Mercurial > repos > bgruening > deeptools
changeset 6:c5847db0cb41 draft
Uploaded
| author | bgruening |
|---|---|
| date | Wed, 14 Aug 2013 07:18:18 -0400 |
| parents | 1f312af2f8db |
| children | 77487c05ffc7 |
| files | bamCompare.xml bamCorrelate.xml bamCoverage.xml bamFingerprint.xml bigwigCompare.xml computeGCBias.xml computeMatrix.xml correctGCBias.xml heatmapper.xml profiler.xml tool_dependencies.xml |
| diffstat | 11 files changed, 135 insertions(+), 112 deletions(-) [+] |
line wrap: on
line diff
--- a/bamCompare.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/bamCompare.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,9 +1,10 @@ -<tool id="bamCompare" name="bamCompare" version="1.0"> +<tool id="deeptools_bamCompare" name="bamCompare" version="1.0"> <description>normalizes and compares two BAM files to obtain the ratio, log2ratio or difference.</description> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> <requirement type="package" version="1.7.1">numpy</requirement> <requirement type="package" version="0.1">ucsc_tools</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> bamCompare @@ -34,11 +35,16 @@ --ratio $comparison.type #if $comparison.type=='subtract': - #if $comparison.normalization.type=='rpkm': - --normalizeUsingRPKM - #elif $comparison.normalization.type=='1x': - --normalizeTo1x $comparison.normalization.normalizeTo1x - #end if + #if $comparison.normalization.type=='rpkm': + --normalizeUsingRPKM + #elif $comparison.normalization.type=='1x': + --normalizeTo1x $comparison.normalization.normalizeTo1x + #end if + + #if str($comparison.ignoreForNormalization).strip() != '': + --ignoreForNormalization $comparison.ignoreForNormalization + #end if + #end if #if $advancedOpt.showAdvancedOpt == "yes": @@ -65,10 +71,10 @@ <inputs> <param name="bamFile1" format="bam" type="data" label="Treatment BAM file" - help="The BAM file must be sorted and indexed."/> + help="The BAM file must be sorted."/> <param name="bamFile2" format="bam" type="data" label="Input BAM file" - help="The BAM file must be sorted and indexed."/> + help="The BAM file must be sorted."/> <param name="fragmentLength" type="integer" value="300" min="1" label="Length of the average fragment size" @@ -124,6 +130,9 @@ 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."/> </when> </conditional> + <param name="ignoreForNormalization" type="text" value="" size="50" + label="regions that should be excluded for calculating the scaling factor" + help="Sometimes it makes sense to exclude certain regions when calculating the scaling factor. For example, if you know some regions that you suspect to be present more often in your sample's genome than in the reference genome that will therefore accumulate reads (CNV). Another typical example is the single X chromosome in male samples that should be scaled separately from the diploid autosomes. For example chrX,chrY,chr3. or chr10:12220-128932" /> </when> </conditional> @@ -158,7 +167,7 @@ <param name="minMappingQuality" type="integer" optional="true" value="1" min="1" label="Minimum mapping quality (e.g. BOWTIE2 measures)" - help= "If set, only reads that have a mapping quality score higher than the given value are considered"/> + help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/> <param name="missingDataAsZero" type="boolean" truevalue="yes" falsevalue="no" checked="True" label ="Treat missing data as zero" @@ -194,7 +203,7 @@ .. class:: infomark -If you would like to give us feedback or you run into any trouble, please sent an email to deeptools@googlegroups.com +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_.
