Mercurial > repos > bgruening > deeptools
changeset 18:5ea8782d650c draft
Uploaded
| author | bgruening |
|---|---|
| date | Mon, 03 Feb 2014 13:44:35 -0500 |
| parents | ef65d6b68ccc |
| children | 01bc5ce13498 |
| files | bamCompare.xml bamCorrelate.xml bamCoverage.xml bamFingerprint.xml bigwigCompare.xml computeGCBias.xml computeMatrix.xml correctGCBias.xml deepTools_macros.xml heatmapper.xml profiler.xml tool_dependencies.xml |
| diffstat | 12 files changed, 229 insertions(+), 153 deletions(-) [+] |
line wrap: on
line diff
--- a/bamCompare.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/bamCompare.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_bamCompare" name="bamCompare" version="1.0.2"> +<tool id="deeptools_bamCompare" name="bamCompare" version="1.0.3"> <description>normalizes and compares two BAM files to obtain the ratio, log2ratio or difference. (bam2bigwig)</description> <expand macro="requirements" /> <expand macro="stdio" /> <macros> + <token name="@BINARY@">bamCompare</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -36,19 +37,25 @@ #if $comparison.normalization.type=='rpkm': --normalizeUsingRPKM #elif $comparison.normalization.type=='1x': - --normalizeTo1x $comparison.normalization.normalizeTo1x + + #if $comparison.normalization.effectiveGenomeSize.effectiveGenomeSize_opt == "specific": + --normalizeTo1x $comparison.normalization.effectiveGenomeSize.effectiveGenomeSize + #else: + --normalizeTo1x $comparison.normalization.effectiveGenomeSize.effectiveGenomeSize_opt + #end if + #end if #end if + #if str(region).strip() != '': + --region 'region' + #end if + #if $advancedOpt.showAdvancedOpt == "yes": #if $advancedOpt.smoothLength: --smoothLength '$advancedOpt.smoothLength' #end if - #if str($advancedOpt.region.value) != '': - --region '$advancedOpt.region' - #end if - $advancedOpt.doNotExtendPairedEnds $advancedOpt.ignoreDuplicates @@ -122,9 +129,7 @@ <when value="rpkm" /> <when value="no" /> <when value="1x"> - <param name="normalizeTo1x" type="integer" value="2150570000" - label="Report normalized coverage to 1x sequenceing depth" - help ="Sequencing depth is defined as the total number of mapped reads * fragment length / effective genome size. To use this option, the effective genome size has to be given. Common values are: mm9: 2150570000, hg19:2451960000, dm3:121400000 and ce10:93260000."/> + <expand macro="effectiveGenomeSize" /> </when> </conditional> </when> @@ -135,6 +140,8 @@ <option value="bedgraph">bedgraph</option> </param> + <expand macro="region_limit_operation" /> + <conditional name="advancedOpt"> <param name="showAdvancedOpt" type="select" label="Show advanced options" > <option value="no" selected="true">no</option> @@ -147,10 +154,6 @@ label="Smooth values using the following length (in bp)" help ="The smooth length defines a window, larger than the bin size, to average the number of reads. For example, if the bin size is set to 20 bp and the smooth length is set to 60 bp, then, for each bin size the average of it and its left and right neighbors is considered. Any value smaller than the bin size will be ignored and no smoothing will be applied."/> - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - <param name="doNotExtendPairedEnds" type="boolean" truevalue="--doNotExtendPairedEnds" falsevalue="" label="Do not extend paired ends" help="If set, reads are not extended to match the fragment length reported in the BAM file, instead they will be extended to match the fragment length. Default is to extend the reads if paired end information is available."/> @@ -202,13 +205,18 @@ .. image:: $PATH_TO_IMAGES/norm_IGVsnapshot_indFiles.png +You can find more details in the `bamCompare wiki`_. + +.. _bamCompare wiki: https://github.com/fidelram/deepTools/wiki/Normalizations#wiki-bamCompare + + **Output files**: - same as for bamCoverage, except that you now obtain 1 coverage file that is based on 2 BAM files. ----- -.. class:: infomark +@REFERENCES@ </help> </tool>
