annotate mixcr_analyze.xml @ 0:d38cfb922f95 draft default tip

"planemo upload for repository https://github.com/galaxyproject/iuc/tree/master/tools/mixcr commit b847d69ff272b194e29858c173a7343442f905b2"

<tool id="mixcr_analyze" name="MiXCR Analyze" version="@VERSION@.0">
    <description>immuno clonotyes from sequence data</description>
    <macros>
        <import>mixcr_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
        #import os.path
        #import re
        #def clean(name)
            #set $base_name = $os.path.basename($name)
            #set $name_clean = re.sub('[^\w\-_\.]', '_', $base_name)
            #return $name_clean
        #end def
        #if $imgt.library_selector == 'history':
            #set $libname = $re.sub('.gz$','',$clean($imgt.library.name))
            ln -s -f '$imgt.library' $libname &&
        #end if
        #if str( $fastq_input.fastq_input_selector ) == "paired":
          #set $fq1 = $clean($fastq_input.fastq_input1.name)
          ln -s -f '$fastq_input.fastq_input1' $fq1 &&
          #set $fq2 = $clean($fastq_input.fastq_input2.name)
          ln -s -f '$fastq_input.fastq_input2' $fq2 &&
        #else:
          #set $fq1 = $clean($fastq_input.fastq_input1.name)
          ln -s -f '$fastq_input.fastq_input1' $fq1 &&
        #end if
        mixcr analyze $analyze.pipeline --starting-material $starting_material
        #if $analyze.pipeline == 'amplicon':
            --5-end $analyze.primers5end
            --3-end $analyze.primers3end
            --adapters $analyze.adapters
        #end if
        #if $imgt.library_selector == 'history':
            --align "--library $libname"
            #set $taxonId = str($imgt.species).split(':')[0]
            --species $taxonId
        ## #elif $imgt.library_selector == 'cached':
        #else
            --species $imgt.species
        #end if
        $contig_assembly $impute_germline_on_export $only_productive 
        --receptor-type $receptor_type
        #if str( $fastq_input.fastq_input_selector ) == "paired":
          $fq1 $fq2
        #else:
          $fq1
        #end if
        mixcr_analysis
    ]]></command>
    <inputs>
        <conditional name="analyze">
            <param name="pipeline" type="select" label="amplicon or shotgun data" help="">
                <option value="amplicon">amplicon: enriched targeted TCR/IG libraries (5’RACE, Amplicon, Multiplex, etc)</option>
                <option value="shotgun">shotgun: non-enriched RNA-seq or non-targeted genomic data</option>
            </param>
            <when value="amplicon">
                <param name="primers5end" type="select" label="5’-end of the library.">
                    <help>
                        There are two possible values: 
                            no-v-primers — no V gene primers (e.g. 5’RACE with template switch oligo or a like), 
                            v-primers — V gene single primer / multiple.
                    </help>
                    <option value="no-v-primers">no-v-primers</option>
                    <option value="v-primers">v-primers</option>
                </param>
                <param name="primers3end" type="select" label="3’-end of the library.">
                    <help>
                        There are three possible values: 
                            j-primers — J gene single primer / multiplex, 
                            j-c-intron-primers — J-C intron single primer / multiplex, 
                            c-primers — C gene single primer / multiplex (e.g. IGHC primers specific to different immunoglobulin isotypes).
                    </help>
                    <option value="j-primers">j-primers</option>
                    <option value="j-c-intron-primers">j-c-intron-primers</option>
                    <option value="c-primers">c-primers</option>
                </param>
                <param name="adapters" type="select" label="Presence of PCR primers and/or adapter sequences">
                    <help>
                        If sequences of primers used for PCR or adapters are present in sequencing data, 
                        it may influence the accuracy of V, J and C gene segments identification and CDR3 mapping. 
                    </help>
                    <option value="adapters-present">adapters-present</option>
                    <option value="no-adapters">no-adapters</option>
                </param>
            </when>
            <when value="shotgun"/>
        </conditional>
        <param name="starting_material" type="select" label="Type of starting material: RNA or DNA" help="">
            <option value="rna">RNA</option>
            <option value="dna">DNA</option>
        </param>
        <conditional name="fastq_input">
            <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data">
                <option value="single">single-end fastq</option>
                <option value="paired">paired-end fastq</option>
            </param>
            <when value="paired">
                <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" label="Select first set of reads" help="Specify dataset with forward reads"/>
                <param name="fastq_input2" type="data" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" label="Select second set of reads" help="Specify dataset with reverse reads"/>
            </when>
            <when value="single">
                <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2,fasta" label="Select sequence dataset" help="Specify dataset with single reads"/>
            </when>
        </conditional>
        <conditional name="imgt">
            <param name="library_selector" type="select" label="Library selector" help="Select between paired and single end data">
                <option value="builtin">MiXCR builtin library</option>
                <!-- <option value="cached">repseqio IMGT library</option> -->
                <option value="history">history repseqio IMGT library</option>
            </param>
            <when value="builtin">
                <param name="species" type="text" label="Species">
                    <option value="9606">HomoSapiens</option>
                    <option value="MusMusculus">MusMusculus</option>
                    <option value="rat">rat</option>
                </param>
            </when>
            <!--
            <when value="cached">
                <param name="library" type="select" label="repseqio IMGT library">
                    <options from_data_table="imgt_library">
                        <column name="name" index="1"/>
                        <column name="value" index="2"/>
                    </options>
                </param>
                <param name="species" type="select" label="Species">
                    <options from_data_table="imgt_library">
                        <column name="name" index="3"/>
                        <column name="value" index="3"/>
                        <filter type="param_value" ref="library" column="2" />
                        <filter type="multiple_splitter" column="3" separator=","/>
                    </options>
                </param>
            </when>
            -->
            <when value="history">
                <param name="library" type="data" format="imgt.json" label="repseqio IMGT library">
                    <help><![CDATA[
Data coming from IMGT server may be used for academic research only, 
provided that it is referred to IMGT®, and cited as:MiXCR is a universal framework that processes big immunome data from raw sequences to quantitated clonotypes. MiXCR efficiently handles paired- and single-end reads, considers sequence quality, corrects PCR errors and identifies germline hypermutations. The software supports both partial- and full-length profiling and employs all available RNA or DNA information, including sequences upstream of V and downstream of J gene segments.