--- a/bamCorrelate.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/bamCorrelate.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,7 +1,8 @@ -<tool id="bamCorrelate" name="bamCorrelate" version="1.0.1"> +<tool id="deeptools_bamCorrelate" name="bamCorrelate" version="1.0.1"> <description>correlates pairs of BAM files</description> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> #import tempfile @@ -46,10 +47,7 @@ #end if #if $advancedOpt.showAdvancedOpt == "yes": - #if $advancedOpt.smoothLength: - --smoothLength '$advancedOpt.smoothLength' - #end if - + #if str($advancedOpt.region.value) != '': --region '$advancedOpt.region' #end if @@ -73,7 +71,7 @@ <repeat name="inputs" title="Input files" min="2"> <param name="bamfile" type="data" format="bam" label="Bam file" - help="The BAM file must be sorted and indexed."/> + help="The BAM file must be sorted."/> <param name="label" type="text" size="30" optional="true" value="" label="Label" help="Label to use in the output. If not given the dataset name will be used instead."/> @@ -81,7 +79,7 @@ <param name="fragmentLength" type="integer" value="300" min="1" label="Length of the average fragment size" - help ="Reads will be extended to match this length unless they are paired-end, in which case they will be extended to match the fragment length. If this value is set to the read length or smaller, the read will not be extended. *Warning* the fragment length affects the normalization to 1x (see "normalize coverage to 1x"). The formula to normalize using the sequencing depth is genomeSize/(number of mapped reads * fragment length). *NOTE*: If the BAM files contain mated and unmated paired-end reads, unmated reads will be extended to match the fragment length."/> + help ="Reads will be extended to match this length unless they are paired-end, in which case they will be extended to match the fragment length. *NOTE*: If the BAM files contain mated and unmated paired-end reads, unmated reads will be extended to match the fragment length."/> <param name="corMethod" type="select" label="Correlation method"> <option value="pearson">Pearson</option> @@ -95,9 +93,7 @@ </param> <when value="no" /> <when value="yes"> - <param name="smoothLength" type="integer" value="1" optional="true" min="1" - 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" @@ -121,11 +117,11 @@ <param name="minMappingQuality" type="integer" optional="true" value="1" min="1" label="Minimum mapping quality" - help= "If set, only reads that have a mapping quality score higher than the given value are considered"/> + help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/> <param name="includeZeros" type="boolean" truevalue="--includeZeros" falsevalue="" label ="Include zeros" - help ="If set, then regions with zero counts for *all* BAM files given are included. The default behavior is to ignore those cases" /> + help ="If set, then regions with zero counts for *all* BAM files given are included. The default behavior is to ignore those cases." /> </when> </conditional> @@ -159,7 +155,7 @@ This tool is useful to assess the overall similarity of different BAM files. A typical application is to check the correlation between replicates or published data sets. -The tool splits the genomes are into bins of given length. For each bin, the number of reads +The tool splits the genomes into bins of given length. For each bin, the number of reads found in each BAM file is counted and a correlation is computed for all pairs of BAM files. @@ -167,14 +163,14 @@ .. class:: infomark -If you would like to give us feedback or you run into any trouble, please sent an email to deeptools@googlegroups.com +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de + </help>
--- a/bamCoverage.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/bamCoverage.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,9 +1,10 @@ -<tool id="bamCoverage" name="bamCoverage" version="1.0"> - <description>Given a BAM file, generates a coverage bigwig file. Multiple options available to count reads and normalize coverage.</description> +<tool id="deeptools_bamCoverage" name="bamCoverage" version="1.0"> + <description> generates a coverage bigWig file from a given BAM file. Multiple options are available to count reads and normalize coverage.</description> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> <requirement type="package" version="0.1">ucsc_tools</requirement> <requirement type="package" version="1.7.1">numpy</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> bamCoverage @@ -26,7 +27,11 @@ #elif $scaling.type=='own': --scaleFactor $scaling.scaleFactor #end if - + + ##if str($ignoreForNormalization).strip() != '': + ## --ignoreForNormalization $ignoreForNormalization + ##end if + #if $advancedOpt.showAdvancedOpt == "yes": #if $advancedOpt.smoothLength: --smoothLength '$advancedOpt.smoothLength' @@ -47,7 +52,7 @@ <inputs> <param name="bamInput" format="bam" type="data" label="Input BAM file" - help="The BAM file must be sorted and indexed."