--- a/bamCorrelate.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/bamCorrelate.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_bamCorrelate" name="bamCorrelate" version="1.0.2"> +<tool id="deeptools_bamCorrelate" name="bamCorrelate" version="1.0.3"> <description>correlates pairs of BAM files</description> <expand macro="requirements" /> <expand macro="stdio" /> <macros> + <token name="@BINARY@">bamCorrelate</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -39,12 +40,12 @@ --BED $mode.region_file #end if - ## options available in both modes - #if $mode.advancedOpt.showAdvancedOpt == "yes": + #### options available in both modes + #if str($mode.region.value) != '': + --region '$mode.region' + #end if - #if str($mode.advancedOpt.region.value) != '': - --region '$mode.advancedOpt.region' - #end if + #if $mode.advancedOpt.showAdvancedOpt == "yes": $mode.advancedOpt.doNotExtendPairedEnds $mode.advancedOpt.ignoreDuplicates @@ -149,18 +150,19 @@ :alt: Heatmap of RNA Polymerase II ChIP-seq +You can find more details in the `bamCorrelate wiki`_. + +.. _bamCorrelate wiki: https://github.com/fidelram/deepTools/wiki/Normalizations#wiki-bamCompare + + **Output files**: - diagnostic plot produced by bamCorrelate is a clustered heatmap displaying the values for each pair-wise correlation, see below for an example - data matrix (optional) in case you want to plot the correlation values using a different program, e.g. R, this matrix can be used - - ----- -.. class:: infomark - @REFERENCES@ </help>
--- a/bamCoverage.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/bamCoverage.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_bamCoverage" name="bamCoverage" version="1.0.2"> +<tool id="deeptools_bamCoverage" name="bamCoverage" version="1.0.3"> <description> generates a coverage bigWig file from a given BAM file. Multiple options are available to count reads and normalize coverage. (bam2bigwig)</description> <expand macro="requirements" /> <expand macro="stdio" /> <macros> + <token name="@BINARY@">bamCoverage</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -21,19 +22,24 @@ #if $scaling.type=='rpkm': --normalizeUsingRPKM #elif $scaling.type=='1x': - --normalizeTo1x $scaling.normalizeTo1x + #if $scaling.effectiveGenomeSize.effectiveGenomeSize_opt == "specific": + --normalizeTo1x $scaling.effectiveGenomeSize.effectiveGenomeSize + #else: + --normalizeTo1x $scaling.effectiveGenomeSize.effectiveGenomeSize_opt + #end if #elif $scaling.type=='own': --scaleFactor $scaling.scaleFactor #end if + #if str(region).strip() != '': + --region 'region' + #end if + #if $advancedOpt.showAdvancedOpt == "yes": #if $advancedOpt.smoothLength: --smoothLength '$advancedOpt.smoothLength' #end if - #if str($advancedOpt.region.value) != '': - --region '$advancedOpt.region' - #end if $advancedOpt.doNotExtendPairedEnds $advancedOpt.ignoreDuplicates @@ -70,9 +76,7 @@ <when value="rpkm"/> <when value="no"/> <when value="1x"> - <param name="normalizeTo1x" type="integer" value="2150570000" - label="Genome size" - help ="Enter the genome size to normalize the reads counts. Sequencing depth is defined as the total number of mapped reads * fragment length / effective genome size. To use this option, the effective genome size has to be given. Common values are: mm9: 2150570000, hg19:2451960000, dm3:121400000 and ce10:93260000."/> + <expand macro="effectiveGenomeSize" /> </when> <when value="own"> <param name="scaleFactor" type="float" value="1" size="3" @@ -85,6 +89,8 @@ <option value="bedgraph">bedgraph</option> </param> + <expand macro="region_limit_operation" /> + <conditional name="advancedOpt"> <param name="showAdvancedOpt" type="select" label="Show advanced options" > <option value="no" selected="true">no</option> @@ -96,10 +102,6 @@ label="Smooth values using the following length (in bp)" help ="The smooth length defines a window, larger than the bin size, to average the number of reads. For example, if the bin size is set to 20 bp and the smooth length is set to 60 bp, then, for each bin size the average of it and its left and right neighbors is considered. Any value smaller than the bin size will be ignored and no smoothing will be applied."/> - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - <param name="doNotExtendPairedEnds" type="boolean" truevalue="--doNotExtendPairedEnds" falsevalue="" label="Do not extend paired ends" help="If set, reads are not extended to match the fragment length reported in the BAM file, instead they will be extended to match the fragment length. Default is to extend the reads if paired end information is available."/> @@ -140,14 +142,17 @@ .. image:: $PATH_TO_IMAGES/norm_IGVsnapshot_indFiles.png +You can find more details in the `bamCoverage wiki`_. + +.. _bamCoverage wiki: https://github.com/fidelram/deepTools/wiki/Normalizations#wiki-bamCoverage + + **Output files**: - coverage file either in bigWig or bedGraph format ----- -.. class:: infomark - @REFERENCES@ </help>
