comparison plink.xml @ 10:2c0ac05fe240 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/plink commit 6d29c051fe8a6564805da7a13668d067c31f0e86

9:272aca44b3dd

<tool id='plink' name='plink' version='@TOOL_VERSION@+galaxy@VERSION_SUFFIX@'>
    <macros>
        <token name='@TOOL_VERSION@'>1.90b6.21</token>
        <token name='@VERSION_SUFFIX@'>0</token>
        <xml name='template_sanitizer'>
            <sanitizer>
                <valid initial='default'>
                    <add value='#' />
                    <add value='@' />

    <xrefs>
        <xref type="bio.tools">plink</xref>
    </xrefs>
    <requirements>
        <requirement type='package' version='@TOOL_VERSION@'>plink</requirement>
    </requirements>
    <command detect_errors='exit_code'><![CDATA[

    ## Create Plink folder for any inputs
    mkdir ./plink_output

    ## If bmerge is set, create folder for merged files
    #if $functions.func == 'data_manage':
        #if $functions.bmerge.set == 'Yes':
            && mkdir bmerge_files
            && ln -s '$functions.bmerge.bed.extra_files_path'/RgeneticsData.bed bmerge_files/bmerge_input.bed
            && ln -s '$functions.bmerge.bed.extra_files_path'/RgeneticsData.bim bmerge_files/bmerge_input.bim
            && ln -s '$functions.bmerge.bed.extra_files_path'/RgeneticsData.fam bmerge_files/bmerge_input.fam
        #end if
    #end if


    #if $inputs.inputs.filetype == 'bfile':
        && ln -s '$inputs.inputs.bed.extra_files_path'/RgeneticsData.bed plink_input/plink_input.bed
        && ln -s '$inputs.inputs.bed.extra_files_path'/RgeneticsData.bim plink_input/plink_input.bim
        && ln -s '$inputs.inputs.bed.extra_files_path'/RgeneticsData.fam plink_input/plink_input.fam
        && plink --bfile plink_input/plink_input
    #elif $inputs.inputs.filetype == 'vcf':
        #if $inputs.inputs.input.is_of_type('bcf'):
            && plink --bcf '$inputs.inputs.input' 
        #else:

        #end if
    #end if

    ## Plink commands by section
    #if $inputs.covar_input:
            --covar '$inputs.covar_input'
    #end if
    #if $inputs.set_pheno.set_pheno == 'Yes':
        --pheno $inputs.set_pheno.pheno $inputs.set_pheno.all_pheno
    #end if
    #if $functions.func == 'filtering':

                #end if
                $functions.sex_founder_filter.nonfounders
            #end if

    #elif $functions.func == 'data_manage':

        #if $functions.bmerge.set == 'Yes':
            --bmerge bmerge_files/bmerge_input
        #end if
        
        #if $functions.template:

                    $functions.sex.mode.female_max
                    $functions.sex.mode.male_min
                #end if
            #end if
        #end if


    #elif $functions.func == 'link':
        #if $functions.set_indep.choice == 'Yes':
            --indep-pairwise $functions.set_indep.window $functions.set_indep.step $functions.set_indep.r2
        #end if
##    #elif $functions.func == 'pair_compare':

            #if $functions.genome.ppc:
                --ppc-gap $functions.genome.ppc
            #end if
        #end if

##    #elif $functions.func == 'scoring':
##
##    #else:
##        --rerun $functions.logfile
##      
    #end if
    --memory \${GALAXY_MEMORY_MB:-8192}

            && mv ./plink_output/*asso* assoc_out
            && find ./assoc_out/. -type f -exec mv {} {}.txt ';'
        #end if
    #end if
    && mkdir '$plink_out.extra_files_path'
    && cp plink_output/plink_output.bed '$plink_out.extra_files_path'/RgeneticsData.bed
    && cp plink_output/plink_output.bim '$plink_out.extra_files_path'/RgeneticsData.bim
    && cp plink_output/plink_output.fam '$plink_out.extra_files_path'/RgeneticsData.fam
    ]]></command>
    <inputs>
        <section name='inputs' title='Data inputs' expanded='true'>
            <conditional name='inputs'>
                <param name='filetype' type='select' label='Main input data type'>

