name} on ${on_string}: circRNA known">
            <filter>mode['selector'] == 'annotate'</filter>
        </data>
        <data name="annotate_low" format="tabular" from_work_dir="low_conf_circularRNA_known.txt" label="${tool.name} on ${on_string}: Low confidence circRNA">
            <filter>mode['selector'] == 'annotate'</filter>
            <filter>mode['low_confidence']</filter>
        </data>
        <data name="assemble" format="tgz" from_work_dir="assemble.tgz" label="${tool.name} on ${on_string}: assemble file">
            <filter>mode['selector'] == 'assemble'</filter>
        </data>
        <data name="denovo_combined" format="tabular" from_work_dir="./denovo/combined_ref.txt" label="${tool.name} on ${on_string}: combined ref">
            <filter>mode['selector'] == 'denovo'</filter>
        </data>
        <data name="denovo_circularRNA" format="tabular" from_work_dir="./denovo/circularRNA_full.txt" label="${tool.name} on ${on_string}: circRNA full">
            <filter>mode['selector'] == 'denovo'</filter>
        </data>
        <data name="denovo_annotated" format="tabular" from_work_dir="./denovo/annotated_circ.txt" label="${tool.name} on ${on_string}: annotated circRNA">
            <filter>mode['selector'] == 'denovo'</filter>
        </data>
        <data name="denovo_novel" format="tabular" from_work_dir="./denovo/novel_circ.txt" label="${tool.name} on ${on_string}: novel circRNA">
            <filter>mode['selector'] == 'denovo'</filter>
        </data>
        <data name="denovo_abs5" format="tabular" from_work_dir="./abs/a5bs.txt" label="${tool.name} on ${on_string}: a5bs">
            <filter>mode['selector'] == 'denovo'</filter>
            <filter>mode['abs']</filter>
        </data>
        <data name="denovo_abs3" format="tabular" from_work_dir="./abs/a3bs.txt" label="${tool.name} on ${on_string}: a3bs">
            <filter>mode['selector'] == 'denovo'</filter>
            <filter>mode['abs']</filter>
        </data>
        <data name="denovo_all_exon" format="tabular" from_work_dir="./as/all_exon_info.txt" label="${tool.name} on ${on_string}: all exon info">
            <filter>mode['selector'] == 'denovo'</filter>
            <filter>mode['as_option'] == 'enabled'</filter>
        </data>
        <data name="denovo_all_intron" format="tabular" from_work_dir="./as/all_intron_info.txt" label="${tool.name} on ${on_string}: all intron info">
            <filter>mode['selector'] == 'denovo'</filter>
            <filter>mode['as_option'] == 'enabled'</filter>
        </data>
        <data name="denovo_a5ss" format="tabular" from_work_dir="./as/all_A5SS_info.txt" label="${tool.name} on ${on_string}: all A5SS info">
            <filter>mode['selector'] == 'denovo'</filter>
            <filter>mode['as_option'] == 'enabled'</filter>
        </data>
        <data name="denovo_a3ss" format="tabular" from_work_dir="./as/all_A3SS_info.txt" label="${tool.name} on ${on_string}: all A3SS info">
            <filter>mode['selector'] == 'denovo'</filter>
            <filter>mode['as_option'] == 'enabled'</filter>
        </data>
    </outputs>
    <tests>
    <test expect_num_outputs="1">
        <!--Test 01: Module align default options-->
        <conditional name="mode">
            <param name="selector" value="align"/>
            <param name="gtf" value="annotation_01.gtf"/>
            <param name="genome" value="reference_01.fa"/>
            <param name="fastq" value="reads_01.fastq,reads_02.fastq,reads_03.fastq"/>
            <param name="skip_tophat_fusion" value="true"/>
        </conditional>
        <output name="alignment">
            <assert_contents>
                <has_size value="3426053" delta="5000"/>
            </assert_contents>
        </output>
    </test>
    <test expect_num_outputs="2">
        <!--Test 02: Module align compressed files-->
        <conditional name="mode">
            <param name="selector" value="align"/>
            <param name="gtf" value="annotation_01.gtf"/>
            <param name="genome" value="reference_01.fa"/>
            <param name="fastq" value="reads_01.fastq.gz,reads_02.fastq.gz,reads_03.fastq.gz"/>
            <param name="skip_tophat_fusion" value="true"/>
            <param name="bw" value="true"/>
            <param name="scale" value="true"/>
        </conditional>
        <output name="alignment">
            <assert_contents>
                <has_size value="3435977" delta="5000"/>
            </assert_contents>
        </output>
        <output name="fusion_junction_bw" value="test_02.bigwig" ftype="bigwig"/>
    </test>
    <test expect_num_outputs="1">
        <!--Test 03: Module parse-->
        <conditional name="mode">
            <param name="selector" value="parse"/>
            <conditional name="aligner">
                <param name="selector" value="MapSplice"/>
