comparison deseq2.xml @ 22:e5c8afac22a7 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/deseq2 commit 1b60ee0faa1291f08620cd03d0f6647700daf862

21:a6fc9228e1a0

<tool id="deseq2" name="DESeq2" version="2.11.40.5">
    <description>Determines differentially expressed features from count tables</description>
    <requirements>
        <requirement type="package" version="1.20.0">bioconductor-deseq2</requirement>
        <!-- Optional dependency of tximport, needed to import kallisto results https://github.com/galaxyproject/usegalaxy-playbook/issues/161 -->
        <requirement type="package" version="2.24.0">bioconductor-rhdf5</requirement>
        <requirement type="package" version="1.8.0">bioconductor-tximport</requirement>
        <requirement type="package" version="1.32.3">bioconductor-genomicfeatures</requirement>
        <requirement type="package" version="1.20.2">r-getopt</requirement>
        <requirement type="package" version="0.8.0">r-ggrepel</requirement>
        <requirement type="package" version="3.0.1">r-gplots</requirement>
        <requirement type="package" version="1.0.10">r-pheatmap</requirement>
        <requirement type="package" version="0.2.20">r-rjson</requirement>

    #if $normVST:
        -v '$vst_out'
    #end if
    #set $filename_to_element_identifiers = {}
    #set $temp_factor_names = list()
    #for $factor in $rep_factorName:
        #set $temp_factor = list()
        #for $level in $factor.rep_factorLevel:
            #set $count_files = list()
            #for $file in $level.countsFile:
                $count_files.append(str($file))
                $filename_to_element_identifiers.__setitem__(os.path.basename(str($file)),  $file.element_identifier)
            #end for
            $temp_factor.append( {str($level.factorLevel): $count_files} )
        #end for
        $temp_factor.reverse()
        $temp_factor_names.append([str($factor.factorName), $temp_factor])
    #end for

        #end if

    #end if
]]></command>
    <inputs>
        <repeat name="rep_factorName" title="Factor" min="1">
            <param name="factorName" type="text" value="FactorName" label="Specify a factor name, e.g. effects_drug_x or cancer_markers"
                help="Only letters, numbers and underscores will be retained in this field">
                <sanitizer>
                    <valid initial="string.letters,string.digits"><add value="_" /></valid>
                </sanitizer>
            </param>
            <repeat name="rep_factorLevel" title="Factor level" min="2" default="2">
                <param name="factorLevel" type="text" value="FactorLevel" label="Specify a factor level, typical values could be 'tumor', 'normal', 'treated' or 'control'"
                    help="Only letters, numbers and underscores will be retained in this field">
                    <sanitizer>
                        <valid initial="string.letters,string.digits"><add value="_" /></valid>
                    </sanitizer>
                </param>
                <param name="countsFile" type="data" format="tabular" multiple="true" label="Counts file(s)"/>
            </repeat>
        </repeat>
        <param name="batch_factors" type="data" format="tabular" optional="true" label="(Optional) provide a tabular file with additional batch factors to include in the model." help="You can produce this file using RUVSeq or svaseq."/>
        <param name="header" type="boolean" truevalue="-H" falsevalue="" checked="true" label="Files have header?" help="If this option is set to Yes, the tool will assume that the count files have column headers in the first row. Default: Yes" />

        <conditional name="tximport">
            <param name="tximport_selector" type="select" label="Choice of Input data">

                <assert_contents>
                    <has_text_matching expression="ENSG00000168671\t1.8841.*\t-0.1180.*\t0.7429.*\t-0.1589.*\t0.8737.*\t0.9999.*" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

22:e5c8afac22a7

<tool id="deseq2" name="DESeq2" version="2.11.40.6">
    <description>Determines differentially expressed features from count tables</description>
    <macros>
        <import>deseq2_macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="1.22.1">bioconductor-deseq2</requirement>
        <!-- Optional dependency of tximport, needed to import kallisto results https://github.com/galaxyproject/usegalaxy-playbook/issues/161 -->
        <requirement type="package" version="2.26.2">bioconductor-rhdf5</requirement>
        <requirement type="package" version="1.10.0">bioconductor-tximport</requirement>
        <requirement type="package" version="1.34.1">bioconductor-genomicfeatures</requirement>
        <requirement type="package" version="1.20.2">r-getopt</requirement>
        <requirement type="package" version="0.8.0">r-ggrepel</requirement>
        <requirement type="package" version="3.0.1">r-gplots</requirement>
        <requirement type="package" version="1.0.10">r-pheatmap</requirement>
        <requirement type="package" version="0.2.20">r-rjson</requirement>