MiXCR is free for academic and non-profit use (see License). 
"IMGT®, the international ImMunoGeneTics information system® http://www.imgt.org (founder and director: Marie-Paule Lefranc, Montpellier, France)."
                    ]]></help>
                </param>
                <param name="species" type="select" label="Species">
                    <options>
                        <filter type="data_meta" ref="library" key="taxon_names" />
                    </options>
                </param>
            </when>
        </conditional>
        <param name="contig_assembly" type="boolean" truevalue="--contig-assembly" falsevalue="" checked="false" label="Assemble full receptor sequences." help="This option may slow down the computation."/>
        <param name="impute_germline_on_export" type="boolean" truevalue="--impute-germline-on-export" falsevalue="" checked="false" label="Use germline segments (printed with lowercase letters) for uncovered gene features"/>
        <param name="only_productive" type="boolean" truevalue="--only-productive" falsevalue="" checked="false" label="Filter out-of-frame and stop-codons in export"/>
        <param name="receptor_type" type="select" label="Dedicated receptor type for analysis">
            <option value="xcr" selected="true">xcr (all T- and B-cell receptor chains are analyzed)</option>
            <option value="tcr">tcr</option>
            <option value="bcr">bcr</option>
            <option value="tra">tra</option>
            <option value="trb">trb</option>
            <option value="trg">trg</option>
            <option value="trd">trd</option>
            <option value="igh">igh</option>
            <option value="igk">igk</option>
            <option value="igl">igl</option>
        </param>
    </inputs>
    <outputs>
        <data name="report" format="txt" label="${tool.name} on ${on_string}: report" from_work_dir="mixcr_analysis.report"/>
        <data name="clonotypes" format="tabular" label="${tool.name} on ${on_string}: clonotypes.ALL" from_work_dir="mixcr_analysis.clonotypes.ALL.txt">
            <actions>
                <action name="comment_lines" type="metadata" default="1" />
                <action name="column_names" type="metadata" default="cloneId,cloneCount,cloneFraction,targetSequences,targetQualities,allVHitsWithScore,allDHitsWithScore,allJHitsWithScore,allCHitsWithScore,allVAlignments,allDAlignments,allJAlignments,allCAlignments,nSeqFR1,minQualFR1,nSeqCDR1,minQualCDR1,nSeqFR2,minQualFR2,nSeqCDR2,minQualCDR2,nSeqFR3,minQualFR3,nSeqCDR3,minQualCDR3,nSeqFR4,minQualFR4,aaSeqFR1,aaSeqCDR1,aaSeqFR2,aaSeqCDR2,aaSeqFR3,aaSeqCDR3,aaSeqFR4,refPoints" />
            </actions>
        </data>
    </outputs>
    <tests>
        <test>
            <conditional name="analyze">
                <param name="pipeline" value="shotgun"/>
            </conditional>
            <param name="starting_material" value="rna"/>
            <conditional name="fastq_input">
                <param name="fastq_input_selector" value="paired"/>
                <param name="fastq_input1" value="sample_IGH_R1.fastq" ftype="fastqsanger"/>
                <param name="fastq_input2" value="sample_IGH_R2.fastq" ftype="fastqsanger"/>
            </conditional>
            <conditional name="imgt">
                <param name="library_selector" value="builtin"/>
                <param name="species" value="9606"/> 
            </conditional>
            <param name="contig_assembly" value="True"/>
            <param name="impute_germline_on_export" value="True"/>
            <param name="only_productive" value="False"/>
            <param name="receptor_type" value="xcr"/>
            <output name="report">
                <assert_contents>
                    <has_text text="Final clonotype count" />
                </assert_contents>
            </output>
            <output name="clonotypes">
                <assert_contents>
                    <has_text text="CARDDGGGKGDYGRLW" />
                </assert_contents>
            </output>
        </test>
        <test>
            <conditional name="analyze">
                <param name="pipeline" value="amplicon"/>
                <param name="primers5end" value="v-primers"/>
                <param name="primers3end" value="j-primers"/>
                <param name="adapters" value="no-adapters"/>
            </conditional>
            <param name="starting_material" value="rna"/>
            <conditional name="fastq_input">
                <param name="fastq_input_selector" value="paired"/>
                <param name="fastq_input1" value="sample_IGH_R1.fastq" ftype="fastqsanger"/>
                <param name="fastq_input2" value="sample_IGH_R2.fastq" ftype="fastqsanger"/>
            </conditional>
            <conditional name="imgt">
                <param name="library_selector" value="builtin"/>
                <param name="species" value="9606"/> 
            </conditional>
            <param name="contig_assembly" value="True"/>
            <param name="impute_germline_on_export" value="True"/>
            <param name="only_productive" value="False"/>
            <param name="receptor_type" value="xcr"/>
            <output name="report">
                <assert_contents>
                    <has_text text="Final clonotype count" />
                </assert_contents>
            </output>
            <output name="clonotypes">
                <assert_contents>
                    <has_text text="CARDDGGGKGDYGRLW" />
                </assert_contents>
            </output>
        </test>