                <option value='stats'>Basic statistics</option>
                <option value='link'>Linkage disequalibrium</option>
                <option value='stratification'>Population stratification</option>
                <option value='association'>Association analysis</option>
                <option value='ibd'>Identity-by-descent</option>
                <!-- <option value='rerun'>Rerun</option> -->
            </param>
            <when value='filtering'>
                <conditional name='id_list'>
                    <param name='func' type='select' label='ID list functions'>

                        <param name='intercept' label='Intercept' type='boolean' truevalue='intercept' falsevalue='' checked='false' help=''/>
                    </when>
                </conditional>
                <param name='lambda' type='float' label='Lambda value' optional='true'/>
            </when>
            <!-- <when value='scoring'>
            </when> -->
            <when value='ibd'>
                <conditional name='genome'>
                    <param name='output_genome' type='select' help='Perform and return results of IBS/IBD computation'>
                        <option value=''>No</option>
                        <option value='Yes'>Yes</option>

        <!--IBD-->
        <data name='genome' format='tabular' from_work_dir='plink_output/plink_output.genome' label='${tool.name}: Genome'>
            <filter>functions['func'] == 'ibd' and functions['genome']['output_genome']</filter>
        </data>
        
        <!--Stratifiction-->
        <data name='mds' format='txt' from_work_dir='plink_output/plink_output.mds' label='${tool.name}: MDS'>
            <filter>functions['func'] == 'stratification' and functions['cluster']['cluster'] == 'Yes' and functions['cluster']['mds']['mds_scaling'] == 'Yes'</filter>
        </data>
        <data name='cluster1' format='tabular' from_work_dir='plink_output/plink_output.cluster1' label='${tool.name}: Cluster 1'>

                <extra_files type="file" name="RgeneticsData.fam" value="vcf_out.fam"/>
            </output>
            <expand macro="log_out_assert"/>
        </test>

        <test expect_num_outputs='8'>
            <section name='inputs'>
                <conditional name='inputs'>
                    <param name='filetype' value='bfile'/>
                    <param name='bed' value='' ftype="pbed">

                </conditional>
            </conditional>
            <expand macro="log_out_assert"/>
            <output name='genome' file='out.genome'/>
        </test>
    </tests>
    <help><![CDATA[
        PLINK is a free, open-source whole genome association analysis toolset, designed to perform a range of basic, large-scale analyses in a computationally efficient manner.

        For detailed usage notes, visit http://www.cog-genomics.org/plink/2.0/

10:2c0ac05fe240

<tool id='plink' name='plink' version='@TOOL_VERSION@+galaxy@VERSION_SUFFIX@'>
    <description>genome association analysis toolset</description>
    <macros>
        <token name='@TOOL_VERSION@'>1.90b6.21</token>
        <token name='@VERSION_SUFFIX@'>1</token>
        <xml name='template_sanitizer'>
            <sanitizer>
                <valid initial='default'>
                    <add value='#' />
                    <add value='@' />

    <xrefs>
        <xref type="bio.tools">plink</xref>
    </xrefs>
    <requirements>
        <requirement type='package' version='@TOOL_VERSION@'>plink</requirement>
        <requirement type='package' version='5.3.0'>gawk</requirement>
    </requirements>
    <command detect_errors='exit_code'><![CDATA[

    ## Create Plink folder for any inputs
    mkdir ./plink_output

    ## If bmerge is set, create folder for merged files
    #if $functions.func == 'data_manage':
        #if $functions.bmerge.set == 'Yes':
            && mkdir bmerge_files
            && ln -s '$functions.bmerge.bed.extra_files_path/RgeneticsData.bed' 'bmerge_files/bmerge_input.bed'
            && ln -s '$functions.bmerge.bed.extra_files_path/RgeneticsData.bim' 'bmerge_files/bmerge_input.bim'
            && ln -s '$functions.bmerge.bed.extra_files_path/RgeneticsData.fam' 'bmerge_files/bmerge_input.fam'
        #end if
    #end if


