comparison chicSignificantInteractions.xml @ 8:640e0e45518a draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hicexplorer commit 07802a6bd441d9da888cfb8283f8c2135704f7c9

7:6ef732512682

        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
        #import re

        mkdir interactionFiles &&
        mkdir targetFolder &&
        mkdir significantFilesFolder &&

        #if $tar_input_conditional.tar_input_selector == 'tar_input':
            ln -s '$tar_input_conditional.interactionFiles' viewpoints.tar && 
            tar -C interactionFiles -xvf viewpoints.tar &&
        #else:
            #for $file in $tar_input_conditional.interactionFiles:
                #set identifier = @ESCAPE_IDENTIFIER_FILE@                
                ln -s '$file' 'interactionFiles/$identifier' &&
            #end for
        #end if
    
        #if $batchmode_conditional.batchmode_selector == 'optionSinglemode':
            #set $interactonfileslist = ' '.join([ '\'interactionFiles/%s\'' % @ESCAPE_IDENTIFIER_FILE@ for $file in $interactionFiles ])
        #end if
        @BINARY@
            #if $batchmode_conditional.batchmode_selector == 'optionSinglemode':
                --interactionFile $interactonfileslist
                --computeSampleNumber $batchmode_conditional.computeSampleNumber
            #else:
                --interactionFile '$batchmode_conditional.interactionFilesOrderFile'
                --interactionFileFolder interactionFiles
                --batchMode
                --targetFileList targetListFile.txt
                --writeFileNamesToFile significantFiles.txt
                --computeSampleNumber $batchmode_conditional.computeSampleNumber
            #end if

            --pValue $pvalue

            #if $filter_conditional.filter_selector == 'optionXfold':
                --xFoldBackground $filter_conditional.xfold
            #else:
                --loosePValue $filter_conditional.loosePvalue

            #end if
            --backgroundModelFile '$backgroundModelFile'
            --resolution $resolution
            --peakInteractionsThreshold $peakInteractionsThreshold
            --range $rangeUpstream $rangeDownstream
            --targetFolder targetFolder
            --outputFolder significantFilesFolder
            $truncateZeroPvalues
            --fixateRange $fixateRange
            -suffix significant_interactions.txt
            --threads @THREADS@

            #if $tar:
                && cd targetFolder
                && tar -cvf ../targetFolder.tar *
                && cd ..
                && rm -rf targetFolder

                && cd significantFilesFolder
                && tar -cvf ../significantFilesFolder.tar *
                && cd ..
                && rm -rf significantFilesFolder