    #if $normVST:
        -v '$vst_out'
    #end if
    #set $filename_to_element_identifiers = {}
    #set $temp_factor_names = list()
    #for $factor in $select_data.rep_factorName:
        #set $temp_factor = list()
        #for $level in $factor.rep_factorLevel:
            #set $count_files = list()
            #if $select_data.how == 'group_tags':
                #for $group in $level.groups.value:
                    #for $file in $select_data.countsFile.get_datasets_for_group($group):
                        $count_files.append(str($file))
                        $filename_to_element_identifiers.__setitem__(os.path.basename(str($file)),  $file.element_identifier)
                    #end for
                #end for
            #else:
                #for $file in $level.countsFile:
                    $count_files.append(str($file))
                    $filename_to_element_identifiers.__setitem__(os.path.basename(str($file)),  $file.element_identifier)
                #end for
            #end if
            $temp_factor.append( {str($level.factorLevel): $count_files} )
        #end for
        $temp_factor.reverse()
        $temp_factor_names.append([str($factor.factorName), $temp_factor])
    #end for

        #end if

    #end if
]]></command>
    <inputs>
        <conditional name="select_data">
            <param name="how" type="select">
                <option value="datasets_per_level">Select datasets per level</option>
                <option value="group_tags">Select group tags corresponding to levels</option>
            </param>
            <when value="group_tags">
                <param name="countsFile" type="data_collection" format="tabular" label="Count file(s) collection" multiple="true"/>
                <expand macro="factor_repeat">
                    <param name="groups" type="group_tag" data_ref="countsFile" multiple="true" label="Select groups that correspond to this factor level"/>
                </expand>
            </when>
            <when value="datasets_per_level">
                <expand macro="factor_repeat">
                    <param name="countsFile" type="data" format="tabular" multiple="true" label="Counts file(s)"/>
                </expand>
            </when>
        </conditional>

        <param name="batch_factors" type="data" format="tabular" optional="true" label="(Optional) provide a tabular file with additional batch factors to include in the model." help="You can produce this file using RUVSeq or svaseq."/>
        <param name="header" type="boolean" truevalue="-H" falsevalue="" checked="true" label="Files have header?" help="If this option is set to Yes, the tool will assume that the count files have column headers in the first row. Default: Yes" />

        <conditional name="tximport">
            <param name="tximport_selector" type="select" label="Choice of Input data">

                <assert_contents>
                    <has_text_matching expression="ENSG00000168671\t1.8841.*\t-0.1180.*\t0.7429.*\t-0.1589.*\t0.8737.*\t0.9999.*" />
                </assert_contents>
            </output>
        </test>
        <!--Ensure group tags can be used to select factor levels -->
        <test expect_num_outputs="1">
            <param name="select_data|how" value="group_tags"/>
            <param name="select_data|countsFile">
                <collection type="list">
                    <element name="1" value="sailfish/sailfish_quant.sf1.tab" tags="group:primary:treated"/>
                    <element name="2" value="sailfish/sailfish_quant.sf2.tab" tags="group:primary:treated"/>
                    <element name="3" value="sailfish/sailfish_quant.sf3.tab" tags="group:primary:treated"/>
                    <element name="4" value="sailfish/sailfish_quant.sf4.tab" tags="group:primary:untreated"/>
                    <element name="5" value="sailfish/sailfish_quant.sf5.tab" tags="group:primary:untreated"/>
                    <element name="6" value="sailfish/sailfish_quant.sf6.tab" tags="group:primary:untreated"/>
                </collection>
            </param>
            <repeat name="rep_factorName">
                <param name="factorName" value="Treatment"/>
                <repeat name="rep_factorLevel">
                    <param name="factorLevel" value="Treated"/>
                    <param name="groups" value="primary:treated"/>
                </repeat>
                <repeat name="rep_factorLevel">
                    <param name="factorLevel" value="Untreated"/>
                    <param name="groups" value="primary:untreated"/>
                </repeat>
            </repeat>
            <param name="pdf" value="False"/>
            <param name="tximport_selector" value="tximport"/>
            <param name="txtype" value="sailfish"/>
            <param name="mapping_format_selector" value="tabular"/>
            <param name="tabular_file" value="tx2gene.tab"/>
            <output name="deseq_out" >
                <assert_contents>
                    <has_text_matching expression="HOXC11\t0.557.*\t0.324.*\t0.437.*\t0.741.*\t0.458.*\t0.999.*"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**