                <param name="fusion_file" value="mapsplice_chimeric.junction"/>
            </conditional>
        </conditional>
        <output name="parse" value="test_03.bed" ftype="bed"/>
    </test>
    <test expect_num_outputs="1">
        <!--Test 04: Module parse STAR-->
        <conditional name="mode">
            <param name="selector" value="parse"/>
            <conditional name="aligner">
                <param name="selector" value="STAR"/>
                <param name="fusion_file" value="STAR_chimeric.junction"/>
                <param name="f" value="true"/>
            </conditional>
        </conditional>
        <output name="parse" value="test_04.bed" ftype="bed"/>
    </test>
    <test expect_num_outputs="1">
        <!--Test 05: Module annotate-->
        <conditional name="mode">
            <param name="selector" value="annotate"/>
            <param name="ref" value="annotation_02.txt"/>
            <param name="genome" value="reference_02.fa"/>
            <param name="bed" value="test_04.bed"/>
        </conditional>
        <output name="annotate" value="test_05.tabular" ftype="tabular"/>
    </test>
    <test expect_num_outputs="2">
        <!--Test 06: Module annotate-->
        <conditional name="mode">
            <param name="selector" value="annotate"/>
            <param name="ref" value="annotation_02.txt"/>
            <param name="genome" value="reference_02.fa"/>
            <param name="bed" value="test_04.bed"/>
            <param name="no_fix" value="true"/>
            <param name="low_confidence" value="true"/>
        </conditional>
        <output name="annotate" value="test_06.tabular" ftype="tabular"/>
    </test>
    <test expect_num_outputs="4">
        <!--Test 07: Module de novo-->
        <conditional name="mode">
            <param name="selector" value="denovo"/>
            <param name="ref" value="annotation_02.txt"/>
            <param name="bed" value="test_04.bed"/>
            <param name="genome" value="reference_02.fa"/>
            <param name="assemble_file" value="assemble.tgz"/>
        </conditional>
        <output name="denovo_combined" value="test_07_combined.txt" ftype="tabular"/>
        <output name="denovo_circularRNA" value="test_07_full.txt" ftype="tabular"/>
        <output name="denovo_annotated" value="test_07_annotated.txt" ftype="tabular"/>
        <output name="denovo_novel" value="test_07_novel.txt" ftype="tabular"/>
    </test>
    <test expect_num_outputs="6">
        <!--Test 08: Module de novo additional options-->
        <conditional name="mode">
            <param name="selector" value="denovo"/>
            <param name="ref" value="annotation_02.txt"/>
            <param name="bed" value="test_04.bed"/>
            <param name="genome" value="reference_02.fa"/>
            <param name="assemble_file" value="assemble.tgz"/>
            <param name="abs" value="true"/>
            <param name="no_fix" value="true"/>
            <param name="rpkm" value="true"/>
        </conditional>
        <output name="denovo_combined" value="test_08_combined.txt" ftype="tabular"/>
        <output name="denovo_circularRNA" value="test_08_full.txt" ftype="tabular"/>
        <output name="denovo_annotated" value="test_08_annotated.txt" ftype="tabular"/>
        <output name="denovo_novel" value="test_08_novel.txt" ftype="tabular"/>
        <output name="denovo_abs5" value="test_08_a5bs.txt" ftype="tabular"/>
        <output name="denovo_abs3" value="test_08_a3bs.txt" ftype="tabular"/>
    </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**Purpose**

CIRCexplorer2 is a comprehensive and integrative circular RNA analysis toolset. It is the successor 
of CIRCexplorer with plenty of new features to facilitate circular RNA identification and characterization.

-------------------

 .. class:: infomark

**Features**

    * Precisely annotate circular RNAs (Annotate)
    * Support multiple circular RNA aligners (TopHat2/TopHat-Fusion, STAR, MapSplice, BWA and segemehl) (Align and Parse)
    * De novo assemble novel circular RNA transcripts (Assemble)
    * Characterize various of alternative (back-)splicing events of circular RNAs (Denovo)
    * Fast identify circuar RNAs with STAR or BWA (Parse)
    * Support both single-read and paired-end sequencing.

-------------------

.. class:: infomark

**Modules** 

CIRCexplorer2 contains 5 modules. Each module functions as an independent component owning its distinctive duty. 
Meanwhile, they inteact with each other, and different circular RNA analysis pipelines are derived from different 
combinations of several modules. Understanding the detailed mechanism of each module could facilitate your circular 
RNA research.

CIRCexplorer2 documentation is available from `here <http://circexplorer2.readthedocs.org/>`_, including installation instructions and tutorial.

    ]]></help>
    <expand macro="citations" />
</tool>