            #end if
    ]]>    </command>
    <inputs>
        <conditional name="tar_input_conditional">
            <param name="tar_input_selector" type="select" label="Compute files individually or in batch mode">
                <option value="tar_input">Tar file</option>
                <option value="interval_input" selected="True">Interval files</option>
            </param>
            <when value="tar_input">
                <param name='interactionFiles' type="data" format="tar" label="Interaction files" multiple="false" />
            </when>
            <when value="interval_input">
                <param name='interactionFiles' type="data" format="interval" label="Interaction files" multiple="true" />
            </when>
        </conditional>
        <conditional name="batchmode_conditional">
            <param name="batchmode_selector" type="select" label="Compute files individually or in batch mode">
                <option value="optionBatchmode">Batch processing</option>
                <option value="optionSinglemode" selected="True">Single file processing</option>
            </param>
            <when value="optionBatchmode">
                <param name='interactionFilesOrderFile' type="data" format="txt" label="Interaction file order" />
                <param name='computeSampleNumber' type="integer" value='2' label="Create one target file for n consecutive files." />
            </when>
            <when value="optionSinglemode">
                <param name='computeSampleNumber' type="integer" value='2' label="Create one target file for n consecutive files." />
            </when>
        </conditional>
        <param name='pvalue' type="float" value='0.05' label="P-value of interaction to be accepted as significant" />
        <conditional name="filter_conditional">
            <param name="filter_selector" type="select" label="List of chromosomes or a BED file containg regions">
                <option value="optionXfold">x-fold over mean background</option>
                <option value="optionLoosePvalue" selected="True">Loose p-value (NB background)</option>
            </param>
            <when value="optionXfold">
                <param name='xfold' type="float" value='2.0' label="X-fold over mean background to be accepted." help='Filter x-fold over background. Used to merge neighboring bins with a broader peak but
                                                    less significant interactions to one peak with high significance. Used only for pValue option.' />
            </when>
            <when value="optionLoosePvalue">
                <param name='loosePvalue' type="float" value='0.3' label="Loose p-value" help='loose p-value threshold value to filter target regions in a first round.
                    Used to merge neighboring bins with a broader peak but less significant interactions to one peak with high significance.
                    Used only for pValue option.' />
            </when>
        </conditional>
        <param argument="--backgroundModelFile" type="data" format='tabular' label="Background model" help="The background file computed by chicViewpointBackgroundModel" />
        <param argument="--peakInteractionsThreshold" type="integer" value="5" label="Minimum interactions" help='The minimum number of interactions a detected peaks needs to have to be considered.' />
        <param argument="--resolution" type="integer" value="1000" label="Bin resolution of the used data" help='Resolution of the bin in genomic units. Values are usually e.g. 1000 for a 1kb, 5000 for a 5kb or 10000 for a 10kb resolution.
            This value is used to merge neighboring bins.' />
        <param name="rangeUpstream" type="integer" value="500000" label="Upstream range" help='Defines the region upstream of a reference point which should be considered in the analysis.' />
        <param name="rangeDownstream" type="integer" value="500000" label="Downstream range" help='Defines the region upstream of a reference point which should be considered in the analysis.' />
        <param argument="--fixateRange" type="integer" value="500000" label="Clip background distance" help='Fixate score of background model starting at distance x. E.g. all values greater 500kb are set to the value of the 500kb bin.' />
        <param name='truncateZeroPvalues' type='boolean' truevalue='--truncateZeroPvalues' falsevalue="" checked="false" label="Truncate zeros by setting them to one." help="Sets all p-values which are equal to zero to one. This has the effect that the associated positions are not part of the significance decision." />
        <param name='tar' type='boolean' checked="false" truevalue='True' label="tar output to one file" help="The output is tarred to one file and not written to a collection. Set this option if the number of files is large." />
    </inputs>
    <outputs>
        <collection name="significantFilesCollection" type="list" label="Significant files">
            <discover_datasets pattern="__name__" format="interval" directory="significantFilesFolder" />
        </collection>
        <collection name="targetFilesCollection" type="list" label="Target files">
            <discover_datasets pattern="__name__" format="interval" directory="targetFolder" />
        </collection>
        <data name="significantFileNames" from_work_dir="significantFiles.txt" format="txt" label="${tool.name} significant file names">
            <filter>batchmode_conditional.batchmode_selector == 'optionBatchmode'</filter>
        </data>
        <data name="targetFileNames" from_work_dir="targetListFile.txt" format="txt" label="${tool.name} target file names">
            <filter>batchmode_conditional.batchmode_selector == 'optionBatchmode'</filter>
        </data>
        <data name="targetFolderTar" from_work_dir="targetFolder.tar" format="tar" label="Target files tar">
            <filter>tar</filter>
        </data>
        <data name="significantFilesFolderTar" from_work_dir="significantFilesFolder.tar" format="tar" label="Significant files tar">
            <filter>tar</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <conditional name="tar_input_conditional">
                <param name="tar_input_selector" value='interval_input' />
                <param name="interactionFiles" value="cHi-C/chicViewpoint/output_3/FL-E13-5_chr1_chr1_14300280_14300280_Eya1.txt,cHi-C/chicViewpoint/output_3/FL-E13-5_chr1_chr1_4487435_4487435_Sox17.txt,cHi-C/chicViewpoint/output_3/FL-E13-5_chr1_chr1_19093103_19093103_Tfap2d.txt,cHi-C/chicViewpoint/output_3/MB-E10-5_chr1_chr1_19093103_19093103_Tfap2d.txt,cHi-C/chicViewpoint/output_3/MB-E10-5_chr1_chr1_14300280_14300280_Eya1.txt,cHi-C/chicViewpoint/output_3/MB-E10-5_chr1_chr1_4487435_4487435_Sox17.txt" />
            </conditional>
            <conditional name="batchmode_conditional">
                <param name="batchmode_selector" value='optionBatchmode' />
                <param name="interactionFilesOrderFile" value='cHi-C/chicViewpoint/fileNames_two_matrices.txt' />
                <param name="computeSampleNumber" value='2' />
            </conditional>
            <param name="pvalue" value='0.2' />