/> + help="The BAM file must be sorted."/> <param name="fragmentLength" type="integer" value="300" min="1" label="Length of the average fragment size" @@ -77,6 +82,13 @@ </when> </conditional> + <!-- + Not yet supported. + <param name="ignoreForNormalization" type="text" value="" size="50" + label="regions that should be excluded for calculating the scaling factor" + help="Sometimes it makes sense to exclude certain regions when calculating the scaling factor. For example, if you know some regions that you suspect to be present more often in your sample's genome than in the reference genome that will therefore accumulate reads (CNV). Another typical example is the single X chromosome in male samples that should be scaled separately from the diploid autosomes. For example chrX,chrY,chr3. or chr10:12220-128932" /> + --> + <param name="outFileFormat" type="select" label="Coverage file format"> <option value="bigwig" selected="true">bigwig</option> <option value="bedgraph">bedgraph</option> @@ -107,7 +119,7 @@ <param name="minMappingQuality" type="integer" optional="true" value="1" min="1" label="Minimum mapping quality" - help= "If set, only reads that have a mapping quality score higher than the given value are considered"/> + help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/> </when> </conditional> </inputs> @@ -129,14 +141,13 @@ .. class:: infomark -If you would like to give us feedback or you run into any trouble, please sent an email to deeptools@googlegroups.com +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de </help> </tool>
--- a/bamFingerprint.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/bamFingerprint.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,7 +1,8 @@ -<tool id="bamFingerprint" name="bamFingerprint" version="1.0"> - <description>plots profiles of bam files</description> +<tool id="deeptools_bamFingerprint" name="bamFingerprint" version="1.0"> + <description>plots profiles of BAM files; useful for assesing ChIP signal strength</description> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> #import tempfile @@ -45,10 +46,7 @@ #end if #if $advancedOpt.showAdvancedOpt == "yes": - #if $advancedOpt.smoothLength: - --smoothLength '$advancedOpt.smoothLength' - #end if - + #if str($advancedOpt.region.value) != '': --region '$advancedOpt.region' #end if @@ -72,7 +70,7 @@ <repeat name="inputs" title="Input files" min="2"> <param name="bamfile" type="data" format="bam" label="Bam file" - help="The BAM file must be sorted and indexed."/> + help="The BAM file must be sorted."/> <param name="label" type="text" size="30" optional="true" value="" label="Label" help="Label to use in the output. If not given the dataset name will be used instead."/> @@ -86,10 +84,7 @@ </param> <when value="no" /> <when value="yes"> - <param name="smoothLength" type="integer" value="1" optional="true" min="1" - 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"" /> @@ -112,11 +107,11 @@ <param name="minMappingQuality" type="integer" optional="true" value="1" min="1" label="Minimum mapping quality" - help= "If set, only reads that have a mapping quality score higher than the given value are considered"/> + help= "If set, only reads that have a mapping quality score higher than the given value are considered. *Note* Bowtie's Mapping quality is related to uniqueness: the higher the score, the more unique is a read. A mapping quality defined by Bowtie of 10 or less indicates that there is at least a 1 in 10 chance that the read truly originated elsewhere."/> <param name="skipZeros" type="boolean" truevalue="--skipZeros" falsevalue="" label ="Include zeros" - help ="If set, then zero counts that happen for *all* bam files given are ignored. This will result in a reduced number of read counts than the specified in number of samples" /> + help ="If set, then zero counts that happen for *all* BAM files given are ignored. This might have the effect that fewer regions are considered than indicated in the option where the number of samples is defined." /> </when> </conditional> @@ -143,7 +138,7 @@ This tool is based on a method developed by Diaz et al. (2012). Stat Appl Genet Mol Biol 11(3). The resulting plot can be used to assess the strength of a ChIP (for factors that bind to narrow regions). -The tool first samples indexed bam files and counts all reads overlapping a window (bin) of specified length. +The tool first samples indexed BAM files and counts all reads overlapping a window (bin) of specified length. These counts are then sorted according to their rank and the cumulative sum of read counts are plotted. An ideal input with perfect uniform distribution of reads along the genome (i.e. without enrichments in open chromatin etc.) should generate a straight diagonal line. A very specific and strong ChIP enrichment will be indicated by a prominent and steep @@ -154,14 +149,13 @@ .. class:: infomark -If you would like to give us feedback or you run into any trouble, please sent an email to deeptools@googlegroups.com +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de </help>
--- a/bigwigCompare.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/bigwigCompare.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,9 +1,10 @@ -<tool id="bigwigCompare" name="bigwigCompare" version="1.0"> +<tool id="deeptools_bigwigCompare" name="bigwigCompare" version="1.0"> <description>normalizes and compares two bigWig files to obtain the ratio, log2ratio or difference</description> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> <requirement type="package" version="0.1">ucsc_tools</requirement> <requirement type="package" version="1.7.1">numpy</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> bigwigCompare @@ -99,14 +100,13 @@ .. class:: infomark -If you would like to give us feedback or you run into any trouble, please sent an email to deeptools@googlegroups.com +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de </help>
--- a/computeGCBias.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/computeGCBias.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,8 +1,9 @@ -<tool id="computeGCBias" name="computeGCBias" version="1.0.1"> +<tool id="deeptools_computeGCBias" name="computeGCBias" version="1.0.1"> <description>to see whether your samples should be normalized for GC bias</description> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <stdio> <exit_code range="0" level="warning" description="Warning" /> @@ -69,7 +70,7 @@ <inputs> <param name="bamInput" format="bam" type="data" label="Input BAM file" - help="The BAM file must be sorted and indexed."/> + help="The BAM file must be sorted."/> <!--<param name="species" type="text" value="" label="Species name abbreviation" />--> <param name="species" type="select" label="Species name abbreviation"> @@ -95,7 +96,7 @@ </conditional> <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 based from the bam file."/> + help ="If paired-end reads are used, the fragment length is computed from the BAM file."/> <conditional name="advancedOpt"> <param name="showAdvancedOpt" type="select" label="Show advanced options" > @@ -117,7 +118,7 @@ <param name="regionSize" type="integer" value="300" min="1" label="Region size" - help ="To plot the reads per GC over a region the size of the region is required. By default, the bin size is set to 300bp, which is close to the standard fragment size for Illumina machines. However, if the depth of sequencing is low a larger bin size will be required, otherwise many bins will not overlap with any read."/> + help ="To plot the reads per GC over a region, the size of the region is required (see below for more details of the mthod). By default, the bin size is set to 300 bp, which is close to the standard fragment size many sequencing applications. However, if the depth of sequencing is low, a larger bin size will be required, otherwise many bins will not overlap with any read."/> <param name="filterOut" type="data" format="bed" optional="true" label="BED file containing genomic regions to be excluded from the estimation of the correction" @@ -145,28 +146,41 @@ <outputs> <data format="tabular" name="outFileName" /> <data format="png" name="biasPlot" label="${tool.name} on ${on_string}: bias plot"> - <filter>(output['showOutputSettings'] == 'yes' and output['saveBiasPlot'] == True)</filter> + <filter>saveBiasPlot is True</filter> + <!--<filter>(output['showOutputSettings'] == 'yes' and output['saveBiasPlot'] == True)</filter>--> </data> </outputs> <help> **What it does** -This tool computes the GC bias ussing the method proposed by Benjamini and Speed (2012). Nucleic Acids Res. +This tool computes the GC bias using the method proposed by Benjamini and Speed (2012). Nucleic Acids Res. (see below for more explanations) The output is used to plot the bias and can also be used later on to correct the bias with the tool correctGCbias. +There are two plots produced by the tool: a boxplot showing the absolute read numbers per genomic-GC bin and an x-y plot +depicting the ratio of observed/expected reads per genomic GC content bin. + +----- + +**Summary of the method used** + +In order to estimate how many reads with what kind of GC content one should have sequenced, we first need to determine how many regions the specific +reference genome contains for each amount of GC content, i.e. how many regions in the genome have 50% GC (or 10% GC or 90% GC or...). +We then sample a large number of equally sized genome bins and count how many times we see a bin with 50% GC (or 10% GC or 90% or...). These EXPECTED values are independent of any +sequencing as it only depends on the respective reference genome (i.e. it will most likely vary between mouse and fruit fly due to their genome's different GC contents). +The OBSERVED values are based on the reads from the sequenced sample. Instead of noting how many genomic regions there are per GC content, we now count the reads per GC content. +In an ideal sample without GC bias, the ratio of OBSERVED/EXPECTED values should be close to 1 regardless of the GC content. Due to PCR (over)amplifications, the majority of ChIP samples +usually shows a significant bias towards reads with high GC content (>50%) ----- .. class:: infomark -Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_. +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. - .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de </help> </tool>
--- a/computeMatrix.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/computeMatrix.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,7 +1,8 @@ -<tool id="computeMatrix" name="computeMatrix" version="1.0"> +<tool id="deeptools_computeMatrix" name="computeMatrix" version="1.0"> <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> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> #import tempfile @@ -82,14 +83,14 @@ <inputs> <repeat name="regionsFiles" title="regions to plot" min="1"> - <param name="regionsFile" format="bed" type="data" label="Regions to plot" help="File, in BED or GFF format, containing the regions to plot."/> + <param name="regionsFile" format="bed" type="data" label="Regions to plot" help="File, in BED format, containing the regions to plot."/> <param name="label" type="text" size="30" optional="true" value="" label="Label" help="Label to use in the output."/> </repeat> - <param name="scoreFile" format="bigwig" type="data" label="Score file" help="Either a bigWig file (containing a score, usually covering the whole genome) or a BAM file. For this last case, coverage counts will be used for the heatmap."/> + <param name="scoreFile" format="bigwig" type="data" label="Score file" help="Should be a bigWig file (containing a score, usually covering the whole genome). You can generate a bigWig file either from a bedGraph or WIG file using UCSC tools or from a BAM file using the deepTool bamCoverage."/> <conditional name="mode" > - <param name="mode_select" type="select" label="computeMatrix has two main output options" help="In the scale-regions mode, all regions in the BED/GFF file are stretched or shrunk to the same length (bp) that is indicated by the user. Reference-point refers to a position within the BED/GFF regions (e.g start of region). In the reference-point mode only those genomic positions before (downstream) and/or after (upstream) the reference point will be plotted."> + <param name="mode_select" type="select" label="computeMatrix has two main output options" help="In the scale-regions mode, all regions in the BED file are stretched or shrunk to the same length (bp) that is indicated by the user. Reference-point refers to a position within the BED regions (e.g start of region). In the reference-point mode only those genomic positions before (downstream) and/or after (upstream) the reference point will be plotted."> <option value="scale-regions" selected="true">scale-regions</option> <option value="reference-point">reference-point</option> </param> @@ -162,7 +163,7 @@ <option value="region_length">region length</option> </param> - <param name="averageTypeBins" type="select" label="Define the type of statistic that should be used over the bin size range"> + <param name="averageTypeBins" type="select" label="Define the type of statistic that should be displayed." help="The value is computed for each bin."> <option value="mean" selected="true">mean</option> <option value="median">median</option> <option value="min">min</option> @@ -171,7 +172,7 @@ <option value="std">std</option> </param> - <param name="missingDataAsZero" type="boolean" truevalue="--missingDataAsZero" falsevalue="" label="Indicate missing data as zero" help="Only for bigwig input! Set to "yes", if missing data should be indicated as zeros. Default is to ignore such cases which will be depicted as black areas in the heatmap. (see "Missing data color" options of the heatmapper for additional options)."/> + <param name="missingDataAsZero" type="boolean" truevalue="--missingDataAsZero" falsevalue="" label="Indicate missing data as zero" help="Set to "yes", if missing data should be indicated as zeros. Default is to ignore such cases which will be depicted as black areas in the heatmap. (see "Missing data color" options of the heatmapper for additional options)."/> <param name="skipZeros" type="boolean" truevalue="--skipZeros" falsevalue="" label="Skip zeros" help="Whether regions with only scores of zero should be included or not. Default is to include them."/> <param name="minThreshold" type="float" optional="true" label="Minimum threshold" help="Any region containing a value that is equal or less than this numeric value will be skipped. This is useful to skip, for example, genes where the read count is zero for any of the bins. This could be the result of unmappable areas and can bias the overall results."/> <param name="maxThreshold" type="float" optional="true" label="Maximum threshold" help="Any region containing a value that is equal or higher that this numeric value will be skipped. The max threshold is useful to skip those few regions with very high read counts (e.g. major satellites) that may bias the average values."