--- a/bamFingerprint.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/bamFingerprint.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_bamFingerprint" name="bamFingerprint" version="1.0.2"> +<tool id="deeptools_bamFingerprint" name="bamFingerprint" version="1.0.3"> <description>plots profiles of BAM files; useful for assesing ChIP signal strength</description> <expand macro="requirements" /> <expand macro="stdio" /> <macros> + <token name="@BINARY@">bamFingerprint</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -29,12 +30,11 @@ --plotFileFormat 'png' #end if + #if str(region).strip() != '': + --region 'region' + #end if + #if $advancedOpt.showAdvancedOpt == "yes": - - #if str($advancedOpt.region.value) != '': - --region '$advancedOpt.region' - #end if - --binSize '$advancedOpt.binSize' --numberOfSamples '$advancedOpt.numberOfSamples' @@ -53,8 +53,12 @@ <inputs> <expand macro="multiple_input_bams" /> + <param name="fragmentLength" type="integer" value="200" min="1" label="Length of the average fragment size"/> + + <expand macro="region_limit_operation" /> + <conditional name="advancedOpt"> <param name="showAdvancedOpt" type="select" label="Show advanced options" > <option value="no" selected="true">no</option> @@ -62,10 +66,6 @@ </param> <when value="no" /> <when value="yes"> - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - <param name="binSize" type="integer" value="10000" min="1" label="Bin size in bp" help="Length in base pairs for a window used to sample the genome."/> @@ -133,6 +133,11 @@ .. image:: $PATH_TO_IMAGES/QC_fingerprint.png +You can find more details in the `bamFingerprint wiki`_. + +.. _bamFingerprint wiki: https://github.com/fidelram/deepTools/wiki/QC#wiki-bamFingerprint + + **Output files**: - Diagnostic plot @@ -140,8 +145,6 @@ ----- -.. class:: infomark - @REFERENCES@ </help>
--- a/bigwigCompare.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/bigwigCompare.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_bigwigCompare" name="bigwigCompare" version="1.0.2"> +<tool id="deeptools_bigwigCompare" name="bigwigCompare" version="1.0.3"> <description>normalizes and compares two bigWig files to obtain the ratio, log2ratio or difference</description> <expand macro="requirements"/> <expand macro="stdio" /> <macros> + <token name="@BINARY@">bigwigCompare</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -18,10 +19,11 @@ --ratio $comparison_type + #if str(region).strip() != '': + --region 'region' + #end if + #if $advancedOpt.showAdvancedOpt == "yes": - #if str($advancedOpt.region.value) != '': - --region '$advancedOpt.region' - #end if --missingDataAsZero $advancedOpt.missingDataAsZero --scaleFactors '$advancedOpt.scaleFactor1:$advancedOpt.scaleFactor2' @@ -49,6 +51,8 @@ <option value="bedgraph">bedgraph</option> </param> + <expand macro="region_limit_operation" /> + <conditional name="advancedOpt"> <param name="showAdvancedOpt" type="select" label="Show advanced options" > <option value="no" selected="true">no</option> @@ -60,10 +64,6 @@ label="Bin size in bp" help="Size of the bins in bp for the ouput of the bigwig/bedgraph file "/> - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - <param name="missingDataAsZero" type="boolean" truevalue="yes" falsevalue="no" checked="True" label ="Treat missing data as zero" help ="This parameter determines if missing data should be replaced with a zero. If set to "no", missing data will be ignored and will not be included in the output file at all. Missing data is defined as those regions for which no value exists in *any* of the bigwig files. The decision to include or exclude missing data depends on the interpretation of the data. Missing data in a bigwig file may mean that there is no information available for certain regions, for example a repetitive region that is not being considered. In the same file regions with low coverage may get zero read counts. If missing data is replaced by zero, this would convert the excluded repetitive regions into regions of low coverage." /> @@ -93,10 +93,9 @@ finally a summarizing value is reported. This value can be the ratio of the number of reads per bin, the log2 of the ratio, the sum or the difference. + ----- -.. class:: infomark - @REFERENCES@ </help>