    </tests>
    <help><![CDATA[
**MiXCR** **a universal tool for fast and accurate analysis of T- and B- cell receptor repertoire sequencing data**

MiXCR_ is a universal framework that processes big immunome data from raw sequences to quantitated clonotypes. MiXCR_ efficiently handles paired- and single-end reads, considers sequence quality, corrects PCR errors and identifies germline hypermutations. The software supports both partial- and full-length profiling and employs all available RNA or DNA information, including sequences upstream of V and downstream of J gene segments.

**MiXCR is free for academic and non-profit use** (see License_).

This tool runs the MiXCR_ analyze_ pipeline.  
Generally, there two distinct types of library preparation which correspond to the two analyze pipelines:

      - analyze_ amplicon_ for analysis of targeted TCR/IG library amplification (5’RACE, Amplicon, Multiplex, etc).
      - analyze_ shotgun_ for analysis of random fragments (RNA-Seq, Exome-Seq, etc).


MiXCR_ has builtin libraries for human, mouse and rat.  Additional compiled IMGT_ libraries can be imported into your Galaxy history as datatype: *imgt.json* from: https://github.com/repseqio/library-imgt/releases

NOTE:  The imgt.201822-5.sv4.json.gz release has the rattus genus taxonId:10114 for rat, whereas the mixcr builtin library has the rattus norvegicus species taxId:10116 for rat.  If you encounter imgt library loading errors from mixcr, you may have to substitute 10116 for 10114 in the imgt.201822-5.sv4.json.gz file.

**Data coming from IMGT server may be used for academic research only**, provided that it is referred to IMGT®, and cited as "IMGT®, the international ImMunoGeneTics information system® http://www.imgt.org (founder and director: Marie-Paule Lefranc, Montpellier, France)."

.. _MiXCR: https://mixcr.readthedocs.io/en/latest/index.html
.. _analyze: https://mixcr.readthedocs.io/en/latest/analyze.html
.. _amplicon: https://mixcr.readthedocs.io/en/latest/analyze.html#analysis-of-targeted-tcr-ig-libraries
.. _shotgun: https://mixcr.readthedocs.io/en/latest/analyze.html#analysis-of-non-enriched-or-random-fragments
.. _License: https://mixcr.readthedocs.io/en/latest/license.html#license
.. _IMGT: https://github.com/repseqio/library-imgt/releases
    ]]></help>
    <expand macro="citations" />
</tool>