/> @@ -209,19 +210,17 @@ <help> **What it does** -This tool summarizes and prepares an intermediary file containing scores associated with genomic regions that can be used afterwards to plot a heatmap or a profile. Typically, these genomic regions are genes, but any other regions defined in a BED or GFF format can be used. This tool can also be used to filter and sort regions according to their score. +This tool summarizes and prepares an intermediary file containing scores associated with genomic regions that can be used afterwards to plot a heatmap or a profile. Typically, these genomic regions are genes, but any other regions defined in a BED or INTERVAL format can be used. This tool can also be used to filter and sort regions according to their score. ----- .. class:: infomark -Please acknowledge that this tool **is still in development** and we will be very happy to receive feedback from the users. If you run into any trouble please sent an email to `Fidel Ramirez`_. +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. - .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de </help> </tool>
--- a/correctGCBias.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/correctGCBias.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,8 +1,9 @@ -<tool id="correctGCBias" name="correctGCBias" version="1.0.1"> - <description>use the output from computeGCBias to obtain corrected sample files</description> +<tool id="deeptools_correctGCBias" name="correctGCBias" version="1.0.1"> + <description>uses the output from computeGCBias to generate corrected BAM files</description> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> <requirement type="package" version="0.1">ucsc_tools</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> #import tempfile @@ -44,7 +45,7 @@ <param name="GCbiasFrequenciesFile" type="data" format="tabular" label="Output of computeGCBias" /> - <param name="bamInput" format="bam" type="data" label="Input BAM file" help="The BAM file must be sorted and indexed."/> + <param name="bamInput" format="bam" type="data" label="Input BAM file" help="This should be same file that was used for computeGCbias. The BAM file must be sorted."/> <param name="species" type="select" label="Species name abbreviation"> <option value="hg19">hg19</option> @@ -111,14 +112,14 @@ .. class:: infomark -If you would like to give us feedback or you run into any trouble, please sent an email to deeptools@googlegroups.com +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de + </help>
--- a/heatmapper.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/heatmapper.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,4 +1,4 @@ -<tool id="heatmapper" name="Heatmapper" version="1.0"> +<tool id="deeptools_heatmapper" name="heatmapper" version="1.0"> <description>creates a heatmap for a score associated to genomic regions</description> <requirements> @@ -7,7 +7,8 @@ <requirement type="package" version="1.2.1">matplotlib</requirement> <requirement type="package" version="0.12.0">scipy</requirement> <requirement type="package" version="0.1">ucsc_tools</requirement> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> @@ -119,8 +120,8 @@ <when value="yes"> <param name="sortRegions" type="select" label="Sort regions" help="Whether the heatmap should present the regions sorted. The default is to sort in descending order based on the mean value per region."> - <option value="no" selected="true">no ordering</option> - <option value="descend">descending order</option> + <option value="no">no ordering</option> + <option value="descend" selected="true">descending order</option> <option value="ascend">ascending order</option> </param> @@ -347,19 +348,19 @@ **What it does** -HeatMapper visualizes scores associated with genomic regions, for example log2 fold change values obtained from ChIP-seq experiments. Those values can be visualized individually along each of the regions provided by the user. +The heatmapper visualizes scores associated with genomic regions, for example ChIP enrichment values around the TSS of genes. Those values can be visualized individually along each of the regions provided by the user in INTERVAL or BED format. In addition to the heatmap, an average profile plot is plotted on top of the heatmap (can be turned off by the user; it can also be generated separately by the tool profiler). We implemented vast optional parameters and we encourage you to play around with the min/max values displayed in the heatmap as well as with the different coloring options. If you would like to plot heatmaps for different groups of genomic regions individually, e.g. one plot per chromosome, simply supply each group as an individual BED file. ----- .. class:: infomark -If you would like to give us feedback or you run into any trouble, please sent an email to deeptools@googlegroups.com +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de + </help> </tool>