    #if $inputs.inputs.filetype == 'bfile':
        && ln -s '$inputs.inputs.bed.extra_files_path/RgeneticsData.bed' 'plink_input/plink_input.bed'
        && ln -s '$inputs.inputs.bed.extra_files_path/RgeneticsData.bim' 'plink_input/plink_input.bim'
        && ln -s '$inputs.inputs.bed.extra_files_path/RgeneticsData.fam' 'plink_input/plink_input.fam'
        && plink --bfile plink_input/plink_input
    #elif $inputs.inputs.filetype == 'vcf':
        #if $inputs.inputs.input.is_of_type('bcf'):
            && plink --bcf '$inputs.inputs.input' 
        #else:

        #end if
    #end if

    ## Plink commands by section
    #if $inputs.covar_input:
        --covar '$inputs.covar_input'
    #end if
    #if $inputs.set_pheno.set_pheno == 'Yes':
        --pheno $inputs.set_pheno.pheno $inputs.set_pheno.all_pheno
    #end if
    #if $functions.func == 'filtering':

                #end if
                $functions.sex_founder_filter.nonfounders
            #end if

    #elif $functions.func == 'data_manage':
        #if $functions.bmerge.set == 'Yes':
            --bmerge bmerge_files/bmerge_input
        #end if
        
        #if $functions.template:

                    $functions.sex.mode.female_max
                    $functions.sex.mode.male_min
                #end if
            #end if
        #end if
    #elif $functions.func == 'link':
        #if $functions.set_indep.choice == 'Yes':
            --indep-pairwise $functions.set_indep.window $functions.set_indep.step $functions.set_indep.r2
        #end if
##    #elif $functions.func == 'pair_compare':

            #if $functions.genome.ppc:
                --ppc-gap $functions.genome.ppc
            #end if
        #end if

    #elif $functions.func == 'scoring':
        --score '$functions.score_file' $functions.variant_id_i $functions.allel_codes_j $functions.scores_k $functions.header $functions.sum
##    #else:
##        --rerun $functions.logfile
##      
    #end if
    --memory \${GALAXY_MEMORY_MB:-8192}

            && mv ./plink_output/*asso* assoc_out
            && find ./assoc_out/. -type f -exec mv {} {}.txt ';'
        #end if
    #end if
    && mkdir '$plink_out.extra_files_path'
    && cp plink_output/plink_output.bed '$plink_out.extra_files_path/RgeneticsData.bed'
    && cp plink_output/plink_output.bim '$plink_out.extra_files_path/RgeneticsData.bim'
    && cp plink_output/plink_output.fam '$plink_out.extra_files_path/RgeneticsData.fam'
    #if $functions.func == 'scoring':
        && awk -v OFS="\t" '{$1=$1; print}' plink_output/plink_output.profile > plink_output/plink_output.profile.tab
    #end if
    ]]></command>
    <inputs>
        <section name='inputs' title='Data inputs' expanded='true'>
            <conditional name='inputs'>
                <param name='filetype' type='select' label='Main input data type'>

                <option value='stats'>Basic statistics</option>
                <option value='link'>Linkage disequalibrium</option>
                <option value='stratification'>Population stratification</option>
                <option value='association'>Association analysis</option>
                <option value='ibd'>Identity-by-descent</option>
                <option value='scoring'>Apply a linear scoring system (--score)</option>
                <!-- <option value='rerun'>Rerun</option> -->
            </param>
            <when value='filtering'>
                <conditional name='id_list'>
                    <param name='func' type='select' label='ID list functions'>