            <conditional name="filter_conditional">
                <param name="filter_selector" value='optionLoosePvalue' />
                <param name="loosePvalue" value='0.5' />
            </conditional>

            <param name="backgroundModelFile" value="cHi-C/background.txt" />
            <param name="rangeUpstream" value="200000" />
            <param name="rangeDownstream" value="200000" />

            <output_collection name="significantFilesCollection" type="list" count="6">
                <element name="FL-E13-5_chr1_chr1_4487435_4487435_Sox17_significant_interactions.txt" ftype="interval">
                    <assert_contents>
                        <has_text text="4480000" />
                        <has_text text="chr1" />
                        <has_text text="Sox17" />
                        <has_text text="810.0" />
                        <has_text text="interactions" />
                    </assert_contents>
                </element>
                <element name="FL-E13-5_chr1_chr1_14300280_14300280_Eya1_significant_interactions.txt" ftype="interval">
                    <assert_contents>
                        <has_text text="14274000" />
                        <has_text text="chr1" />
                        <has_text text="Eya1" />
                        <has_text text="interactions" />
                    </assert_contents>
                </element>
                <element name="FL-E13-5_chr1_chr1_19093103_19093103_Tfap2d_significant_interactions.txt" file="cHi-C/chicSignificantInteractions/output_5/FL-E13-5_chr1_chr1_19093103_19093103_Tfap2d_significant_interactions.txt" ftype="interval" lines_diff="4" />
                <element name="MB-E10-5_chr1_chr1_4487435_4487435_Sox17_significant_interactions.txt" ftype="interval">
                    <assert_contents>
                        <has_text text="4480000" />
                        <has_text text="chr1" />
                        <has_text text="Sox17" />
                        <has_text text="interactions" />
                        <has_text text="93000" />
                        <has_text text="978.0" />
                    </assert_contents>
                </element>
                <element name="MB-E10-5_chr1_chr1_14300280_14300280_Eya1_significant_interactions.txt" file="cHi-C/chicSignificantInteractions/output_5/MB-E10-5_chr1_chr1_14300280_14300280_Eya1_significant_interactions.txt" ftype="interval" lines_diff="4" />
                <element name="MB-E10-5_chr1_chr1_19093103_19093103_Tfap2d_significant_interactions.txt" ftype="interval">
                    <assert_contents>
                        <has_text text="19077000" />
                        <has_text text="chr1" />
                        <has_text text="Tfap2d" />
                        <has_text text="interactions" />
                        <has_text text="-15000" />
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="targetFilesCollection" type="list" count="3">
                <element name="FL-E13-5_MB-E10-5_chr1_chr1_4487435_4487435_Sox17_target.txt" ftype="interval">
                    <assert_contents>
                        <has_text text="4555000" />
                        <has_text text="chr1" />
                        <has_text text="p-value" />
                        <has_text text="interactions" />
                    </assert_contents>
                </element>
                <element name="FL-E13-5_MB-E10-5_chr1_chr1_14300280_14300280_Eya1_target.txt" file="cHi-C/chicSignificantInteractions/output_5_target/FL-E13-5_MB-E10-5_chr1_chr1_14300280_14300280_Eya1_target.txt" ftype="interval" lines_diff="4" />
                <element name="FL-E13-5_MB-E10-5_chr1_chr1_19093103_19093103_Tfap2d_target.txt" ftype="interval">
                    <assert_contents>
                        <has_text text="19143000" />
                        <has_text text="chr1" />
                        <has_text text="p-value" />
                        <has_text text="19150000" />
                    </assert_contents>
                </element>
            </output_collection>
            <output name="targetFileNames" file="cHi-C/chicSignificantInteractions/output_5_target_list.txt" ftype="txt" />
            <output name="significantFileNames" file="cHi-C/chicSignificantInteractions/output_5_significant_files.txt" ftype="txt" />
        </test>
        <test>
            <conditional name="tar_input_conditional">
                <param name="tar_input_selector" value='interval_input' />
                <param name="interactionFiles" value="cHi-C/chicViewpoint/output_1/FL-E13-5_chr1_chr1_14300280_14300280_Eya1.txt,cHi-C/chicViewpoint/output_1/MB-E10-5_chr1_chr1_14300280_14300280_Eya1.txt" />
            </conditional>
            <conditional name="batchmode_conditional">
                <param name="batchmode_selector" value='optionSinglemode' />
                <param name="computeSampleNumber" value="1" />
            </conditional>
            <param name="pvalue" value='0.2' />