--- a/computeGCBias.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/computeGCBias.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_computeGCBias" name="computeGCBias" version="1.0.2"> +<tool id="deeptools_computeGCBias" name="computeGCBias" version="1.0.3"> <description>to see whether your samples should be normalized for GC bias</description> <expand macro="requirements" /> <expand macro="stdio" /> <macros> + <token name="@BINARY@">computeGCBias</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -24,10 +25,11 @@ --effectiveGenomeSize $effectiveGenomeSize.effectiveGenomeSize_opt #end if + #if str(region).strip() != '': + --region 'region' + #end if + #if $advancedOpt.showAdvancedOpt == "yes": - #if str($advancedOpt.region.value) != '': - --region '$advancedOpt.region' - #end if --sampleSize '$advancedOpt.sampleSize' --regionSize '$advancedOpt.regionSize' @@ -56,6 +58,9 @@ <param name="fragmentLength" type="integer" value="300" min="1" label="Fragment length used for the sequencing" help ="If paired-end reads are used, the fragment length is computed from the BAM file."/> + + <expand macro="region_limit_operation" /> + <conditional name="advancedOpt"> <param name="showAdvancedOpt" type="select" label="Show advanced options" > <option value="no" selected="true">no</option> @@ -63,10 +68,6 @@ </param> <when value="no" /> <when value="yes"> - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - <param name="sampleSize" type="integer" value="50000000" min="1" label="Number of sampling points to be considered" /> @@ -131,6 +132,11 @@ .. image:: $PATH_TO_IMAGES/QC_GCplots_input.png +You can find more details in the `computeGCBias wiki`_. + +.. _computeGCBias wiki: https://github.com/fidelram/deepTools/wiki/QC#wiki-computeGCbias + + **Output files**: - Diagnostic plot @@ -145,8 +151,6 @@ ----- -.. class:: infomark - @REFERENCES@ </help>
--- a/computeMatrix.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/computeMatrix.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_computeMatrix" name="computeMatrix" version="1.0.2"> +<tool id="deeptools_computeMatrix" name="computeMatrix" version="1.0.3"> <description>summarizes and prepares an intermediary file containing scores associated with genomic regions that can be used afterwards to plot a heatmap or a profile</description> <expand macro="requirements" /> <expand macro="stdio" /> <macros> + <token name="@BINARY@">computeMatrix</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -51,8 +52,8 @@ --afterRegionStartLength $mode.afterRegionStartLength #else --regionBodyLength $mode.regionBodyLength - --startLabel $mode.startLabel - --endLabel $mode.endLabel + --startLabel "$mode.startLabel" + --endLabel "$mode.endLabel" #if $mode.regionStartLength.regionStartLength_select == "yes": --beforeRegionStartLength $mode.regionStartLength.beforeRegionStartLength --afterRegionStartLength $mode.regionStartLength.afterRegionStartLength @@ -100,18 +101,17 @@ <param name="regionBodyLength" type="integer" value="500" label="Distance in bp to which all regions are going to be fitted"/> <param name="startLabel" type="text" value="TSS" size="10" label="Label for the region start" help ="Label shown in the plot for the start of the region. Default is TSS (transcription start site), but could be changed to anything, e.g. "peak start"." /> <param name="endLabel" type="text" value="TES" size="10" label="Label for the region end" help="Label shown in the plot for the region end. Default is TES (transcription end site)."/> - <conditional name="regionStartLength"> - <param name="regionStartLength_select" type="select" label="Set distance up- and downstream of the given regions"> - <option value="no" selected="true">no</option> - <option value="yes">yes</option> - </param> - <when value="no" /> - <when value="yes"> - <param name="beforeRegionStartLength" type="integer" value="1000" min="1" optional="true" label="Distance upstream of the start site of the regions defined in the region file" help="If the regions are genes, this would be the distance upstream of the transcription start site."/> - - <param name="afterRegionStartLength" type="integer" value="1000" min="1" optional="true" label="Distance downstream of the end site of the given regions" help="If the regions are genes, this would be the distance downstream of the transcription end site."/> - </when> - </conditional> + <conditional name="regionStartLength"> + <param name="regionStartLength_select" type="select" label="Set distance up- and downstream of the given regions"> + <option value="no" selected="true">no</option> + <option value="yes">yes</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="beforeRegionStartLength" type="integer" value="1000" min="1" optional="true" label="Distance upstream of the start site of the regions defined in the region file" help="If the regions are genes, this would be the distance upstream of the transcription start site."/> + <param name="afterRegionStartLength" type="integer" value="1000" min="1" optional="true" label="Distance downstream of the end site of the given regions" help="If the regions are genes, this would be the distance downstream of the transcription end site."/> + </when> + </conditional> </when> <when value="reference-point"> @@ -208,9 +208,12 @@ :alt: Relationship between computeMatrix, heatmapper and profiler ------ +You can find more details in the `computeMatrix wiki`_. -.. class:: infomark +.. _computeMatrix wiki: https://github.com/fidelram/deepTools/wiki/Visualizations#wiki-computeMatrix + + +----- @REFERENCES@