                        <param name='intercept' label='Intercept' type='boolean' truevalue='intercept' falsevalue='' checked='false' help=''/>
                    </when>
                </conditional>
                <param name='lambda' type='float' label='Lambda value' optional='true'/>
            </when>
            <when value='scoring'>
                <!-- this implements a part of the -\-score parameter -->
                <param name='score_file' format='tabular' type='data' label='Scoring system which should be applied to all samples'/>
                <param name="variant_id_i" type="data_column" data_ref="score_file" label="Variant ID column"/>
                <param name="allel_codes_j" type="data_column" data_ref="score_file" label="Allel column"/>
                <param name="scores_k" type="data_column" data_ref="score_file" label="Score column"/>
                <param name='header' type='boolean' truevalue='header' falsevalue='' checked='false' label='Is a header line present in the scores file?'/>

                <param name="sum" type="select" label="How to combine the valid per-variant scores?" help="Average is the default, but it can be changed to sum.">
                    <option value="">Final scores are averages of the valid per-variant scores</option>
                    <option value="sum">Report sums (sum; can not be used with 'no-mean-imputation'; is automatically on with dosage data)</option>
                    <option value="no-sum">Disable sum (no-sum)</option>
                </param>
            </when>
            <when value='ibd'>
                <conditional name='genome'>
                    <param name='output_genome' type='select' help='Perform and return results of IBS/IBD computation'>
                        <option value=''>No</option>
                        <option value='Yes'>Yes</option>

        <!--IBD-->
        <data name='genome' format='tabular' from_work_dir='plink_output/plink_output.genome' label='${tool.name}: Genome'>
            <filter>functions['func'] == 'ibd' and functions['genome']['output_genome']</filter>
        </data>
        
        <!--scores-->
        <data name='scores' format='tabular' from_work_dir='plink_output/plink_output.profile.tab' label='${tool.name}: Scores'>
            <filter>functions['func'] == 'scoring'</filter>
        </data>

        <!--Stratifiction-->
        <data name='mds' format='txt' from_work_dir='plink_output/plink_output.mds' label='${tool.name}: MDS'>
            <filter>functions['func'] == 'stratification' and functions['cluster']['cluster'] == 'Yes' and functions['cluster']['mds']['mds_scaling'] == 'Yes'</filter>
        </data>
        <data name='cluster1' format='tabular' from_work_dir='plink_output/plink_output.cluster1' label='${tool.name}: Cluster 1'>

                <extra_files type="file" name="RgeneticsData.fam" value="vcf_out.fam"/>
            </output>
            <expand macro="log_out_assert"/>
        </test>

        
        <test expect_num_outputs='8'>
            <section name='inputs'>
                <conditional name='inputs'>
                    <param name='filetype' value='bfile'/>
                    <param name='bed' value='' ftype="pbed">

                </conditional>
            </conditional>
            <expand macro="log_out_assert"/>
            <output name='genome' file='out.genome'/>
        </test>
        <!-- scoring function test-->
        <test expect_num_outputs='3'>
            <section name='inputs'>
                <conditional name='inputs'>
                    <param name='filetype' value='bfile'/>
                    <param name='bed' value='' ftype="pbed">
                        <composite_data value="plink.bim"/>
                        <composite_data value="plink.bed"/>
                        <composite_data value="plink.fam"/>
                    </param>
                </conditional>
            </section>
            <conditional name='functions'>
                <param name='func' value='scoring'/>
                <param name='score_file' value='scores_file.tab'/>
                <param name='variant_id_i' value='1'/>
                <param name='allel_codes_j' value='2'/>
                <param name='scores_k' value='3'/>
                <param name='header' value='true'/>
                <param name='sum' value='sum'/>
            </conditional>
            <expand macro="log_out_assert"/>
            <output name='scores' file='scores_results.tab'/>
        </test>
    </tests>
    <help><![CDATA[
        PLINK is a free, open-source whole genome association analysis toolset, designed to perform a range of basic, large-scale analyses in a computationally efficient manner.

        For detailed usage notes, visit http://www.cog-genomics.org/plink/2.0/