--- a/profiler.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/profiler.xml Wed Aug 14 07:18:18 2013 -0400 @@ -1,9 +1,10 @@ -<tool id="dt_profiler" name="profiler" version="1.0"> +<tool id="deeptools_profiler" name="profiler" version="1.0"> <description> creates a profile plot for a score associated to genomic regions </description> <requirements> - <requirement type="package" version="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b">deepTools</requirement> + <requirement type="package" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079">deepTools</requirement> + <requirement type="package" >deepTools</requirement> </requirements> <command> profiler @@ -13,16 +14,16 @@ #if $output.showOutputSettings == "yes" #set newoutFileName = str($outFileName)+"."+str($output.outFileFormat) --outFileName $newoutFileName - #if $output.outFileNameData: - --outFileNameData '$output.outFileNameData' + #if $output.saveData: + --outFileNameData '$outFileNameData' #end if - #if $output.outFileNameMatrix: - --outFileNameMatrix '$output.outFileNameMatrix' + #if $output.saveMatrix: + --outFileNameMatrix '$outFileNameMatrix' #end if - - #if $output.outFileSortedRegions: - --outFileSortedRegions '$output.outFileSortedRegions' + + #if $output.saveSortedRegions: + --outFileSortedRegions '$outFileSortedRegions' #end if #else #set newoutFileName = str($outFileName)+".png" @@ -32,7 +33,6 @@ #if $scaleRegions.showScaleRegionsOpt == "yes": --startLabel $scaleRegions.startLabel --endLabel $scaleRegions.endLabel - --refPointLabel $scaleRegions.refPointLabel #end if #if $advancedOpt.showAdvancedOpt == "yes" @@ -76,7 +76,6 @@ <when value="yes"> <param name="startLabel" type="text" value="TSS" size="10" label="Label for the region start" help ="[only for scale-regions mode] Label shown in the plot for the start of the region. Default is TSS (transcription start site), but could be changed to anything, e.g. "peak start"." /> <param name="endLabel" type="text" value="TES" size="10" label="Label for the region end" help="[only for scale-regions mode] Label shown in the plot for the region end. Default is TES (transcription end site)."/> - <param name="refPointLabel" type="text" value="TSS" size="10" label="Reference point label" help ="[only for scale-regions mode] Label shown in the plot for the reference-point. Default is the same as the reference point selected (e.g. TSS), but could be anything, e.g. "peak start" etc." /> </when> </conditional> @@ -141,12 +140,12 @@ </inputs> <outputs> <data format="png" name="outFileName" label="${tool.name} image"> - <change_format> - <when input="output.outFileFormat" value="pdf" format="pdf" /> - <when input="output.outFileFormat" value="svg" format="svg" /> - <when input="output.outFileFormat" value="eps" format="eps" /> - <when input="output.outFileFormat" value="emf" format="emf" /> - </change_format> + <change_format> + <when input="output.outFileFormat" value="pdf" format="pdf" /> + <when input="output.outFileFormat" value="svg" format="svg" /> + <when input="output.outFileFormat" value="eps" format="eps" /> + <when input="output.outFileFormat" value="emf" format="emf" /> + </change_format> </data> <data format="tabular" name="outFileNameData" label="${tool.name} raw plot data"> <filter>(output['showOutputSettings'] == 'yes' and output['saveData'] == True)</filter> @@ -164,21 +163,20 @@ This tool creates a profile plot for a score associated to genomic regions. Typically, these regions are genes, but any other regions defined in a BED or -GFF format will work. A preprocessed matrix generated by the tool +INTERVAL format will work. A preprocessed matrix generated by the tool computeMatrix is required. ----- .. class:: infomark -If you would like to give us feedback or you run into any trouble, please sent an email to deeptools@googlegroups.com +If you would like to give us feedback or you run into any trouble, please send an email to deeptools@googlegroups.com This tool is developed by the `Bioinformatics and Deep-Sequencing Unit`_ at the `Max Planck Institute for Immunobiology and Epigenetics`_. .. _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 -.. _Fidel Ramirez: ramirez@ie-freiburg.mpg.de </help> </tool>
--- a/tool_dependencies.xml Tue Aug 06 08:20:47 2013 -0400 +++ b/tool_dependencies.xml Wed Aug 14 07:18:18 2013 -0400 @@ -42,11 +42,11 @@ <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="1.5.1_59e067cce039cb93add04823c9f51cab202f8c2b"> + <package name="deepTools" version="1.5.1_df852fa1ef13251a17274ee18fbf919fbc515079"> <install version="1.0"> <actions> <action type="shell_command">git clone --recursive https://github.com/fidelram/deepTools.git</action> - <action type="shell_command">git reset --hard 59e067cce039cb93add04823c9f51cab202f8c2b</action> + <action type="shell_command">git reset --hard df852fa1ef13251a17274ee18fbf919fbc515079</action> <action type="make_directory">$INSTALL_DIR/lib/python</action> <action type="shell_command"> export PYTHONPATH=$PYTHONPATH:$INSTALL_DIR/lib/python &&