--- a/correctGCBias.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/correctGCBias.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_correctGCBias" name="correctGCBias" version="1.0.2"> +<tool id="deeptools_correctGCBias" name="correctGCBias" version="1.0.3"> <description>uses the output from computeGCBias to generate corrected BAM files</description> <expand macro="requirements" /> <expand macro="stdio" /> <macros> + <token name="@BINARY@">correctGCBias</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -32,15 +33,17 @@ --effectiveGenomeSize $effectiveGenomeSize.effectiveGenomeSize_opt #end if + #if str(region).strip() != '': + --region 'region' + #end if + #if $advancedOpt.showAdvancedOpt == "yes": - #if str($advancedOpt.region.value) != '': - --region '$advancedOpt.region' - #end if --binSize '$advancedOpt.binSize' #end if - #set newoutFileName="corrected."+str($outFileFormat) - --correctedFile $newoutFileName; + ###set newoutFileName="corrected."+str($outFileFormat) + ##--correctedFile $newoutFileName; + --correctedFile "corrected.bam"; mv $newoutFileName $outFileName </command> @@ -50,11 +53,14 @@ <expand macro="reference_genome_source" /> <expand macro="effectiveGenomeSize" /> + <!-- <param name="outFileFormat" type="select" label="File format of the output"> <option value="bam">bam</option> <option value="bw">bigwig</option> <option value="bg">bedgraph</option> </param> + --> + <expand macro="region_limit_operation" /> <conditional name="advancedOpt"> <param name="showAdvancedOpt" type="select" label="Show advanced options" > @@ -63,10 +69,6 @@ </param> <when value="no" /> <when value="yes"> - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - <param name="binSize" type="integer" value="50" min="1" label="Bin size in bp" help="Size of the bins in bp for the ouput of the bigwig/bedgraph file."/> @@ -75,11 +77,11 @@ </inputs> <outputs> <data format="bam" name="outFileName"> - <change_format> + <!--<change_format> <when input="outFileFormat" value="bw" format="bigwig" /> <when input="outFileFormat" value="bam" format="bam" /> <when input="outFileFormat" value="bg" format="bedgraph" /> - </change_format> + </change_format>--> </data> </outputs> <help> @@ -89,14 +91,18 @@ This tool requires the output from computeGCBias to correct the given BAM files according to the method proposed by Benjamini and Speed (2012). Nucleic Acids Res. The resulting BAM files can be used in any downstream analyses, but be aware that you should not filter out duplicates from here on. + +You can find more details in the `correctGCBias wiki`_. + +.. _correctGCBias wiki: https://github.com/fidelram/deepTools/wiki/QC#wiki-correctGCbias + + **Output files**: - GC-normalized BAM file ----- -.. class:: infomark - @REFERENCES@ </help>
--- a/deepTools_macros.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/deepTools_macros.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,5 +1,8 @@ <macros> <xml name="bamCorrelate_mode_actions"> + + <expand macro="region_limit_operation" /> + <conditional name="advancedOpt"> <param name="showAdvancedOpt" type="select" label="Show advanced options" > <option value="no" selected="true">no</option> @@ -7,10 +10,6 @@ </param> <when value="no" /> <when value="yes"> - <param name="region" type="text" value="" - label="Region of the genome to limit the operation to" - help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> - <param name="doNotExtendPairedEnds" type="boolean" truevalue="--doNotExtendPairedEnds" falsevalue="" label="Do not extend paired ends" help="If set, reads are not extended to match the fragment length reported in the BAM file, instead they will be extended to match the fragment length. Default is to extend the reads if paired end information is available."