            <conditional name="filter_conditional">
                <param name="filter_selector" value='optionXfold' />
                <param name="xfold" value='1.5' />
            </conditional>

            <param name="backgroundModelFile" value="cHi-C/background.txt" />
            <param name="rangeUpstream" value="200000" />
            <param name="rangeDownstream" value="200000" />

            <output_collection name="significantFilesCollection" type="list" count="2">
                <element name="FL-E13-5_chr1_chr1_14300280_14300280_Eya1_significant_interactions.txt" file="cHi-C/chicSignificantInteractions/output_3/FL-E13-5_chr1_chr1_14300280_14300280_Eya1_output_significant.txt" ftype="interval" lines_diff="4" />
                <element name="MB-E10-5_chr1_chr1_14300280_14300280_Eya1_significant_interactions.txt" ftype="interval">
                    <assert_contents>
                        <has_text text="14295000" />
                        <has_text text="chr1" />
                        <has_text text="Eya1" />
                        <has_text text="interactions" />
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="targetFilesCollection" type="list" count="2">
                <element name="FL-E13-5_chr1_chr1_14300280_14300280_Eya1_target.txt" file="cHi-C/chicSignificantInteractions/output_3_target/FL-E13-5_chr1_chr1_14300280_14300280_Eya1_target.txt" ftype="interval" lines_diff="4" />
                <element name="MB-E10-5_chr1_chr1_14300280_14300280_Eya1_target.txt" file="cHi-C/chicSignificantInteractions/output_3_target/MB-E10-5_chr1_chr1_14300280_14300280_Eya1_target.txt" ftype="interval" lines_diff="4" />
            </output_collection>
        </test>

        <test>
            <conditional name="tar_input_conditional">
                <param name="tar_input_selector" value='interval_input' />
                <param name="interactionFiles" value="cHi-C/chicViewpoint/output_3/FL-E13-5_chr1_chr1_14300280_14300280_Eya1.txt,cHi-C/chicViewpoint/output_3/FL-E13-5_chr1_chr1_4487435_4487435_Sox17.txt,cHi-C/chicViewpoint/output_3/FL-E13-5_chr1_chr1_19093103_19093103_Tfap2d.txt,cHi-C/chicViewpoint/output_3/MB-E10-5_chr1_chr1_19093103_19093103_Tfap2d.txt,cHi-C/chicViewpoint/output_3/MB-E10-5_chr1_chr1_14300280_14300280_Eya1.txt,cHi-C/chicViewpoint/output_3/MB-E10-5_chr1_chr1_4487435_4487435_Sox17.txt" />
            </conditional>
            <conditional name="batchmode_conditional">
                <param name="batchmode_selector" value='optionBatchmode' />
                <param name="interactionFilesOrderFile" value='cHi-C/chicViewpoint/fileNames_two_matrices.txt' />
                <param name="computeSampleNumber" value='2' />
            </conditional>
            <param name="pvalue" value='0.2' />

            <conditional name="filter_conditional">
                <param name="filter_selector" value='optionLoosePvalue' />
                <param name="loosePvalue" value='0.5' />
            </conditional>

            <param name="backgroundModelFile" value="cHi-C/background.txt" />
            <param name="rangeUpstream" value="200000" />
            <param name="rangeDownstream" value="200000" />

            <param name='tar' value='True' />

            <output name="targetFolderTar" file="cHi-C/chicSignificantInteractions/targetFolder.tar" ftype='tar' compare="sim_size" delta='40000' />
            <output name="significantFilesFolderTar" file="cHi-C/chicSignificantInteractions/significantFilesFolder.tar" ftype='tar' compare="sim_size" delta='40000' />
            <output name="targetFileNames" file="cHi-C/chicSignificantInteractions/output_5_target_list.txt" ftype="txt" />
            <output name="significantFileNames" file="cHi-C/chicSignificantInteractions/output_5_significant_files.txt" ftype="txt" />
        </test>

        <test>
            <conditional name="tar_input_conditional">
                <param name="tar_input_selector" value='tar_input' />
                <param name="interactionFiles" value="cHi-C/chicViewpoint/viewpoints.tar" />
            </conditional>
            <conditional name="batchmode_conditional">
                <param name="batchmode_selector" value='optionBatchmode' />
                <param name="interactionFilesOrderFile" value='cHi-C/chicViewpoint/fileNames_two_matrices.txt' />
                <param name="computeSampleNumber" value='2' />
            </conditional>
            <param name="pvalue" value='0.2' />

            <conditional name="filter_conditional">
                <param name="filter_selector" value='optionLoosePvalue' />
                <param name="loosePvalue" value='0.5' />
            </conditional>

            <param name="backgroundModelFile" value="cHi-C/background.txt" />
            <param name="rangeUpstream" value="200000" />
            <param name="rangeDownstream" value="200000" />

            <param name='tar' value='True' />

            <output name="targetFolderTar" file="cHi-C/chicSignificantInteractions/targetFolder.tar" ftype='tar' compare="sim_size" delta='40000' />
            <output name="significantFilesFolderTar" file="cHi-C/chicSignificantInteractions/significantFilesFolder.tar" ftype='tar' compare="sim_size" delta='40000' />

            <output name="targetFileNames" file="cHi-C/chicSignificantInteractions/output_5_target_list.txt" ftype="txt" compare="sim_size" delta='40000' />
            <output name="significantFileNames" file="cHi-C/chicSignificantInteractions/output_5_significant_files.txt" ftype="txt" compare="sim_size" delta='40000' />
        </test>
    </tests>
    <help><![CDATA[

Significant interaction detection
=================================

8:640e0e45518a

        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
        #import re
      
        @BINARY@
    
            --interactionFile '$interactionFile'
    
            --pValue $pvalue

            #if $filter_conditional.filter_selector == 'optionXfold':
                --xFoldBackground $filter_conditional.xfold
            #else:
                --loosePValue $filter_conditional.loosePvalue

            #end if
            --backgroundModelFile '$backgroundModelFile'
            --peakInteractionsThreshold $peakInteractionsThreshold
            --range $rangeUpstream $rangeDownstream
            --combinationMode $mode_selector
            --outFileNameSignificant significant.hdf5
            --outFileNameTarget target.hdf5
            $truncateZeroPvalues
            --fixateRange $fixateRange
            --threads @THREADS@

    ]]>    </command>
    <inputs>
        <param name="interactionFile" type="data" format="h5" label="The interaction data file created by chicViewpoint" />

        <param name="pvalue" type="float" value="0.05" label="P-value of interaction to be accepted as significant" />
        <conditional name="filter_conditional">
            <param name="filter_selector" type="select" label="List of chromosomes or a BED file containg regions">
                <option value="optionXfold">x-fold over mean background</option>
                <option value="optionLoosePvalue" selected="True">Loose p-value (NB background)</option>
            </param>
            <when value="optionXfold">
                <param name="xfold" type="float" value="2.0" label="X-fold over mean background to be accepted." help="Filter x-fold over background. 
                    Used to merge neighboring bins with a broader peak but less significant interactions to one peak with high significance. Used only for pValue option." />
            </when>
            <when value="optionLoosePvalue">
                <param name="loosePvalue" type="float" value="0.3" label="Loose p-value" help="loose p-value threshold value to filter target regions in a first round.
                    Used to merge neighboring bins with a broader peak but less significant interactions to one peak with high significance.
                    Used only for pValue option." />
            </when>
        </conditional>

        <param argument="--backgroundModelFile" type="data" format="tabular" label="Background model" help="The background file computed by chicViewpointBackgroundModel" />
        <param argument="--peakInteractionsThreshold" type="integer" value="5" label="Minimum interactions" help="The minimum number of interactions a detected peaks needs to have to be considered." />

        <param name="mode_selector" type="select" label="Process matrices independently or combine always two (for differential analysis preparation)">
                <option value="dual">Dual</option>
                <option value="single" selected="True">Single</option>
        </param>
        <param name="rangeUpstream" type="integer" value="500000" label="Upstream range" help="Defines the region upstream of a reference point which should be considered in the analysis." />
        <param name="rangeDownstream" type="integer" value="500000" label="Downstream range" help="Defines the region upstream of a reference point which should be considered in the analysis." />
        <param argument="--fixateRange" type="integer" value="500000" label="Clip background distance" help="Fixate score of background model starting at distance x. E.g. all values greater 500kb are set to the value of the 500kb bin." />
        <param name="truncateZeroPvalues" type="boolean" truevalue="--truncateZeroPvalues" falsevalue="" checked="false" label="Truncate zeros by setting them to one." help="Sets all p-values which are equal to zero to one. This has the effect that the associated positions are not part of the significance decision." />
    </inputs>

    <outputs>
        <data name="significantFile" from_work_dir="significant.hdf5" format="h5" label="${tool.name} significant file" />
        <data name="targetFile" from_work_dir="target.hdf5" format="h5" label="${tool.name} target file" />
    </outputs>
    <tests>
        <test>
            <param name="interactionFile" value="cHi-C/chicViewpoint/two_matrices.hdf5" />
            <param name="pvalue" value="0.2" />

            <conditional name="filter_conditional">
                <param name="filter_selector" value="optionLoosePvalue" />
                <param name="loosePvalue" value="0.5" />
            </conditional>
            <param name="mode_selector" value="dual" />
            <param name="backgroundModelFile" value="cHi-C/background.txt" />
            <param name="rangeUpstream" value="200000" />
            <param name="rangeDownstream" value="200000" />

            <output name="significantFile" ftype="h5">
                <assert_contents>
                    <has_h5_attribute key="combinationMode" value="dual" />
                    <has_h5_attribute key="mode_preselection" value="loosePValue" />
                    <has_h5_attribute key="type" value="significant" />
                </assert_contents>
            </output>

            <output name="targetFile" ftype="h5">
                <assert_contents>
                     <has_h5_attribute key="combinationMode" value="dual" />
                    <has_h5_attribute key="mode_preselection" value="loosePValue" />
                    <has_h5_attribute key="type" value="target" />
                </assert_contents>
            </output>
        </test>
      
    </tests>
    <help><![CDATA[

Significant interaction detection
=================================