Mercurial > repos > bgruening > diffbind
diff diffbind.xml @ 30:6b235ac52faf draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/diffbind commit fd148a124034b44d0d61db3eec32ff991d8c152c
| author | iuc |
|---|---|
| date | Mon, 08 Jul 2024 18:31:37 +0000 |
| parents | 3aa2c26cc990 |
| children |
line wrap: on
line diff
--- a/diffbind.xml Tue Aug 31 08:02:07 2021 +0000 +++ b/diffbind.xml Mon Jul 08 18:31:37 2024 +0000 @@ -1,13 +1,18 @@ -<tool id="diffbind" name="DiffBind" version="2.10.0+galaxy0"> +<tool id="diffbind" name="DiffBind" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> <description> differential binding analysis of ChIP-Seq peak data</description> + <macros> + <token name="@TOOL_VERSION@">3.12.0</token> + <token name="@VERSION_SUFFIX@">0</token> + <token name="@PROFILE@">22.05</token> + </macros> <xrefs> <xref type="bio.tools">diffbind</xref> + <xref type="bioconductor">diffbind</xref> </xrefs> <requirements> - <requirement type="package" version="2.10.0">bioconductor-diffbind</requirement> - <requirement type="package" version="3.5.1">r-base</requirement> - <requirement type="package" version="1.20.3">r-getopt</requirement> - <requirement type="package" version="0.2.20">r-rjson</requirement> + <requirement type="package" version="@TOOL_VERSION@">bioconductor-diffbind</requirement> + <requirement type="package" version="1.20.4">r-getopt</requirement> + <requirement type="package" version="4.0.16">bioconductor-edger</requirement> </requirements> <stdio> <regex match="Execution halted" @@ -36,14 +41,14 @@ #for $g in $rep_group: - #set $peak_files = list() - #set $bam_files = list() - #set $bam_controls = list() + #set $peak_files = dict() + #set $bam_files = dict() + #set $bam_controls = dict() #for $file in $g.peaks: #set $file_name = str($g.groupName) + "-" + re.sub('[^\w\-]', '_', str($file.element_identifier)) + "-peaks.bed" ln -s '${file}' '${file_name}' && - $peak_files.append($file_name) + #set $peak_files[str($file.element_identifier)] = str($file_name) #end for #for $bam in $g.bamreads: @@ -52,24 +57,30 @@ #set $bam_index = $bam_name + "-bamreads.bai" ln -s '${bam}' '${bam_file}' && ln -s '${bam.metadata.bam_index}' '${bam_index}' && - $bam_files.append($bam_file) + #set $bam_files[str($bam.element_identifier)] = str($bam_file) #end for - $temp_factor.append( {str($g.groupName): $peak_files} ) - $temp_factor.append( {str($g.groupName): $bam_files} ) + #if len($peak_files.keys()) != len($bam_files.keys()) + >&2 echo "Group $g.groupName: same number of Peak and Bam files needs to be given" && exit 1 && + #end if + $temp_factor.append( {str($g.groupName): [f[1] for f in sorted($peak_files.items())]} ) + $temp_factor.append( {str($g.groupName): [f[1] for f in sorted($bam_files.items())]} ) #if str( $g.bamcontrol ) != 'None': #for $ctrl in $g.bamcontrol: #set $ctrl_name = re.sub('[^\w\-]', '_', str($ctrl.element_identifier)) #set $ctrl_file = $ctrl_name + "-bamcontrol.bam" - #set ctrl_index = $ctrl_name + "-bamcontrol.bai" + #set $ctrl_index = $ctrl_name + "-bamcontrol.bai" #if $ctrl_file not in json.dumps($temp_factor): ln -s '${ctrl}' '${ctrl_file}' && ln -s '${ctrl.metadata.bam_index}' '${ctrl_index}' && #end if - $bam_controls.append($ctrl_file) + #set $bam_controls[str($ctrl.element_identifier)] = str($ctrl_file) #end for - $temp_factor.append( {str($g.groupName): $bam_controls} ) + #if len($peak_files.keys()) != len($bam_files.keys()) + >&2 echo "Group $g.groupName: same number of Peak and Bam control files needs to be given" && exit 1 && + #end if + $temp_factor.append( {str($g.groupName): [f[1] for f in sorted($bam_controls.items())]} ) #end if #end for @@ -82,13 +93,15 @@ -i '#echo json.dumps(temp_factor_names)#' -o '$outfile' + -m '$method' -t $th -f $out.format -p '$plots' - - #if $scorecol: - -n "$scorecol" + -O $minoverlap + #if $use_blacklist: + -B #end if + -n $scorecol #if $lowerbetter: -l "$lowerbetter" #end if @@ -126,8 +139,17 @@ <param name="bamreads" type="data" format="bam" multiple="true" label="Read BAM files" help="Specify the Read BAM files used in the Peak calling. The input order of the BAM files for the samples MUST match the input order of the peaks files."/> <param name="bamcontrol" type="data" format="bam" multiple="true" optional="True" label="Control BAM files" help="If specifying a control BAM file, all samples are required to specify one, see Help section below. The input order of the BAM files for the samples MUST match the input order of the peaks files."