/> @@ -37,13 +36,21 @@ </when> </conditional> </xml> + + <xml name="region_limit_operation"> + <param name="region" type="text" value="" + label="Region of the genome to limit the operation to" + help="This is useful when testing parameters to reduce the computing time. The format is chr:start:end, for example "chr10" or "chr10:456700:891000"" /> + </xml> + <token name="@THREADS@">--numberOfProcessors "\${GALAXY_SLOTS:-4}"</token> <xml name="requirements"> <requirements> + <requirement type="binary">@BINARY@</requirement> <requirement type="package" >samtools</requirement> <requirement type="package" >deepTools</requirement> <requirement type="package" >ucsc_tools</requirement> - <requirement type="package" version="1.5.4_e5c75f3e967be0fa1d6dbcbb63a0f992e1cdcd61">deepTools</requirement> + <requirement type="package" version="1.5.4_1093b2d281576f23ee04740bd5eae3f7b8422f7e">deepTools</requirement> <requirement type="package" version="0.1">ucsc_tools</requirement> <requirement type="package" version="1.7.1">numpy</requirement> <requirement type="package" version="0.7.7">pysam</requirement> @@ -53,7 +60,45 @@ <requirement type="package" version="12-2013">bx-python</requirement> <yield /> </requirements> + <version_command>@BINARY@ --version</version_command> </xml> + + <xml name="kmeans_clustering"> + + <conditional name="used_multiple_regions"> + <param name="used_multiple_regions_options" type="select" + label="Did you used multiple regions in ComputeMatrix?" + help="Would you like to cluster the regions according to the similarity of the signal distribution? This is only possible if you used computeMatrix on only one group of regions."> + <option value="yes">Yes, I used multiple regions.</option> + <option value="no">No, I used only one region.</option> + </param> + <when value="no"> + <conditional name="clustering"> + <param name="clustering_options" type="select" label="Clustering algorithm"> + <option value="none">No clustering</option> + <option value="kmeans">Kmeans clustering</option> + </param> + <when value="kmeans"> + <param name="k_kmeans" type="integer" value="0" label="Number of clusters to compute" + help="When this option is set, then the matrix is split into clusters using the kmeans algorithm. Only works for data that is not grouped, otherwise only the first group will be clustered. If more specific clustering methods are required it is advisable to save the underlying matrix and run the clustering using other software. The plotting of the clustering may fail (Error: Segmentation fault) if a cluster has very few members compared to the total number or regions. (default: None)."/> + </when> + <when value="none" /> + </conditional> + </when> + <when value="yes" /> + </conditional> + + </xml> + <token name="@kmeans_clusterin@"> + #if $advancedOpt.used_multiple_regions.used_multiple_regions_options == 'no': + #if $advancedOpt.used_multiple_regions.clustering.clustering_options == 'kmeans': + #if int($advancedOpt.used_multiple_regions.clustering.k_kmeans) > 0: + --kmeans $advancedOpt.used_multiple_regions.clustering.k_kmeans + #end if + #end if + #end if + </token> + <xml name="stdio"> <stdio> <exit_code range="1:" /> @@ -66,7 +111,9 @@ </xml> <token name="@REFERENCES@"> -For more informations, please visit our `project site`_. +.. class:: infomark + +For more informations, please visit the `project site`_. If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com @@ -75,7 +122,7 @@ .. _Bioinformatics and Deep-Sequencing Unit: http://www3.ie-freiburg.mpg.de/facilities/research-facilities/bioinformatics-and-deep-sequencing-unit/ .. _Max Planck Institute for Immunobiology and Epigenetics: http://www3.ie-freiburg.mpg.de -.. _project site: https://github.com/fidelram/deepTools +.. _project site: https://github.com/fidelram/deepTools/wiki/ </token> @@ -146,15 +193,19 @@ help="The effective genome size is the portion of the genome that is mappable. Large fractions of the genome are stretches of NNNN that should be discarded. Also, if repetitive regions were not included in the mapping of reads, the effective genome size needs to be adjusted accordingly. See Table 2 of http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0030377 or http://www.nature.com/nbt/journal/v27/n1/fig_tab/nbt.1518_T1.html for several effective genome sizes."> - <option value="2150570000">mm9</option> - <option value="2451960000">hg19</option> - <option value="121400000">dm3</option> - <option value="93260000">ce10</option> + <option value="93260000">ce10 (93260000)</option> + <option value="121400000">dm3 (121400000)</option> + <option value="2451960000" selected="true">hg19 (2451960000)</option> + <option value="2150570000">mm9 (2150570000)</option> <option value="specific">user specified</option> </param> <when value="specific"> <param name="effectiveGenomeSize" type="integer" value="" label="Effective genome size" /> </when> + <when value="2150570000" /> + <when value="2451960000" /> + <when value="121400000" /> + <when value="93260000" /> </conditional> </xml>
--- a/heatmapper.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/heatmapper.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,8 +1,9 @@ -<tool id="deeptools_heatmapper" name="heatmapper" version="1.0.2"> +<tool id="deeptools_heatmapper" name="heatmapper" version="1.0.3"> <description>creates a heatmap for a score associated to genomic regions</description> <expand macro="requirements"/> <expand macro="stdio" /> <macros> + <token name="@BINARY@">heatmapper</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -80,13 +81,7 @@ $advancedOpt.onePlotPerGroup - #if $advancedOpt.used_multiple_regions.used_multiple_regions_options == 'yes': - #if $advancedOpt.used_multiple_regions.clustering.clustering_options == 'kmeans': - #if int($advancedOpt.used_multiple_regions.clustering.k_kmeans) > 0: - --kmeans $advancedOpt.used_multiple_regions.clustering.k_kmeans - #end if - #end if - #end if + @kmeans_clusterin@ #end if </command> @@ -147,7 +142,6 @@ <param name="whatToShow" type="select" label="What to show" help ="The default is to include a summary or profile plot on top of the heatmap and a heatmap colorbar."> <option value="plot, heatmap and colorbar" selected="true">summary plot, heatmap and colorbar</option> - <option value="plot only">summary plot only</option> <option value="plot and heatmap">summary plot and heatmap (no colorbar)</option> <option value="heatmap only">heatmap only</option> <option value="heatmap and colorbar">heatmap and colorbar</option> @@ -171,28 +165,8 @@ label="Do one plot per group" help="When computeMatrix was used on more than one group of genes, the average plots for all the groups will be drawn in one panel by default. If this option is set, each group will get its own plot, stacked on top of each other."/> - <conditional name="used_multiple_regions"> - <param name="used_multiple_regions_options" type="select" - label="Did you used multiple regions in ComputeMatrix?" - help="That option is only relevant if you want to cluster the results. Clustering is only available with one selected region in ComputeMatrix."> - <option value="no">No, I used only one region.</option> - <option value="yes">Yes, I used multiple regions.</option> - </param> - <when value="yes"> - <conditional name="clustering"> - <param name="clustering_options" type="select" label="Clustering algorithm"> - <option value="none">No clustering</option> - <option value="kmeans">Kmeans clustering</option> - </param> - <when value="kmeans"> - <param name="k_kmeans" type="integer" value="0" label="Number of clusters to compute" - help="When this option is set, then the matrix is split into clusters using the kmeans algorithm. Only works for data that is not grouped, otherwise only the first group will be clustered. If more specific clustering methods are required it is advisable to save the underlying matrix and run the clustering using other software. The plotting of the clustering may fail (Error: Segmentation fault) if a cluster has very few members compared to the total number or regions. (default: None)."/> - </when> - <when value="none" /> - </conditional> - </when> - <when value="no" /> - </conditional> + <expand macro="kmeans_clustering" /> + </when> </conditional> </inputs> @@ -224,9 +198,12 @@ :alt: Heatmap of RNA Polymerase II ChIP-seq ------ +You can find more details in the `heatmapper wiki`_. -.. class:: infomark +.. _heatmapper wiki: https://github.com/fidelram/deepTools/wiki/Visualizations#wiki-heatmapper + + +----- @REFERENCES@
--- a/profiler.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/profiler.xml Mon Feb 03 13:44:35 2014 -0500 @@ -1,10 +1,11 @@ -<tool id="deeptools_profiler" name="profiler" version="1.0.2"> +<tool id="deeptools_profiler" name="profiler" version="1.0.3"> <description> creates a profile plot for a score associated to genomic regions </description> <expand macro="requirements" /> <expand macro="stdio" /> <macros> + <token name="@BINARY@">profiler</token> <import>deepTools_macros.xml</import> </macros> <command> @@ -42,10 +43,14 @@ --regionsLabel '$advancedOpt.regionsLabel' - #if str($advancedOpt.plotTitle.value) != "None": + #if str($advancedOpt.plotTitle).strip() != "": --plotTitle '$advancedOpt.plotTitle' #end if + #if str($advancedOpt.colors).strip() != "": + --colors #echo ' '.join( ["'%s'" % $color for $color in $advancedOpt.colors.split()] )# + #end if + $advancedOpt.onePlotPerGroup #if $advancedOpt.yMin: @@ -59,6 +64,9 @@ #if str($advancedOpt.yAxisLabel.value) != "None": --yAxisLabel '$advancedOpt.yAxisLabel' #end if + + @kmeans_clusterin@ + #end if </command> <inputs> @@ -101,19 +109,26 @@ label="Plot width" help="Width in cm. The default value is 8 centimeters. The minimum value is 1 cm." /> <param name="plotType" type="select" label="Plot type" - help="For the summary plot (profile) only. The "lines" option will plot the profile line based on the average type selected. The "fill" option fills the region between zero and the profile curve. The fill in color is semi transparent to distinguish different profiles. The "std" option colors the region between the profile and the standard deviation of the data. As in the case of fill, a semi-transparent color is used. The option "overlapped_lines" plots each region values, one on top of the other; this option only works if "one plot per proup" is set."> + help="For the summary plot (profile) only. The "lines" option will plot the profile line based on the average type selected. The "fill" option fills the region between zero and the profile curve. The fill in color is semi transparent to distinguish different profiles. The "add standard error" option colors the region between the profile and the standard error of the data. As in the case of fill, a semi-transparent color is used. The option "overlapped_lines" plots each region values, one on top of the other; this option only works if "one plot per proup" is set."> <option value="lines" selected="true">lines</option> <option value="fill">fill</option> - <option value="std">std</option> + <option value="se">add standard error</option> <option value="overlapped_lines">overlapped lines</option> </param> <param name="regionsLabel" type="text" value="genes" size="30" label="Labels for the regions plotted in the heatmap" help="If more than one region is being plotted a list of labels separated by comma and limited by quotes, is required. For example, "label1, label2"."/> <param name="plotTitle" type="text" value="" size="30" label="Title of the plot" help="Title of the plot, to be printed on top of the generated image. Leave blank for no title." /> + <param name="colors" type="text" value="" size="40" label="List of colors to use for the plotted lines" help="Color names and html hex strings (e.g. #eeff22) are accepted. The color names should be given separated by spaces. (--colors red blue green)"> + <validator type="expression" message="Only numbers, digits, '#' and spaces are allowed.">all(c in ' #abcdefghijklmnopqrstuvwxyz0123456789' for c in value)</validator> + </param> + <param name="onePlotPerGroup" type="boolean" truevalue="--onePlotPerGroup" falsevalue="" label="Do one plot per group" help="When the region file contains groups separated by "#", the default is to plot the averages for the distinct plots in one plot. If this option is set, each group will get its own plot, stacked on top of each other."/> <param name="yMin" type="float" value="" size="3" label="Minimum value for the Y-axis of the summary plot. Leave empty for automatic values" optional="true"/> <param name="yMax" type="float" value="" size="3" label="Maximum value for Y-axis of the summary plot. Leave empty for automatic values" optional="true"/> <param name="xAxisLabel" type="text" value="gene distance (bp)" size="50" label="Description for the x-axis label" /> <param name="yAxisLabel" type="text" value="" size="50" label="Description for the y-axis label for the top panel" /> + + <expand macro="kmeans_clustering" /> + </when> </conditional> </inputs> @@ -137,9 +152,12 @@ :alt: Meta-gene profile of Rna Polymerase II ------ +You can find more details in the `profiler wiki`_. -.. class:: infomark +.. _profiler wiki: https://github.com/fidelram/deepTools/wiki/Visualizations#wiki-profiler + + +----- @REFERENCES@
--- a/tool_dependencies.xml Sat Dec 21 14:26:06 2013 -0500 +++ b/tool_dependencies.xml Mon Feb 03 13:44:35 2014 -0500 @@ -57,7 +57,7 @@ <readme>The tools downloaded by this dependency definition are free for academic use. TODO: UCSC tools are only available with their latest version. That is not good for reproducibility.</readme> </package> - <package name="deepTools" version="1.5.4_e5c75f3e967be0fa1d6dbcbb63a0f992e1cdcd61"> + <package name="deepTools" version="1.5.4_1093b2d281576f23ee04740bd5eae3f7b8422f7e"> <install version="1.0"> <actions> <action type="shell_command">git clone --recursive https://github.com/fidelram/deepTools.git</action> @@ -79,7 +79,7 @@ <package name="scipy" version="0.12.0" /> </repository> </action> - <action type="shell_command">git reset --hard e5c75f3e967be0fa1d6dbcbb63a0f992e1cdcd61</action> + <action type="shell_command">git reset --hard 1093b2d281576f23ee04740bd5eae3f7b8422f7e</action> <action type="make_directory">$INSTALL_DIR/lib/python</action> <action type="shell_command"> export PYTHONPATH=$PYTHONPATH:$INSTALL_DIR/lib/python &&