/> </repeat> - - <param name="scorecol" type="integer" min="0" value="8" label="Score Column" help="Column in peak files that contains peak scores. Default: 8 (narrowPeak)"> + <param name="method" type="select" label="Underlying method by which to analyze differential binding affinity"> + <option value="DBA_DESEQ2" selected="True">DESeq2</option> + <option value="DBA_EDGER">edgeR</option> + </param> + <param name="use_blacklist" type="boolean" truevalue="True" falsevalue="" checked="False" label="Filters peak intervals that overlap a blacklist from ENCODE" help="Works with human, mouse, worm and fly. Assembly version is determined from the BAM files." /> + <param name="minoverlap" type="integer" min="1" value="2" label="Only include peaks in at least this many peaksets in the main binding matrix"> + <sanitizer> + <valid initial="string.digits"/> + </sanitizer> + </param> + <param name="scorecol" type="integer" min="0" value="5" label="Score Column" help="Column in peak files that contains peak scores. Default: 5 (narrowPeak)"> <sanitizer> <valid initial="string.digits"/> </sanitizer> @@ -214,6 +236,28 @@ </assert_contents> </output> </test> + <!-- Ensure EDGER works --> + <test expect_num_outputs="3"> + <repeat name="rep_group"> + <param name="groupName" value="Resistant"/> + <param name="peaks" ftype="bed" value="BT474_ER_1.bed.gz,BT474_ER_2.bed.gz"/> + <param name="bamreads" ftype="bam" value="BT474_ER_1.bam,BT474_ER_2.bam" /> + </repeat> + <repeat name="rep_group"> + <param name="groupName" value="Responsive"/> + <param name="peaks" ftype="bed" value="MCF7_ER_1.bed.gz,MCF7_ER_2.bed.gz"/> + <param name="bamreads" ftype="bam" value="MCF7_ER_1.bam,MCF7_ER_2.bam" /> + </repeat> + <param name="scorecol" value="5" /> + <param name="method" value="DBA_EDGER" /> + <param name="format" value="interval"/> + <param name="pdf" value="True" /> + <param name="binding_matrix" value="True" /> + <param name="rscript" value="False"/> + <output name="outfile" ftype="interval" value="out_diffbind_edger.interval" /> + <output name="plots" value="out_plots_edger.pdf" compare="sim_size" /> + <output name="binding_matrix" value="out_binding_matrix_edger.tab" /> + </test> <!-- Ensure control BAMs input works --> <test expect_num_outputs="1"> <repeat name="rep_group"> @@ -264,6 +308,40 @@ <param name="format" value="tabular"/> <output name="outfile" ftype="tabular" file="out_diffbind.tab" /> </test> + <!-- Ensure minoverlap works --> + <test expect_num_outputs="1"> + <repeat name="rep_group"> + <param name="groupName" value="Resistant"/> + <param name="peaks" ftype="bed" value="BT474_ER_1.bed.gz,BT474_ER_2.bed.gz"/> + <param name="bamreads" ftype="bam" value="BT474_ER_1.bam,BT474_ER_2.bam" /> + </repeat> + <repeat name="rep_group"> + <param name="groupName" value="Responsive"/> + <param name="peaks" ftype="bed" value="MCF7_ER_1.bed.gz,MCF7_ER_2.bed.gz"/> + <param name="bamreads" ftype="bam" value="MCF7_ER_1.bam,MCF7_ER_2.bam" /> + </repeat> + <param name="minoverlap" value="1" /> + <param name="scorecol" value="5" /> + <param name="format" value="tabular"/> + <output name="outfile" ftype="tabular" file="out_diffbind_minoverlap1.tab" /> + </test> + <!-- Ensure blacklist filtering works --> + <test expect_num_outputs="1"> + <repeat name="rep_group"> + <param name="groupName" value="Resistant"/> + <param name="peaks" ftype="bed" value="BT474_ER_1.bed.gz,BT474_ER_2.bed.gz"/> + <param name="bamreads" ftype="bam" value="BT474_ER_1.bam,BT474_ER_2.bam" /> + </repeat> + <repeat name="rep_group"> + <param name="groupName" value="Responsive"/> + <param name="peaks" ftype="bed" value="MCF7_ER_1.bed.gz,MCF7_ER_2.bed.gz"/> + <param name="bamreads" ftype="bam" value="MCF7_ER_1.bam,MCF7_ER_2.bam" /> + </repeat> + <param name="use_blacklist" value="True"/> + <param name="scorecol" value="5" /> + <param name="format" value="tabular"/> + <output name="outfile" ftype="tabular" file="out_diffbind_blacklist.tab" /> + </test> </tests> <help><![CDATA[ @@ -308,6 +386,11 @@ be associated with each peakset (one for the ChIP data, and optionally another representing a control sample) +Inputs for a group will be sorted by identifier before processing. For each group the corresponding +sets of peak and BAM files need to be provided. Ideally this is accomplished by providing the data in +collections. + + **Groups** You have to specify the name of the Group and the peak and BAM files for the two Groups you want to compare (e.g Resistant and Responsive) in the tool form above. @@ -403,11 +486,11 @@ ===== ====== ====== ======== ===== ====== Chrom Start End Name Score Strand ===== ====== ====== ======== ===== ====== - chr18 394599 396513 DiffBind 0 \. - chr18 111566 112005 DiffBind 0 \. - chr18 346463 347342 DiffBind 0 \. - chr18 399013 400382 DiffBind 0 \. - chr18 371109 372102 DiffBind 0 \. + chr18 394599 396513 DiffBind 0 \. + chr18 111566 112005 DiffBind 0 \. + chr18 346463 347342 DiffBind 0 \. + chr18 399013 400382 DiffBind 0 \. + chr18 371109 372102 DiffBind 0 \. ===== ====== ====== ======== ===== ====== Example - **Tabular format**: